US Pat. No. 11,113,880

SYSTEM AND METHOD FOR OPTIMIZING THE RENDERING OF DYNAMICALLY GENERATED GEOMETRY

Facebook Technologies, LL...


1. A method comprising, by a computing system:receiving a request to render an image of a virtual scene from a viewpoint, the image comprising at least one virtual object visible from the viewpoint;
determining a position of the virtual object relative to a lens used for viewing the image;
determining a number of pixels required for depicting the virtual object in the image;
determining a geometry simplification level for the virtual object based on the determined position of the virtual object relative to the lens, distortion characteristics associated with the lens at an area covered by the virtual object and the number of pixels required for depicting the virtual object in the image;
generating a mesh representation of the virtual object based on the determined geometry simplification level, wherein a number of polygons used in the mesh representation depends on the determined geometry simplification level; and
rendering the image of the virtual scene using at least the generated mesh representation of the virtual object.

US Pat. No. 11,113,879

SYSTEMS AND METHODS FOR GENERATING AUGMENTED REALITY ENVIRONMENTS FROM TWO-DIMENSIONAL DRAWINGS


1. A system for generating an augmented reality environment from a two-dimensional illustration of a floorplan, comprising:means for capturing an image of an two-dimensional illustration of a floorplan of a structure; and
a processor in communication with the means for capturing the image, the processor:calibrating the means for capturing the image by determining at least one parameter of the image based on a set of patterned images and a library;
calculating a position and an orientation of the means for capturing the image relative to a coordinate system based on a set of augmented reality markers, the set of augmented reality markers being positioned proximate to the two-dimensional illustration of the floorplan of the structure and being one of synthetic markers or fiducial markers;
detecting a target area comprising the two-dimensional illustration of the floorplan of the structure based on the set of augmented reality markers;
processing the two-dimensional illustration of the floorplan of the structure by applying a line segment detection algorithm to detect two-dimensional line segments within the detected target area;
generating a three-dimensional model of the structure based on the processed two-dimensional illustration of the floorplan of the structure by projecting each detected two-dimensional line segment into a three-dimensional reference plane where the augmented reality markers are positioned; and
rendering the three-dimensional model of the structure superimposed on the processed two-dimensional illustration of the floorplan of the structure.


US Pat. No. 11,113,878

SCREEN TILE PAIR-BASED BINOCULAR RENDERING PIPELINE PROCESS AND METHOD

ZHEJIANG UNIVERSITY, Han...


1. A screen tile-pair based binocular rendering pipeline process and method, comprising the following steps:(1) dividing an entire space into a plurality of screen tile pairs according to the spatial relationship of left and right visual angles in binocular drawing, and generating a primitive list in the input scene corresponding thereto for each screen tile pair;
(2) after generating the screen tile pairs, obtaining a plurality of spatially consistent surfaces by searching the screen tile pairs, wherein the spatially consistent surface is a surface formed by spaces corresponding to a plurality of connected screen tile pairs; and
(3) after obtaining a plurality of spatial consistency surfaces, scheduling all the screen tile pairs, and simultaneously rasterizing ang drawing the primitives corresponding to each screen tile pair;
wherein, the specific steps of Step (1) are as follows:
(1-1) according to a present screen tile size n×n, dividing the screens corresponding to left and right visual angles, respectively, into a plurality of screen tiles Tj0 and Tj1; wherein, j=1,2, . . . , N represents the serial number of the screen tiles, and the serial number j is incremented from left to right, from top to small, N is the total number of the screen tiles, 0 represent left in Tj0 and 1 represent right in Tj1;
(1-2) respectively calculating positions LPi0 and LPi1 of an input i-th primitive Pi projected on the screens corresponding to left and right visual angles, wherein i=1, 2, M, M is the total number of the input primitives, and 0 represent left in LPi0 and 1 represent right in LPi1;
(1-3) after the positions LPi0 and LPi1 are determined, respectively calculating screen tiles covered by the positions LPi0 and LPi1, and the screen tiles form screen tile set TPi0, and TPi1 covered by the primitive Pi;
(1-4) in a screen tile unit, according to each polar line in the horizontal direction, simultaneously traversing from left to right the screen tiles on the current polar line in the screens corresponding to left and right visual angles, and determining whether the current primitive Pcur belongs to the currently traversed screen tile pair (Tcur0, Tcur1);
(1-5) constructing a double-layer index in the traversing process, wherein the first layer index is a primitive index, which is a primitive list on the space corresponding to the screen tiles; the second layer index is an index of the primitives on the screen tiles, which is an index list of primitives on the screen tiles corresponding to the corresponding space of the screen tile pairs.

US Pat. No. 11,113,877

SYSTEMS AND METHODS FOR GENERATING THREE DIMENSIONAL GEOMETRY

Hover Inc., San Francisc...


1. A method of generating a building model, the method comprising:receiving a plurality of initial two-dimensional images, each image comprising at least one surface of a building object;
creating, from the plurality of initial two-dimensional images, a point cloud representing a plurality of surfaces of the building object in a three-dimensional (3D) coordinate system;
defining a plurality of edges within the point cloud for at least one of the plurality of surfaces;
creating a simplified geometry for the at least one of the plurality of surfaces based on an average planar fit of data points within the defined edges of the at least one surface;
constructing a 3D building model of the building object based on the simplified geometry;
correlating at least two vertices of the 3D building model with an orthogonal image of the building object; and
scaling the 3D building model based on the correlated orthogonal image.

US Pat. No. 11,113,876

METHOD FOR DISPLAYING A 3D SCENE GRAPH ON A SCREEN

HUAWEI TECHNOLOGIES CO., ...


1. A method for displaying a three-dimensional (3D) scene on a screen comprising 3D resources, the method comprising:attaching, by applications, the 3D resources to a set of nodes in a scene graph;
connecting, by the applications, a first sub-set of nodes in the scene graph to a first process and a second sub-set of nodes in the scene graph to a second process, wherein one or more 3D resources which are attached to the first sub-set of nodes correspond to a first application and one or more 3D resources which are attached to the second sub-set of nodes correspond to a second application, and wherein the first process is running in a first application context and the second process is running in a second application context; and
performing, by a 3D display server, a rendering of the scene graph based on the 3D resources obtained from the first process and the second process to display the 3D scene on the screen by computing at least one of reflections, refractions, shadowing, or shading of at least one 3D resource with respect to at least another 3D resource, wherein the 3D resources represent elementary 3D objects comprising textures, shades, or meshes, wherein the elementary 3D objects are rendered by the 3D display server, wherein the first process and the second process register with the 3D display server, wherein the first process and the second process communicate with the 3D display server using a process separation interface provided by the 3D display server, wherein the process separation interface is used by the 3D display server to separately communicate with the first process and the second process, and wherein the process separation interface provides conflict avoided accesses which are initiated by the first process and the second process accessing to a same node of the scene graph.

US Pat. No. 11,113,875

VISUALIZATION TOOLS FOR POINT CLOUDS AND 3D IMAGERY

Illuscio, Inc., Culver C...


1. A method comprising:receiving a point cloud comprising a plurality of data points that are distributed across a plurality of different planes and that collectively produce a three-dimensional (“3D”) image, each data point of the plurality of data points comprising a set of elements with values that define a position of the data point in 3D space and attributes that specify visual characteristics of the data point;
selecting a set of the plurality of data points that are located within a particular slice of the point cloud, wherein the set of data points comprises fewer data points than the plurality of data points;
determining a position of a camera relative to the set of data points;
ordering the set of data points to a set of planes based on a distance between the position of each data point from the set of data points and the position of the camera;
generating a first visualization by rendering the visual characteristics of each particular data point of the set of data points at the position defined for that particular data point in the 3D space by the values of that particular data point;
generating a second visualization that positions each particular data point of the set of data points based on one or more of the attributes that specify the visual characteristics of the particular data point rather than positioning the particular data point based on the position defined by the values of that particular data point, wherein generating the second visualization comprises generating a different layer for the second visualization based on the visual characteristics of each subset of the set of data points that are ordered to a different plane of the set of planes as a result of said ordering; and
presenting the first visualization and the second visualization together on a display, wherein the second visualization presents the one or more attributes for the set of data points in a different format than the rendering of the set of data points in the first visualization.

US Pat. No. 11,113,873

MODELING ARTICULATED OBJECTS

Zoox, Inc., Foster City,...


1. A system comprising: one or more processors;non-transitory computer-readable media storing instructions executable by the one or more processors to cause the system to perform operations comprising:
receiving a plurality of points associated with an object;
generating a first model representative of the object, the first model comprising a first rectangle connected to a second rectangle at a pivot, the first rectangle comprising a first end, a second end spaced from the first end by a first length, a first side, and a second side spaced from the first side by a first width, the second rectangle comprising a third end, a fourth end spaced from the third end by a second length, a third side, and a fourth side spaced from the third side by a second width, the pivot being coincident with a first midpoint on the second end and a second midpoint on the third end;
determining, for a point of the plurality of points, a first distance of the point to the first rectangle and a second distance of the point to the second rectangle;
determining, for the point and based at least in part on the first distance and the second distance, a first probability that the point is associated with the first rectangle and a second probability that the point is associated with the second rectangle;
generating, based at least in part on the first probability and the second probability, a second model representative of the object, the second model comprising the first rectangle and the second rectangle, wherein at least one of:the first rectangle is rotated relative to the second rectangle about the pivot, or
at least one of the first width, the second width, the first length, or the second length is altered relative to the first model; and

controlling, based at least in part on the second model as a representation of the object in an environment of an autonomous vehicle, the autonomous vehicle to navigate the environment relative to the object.

US Pat. No. 11,113,872

ADAPTIVE MULTISAMPLING BASED ON VERTEX ATTRIBUTES

Intel Corporation, Santa...


1. At least one non-transitory computer readable storage medium comprising a set of instructions, which when executed by a computing device, cause the computing device to:generate a lookup table that is to be programmable;
program the lookup table to include shading rate related data, wherein the shading rate related data includes a first parameter that corresponds to a first shading rate, further wherein the shading rate related data includes a second parameter that corresponds to a second shading rate, wherein the first shading rate is lower than the second shading rate, wherein the first shading rate is associated with a first object that is to be moving, and the second shading rate is associated with a second object at a different position from the first object; and
assign a shading operation associated with a viewport and the shading rate related data so that a first region is shaded at the first shading rate and a second region is shaded at the second shading rate.

US Pat. No. 11,113,871

SCENE CROP VIA ADAPTIVE VIEW-DEPTH DISCONTINUITY

AUTODESK, INC., San Rafa...


1. A computer-implemented method for cropping a three-dimensional (3D) scene, comprising:(a) acquiring the 3D scene, wherein the 3D scene comprises:(i) multiple 3D images, wherein each 3D image is from a view angle of an image capture device; and
(ii) a depth map for each 3D image, wherein the depth map comprises two or more depth values, wherein each of the two or more depth values is measured from the image capture device to an object in the 3D image;

(b) sorting the two or more depth values for each 3D image resulting in a sorted depth map for each image;
(c) determining multiple initial cutoff depths, wherein each of the multiple initial cutoff depths is based on the view angle;
(d) determining a cutoff relaxation depth, wherein the cutoff relaxation depth is based on a jump, between two of the two or more depth values, that exceeds a jump threshold;
(e) generating a confidence map for each depth map, wherein the confidence map indicates whether each depth value is above or below the cutoff relaxation depth;
(f) generating an aggregated model that combines the confidence maps for all of the 3D images in the 3D scene;
(g) generating a bounding volume out of the aggregated model; and
(h) cropping out points from the 3D scene based on the bounding volume.

US Pat. No. 11,113,870

METHOD AND APPARATUS FOR ACCESSING AND TRANSFERRING POINT CLOUD CONTENT IN 360-DEGREE VIDEO ENVIRONMENT

Samsung Electronics Co., ...


1. A method for transmitting data related to content including an omnidirectional image and a point cloud object, the method comprising:generating media data and metadata for the content including the omnidirectional image and the point cloud object; and
transmitting the generated media data and the generated metadata,
wherein the metadata comprises information for specifying sub-spaces of a bounding space which is located within a space corresponding to the omnidirectional image and contains the point cloud object inside the bounding space, and
wherein the information for specifying the sub-spaces of the bounding space comprises information specifying whether the bounding space is uniformly divided into the sub-spaces.

US Pat. No. 11,113,869

TECHNIQUES FOR GENERATING VISUALIZATIONS OF RAY TRACING IMAGES

Microsoft Technology Lice...


1. A method for providing a structure to a visualization application, comprising:obtaining, by a graphics processing unit (GPU) and based on a request from a different application executing on a central processing unit (CPU), a structure that specifies ray tracing instructions for generating an image for the different application; and
providing, by the GPU and based on a request from the visualization application, the structure to the visualization application, wherein the visualization application is a separate application from the different application and is executing on the CPU or a different CPU to separately generate the image.

US Pat. No. 11,113,868

RASTERED VOLUME RENDERER AND MANIPULATOR

INTUITIVE RESEARCH AND TE...


1. A method for displaying sequential two-dimensional data referenced to a three-dimensional representation, the method comprising:converting two-dimensional images into two-dimensional image textures;
rendering the two-dimensional image textures onto render targets;
stamping the render targets onto sequentially tiled textures;
modifying the colors of each tiled texture based on user-defined parameters; and
setting texture parameters in master tiled material and adding the master tiled material to a mesh;
virtually projecting arbitrary rays into the mesh from a face of a virtual camera and displaying, on a display, returned ray values from an intersection of the arbitrary rays with color pixels from the mesh.

US Pat. No. 11,113,867

DISPLAY ENGINE FOR POST-RENDERING PROCESSING

Facebook Technologies, LL...


1. A method comprising, by a computing system:generating a plurality of ray bundles for casting into an artificial reality scene that comprises one or more surfaces to determine whether the one or more surfaces are visible from a viewpoint, wherein each ray bundle of the plurality of ray bundles comprises two or more rays;
determining points of intersection between the rays of the plurality of ray bundles and the one or more surfaces by comparing one or more corners of each of the plurality of ray bundles to the one or more surfaces;
determining, based on the points of intersection, color values corresponding to output positions of a display system;
accessing brightness adjustment data corresponding to the output positions of the display system, wherein the brightness adjustment data are determined based on one or more non-uniformity characteristics of the display system;
applying one or more brightness adjustments to the color values based on the brightness adjustment data corresponding to the output positions to which the color values correspond; and
providing the color values for display at the corresponding output positions of the display system.

US Pat. No. 11,113,866

METHOD AND APPARATUS FOR POINT CLOUD COMPRESSION

TENCENT AMERICA LLC, Pal...


1. A method for point cloud encoding, comprising:determining, from a point cloud, at least a first set of candidate source points that are associated with a target point in a geometry image reconstructed from a compressed geometry image for the point cloud;
weighting a color of a candidate source point in the first set based on a combination of a location difference between the candidate source point and the target point, and a color difference between the color of the candidate source point and an aggregate color of the first set of candidate source points;
determining a color of the target point based on a first weighted color average of the first set of candidate source points; and
encoding texture of the point cloud with the target point having the determined color.

US Pat. No. 11,113,865

THREE-DIMENSIONAL GENERATIVE DESIGN BASED ON TWO-DIMENSIONAL SKETCHING

AUTODESK, INC., San Rafa...


1. A computer-implemented method for generating a three-dimensional model from a two-dimensional sketch, the method comprising:generating, based on a two-dimensional sketch, a problem definition comprising a non-linear constraint relationship between a first sketch element comprising a first set of two-dimensional points and a second sketch element comprising a second-set of two-dimensional points included in the two-dimensional sketch, wherein the non-linear constraint relationship comprises a non-linear function that relates a first parameter of the first sketch element with a second parameter of the second sketch element;
generating a three-dimensional computer model comprising a modification to one or more two-dimensional points in at least one of the first sketch element and the second sketch element to satisfy the non-linear constraint relationship; and
causing the three-dimensional computer model to be displayed.

US Pat. No. 11,113,864

GENERATIVE IMAGE SYNTHESIS FOR TRAINING DEEP LEARNING MACHINES

The Boeing Company, Chic...


1. A method performed by one or more processors of a computer system, the method comprising:generating deep learning training data, wherein generating the deep learning training data includes:generating a two-dimensional (2D) scene from an electronic representation of a first three-dimensional (3D) scene of a 3D occupancy grid map;
generating first label data for one or more objects of the 2D scene;
executing generative modelling on the 2D scene to create one or more realistic 2D scenes;
creating multiple specialized 2D scenes from each of the one or more realistic 2D scenes, each specialized 2D scene having one or more pixels that differ from each other specialized 2D scene created from each realistic 2D scene; and
generating final label data for the one or more objects in the multiple specialized 2D scenes.


US Pat. No. 11,113,863

RENDERING CONTENT IN A 3D ENVIRONMENT

Google LLC, Mountain Vie...


1. A computer-implemented method, comprising:displaying, on a display of a computing system, a three-dimensional (3D) environment;
prior to user interaction with a virtual object in the 3D environment, rendering the virtual object in a first display mode in which the virtual object presents a first set of third-party content, wherein the first display mode has a first computational demand for rendering the virtual object in the first display mode; and
in response to detecting user interaction with the virtual object in the 3D environment while the virtual object is rendered in the first display mode, re-rendering the virtual object in the 3D environment in a second display mode in which the first set of third-party content is replaced with a second set of third-party content on the virtual object, wherein the second display mode has a second computational demand for rendering the virtual object that is higher than the first computational demand for rendering the virtual object in the first display mode, wherein the virtual object includes an instruction for re-rendering the virtual object in the second display mode from the first display mode, wherein the computing system receives the instruction prior to user interaction with the virtual object in the 3D environment.

US Pat. No. 11,113,862

SIMULATING MOTION OF COMPUTER SIMULATION CHARACTERS TO ACCOUNT FOR SIMULATED INJURIES TO THE CHARACTERS USING CURRENT MOTION MODEL

Sony Interactive Entertai...


1. An apparatus comprising:at least one processor programmed with instructions which are executable by the at least one processor to:
identify in a computer simulation comprising at least one character an injury to the character; and
alter at least one of: a body weight of a simulated limb of the character by increasing the body weight, a length of a simulated limb of the character, a number of links in a skeleton of the character to cause an animation of the character to mimic motion of an injured human.

US Pat. No. 11,113,861

IMITATING MOTION CAPTURE CLIPS USING A NEURAL NETWORK

Nvidia Corporation, Sant...


1. A method of imitating a reference object from a motion capture (MOCAP) video clip using a physics simulator and a neural network (NN), comprising:tracking the reference object using a movement agent of a target object; and
adjusting a movement of the target object using a stability threshold and the movement agent, wherein the movement agent utilizes an output from the NN to provide modifications to the movement,
wherein the output is indicative of at least one of: one or more joint torques, one or more joint positionings, one or more applied forces, or one or more proportional derivative (PD) controller gain parameters, and
wherein the NN is at least one of a tracking NN or a recovery NN and the adjusting further comprises assigning a tracking agent as the movement agent and the tracking NN as the NN, when the stability threshold is satisfied.

US Pat. No. 11,113,860

PARTICLE-BASED INVERSE KINEMATIC RENDERING SYSTEM

ELECTRONIC ARTS INC., Re...


1. A system comprising:at least one data store comprising game application data and a plurality of prediction models associated with one or more virtual character models; and
a computing device in electronic communication with the data store and configured to execute a game application based in part on the game application data, the game application configured to:generate a virtual game environment;
determine a first pose of a first virtual character model within the virtual game environment, the first virtual character model comprising a plurality of rigid bodies connected by a plurality of joints, each joint connected to at least one rigid body, wherein the first pose of the first virtual character model is a first arrangement of the plurality of rigid bodies and the plurality of joints of the first virtual character model;
render at least a portion of the first pose of the first virtual character model within a frame during runtime of the game application;
receive an instruction to change the first pose of the first virtual character model in response to a first movement of at least one joint of the first virtual character model during runtime of the game application;
determine a second pose for the first virtual character model by:calculating an estimated pose of the first virtual character model based at least in part on a first prediction model of the plurality of prediction models wherein the estimated pose is not output for rendering during runtime of the game application; and
using the estimated pose as an input to a second prediction model of the plurality of prediction models;
calculating the second pose of the first virtual character model based, at least in part, on an output of the second prediction model of the plurality of prediction models, wherein the estimated pose and the second pose are calculated in response to the first movement of the at least one joint of the first virtual character model, wherein the estimated pose is a pose distinct from the first post and the second pose; and

render at least a portion of the second pose of the first virtual character model within a frame during runtime of the game application.


US Pat. No. 11,113,859

SYSTEM AND METHOD FOR RENDERING THREE DIMENSIONAL FACE MODEL BASED ON AUDIO STREAM AND IMAGE DATA

Facebook Technologies, LL...


1. A method comprising:receiving, by one or more processors through a microphone, a vocal output of a person over a plurality of time instances, as an audio stream;
acquiring, by the one or more processors through an imaging device, images of facial expressions of the person over the plurality of time instances, as corresponding image data;
predicting, by the one or more processors, phonemes of the vocal output according to the audio stream;
translating, by the one or more processors, the predicted phonemes of the vocal output into visemes;
determining, by the one or more processors, a plurality of blendshapes and corresponding weights, according to the corresponding image data, to form a three-dimensional (3D) model of an avatar of the person incorporating the facial expressions of the person, the plurality of blendshapes comprising 3D structures, the corresponding weights indicating an amount of transformation applied to the 3D structures of the 3D model of the avatar;
combining, by the one or more processors, the visemes with the 3D model of the avatar to form a 3D representation of the avatar, by synchronizing the visemes with the 3D model of the avatar over the plurality of time instances; and
rendering, by the one or more processors, the 3D representation of the avatar with the incorporated facial expressions of the person in synchronization with rendering of the audio stream.

US Pat. No. 11,113,858

SYSTEM AND METHOD FOR DEEP COMPOSITING OF IMAGES IN WEB BROWSERS

Inventive Software, LLC, ...


1. A system comprising:a workstation including a first processor executing graphical software instructions for receiving an input, for generating image data from the received input, and for transmitting the image data;
a render server including a second processor for:receiving the image data;
generating a graphical file from the received image data including:deriving distinct data from an alpha image, a z-depth image, and red-green-blue (RGB) variants of the image data;
minimizing the distinct data by: (i) slicing the alpha image, the z-depth image and the RGB variants; (ii) discarding unused parts thereof such that only used parts remain; and (iii) slicing the remaining used parts into a minimal sets;
deriving shading data from the image data; and
combining the minimized distinct data and the shading data to generate an optimized data package in the graphical file; and

transmitting the graphical file; and

a user device remote from the render server, wherein the user device includes a third processor and a display operating a browser, wherein the third processor receives the graphical file and renders the image data in the browser using the graphical file.

US Pat. No. 11,113,857

DISPLAY METHOD AND APPARATUS AND ELECTRONIC DEVICE THEREOF

LENOVO (BEIJING) CO., LTD...


1. A display method for an electronic device, comprising:displaying, by a display of the electronic device, a first image based on a first scene;
detecting, by a processor of the electronic device, whether a first condition with respect to a viewer in the first scene is satisfied;
in response to the first condition being satisfied, switching the first image in a first direction of the first scene to a second image in a second direction in the first scene, wherein:the first image corresponds to a first portion of the first scene;
the second image includes a character image of the viewer and an image corresponding to a second portion of the first scene, the second portion being different from the first portion; and
the first direction is different from the second direction;

obtaining the character image of the viewer, including one of:obtaining a real image of the viewer captured by a camera to obtain the character image;
obtaining the real image of the viewer captured by the camera and modifying the real image to compose the character image;
obtaining an account image of a user account of the viewer to obtain the character image; or,
obtaining the account image of the user account of the viewer and modifying the account image to compose the character image; and

displaying, by the display, the second image.

US Pat. No. 11,113,856

INFORMATION DISPLAYING SYSTEM AND INFORMATION DISPLAYING DEVICE

Ricoh Company, Ltd., Tok...


1. An information displaying system comprising:a memory storing a program;
a display device, and
a processor configured to execute the program to implement a process including:displaying a time axis region on the display device, the time axis region being configured to display a first time axis of a biosignal along a first direction, to display a second time axis of the biosignal along the first direction, and to display a first mark on the first time axis in the time axis region, the first time axis representing an entire period of time when the biosignal was measured, and the first mark being a pointer mark indicating a time point designated by a user,
displaying a signal display region on the display device, the signal display region being configured to display a plurality of waveforms of the biosignal side by side in a second direction which is different from the first direction, the second time axis displayed on the time axis region representing a period of time when the waveforms displayed on the signal display region were obtained;
in response to receiving, from the user, an operation of designating a specific time point on the signal display region, displaying the first mark at a location on the first time axis in the time axis region corresponding to the specific time point on the signal display region; and
in response to receiving an operation of designating a section on the first time axis in the time axis region from the user,displaying, in the signal display region, the plurality of waveforms for a time range corresponding to the designated section on the first time axis, and
in a case in which the first mark displayed on the first time axis is located within the designated section on the first time axis, displaying, in the signal display region, a line crossing the plurality of waveforms in the second direction at the time point indicated by the first mark.



US Pat. No. 11,113,855

EXPRESSION INTERPRETATION ENGINE FOR COMPUTER MAP VISUALIZATIONS

Mapbox, Inc., San Franci...


1. A computer-implemented method of editing and representing property values for a digital map, comprising:storing a library of expressions for styling a digital map, the library of expressions comprising at least one of data field lookup operations, logical operations, mathematical operations, string operations, and color operations;
retrieving electronic map data from a style sheet corresponding to a vector map tile set for the digital map;
displaying a user interface comprising:a property editor panel displaying a plurality of map styles that reference a portion of the electronic map data; and
a visual map portion displaying a representation of the electronic map data with the map styles applied;

for a selected map style, displaying in the property editor panel a plurality of style properties and a text field corresponding to a particular style property of the plurality of style properties for receiving expressions for the particular style property;
receiving, via the text field, a portion of an expression to apply to the style property;
determining, from the library of expressions, a set of suggested expressions corresponding to the style property based on the received portion of the expression;
displaying at least one suggested expression of the set of suggested expressions at the property editor panel;
retrieving inline documentation describing functionality of an expression for at least one suggested expression in the set of suggested expressions;
displaying the retrieved inline documentation adjacent to the set of suggested expressions within the property editor panel;
receiving user selection of a particular suggested expression from the displayed suggested expressions;
applying the particular expression to the electronic map data for the style property; and
rendering in the visual map portion an edited representation of the electronic map data for the style property with the particular expression applied.

US Pat. No. 11,113,854

METHODS AND DEVICES FOR CAPTURING HEURISTIC INFORMATION VIA A SKETCHING TOOL

DECISIONNEXT, INC., San ...


1. A method comprising:at an electronic device with a display device and one or more input devices:
displaying, on the display device, a first graphing area including a first section presenting a plot of a first set of data points for a first variable and a second section;
while displaying the first section presenting the plot of the first set of data points for the first variable:detecting, via the one or more input devices, a user input moving within the second section to define a path;
determining, based on the path, a second set of data points for the first variable; and
displaying, on the display device, the second section presenting a plot of the second set of data points for the first variable;

determining, based at least on the second set of data points for the first variable, a set of data points for a second variable; and
displaying, on the display device, a second graphing area presenting a plot of the set of data points for the second variable.

US Pat. No. 11,113,853

SYSTEMS AND METHODS FOR BLENDING AND AGGREGATING MULTIPLE RELATED DATASETS AND RAPIDLY GENERATING A USER-DIRECTED SERIES OF INTERACTIVE 3D VISUALIZATIONS

AQUMIN, LLC, Houston, TX...


1. A method for blending and aggregating multiple related datasets and rapidly generating a user-directed series of interactive three-dimensional landscape visualizations, comprising:a) transforming multiple related datasets into a blended data model (BDM) using a computer processor; the BDM comprising a plurality of Scopes, a plurality of Metrics and a plurality of Values, wherein each Scope includes a plurality of Entities, and wherein transforming the multiple datasets into the BDM comprises: determining a Target Scope from the plurality of Scopes for each dataset; transforming rows, columns and data values from the multiple datasets to the plurality of Entities, Metrics and Values; determining additional Computed Metrics and Computed Values; determining a Scope Hierarchy; determining Neighbor Entities for each Entity; determining Aggregate Functions for each Metric; and computing Aggregate Values for the plurality of Metrics using the Scope Hierarchy, the additional Computed Metrics, the plurality of Values, the additional Computed Values, the plurality of Entities and the Neighbor Entities;
b) selecting a Data View from the BDM, wherein the Data View is comprised of one or more of the plurality of Entities and one or more of the plurality of Metrics; and
c) transforming the Data View to the three-dimensional landscape visualization.

US Pat. No. 11,113,852

SYSTEMS AND METHODS FOR TRENDING PATTERNS WITHIN TIME-SERIES DATA

Oracle International Corp...


18. A system comprising:one or more hardware processors;
one or more non-transitory computer-readable media storing instructions which, when executed by the one or more hardware processors, cause operations comprising:classifying, by a machine learning process, a first set of data points within a set of time-series data as sparse seasonal highs and a second set of data points within the set of time-series data as dense seasonal highs, wherein the sparse seasonal highs have a duration less than a threshold within a seasonal period, wherein the dense seasonal highs have a duration that satisfies the threshold within the seasonal period;
generating, within at least one of volatile or non-volatile storage based on said classifying, a plurality of groups of data points including (a) a first group that includes the first set of data points and represents sparse seasonal highs, and (b) a second group that includes the second set of data points and represents dense seasonal highs, wherein the first group of data points and the second group of data points span multiple cycles of the seasonal period;
determining a set of pairwise slopes for data point pairs formed from data points that are in the first group of data points representing sparse seasonal highs and not in the second group of data points representing dense seasonal highs and that are separated by at least one cycle of the seasonal period;
assigning a respective weight to each respective pairwise slope in the set of pairwise slopes as a function of which seasonal cycle each data point used to compute the respective pairwise slope is in relative to other data points in the first group, wherein data points in a first seasonal cycle are assigned a first weight and wherein data points in a second seasonal cycle are assigned a second weight that is different than the first weight;
determining a cumulative weight for the sparse seasonal highs that is a balance for a cumulative total obtained by aggregating the respective weight for each respective pairwise slope in the set of pairwise slopes;
determining, based at least in part on the cumulative weight for the sparse seasonal highs and the plurality of pairwise slopes constrained to the set of pairwise slopes for data point pairs formed from data points that are in the first group of data points representing sparse seasonal highs and not in the second group of data points representing dense seasonal highs and that are separated by at least one cycle of the seasonal period, a representative trend rate for the seasonal highs;
training a forecasting model based on the representative trend rate such that data points in the first group of data points representing sparse seasonal highs are not paired with data points from the second group of data points representing dense seasonal highs such that data points representing sparse seasonal highs are trended independently of data points representing dense seasonal4ows highs;
generating, within at least one of volatile or non-volatile storage using the trained forecasting model and based at least in part on the representative trend rate for the sparse seasonal highs, a set of forecasted sparse seasonal high values; and
deploying or consolidating at least one computing resource to account for projected resource utilization in the set of forecasted sparse seasonal high values.


US Pat. No. 11,113,851

CORRECTION OF SHARP-EDGE ARTIFACTS IN DIFFERENTIAL PHASE CONTRAST CT IMAGES AND ITS IMPROVEMENT IN AUTOMATIC MATERIAL IDENTIFICATION

The Board of Trustees of ...


5. A method for correcting image data from a differential phase contrast imaging system comprising:obtaining image data comprising distorted data due to spatial variation; and
correcting the image data by correcting the distorted data, wherein the correcting the data, comprises at least one cycle, wherein each cycle comprises:
a) performing a Hilbert-filtered back projection of the data to create an image;
b) setting all positive-valued pixels to zero in the image, and keeping all values of pixels with negative values in the image to create a negative value image with the only negative-valued data;
c) projecting the negative value image with only negative-valued data to produce a correction sinogram;
d) differentiating the correction sinogram to provide a differentiated correction sinogram;
e) keeping pixels with highest absolute values in the differentiated correction sinogram;
f) multiplying the highest absolute values by a factor;
g) subtracting the highest absolute values multiplied by the factor from the data to create corrected data; and
h) replacing the data with the corrected data.

US Pat. No. 11,113,850

ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF

SAMSUNG ELECTRONICS CO., ...


1. An electronic apparatus comprising:a communicator;
a camera; and
a processor configured to:control the camera to obtain an image including a display apparatus,
identify the display apparatus in the image,
identify a display area corresponding to the identified display apparatus in the image and a surrounding area excluding the display area in the image,
identify a plurality of shapes of a plurality of objects included in the surrounding area,
identify a pattern corresponding to the image based on a shape that occupies the surrounding area at a predetermined ratio or more among the plurality of shapes,
cluster colors of the surrounding area into a plurality of clustered colors, and
control the communicator to communicate with the display apparatus such that an image by applying the plurality of clustered colors to the identified pattern is output by the display apparatus.


US Pat. No. 11,113,849

METHOD OF CONTROLLING VIRTUAL CONTENT, TERMINAL DEVICE AND COMPUTER READABLE MEDIUM

GUANGDONG VIRTUAL REALITY...


1. A terminal device, comprising:a display configured to display a virtual object;
a camera configured to capture a target image including a marker;
at least one processor; and
a memory storing one or more programs configured to be executed by the at least one processor, the one or more programs including instructions of:
acquiring the target image including the marker, wherein a plurality of sub-markers are distributed on the marker, features of the plurality of sub-makers are different, each of the plurality of sub-markers comprises at least one feature point, the feature comprises information of the at least one feature point of the sub-marker;
determining a blocked target according to a blocked feature, wherein the blocked target is a blocked sub-marker of the plurality of sub-markers in the target image;
acquiring, as a reference, at least one blocked sub-marker determined within a preset period before a target time point, wherein the target time point is a time point at which the blocked target is determined to be blocked,
determining blocking change information according to the reference and the blocked target, the blocking change information comprises target change information indicating a change trend from the reference to the blocked target,
generating a control instruction for the virtual object according to the blocking change information;
generating a sub-control instruction for the virtual object according to blocked information of the blocked target; and
controlling the displayed virtual object based on the control instruction and the sub-control instruction.

US Pat. No. 11,113,847

CONVERSION OF INFRASTRUCTURE MODEL GEOMETRY TO A TILE FORMAT

Bentley Systems, Incorpor...


1. A method comprising:receiving, by a backend module executing on a remote computing device from a frontend module executing on a local computing device, a request for tile contents of a selected tile that corresponds to a node of a hierarchical level of detail (HLOD) sub-tree that supports a view of a model to be shown by the frontend module;
computing, by the backend module, a space of the selected tile;
processing, by the backend module, geometry within the space of the selected tile bycalculating a tolerance for stroking or faceting at a level of detail (LOD) of the tile;
retaining geometry that contributes visibly at the LOD of the tile as indicated by the tolerance and discarding geometry too small to contribute visibly at the LOD as indicated by the tolerance, to produce an accumulated geometry, and
converting the accumulated geometry from high-level geometric primitives having a symbology to low-level primitives, wherein the high-level geometric primitives are b-splines, curves, cones or polyfaces, the low-level primitives are polylines or meshes, and the symbology is a color, line width or material;

encoding, by the backend module, the geometry into the tile contents; and
transmitting the tile contents to the frontend module on the local computing device to enable the frontend module to display the view of the model on a display screen of the local computing device without the frontend module utilizing high-level geometric primitives.

US Pat. No. 11,113,846

COEFFICIENT CONTEXT MODELING IN VIDEO CODING

HULU, LLC, Santa Monica,...


1. A method comprising:determining, by a computing device, a plurality of classes of bins that are used to determine a context model for entropy coding of a current block in a video;
calculating, by the computing device, a first value for a first class of bins in the plurality of classes of bins for a first bin plane;
calculating, by the computing device, a second value for a second class of bins in the plurality of classes of bins for the first bin plane;
weighting, by the computing device, the first value for the first class of bins by a first weight to generate a weighted first value and weighting the second value for the second class of bins by a second weight to generate a weighted second value;
selecting, by the computing device, a third value for a second bin plane; and
selecting, by the computing device, a context model based on the first weighted value, the second weighted value, and the third value.

US Pat. No. 11,113,845

POINT CLOUD COMPRESSION USING NON-CUBIC PROJECTIONS AND MASKS

Apple Inc., Cupertino, C...


1. A system, comprising:one or more sensors configured to capture a plurality of points that make up a point cloud, wherein respective ones of the points comprise spatial information for the point and attribute information for the point; and
an encoder configured to compress the point cloud, wherein to compress the point cloud, the encoder is configured to:
generate, for the point cloud, one or more projected images;
pack the generated one or more projected images into one or more image frames, wherein respective sets of pixels of the one or more image frames covered by respective ones of the projected images comprise pixel values that correspond to values for the respective ones of the projected images;
pad pixels in the one or more image frames that are not covered by the one or more projected images with a pad;
encode the one or more image frames; and
encode information indicating pixels of the one or more image frames that correspond to active regions or non-active regions of the one or more image frames, wherein the pixels that are covered by the pad are indicated as non-active regions.

US Pat. No. 11,113,844

SYSTEMS AND METHODS FOR AUTOMATIC QUALITY ASSESSMENT OF MULTIPLE-CAMERA CALIBRATION

The Boeing Company, Chic...


1. A method for assessing calibration of an array of cameras, the method comprising:inputting captured images from at least two cameras of the array of cameras, the captured images comprising features from an image;
extracting one or more extracted features from the captured images;
matching one or more extracted features between pairs of the at least two cameras to create a set of matched features;
selecting matching points from the set of matched features by:selecting matching points based on a distance ratio; and
applying a homography transform with RANSAC (RANdom SAmple Consensus);

generating a three-dimensional reconstruction of objects in a field of view of the at least two cameras; and
outputting the three-dimensional reconstruction wherein the three-dimensional reconstruction comprises indicators of calibration errors.

US Pat. No. 11,113,843

METHOD FOR CALIBRATING THE ORIENTATION OF A CAMERA MOUNTED TO A VEHICLE

Aptiv Technologies Limite...


1. A method for calibrating the orientation of a camera mounted to a vehicle, in particular a truck, comprising the steps ofplacing the camera in front of a calibration pattern defining at least two horizontal lines and two vertical lines;
acquiring an image of the calibration pattern with the camera, the image having a first axis and a second axis at least essentially corresponding to a horizontal axis and a vertical axis, respectively;
identifying, with a microcontroller in communication with the camera, representations of the horizontal lines and the vertical lines within the acquired image;
determining, with the microcontroller, a horizontal vanishing point from the representations of the horizontal lines;
determining, with the microcontroller, a vertical vanishing point from the representations of the vertical lines;
and
determining, with the microcontroller, a roll angle, wherein calculating the roll angle comprises determining an angle of the line segment defined by a horizontal vanishing point and a principal point of the image with respect to the first axis by calculating the inverse tangent of the quotient of a second coordinate of the horizontal vanishing point measured along the second axis and the first coordinate of the horizontal vanishing point;
determining, with the microcontroller, a yaw angle by calculating the inverse tangent of the quotient of a focal length of the camera and the product of a pixel pitch of the camera and the first coordinate of the horizontal vanishing point or of a corrected horizontal vanishing point;
determining, with the microcontroller, a pitch angle by calculating the inverse tangent of the quotient of a focal length of the camera and the product of a pixel pitch of the camera and the second coordinate of the vertical vanishing point or of a corrected vertical vanishing point; and
adjusting, with the microcontroller, an orientation of the image acquired by the camera based on at least one of the roll angle, the yaw angle, and the pitch angle.

US Pat. No. 11,113,842

METHOD AND APPARATUS WITH GAZE ESTIMATION

Samsung Electronics Co., ...


1. A processor-implemented gaze estimation method, comprising:obtaining an image including an eye region of a user;
extracting, from the obtained image, a first feature of data;
obtaining a second feature of data used for calibration of a neural network model;
estimating a gaze of the user using the first feature and the second feature; and
estimating a position of a gaze point in a gaze area of the user from the first feature and the second feature using the neural network model, including:calculating, using the neural network model, a probability that the gaze point is included in each of subareas into which the gaze area is divided, based on a calculated feature difference between the first feature and the second feature; and
determining, to be the position of the gaze point, a center position of a subarea having a greatest probability among probabilities calculated for the subareas.


US Pat. No. 11,113,841

SELF-LEARNING THREE-DIMENSIONAL BOUNDARIES FROM IMAGES

Amazon Technologies, Inc....


1. A system, comprising:a camera; and
a computer system communicatively coupled with the camera, the computer system comprising one or more processors and one or more computer-readable storage media storing instructions that, upon execution by the one or more processors, cause the computer system to, at least:receive, from the camera, a first image of a first plurality of images representing a motion of a first vehicle license plate through a portion of a parking lot, the portion being within a field of view of the camera;
determine, based at least in part on the first image, a location of the first vehicle license plate shown in the first image;
determine, based at least in part on the first image, a physical characteristic of the first vehicle license plate shown in the first image, the physical characteristic being common with a second vehicle license plate;
generate a three-dimensional (3D) representation of the portion of the parking lot based at least in part on (i) the location and (ii) the physical characteristic;
subsequent to generating the 3D representation of the portion of the parking lot, receive, from the camera, a second image of a second plurality of images, the second image showing the portion of the parking lot and the second vehicle license plate;
determine a 3D position of the second vehicle license plate in the 3D representation based at least in part on (i) a second location of the second vehicle license plate shown in the second image, and (ii) the physical characteristic shown in the second image;
determine that a vehicle is parked in the parking lot, the vehicle being associated with the second vehicle license plate;
based in part on determining that the vehicle is parked, determine that the 3D position belongs to a cluster of 3D positions of one or more vehicle license plates shown in the second plurality of images; and
generate a 3D boundary of a parking space within the portion of the parking lot based at least in part on the 3D positions of the cluster, the parking space corresponding to where the vehicle is parked.


US Pat. No. 11,113,840

SYSTEMS AND METHODS FOR DETECTING OBJECTS IN IMAGES

ZHEJIANG DAHUA TECHNOLOGY...


1. An image processing system configured to detect objects in images, comprising:a bus;
at least one storage medium connected to the bus, including a set of instructions for object detection; and
logic circuits in communication with the at least one storage medium via the bus, wherein when executing the set of instructions, the logic circuits:obtain first electronic signals including an image including an object;
generate one or more feature vectors related to the image based on a first convolutional neural network, the one or more feature vectors including a plurality of parameters;
determine a position of the object based on at least one of the plurality of parameters;
determine a category associated with the object based on at least one of the plurality of parameters;
determine that the object includes a predetermined scene; and
obtain a first feature of the object in the image based on a second convolutional neural network, wherein the predetermined scene includes a person close to a window of a vehicle; and the first feature includes whether the person is fastened with a seat belt.


US Pat. No. 11,113,839

METHOD, APPARATUS, AND SYSTEM FOR FEATURE POINT DETECTION

HERE Global B.V., Eindho...


1. A method comprising:processing image data associated with a grid cell of an image to determine at least one feature point corresponding to a feature detected in the image;
parametrically encoding a position of the at least one feature point with respect to a coordinate system referenced to the grid cell; and
providing an output to represent the at least one feature point,
wherein the output includes one or more parameters indicating an encoded position of the at least one feature point, one or more attributes of the feature, or a combination thereof.

US Pat. No. 11,113,838

DEEP LEARNING BASED TATTOO DETECTION SYSTEM WITH OPTIMIZED DATA LABELING FOR OFFLINE AND REAL-TIME PROCESSING

NEC Corporation


1. A computer-implemented method executed by at least one processor for detecting tattoos on a human body, the method comprising:inputting a plurality of images into a tattoo detection module;
selecting one or more images of the plurality of images including tattoos with at least three keypoints, the at least three keypoints having auxiliary information related to the tattoos;
manually labeling tattoo locations in the plurality of images including tattoos to create labeled tattoo images;
increasing a size of the labeled tattoo images identified to be below a predetermined threshold by padding a width and height of the labeled tattoo images;
training two different tattoo detection deep learning models with the increased size labeled tattoo images defining tattoo training data; and
executing either the first tattoo detection deep learning model or the second tattoo detection deep learning model based on a performance of a general-purpose graphical processing unit (GPGPU).

US Pat. No. 11,113,837

SENSOR MAPPING TO A GLOBAL COORDINATE SYSTEM

7-ELEVEN, INC., Irving, ...


1. An object tracking system, comprising:a first sensor configured to capture a first frame of a global plane for at least a portion of a space, wherein:the global plane represents (x,y) coordinates for the at least a portion of the space;
the first frame comprises a plurality of pixels; and
each pixel from the plurality of pixels is associated with a pixel location comprising a pixel row and a pixel column; and

a tracking system operably coupled to the first sensor, comprising:one or more memories operable to store a first homography associated with the first sensor, wherein:the first homography comprises coefficients that translate between pixel locations in the first frame and (x,y) coordinates in the global plane; and

one or more processors operably coupled to the one or more memories, configured to:receive a first (x,y) coordinate identifying a first x-value and a first y-value in the global plane where a first marker is located in the space, wherein the first marker is a first object identifying a first location in the space;
receive a second (x,y) coordinate identifying a second x-value and a second y-value in the global plane where a second marker is located in the space, wherein the second marker is a second object identifying a second location in the space;
receive the first frame;
identify the first marker and the second marker within the first frame;
determine a first pixel location in the first frame for the first marker, wherein the first pixel location comprises a first pixel row and a first pixel column of the first marker;
determine a second pixel location in the first frame for the second marker, wherein the second pixel location comprises a second pixel row and a second pixel column of the second marker; and
generate the first homography based on the first (x,y) coordinate, the second (x,y) coordinate, the first pixel location, and the second pixel location.



US Pat. No. 11,113,836

OBJECT DETECTION METHOD, DEVICE, APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM

Baidu Online Network Tech...


1. An object detection method, comprising:obtaining an enclosing frame of a target object in an input image;
according to the enclosing frame, calculating respective overlap degrees of the enclosing frame of the target object with respective candidate frames in a candidate frame set, the candidate frame set is a predetermined frame set associated with the category of the target object in the input image and each target object in the input image has one corresponding candidate frame set;
determining a predetermined number of candidate frames with overlap degrees thereof ranked in the top as reference frames;
generating a size-related feature according to respective sizes of the reference frames and a size of the enclosing frame; and
detecting an object in the input image by applying the size-related feature in a machine learning model.

US Pat. No. 11,113,835

PLANT POINT CLOUD ACQUISITION, REGISTRATION AND OPTIMIZATION METHOD BASED ON TOF CAMERA

ZHEJIANG UNIVERSITY, Han...


1. A plant point cloud acquisition, registration, and optimization method based on a time of flight (TOF) camera, comprising:(1) placing a to-be-tested plant on a turntable, adjusting a view angle of the TOF camera, and aligning the TOF camera with the to-be-tested plant;
(2) turning on the turntable so that it rotates automatically, and enabling the TOF camera to acquire point cloud data of the to-be-tested plant at intervals;
(3) performing real-time preprocessing on each frame of point cloud data acquired by the TOF camera;
(4) performing registration and optimization on every two adjacent frames of point cloud data, and then integrating the data to obtain complete plant point cloud data, comprising:
(4-1) transforming a coordinate system of a second point cloud P2 to a coordinate system of a first point cloud P1 to obtain a point cloud P2?;
(4-2) triangulating P1 and P2?, removing boundary points that do not form a triangular patch, but retaining points inside that do not form a triangular patch;
(4-3) searching for a triangular patch of P2? within the neighborhood of each triangular patch in P1, and checking whether the triangular patch in P1 intersects with or is in parallel to the triangular patches within the neighborhood;
(4-4) according to the intersection and parallelism relationship, adjust a point cloud set of P2? that is within the neighborhood of the triangular patch in P1 to obtain a point cloud P2?;
(4-5) adding points in P2? that do not form a triangular patch to P2?, and then performing downsampling to obtain a point set P2?deal;
(4-6) transforming a coordinate system of an i-th point cloud Pi to the coordinate system of the first point cloud P1 to obtain a point cloud Pi?, and repeating steps (4-2) to (4-5) to obtain Pi?deal, wherein i?3; and
(4-7) integrating P1, P2?deal, and Pi?deal to obtain the complete plant point cloud data; and
(5) using statistical filtering to remove the discrete noise in the plant point cloud data obtained in the registration and optimization process to obtain final point cloud data.

US Pat. No. 11,113,834

COMPUTER-IMPLEMENTED METHOD FOR DETERMINING A LOCAL DEVIATION OF A GEOMETRY OF AN OBJECT FROM A TARGET GEOMETRY OF THE OBJECT

Volume Graphics GmbH, He...


1. A computer-implemented method for determining a local deviation of a geometry of an object from a target geometry of the object from a digital representation of the object, wherein the object representation comprises a plurality of items of image information of the object, wherein an item of image information indicates a value of a measured variable for the object at a defined position of the object, wherein the method comprises the following steps:ascertaining the object representation,
ascertaining a distance field from the items of image information of the object representation, wherein the distance field comprises a plurality of distance values, wherein a distance value for a specific point of the distance field specifies the shortest spacing of the point to a closest material boundary surface of the geometry of the object,
ascertaining the target geometry of the object,
registering the target geometry of the object on the material boundary surfaces of the geometry of the object specified by the distance values, and
ascertaining the local deviation of the geometry of the object from the target geometry of the object at a test point on a material boundary surface predetermined by the target geometry by reading out the distance value of the distance field at the position of the test point.

US Pat. No. 11,113,833

OBJECT DETECTION SYSTEM

KONICA MINOLTA, INC., To...


1. An object detection system comprising:a depth image detector that detects a depth image from an external environment; and
a moving object extractor that extracts a moving object desired to be extracted from the depth image,
wherein the moving object extractor registers in advance the depth image in a memory as a background while the moving object to be extracted does not exist, and extracts only a pixel whose current depth is present on a nearer side than a depth of the background as a candidate for a pixel corresponding to the moving object to be extracted;
wherein the moving object extractor further makes a determination to extract, as the moving object to be extracted, a pixel from a pixel group composed of pixels of the candidates having been extracted, and for a portion not extracted as the moving object to be extracted, updates and registers a depth of the pixel in the memory as the depth of the background; and
wherein the moving object extractor determines a size of the pixel group, compares the size of the pixel group to a threshold value, and when the size of the pixel group exceeds the threshold value the pixel group is registered as background.

US Pat. No. 11,113,832

APERTURE SUPERVISION FOR SINGLE-VIEW DEPTH PREDICTION

Google LLC, Mountain Vie...


1. A method comprising:obtaining a plurality of images, wherein a set of at least two images of the plurality of images describe a common scene, wherein the set of at least two images comprises a source image having a first depth-of-field and a target image having a second depth-of-field, wherein the second depth-of-field is less than the first depth-of-field;
determining, using an artificial neural network, a depth map for the common scene based on the source image;
determining, based on the determined depth map for the common scene, a predicted image based on the source image such that the predicted image has a depth-of-field corresponding to the second depth-of-field;
determining a difference between the predicted image and the target image;
updating the artificial neural network based on the determined difference;
obtaining an image of a scene of interest; and
using the updated artificial neural network to generate a depth map for the scene of interest based on the image of the scene of interest.

US Pat. No. 11,113,831

REDUCING TEXTURED IR PATTERNS IN STEREOSCOPIC DEPTH SENSOR IMAGING

Sony Corporation, Tokyo ...


1. A device comprising:an infrared (IR) projector configured to project an IR texture pattern onto a scene;
an image sensor comprising a plurality of sub-pixels, the image sensor configured to generate raw input image data based on an image capture of the scene comprising a projection of the IR texture pattern, wherein the raw input image data comprises an IR texture pattern residual from the IR texture pattern received at the image sensor through at least some red, green, and blue color filter elements;
a color filter array adjacent to the image sensor, the color filter array comprising red, green, and blue color filter elements, each of the red, green, and blue color filter elements corresponding to one of the plurality of sub-pixels, and the red, green, and blue color filter elements including the at least some red, green, and blue color filter elements; and
an image signal processor coupled to the image sensor, the image signal processor configured toreceive the raw input image data, and

generate output image data by applying a color correction transform to the raw input image data or image data corresponding to the raw input image data, the color correction transform corrects the IR texture pattern residual in the output image data, and the output image data has a reduced IR texture pattern residual relative to the raw input image data.

US Pat. No. 11,113,830

METHOD FOR GENERATING SIMULATED POINT CLOUD DATA, DEVICE, AND STORAGE MEDIUM

BAIDU ONLINE NETWORK TECH...


1. A method for generating simulated point cloud data, comprising:acquiring at least one frame of point cloud data collected by a road collecting device in an actual environment without a dynamic obstacle as static scene point cloud data;
setting, according to set position association information, at least one dynamic obstacle in a coordinate system matching the static scene point cloud data;
simulating in the coordinate system, according to the static scene point cloud data, a plurality of simulated scanning lights emitted by a virtual scanner located at an origin of the coordinate system, comprising connecting the origin of the coordinate system to each point in the static scene point cloud data respectively to obtain a plurality of line segments as the plurality of simulated scanning lights; and
updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle.

US Pat. No. 11,113,829

DOMAIN ADAPTATION FOR ANALYSIS OF IMAGES

GM GLOBAL TECHNOLOGY OPER...


1. A system for analyzing images, comprising:a processor including a receiving module configured to receive an image associated with a target domain;
a domain adaptation module configured to characterize one or more features represented in the received image based on a domain adaptation model, the domain adaptation model generated using a machine learning algorithm to train the domain adaptation model, the machine learning algorithm configured to train the domain adaptation model based on one or more source domain images associated with a source domain, one or more previously acquired images associated with the target domain, and acquired characterization data associated with the target domain, the one or more source domain images having one or more source domain classification labels assigned to one or more features of the one or more source domain images, the machine learning algorithm configured to generate a target domain classification label based on comparing the one or more features to the one or more previously acquired images associated with the target domain; and
an output module configured to output the received image with characterization data identifying one or more features characterized by the domain adaptation module.

US Pat. No. 11,113,828

DETERMINING SENSOR INSTALLATION CHARACTERISTICS FROM CAMERA IMAGE

Google LLC, Mountain Vie...


1. A computer-implemented method comprising:receiving an image of at least a portion of a room, the image of the room comprising an image of a sensor mounted in the room;
receiving at least one optical parameter related to the image of the room;
determining a distance between the sensor and a camera that captured the image of the room, wherein the determination of the distance is based at least in part on the image of the room, on the optical parameters, and on known physical dimensions of the sensor;
determining a sensitivity requirement of the sensor, based on the distance;
sending the determined sensitivity requirement to control logic of the sensor; and
configuring the sensor to operate at the determined sensitivity requirement to determine an alarm event.

US Pat. No. 11,113,827

PATTERN-TO-DESIGN ALIGNMENT FOR ONE-DIMENSIONAL UNIQUE STRUCTURES

KLA Corporation, Milpita...


1. A system comprising:an energy source that generates an energy beam;
a stage configured to secure a wafer in a path of the energy beam;
a detector that receives the energy beam reflected from the wafer on the stage; and
a processor in electronic communication with the detector; wherein the processor is configured to:determine one or more care areas for a first image of a die on the wafer according to a 1D offset correction, wherein the 1D offset correction is based on a 1D offset between the first image and a second image for each of image frames and the 1D offset correction is further based on a 1D offset between a design and the second image for each of the image frames.


US Pat. No. 11,113,826

ASSISTED MATERIAL DATA COLLECTION

Centric Software, Inc., ...


1. A method comprising:capturing an initial material sample image using an application executing on a mobile device, wherein the initial material sample image includes at least the following visible areas:
a sample material area, and
a capture guide area including a capture guide and a set of alignment indicators included on the capture guide of at least three alignment indicators;
identifying positions for the set of alignment indicators from the captured initial material sample image;
overlaying the positions for the set of alignment indicators with a set of application provided alignment indicators that indicate where in the captured initial material sample image the set of alignment indicators are found;
in response to identifying the positions for the set of alignment indicators, transforming the initial material sample image, based upon a bounded polygon formed using the set of application provided alignment indicators, to render an alignment corrected material sample image;
identifying, from the alignment corrected material sample image, a sample material swatch area, wherein the sample material swatch area includes at least one instance of a pattern found in the initial material sample image; and
storing on the mobile device the sample material swatch area and the initial material sample image.

US Pat. No. 11,113,825

MULTI-SURFACE IMAGE PROJECTION ITEM TRACKING SYSTEM

ACCEL ROBOTICS CORPORATIO...


1. A projected image item tracking system comprising:a processor coupled toa sensor configured to generatean enter signal when a shopper reaches into or towards an item storage area in a store, wherein said item storage area comprises a volume in said store that contains items; and,
an exit signal when said shopper retracts from said item storage area; and,

a plurality of cameras oriented to view said item storage area;

wherein said processor is configured toobtain a plurality of before images captured by said plurality of cameras, each before image of said plurality of before images corresponding to a camera of said plurality of cameras, wherein said each before image is captured at a time before said enter signal;
obtain a plurality of after images captured by said plurality of cameras, each after image of said plurality of after images corresponding to a camera of said plurality of cameras, wherein said each after image is captured at a time after said exit signal;
project said plurality of before images onto two or more surfaces contained in said volume associated with said item storage area to generate a plurality of projected before images corresponding to each combination of a surface of said two or more surfaces and a camera of said plurality of cameras;
project said plurality of after images onto said two or more surfaces to generate a plurality of projected after images corresponding to said each combination of a surface of said two or more surfaces and a camera of said plurality of cameras;
analyzesaid plurality of projected before images, and
said plurality of projected after images, toidentify an item of said items taken from or put into said item storage area between said enter signal and said exit signal; and,
associate said item with said shopper;



wherein said two or more surfaces are at different positions along a sweep axis in said volume associated with said item storage area.

US Pat. No. 11,113,824

HEADING ANGLE ESTIMATION FOR OBJECT TRACKING

Aptiv Technologies Limite...


1. A method of tracking a moving object at least partially in a pathway of a host vehicle, the method comprising:detecting, with a ranging sensor of the host vehicle, one or more points on the moving object over time to obtain a plurality of detections;
determining, with a processor, a position of each of the detections of points on the moving object relative to a two-dimensional world coordinate system;
determining, with the processor, a spatial relationship between the determined positions of the detections of points on the moving object to define a shape that encompasses the determined positions and that is in the two-dimensional world coordinate system; and
determining, with the processor, an estimated heading angle of the moving object based on the spatial relationship and based on an orientation of the defined shape relative to the two-dimensional world coordinate system.

US Pat. No. 11,113,823

THREE-DIMENSIONAL DETECTION AND TRACKING PIPLINE RECOMMENDATION USING PERFORMANCE PREDICTION

SEIKO EPSON CORPORATION, ...


1. A non-transitory computer readable medium for storing instructions that enable one or more processors to:train a first regressor on the basis of (i) training input data sets of test objects and (ii) first performance data sets indicating performances of a first pipeline, so that the first regressor predicts the first performance data sets of the first pipeline when the respective training input data sets are input to the first regressor,
wherein the first performance data sets include first correct detection rates of first poses of the test objects over respective reference poses of the test objects, the first poses of the test objects being derived by a pose derivation device running the first pipeline to derive the first poses based on the respective training input data sets and respective images of the test objects captured by a camera, and,
train a second regressor on the basis of (iii) the training input data sets of the test objects and (iv) second performance data sets indicating performances of a second pipeline, so that the second regressor predicts the second performance data sets when the respective training input data sets are input to the second regressor,
wherein the second performance data sets include second correct detection rates of second poses of the test objects over the respective reference poses of the test objects, the second poses of the test objects being derived by the pose derivation device running the second pipeline different from the first pipeline to derive the second poses based on the respective training input data sets and the respective images of the test objects captured by the camera.

US Pat. No. 11,113,822

MOVING OBJECT IDENTIFICATION FROM A VIDEO STREAM

International Business Ma...


1. An apparatus comprising:at least one processor;
a memory coupled to the at least one processor;
a video stream residing in the memory, wherein the video stream comprises a plurality of frames; and
a video stream moving object identifier that processes the plurality of frames in the video stream by performing pixel analysis of sequential frames to identify a moving object, resizes the moving object according to input rules for a neural network object classifier, sends the resized moving object to the neural network object classifier, and receives from the neural network object classifier an identification of the resized moving object,
wherein the resizing of the moving object comprises:resizing a large dimension of the moving object to be less than a largest maximum dimension for an input object for the neural network classifier, and
filling a remainder of the moving object with random noise to make the moving object a desired size for the neural network object classifier.


US Pat. No. 11,113,821

SYSTEM, METHOD, AND COMPUTER PROGRAM FOR ADJUSTING IMAGE CONTRAST USING PARAMETERIZED CUMULATIVE DISTRIBUTION FUNCTIONS

DUELIGHT LLC, Sunnyvale,...


1. A device, comprising:a non-transitory memory storing instructions; and
one or more processors in communication with the non-transitory memory, wherein the one or more processors execute the instructions to:receive a first image;
divide the first image into two or more pixel regions;
for at least one of the two or more pixel regions, compute a first histogram;
based on the first histogram, compute a first cumulative distribution function;
based on the first cumulative distribution function, extract:a first curve fit coefficient,
a first point associated with the first curve fit coefficient,
a first angle associated with the first curve fit coefficient,
a second curve fit coefficient,
a second point associated with the second curve fit coefficient, and
a second angle associated with the second curve fit coefficient;

create an interpolated cumulative distribution function based on the first curve fit coefficient, the first point, the first angle, the second curve fit coefficient, the second point, and the second angle; and
apply the interpolated cumulative distribution function to the at least one of the two or more pixel regions.


US Pat. No. 11,113,820

METHOD OF LINE DETECTION

Apical Limited, Cambridg...


1. A method for detecting a line in an image, the method comprising:identifying a candidate line break region in the image, wherein identifying the candidate line break region comprises identifying a first pixel of the image and a second pixel of the image, between which the candidate line break region appears, a characteristic of the first pixel and the second pixel having a predetermined similarity relationship;
assigning to a pixel of the candidate line break region a gradient amplitude based on at least one of a gradient amplitude of the first pixel and a gradient amplitude of the second pixel; and
assigning to a pixel of the candidate line break region a gradient angle based on at least one of a gradient angle of the first pixel and a gradient angle of the second pixel; and
using the identified candidate line break region to assist in detecting a line in the image,
wherein the detecting of the line in the image is based on the assigned gradient amplitude and the assigned gradient angle.

US Pat. No. 11,113,819

GRAPHICAL FIDUCIAL MARKER IDENTIFICATION SUITABLE FOR AUGMENTED REALITY, VIRTUAL REALITY, AND ROBOTICS

NVIDIA Corporation, Sant...


1. A method comprising:receiving image data representative of an image;
converting the image data from a higher dimensional color space to a converted image in a lower dimensional color space;
identifying first pixels corresponding to boundaries in the converted image;
detecting second pixels that represent candidate corner points;
determining a set of the candidate corner points that are within a threshold pixel distance to at least one of the boundaries based at least in part on comparing the first pixels to the second pixels;
analyzing the set of the candidate corner points to determine a subset of the candidate corner points representative of corners of at least one polygon; and
applying at least one filter to the at least one polygon to identify a polygon of the at least one polygon as corresponding to a fiducial marker boundary of a fiducial marker.

US Pat. No. 11,113,818

TIMING CONTROLLER AND OPERATING METHOD THEREOF

HIMAX TECHNOLOGIES LIMITE...


11. An operating method of a timing controller, comprising:providing image data of an input image comprising a plurality of pixels;
dividing the input image into a plurality of image blocks along a horizontal direction;
selecting the pixels located at one of columns of each of the image blocks as a plurality of target pixels;
obtaining each of gray levels of the pixels;
generating an average representative gray level of each of the image blocks according to a histogram of the gray levels of each of the image blocks;
inputting the average representative gray level of each of the image blocks into a first lookup table to obtain a first gain of corresponding image block;
inputting a vertical pixel position of each of the target pixels of each of the image blocks and the average representative gray level of the corresponding image blocks into a second lookup table to obtain a second gain of the corresponding target pixel of the corresponding image block;
obtaining each of compensated gray levels of the target pixels of each of the image blocks by multiplying the gray level of the corresponding target pixel, the first gain of the corresponding image block, and the second gain of the corresponding target pixel;
replacing the gray levels of the target pixels with the compensated gray levels of the corresponding target pixels, respectively, so as to acquire compensated image data; and
displaying an image via a display device comprising the timing controller according to the compensated image data.

US Pat. No. 11,113,817

SYSTEM AND METHOD FOR IDENTIFYING TARGET REGIONS PRIOR TO ORGANS AT RISK SEGMENTATION

TENCENT AMERICA LLC, Pal...


1. A method for generating a three dimensional (3D) bounding box of a region of interest (ROI) of a patient, comprising:receiving, by a device, a two dimensional (2D) maximum intensity projection (MIP) image that is an axial view of the patient;
receiving, by the device, a 2D MIP image that is a sagittal view of the patient;
detecting, by the device, a first 2D bounding box of the ROI of the patient using the 2D MIP image that is the axial view of the patient;
detecting, by the device, a second 2D bounding box of the ROI of the patient using the 2D MIP image that is the sagittal view of the patient;
receiving, by the device, a 3D MIP image of the patient;
generating, by the device, the 3D bounding box of the ROI of the patient using only the first 2D bounding box, the second 2D bounding box, and the 3D MIP image of the patient;
removing, by the device, data of the 3D MIP image that is not within the 3D bounding box, prior to performing organ at risk (OAR) segmentation; and
providing, by the device, the 3D MIP image including the 3D bounding box of the ROI of the patient and from which the data has been removed to permit the OAR segmentation using the 3D MIP image including the 3D bounding box of the ROI and from which the data has been removed.

US Pat. No. 11,113,816

IMAGE SEGMENTATION APPARATUS, METHOD AND RELEVANT COMPUTING DEVICE

BOE TECHNOLOGY GROUP CO.,...


1. An image segmentation apparatus, comprising:a feature extractor configured to extract N image semantic features having different scales from an input image, where N is an integer not less than 3; and
a feature processor comprising cascaded dense-refine networks and being configured to perform feature processing on the N image semantic features to obtain a binarized mask image of the input image,
wherein each of the dense-refine networks is configured to generate a low-frequency semantic feature from semantic features input thereto by: performing densely-connected convolution processing on the semantic features respectively to obtain respective image global features, performing feature fusion on the image global features to obtain a fused image global feature, and performing pooling processing on the fused image global feature to generate and output the low-frequency semantic feature; and
wherein the semantic features are selected from a group consisting of the N image sematic features and low-frequency semantic features generated by the dense-refine networks, and the feature processor is configured to obtain the binarized mask image based on a low-frequency semantic features generated by the dense-refine networks.

US Pat. No. 11,113,815

VIDEO PROCESSING METHODS AND SOFTWARE ARCHITECTURES FOR ANALYZING TRANSFORMATION IN OBJECTS

Purdue Research Foundatio...


1. A software architecture encoded on a non-transitory computer readable medium, the software architecture processing a method of processing a video, wherein the method comprises:discarding a set of unusable frames from a video, wherein the video comprises an object of interest;
selecting a set of usable frames and a reference frame from the video;
performing a first registration of each usable frame of the set of useable frames to the reference frame, thereby generating a set of updated usable frames;
storing a plurality of variables corresponding to the object of interest from each updated usable frame using a feature extraction algorithm;
detecting the object of interest from the each updated usable frame using the feature extraction algorithm;
determining a sub region containing the object of interest in the each updated useable frame;
performing color image contrast enhancement on each sub region of the each updated usable frame, thereby producing a plurality of enhanced updated usable sub region frames;
converting each enhanced updated useable sub region frame of the plurality of enhanced updated usable sub region frames into a grayscale sub region frame, thereby producing a plurality of greyscale sub region frames;
performing a second registration of each greyscale sub region frame of the plurality of greyscale sub region frames, thereby generating a plurality of updated greyscale sub region frames; and
calculating transformation parameters between the plurality of updated greyscale sub region frames.

US Pat. No. 11,113,814

DETERMINING RESPIRATORY PHASE FROM FLUOROSCOPIC IMAGES

APN Health, LLC, Pewauke...


1. A method of determining respiratory phase of a living body from a sequence of digitized fluoroscopic images of a living-body region exhibiting respiratory displacement, the method employing programmable computing apparatus and comprising the steps of:in each living-body-region image in the sequence, defining one or more zones with each image having identical image-to-image zone locations, sizes, and shapes;
for each image, computing an average pixel intensity for each zone to form a sequence thereof for each zone;
for each zone, modifying the average pixel intensities by:computing the mean value of the sequence of average pixel intensities for such zone; and
subtracting the mean from each average pixel intensity in the zone;

for each zone sequence, computing a figure-of-merit;
selecting the zone having the highest figure-of-merit; and
using the sequence of pixel intensities of the selected zone to determine respiratory phase.

US Pat. No. 11,113,813

EVALUATING A CONDITION OF A PERSON

SIEMENS HEALTHCARE GMBH, ...


1. A computer-implemented method for evaluating a condition of a person, comprising:acquiring a first image of at least a mouth of the person at a first time at which the person performs a first facial expression;
determining at least one characteristic of the first facial expression based at least on the first image acquired;
acquiring a second image of at least the mouth of the person at a second time at which the person performs a second facial expression, the first facial expression and the second facial expression being of a same first type of facial expression;
determining at least one characteristic of the second facial expression based at least on the second image acquired;
determining at least one difference between the at least one characteristic of the first facial expression determined and the at least one characteristic of the second facial expression determined; and
generating an output signal indicating the condition of the person based at least on the at least one difference determined,
wherein at least one of the acquiring of the first image and the acquiring of the second image includes acquiring a video of at least the mouth of the person and determining a characterizing frame of the video acquired as at least one of the first image acquired and the second image acquired, and
wherein one ofthe characterizing frame of the video acquired is automatically determined based on a criterion, or
a user or the person is prompted to select one of the frames of the video acquired as the characterizing frame.


US Pat. No. 11,113,812

QUANTITATIVE IMAGING FOR DETECTING VULNERABLE PLAQUE

ELUCID BIOIMAGING INC., ...


1. A method for computer aided detection of high risk plaque for a pathology using an enriched radiological dataset, the method comprising:receiving a radiological dataset for a patient, wherein the radiological dataset is obtained non-invasively;
enriching the dataset by performing analyte measurement and/or classification of one or more of: (i) anatomic structure, (ii) shape or geometry or (iii) tissue characteristic, type or character, with objective validation for a set of analytes relevant to a pathology, wherein the analyte measurement and/or classification of anatomic structure, shape, or geometry and/or tissue characteristic, type, or character includes semantic segmentation to identify and classify regions of interest in the radiological dataset, wherein the regions of interest are identified with respect to cross-sections of a tubular structure in the radiological dataset; and
using a machine learned classification approach based on known ground truths to process the enriched dataset and determine a high risk plaque for the pathology.

US Pat. No. 11,113,811

SYSTEMS, METHODS, AND DEVICES FOR MEDICAL IMAGE ANALYSIS, DIAGNOSIS, RISK STRATIFICATION, DECISION MAKING AND/OR DISEASE TRACKING

Cleerly, Inc., New York,...


1. A normalization device configured to facilitate normalization of medical images of a coronary region of a subject for an algorithm-based medical imaging analysis, the normalization device comprising:a substrate having a width, a length, and a depth dimension, the substrate having a proximal surface and a distal surface, the proximal surface adapted to be placed adjacent to a surface of a body portion of the subject; a plurality of compartments positioned within the substrate, each of the plurality of compartments configured to hold a sample of a known material, wherein: a first subset of the plurality of compartments hold at least one sample of a contrast material, a second subset of the plurality of compartments hold samples of materials representative of materials to be analyzed by the algorithm-based medical imaging analysis, wherein a first compartment of the first subset of the plurality of compartments is positioned immediately adjacent to a second compartment of the second subset of the plurality of compartments such that a first sample held in the first compartment is juxtaposed with a second sample held in the second compartment
wherein the samples of materials representative of materials to be analyzed comprise at least two samples of calcium having different radiodensities, and a third subset of the plurality of compartments hold at least one sample of a phantom material;
and an attachment mechanism on the proximal surface of the substrate and configured to attach the normalization device to the body portion of the subject.

US Pat. No. 11,113,810

X-RAY CT SCANNER, IMAGE GENERATION METHOD, AND IMAGE GENERATION PROGRAM

HITACHI, LTD., Tokyo (JP...


1. An X-ray CT system comprising,a raw data acquisition part configured to acquire raw data obtained by applying X-rays to a subject placed in imaging space and by detecting a distribution of X-ray strength passing through the subject, the raw data being associated with multiple views at different X-ray irradiation angles to the subject,
an image reconstructor configured to apply a smoothing process to the raw data associated with multiple views, followed by image reconstruction to obtain a smoothed image of a predetermined region to be imaged in the imaging space,
a sharpening processor configured to apply more intense sharpening to pixels in a region of a central part of the subject in the smoothed image, than to pixels in a region of a peripheral part of the subject, and
a subject model generator configured to create a subject model that represents a form and position of the subject in the region to be imaged, in an approximate manner, by using one or more predetermined shapes and the position thereof,
wherein the sharpening processor brings the subject model into correspondence with the smoothed image, and applies more intense sharpening to pixels in the region of the smoothed image corresponding to the region of the central part of the predetermined shape of the subject model, than to pixels in the region of the smoothed image corresponding to the region of the peripheral part of the predetermined shape.

US Pat. No. 11,113,809

GROUP SPARSITY MODEL FOR IMAGE UNMIXING

VENTANA MEDICAL SYSTEMS, ...


1. A non-transitory computer-readable storage medium storing instructions executable by a processor to perform operations comprising:accessing an image depicting a biological tissue sample, the image comprising colocation markers and non-colocation markers, wherein each of the colocation and non-colocation markers corresponds to a type of cell structure;
associating the colocation markers to a first group of a set of groups based on the type of cell structure indicated by each of the colocation markers, wherein each group of the set of groups represents a particular tissue characteristic;
associating each of the non-colocation markers to a separate group of the set of groups;
generating a group sparsity model for the image, the group sparsity model comprising a fraction of a stain contribution that is estimated based on the colocation markers of the first group and a fraction of a stain contribution that is estimated based on the non-colocation markers of the respective separate groups;
solving the group sparsity model using an unmixing algorithm to yield a least-squares solution for each group of the set of groups; and
outputting a set of unmixed images, wherein each unmixed image of the set of unmixed images corresponds to a group of the set of groups and is determined based at least in part on the least-squares solution of the group.

US Pat. No. 11,113,808

SYSTEM AND METHOD FOR ASSESSING QUALITY OF PRODUCE

Walmart Apollo, LLC, Ben...


1. A system for assessing quality of produce at a facility comprising:a produce assessment station configured to provide a staging area to determine a quality classification of a target produce and comprising:a fixed surface;
a rotatable base disposed on the fixed surface and configured to:rotate on an axis; and
secure the target produce when on the rotatable base;

a first arm coupled to the fixed surface and comprising a microphone;
a second arm comprising a tapping device; and
a local control circuit configured to control and couple to the rotatable base, thefirst arm, and the second arm, the local control circuit configured to:
periodically rotate the rotatable base at a particular angle and at a particular time interval in multiple rotations until the target produce has been rotated in substantially a full circle, wherein the particular angle and the particular time interval are programmed to the local control circuit to automatically rotate the rotatable base periodically; and
receive audio data from the microphone, wherein the audio data corresponds to sound created by the tapping device contacting the target produce at each periodic rotation;


a plurality of sensors coupled to the local control circuit, wherein each of the plurality of sensors is configured to:capture one or more images of the target produce at different side view of the target produce while on the rotatable base; and
provide the one or more images to the local control circuit; and

a portable device wirelessly coupled to the local control circuit, the portable device configured to provide a signal to the local control circuit to initiate the quality classification of the target produce.

US Pat. No. 11,113,807

METHOD OF DETECTING PROCESS IRREGULARITIES BY MEANS OF VOLUME IMAGE DATA OF THE MANUFACTURED OBJECT

EOS GmbH Electro Optical ...


1. A method of detecting a particular process irregularity in an additively manufactured object, comprising the steps of:x) acquiring volume image data of a volume of the object;
y) comparing the volume image data with a number of characteristic data each referring to a selected process irregularity, the characteristic data having been derived in a process of training a detection system that is able to acquire volume image data in an additively manufactured object for detecting process irregularities; and
z) outputting information referring to the particular process irregularity in a finding location in the object if the volume image data in the finding location match the characteristic data of that particular process irregularity,
wherein the process of training the detection system that is able to acquire volume image data in the additively manufactured object for the detection of process irregularities comprises the steps of:a) receiving process irregularity data referring to a selected location within an additively manufactured reference object where a predefined process irregularity occurred during the additive manufacture of the object;
b) acquiring volume image data of a volume of the reference object comprising at least the selected location by the detection system;
c) identifying within the volume image data characteristic data representing a difference between the volume image data of the selected location compared to the volume image data of at least one other location of the reference object and/or of a number of other additively manufactured objects in which in at least one other location no process irregularity has occurred and/or no process irregularity is suspected; and
d) assigning to the predefined process irregularity the characteristic data as a representative of the predefined process irregularity.


US Pat. No. 11,113,806

SYSTEMS AND METHODS FOR MENU DIRECTED INSPECTION

Baker Hughes, a GE Compan...


1. A method of performing non-destructive testing (NDT), comprising:providing, by a processor of an NDT device including a camera and a display, a current view acquired by the camera in the display;
providing, by the processor, an inspection point screen in the display overlaid atop the current view acquired by the camera, the inspection point screen including a tree model identifying a hierarchical arrangement of NDT inspection locations of machinery to be inspected using the NDT device, the tree model including a plurality of nodes ordered within the tree model with respect to the hierarchical arrangement, each node of the plurality of nodes identifying a component of the machinery located at one of the inspection locations;
providing, by the processor, the tree model of the inspection in a web browser of a computing device communicatively coupled to the NDT device, the web browser displaying a web page including the inspection point screen, the tree model, and one or more inspection progress controls controlling recording and playback of inspection data acquired at and associated with each node in the tree model identifying the hierarchical arrangement of the inspection locations of the machinery;
receiving, by the processor, a first user input on the NDT device selecting a node included in the tree model;
acquiring, by the processor, inspection data of the component at the inspection location via the camera;
associating, by the processor, the inspection data with the selected node;
providing, by the processor, the inspection data to the computing device for display in the web page displaying the inspection point screen and the tree model, the inspection data displayed automatically in real-time as the inspection data is acquired; and
receiving a second user input controlling at least one of recording or playback of the inspection data in the inspection point screen displayed in the web page using the one more inspection progress controls.

US Pat. No. 11,113,805

AUTOMATIC ATTACHING 3D TEMPERED GLASS SCREEN PROTECTOR ATTACHING MACHINE


1. An automatic attaching 3D tempered glass screen protector attaching machine comprising an identification device, wherein the identification device comprises: a processor, a camera and a memory;the camera is configured to collect a front picture and a back picture of the mobile phone;
the processor is configured to identify the back picture to determine the brand of the mobile phone, identify the front picture to determine the model of the mobile phone, and determine the category of the screen protector according to the brand and model of the mobile phone, and send the category to the attaching mechanism to complete attaching the screen protector.

US Pat. No. 11,113,804

QUALITY ESTIMATION DEVICE, QUALITY ESTIMATION METHOD, AND QUALITY ESTIMATION PROGRAM

OMRON Corporation, Kyoto...


1. A quality estimation device comprising a processor configured with a program to perform operations comprising:operation as a first acquisition unit configured to acquire first information pertaining to a positioning of a worker executing a work step included in a process for manufacturing a product on a production line;
operation as a second acquisition unit configured to acquire second information pertaining to a usage condition of a tool the worker uses in the work step;
operation as an estimation unit configured to estimate quality of a product being made through the work step according to a degree to which the positioning of the worker represented by the acquired first information conforms to a predetermined first standard comprising an upper threshold associated with a distance between a head of the worker and the tool and a lower threshold associated with the distance between the head of the worker and the tool, and a degree to which the usage condition of the tool represented by the acquired second information conforms to a predetermined second standard comprising an upper threshold associated with an angle of the tool relative to a hand of the worker holding the tool and a lower threshold associated with the angle of the tool relative to the hand of the worker holding the tool; and
operation as an output unit configured to output information pertaining to a result of estimating the quality of the product.

US Pat. No. 11,113,802

PROGRESSIVE IMAGE FUSION

Apple Inc., Cupertino, C...


1. A device, comprising:a memory;
one or more image capture devices;
a display;
a user interface; and
one or more processors operatively coupled to the memory, wherein the one or more processors are configured to execute instructions causing the one or more processors to:obtain a first batch of images captured by the one or more image capture devices;
select a reference image from the first batch of images and register one or more images of the first batch of images to the reference image;
perform a first fusion operation on the registered first batch of images to output a first fused image;
designate the first fused image as a current intermediate fusion image;
successively perform a subsequent fusion sequence at least one time, wherein each subsequent fusion sequence comprises:obtaining a subsequent batch of images captured by the one or more image capture devices;
registering one or more images of the subsequent batch of images to the reference image;
performing a subsequent fusion operation on: the subsequent batch of images, the current intermediate fusion image, and the selected reference image to output an updated fused image; and
designating the updated fused image as the current intermediate fusion image; and

following completion of the last subsequent fusion sequence, store the current intermediate fusion image as an output fused image in the memory.


US Pat. No. 11,113,801

ROBUST IMAGE MOTION DETECTION USING SCENE ANALYSIS AND IMAGE FRAME PAIRS

Apple Inc., Cupertino, C...


1. A device, comprising:a memory;
one or more image capture devices;
a display;
a user interface; and
one or more processors operatively coupled to the memory, wherein the one or more processors are configured to execute instructions causing the one or more processors to:obtain an incoming image stream from the one or more image capture devices;
select two or more images from the incoming image stream, wherein the selected two or more images comprise at least one image frame pair (IFP), wherein the IFP comprises a first image frame and a second image frame that were captured consecutively and with differing exposure settings;
determine one of the first image frame or the second image frame to be designated as a reference image, wherein the determination is based, at least in part, on a comparison of an amount of motion in the first image frame to an amount of motion in the second image frame;
determine one or more of the selected two or more images not designated as a reference image to be designated as candidate images;
register the one or more candidate images with the reference image;
fuse the registered one or more candidate images and the reference image, resulting in a fused image; and
store the fused image in the memory.


US Pat. No. 11,113,800

FILTERING IMAGE DATA USING A NEURAL NETWORK

NVIDIA CORPORATION, Sant...


1. A method for performing spatiotemporal filtering, comprising:identifying image data to be rendered, the image data including:color data, and
one or more auxiliary features that include at least one of one or more view-space shading normals, one or more depth values, or one or more roughness values;

reconstructing the image data to create reconstructed image data, utilizing a filter including a neural network that processes the image data based on the one or more auxiliary features, the neural network having:
one or more skip connections, and
one or more recurrent layers that retain, at least in part, the one or more auxiliary features unchanged; and
returning the reconstructed image data and the unchanged one or more auxiliary features.

US Pat. No. 11,113,799

DISPLAY METHOD AND DISPLAY DEVICE

BEIJING BOE OPTOELECTRONI...


1. A display method for a display device having a lens unit and a display unit, comprising:detecting a first distance between the lens unit and the display unit;
calculating correction information according to the first distance and transmitting the correction information to the display unit; and
displaying a corrected image by the display unit according to the correction information, so that the corrected image is converged into eyes of a user via the lens unit, wherein the corrected image is obtained by correcting an original image according to the first distance.

US Pat. No. 11,113,798

COLLATING SYSTEM, COLLATING METHOD, AND CAMERA DEVICE

PANASONIC I-PRO SENSING S...


1. A collating system comprises:a camera device configured to capture image data of a monitoring target area; and
a server device communicably connected to the camera, and the server device is configured tostore a plurality of reference images from a plurality of viewpoints;
store an image correction model;
process the reference images using the image correction model to generate a plurality of corresponding sharpened reference images;
store the sharpened reference images;
send, to the camera device, the image correction model,

wherein the camera device is configured todetect an object appearing in the captured image data of the monitoring target area,
generate a target image of the object from the captured image data,
generate, using the image correction model received from the server device, a sharpened image based on the target image of the object, and
send the sharpened image to the server device, and

wherein the server device is configured to:receive and store the sharpened image sent from the camera device,
perform collating processing of the object corresponding to the sharpened image based on the sharpened image generated using the image correction model, and the plurality of sharpened reference images generated using the same image correction model used by the camera, and
send a result of the collating processing including identification information of the object to an external device,

wherein the server device is further configured tostore a first image set including an image related to the object,
improve an image quality degradation factor caused by capturing of the object based on the image related to the object and the image correction model, and
add the generated sharpened image in a second image set stored in the server device,

wherein the image quality degradation factor is unevenness occurring in a partial region of the object appearing in the captured image due to sunlight, and
wherein the server devicegenerates a pseudo unevenness in a partial region of the image related to the object read from the first image set,
generates a sharpened image corresponding to the image having the pseudo unevenness based on the image correction model, and
adds the sharpened image in the second image set stored in the server device.


US Pat. No. 11,113,797

PASSIVE FLASH IMAGING

Snap Inc., Santa Monica,...


1. A method comprising:generating, using one or more processors of a user device, an image sequence using an image sensor of the user device;
displaying, on a display device of the user device, the image sequence in a live preview window;
generating an elevated brightness element on the display device while the live preview window is displaying the image sequence, the elevated brightness element being brighter than the live preview window in the display device;
capturing one or more images generated by the image sensor while the elevated brightness element and the live preview window are displayed on the display device; and
resizing the live preview window in the display device, wherein the elevated brightness element is generated in an area of the display device that was occupied by the live preview window prior to resizing.

US Pat. No. 11,113,796

IMAGE ENHANCEMENT CIRCUIT AND METHOD THEREOF

DELTA ELECTRONICS, INC., ...


1. An image enhancement method, comprising:separating an original image signal into a high frequency image signal and a low frequency image signal through performing a wavelet transform by a first transformation circuit;
separating the high frequency image signal into a high frequency separation signal and a high-intermediate frequency separation signal through performing the wavelet transform by a second transformation circuit;
separating the low frequency image signal into a low-intermediate frequency separation signal and a low frequency separation signal through performing the wavelet transform by a third transformation circuit;
enhancing the high frequency separation signal by a high frequency enhancement circuit to generate an enhanced high frequency separation signal;
enhancing the low frequency separation signal by a low frequency enhancement circuit to generate an enhanced low frequency separation signal; and
integrating the enhanced high frequency separation signal, the high-intermediate frequency separation signal, the low-intermediate frequency separation signal and the enhanced low frequency separation signal into an enhanced image signal through performing an inverse wavelet transform by an inverse transformation circuit.

US Pat. No. 11,113,795

IMAGE EDGE PROCESSING METHOD, ELECTRONIC DEVICE, AND COMPUTER READABLE STORAGE MEDIUM

SHENZHEN CHINA STAR OPTOE...


1. An image edge processing method, comprising steps of:extracting a brightness component from an input image;
calculating an edge probability value mp of each pixel in the image according to the brightness component;
calculating an enhancement coefficient ? for each pixel based on the edge probability value mp;
performing a noise detection according to the brightness component, and determining if each pixel in the image is a noise point;
when the pixel is not a noise point, performing a logarithmic processing to the pixel in order to obtain a data w;
enhancing an edge of the image according to the ?, the w and the brightness component in order to obtain an enhanced brightness component data; and
after performing a brightness component synthesis according to the enhanced brightness component data, outputting an enhanced image;
wherein the method further comprises a step of:
when a pixel is a noise point, performing a Gaussian filtering to the pixel in order to perform a noise reduction;
wherein after the step of extracting a brightness component from an input image, the method comprise a step of: increasing the number of bits of the brightness component in order to calculate an edge probability value mp of each pixel in the image according to the brightness component after increasing the number of bits; and
after the step of obtaining an enhanced brightness component data, the method further comprises a step of: converting the enhanced brightness component data to a low bit through dithering in order to perform the brightness component synthesis according to the brightness component data after being converted.

US Pat. No. 11,113,794

SYSTEMS AND METHODS FOR GENERATING DEFOCUS BLUR EFFECTS

Facebook Technologies, LL...


1. A method for using a machine-learning model to generate images with defocus-blur effects based on in-focus input images and corresponding depth maps, the method comprising, by a computing system:receiving current eye-tracking data associated with a user of a head-mounted display;
dynamically adjusting a focal length of the head-mounted display based on the current eye-tracking data;
generating an in-focus image of a scene and a corresponding depth map of the scene;
generating a circle-of-confusion map for the scene based on the depth map, wherein the circle-of-confusion map encodes a desired focal surface in the scene;
generating, using the machine-learning model, an output image with a synthesized defocus-blur effect by processing the in-focus image, the corresponding depth map, and the circle-of-confusion map of the scene; and
displaying the output image with the synthesized defocus-blur effect to the user via the head-mounted display having the adjusted focal length.

US Pat. No. 11,113,793

METHOD AND APPARATUS FOR SMOOTHING A MOTION TRAJECTORY IN A VIDEO


1. A method for smoothing a motion trajectory in a video, comprising:obtaining a video frame sequence of an input video, and obtaining an original rotation matrix Rold of each video frame;
obtaining an original rotation matrix sequence xold=[R1old, R2old, . . . , Rnold]T of the video frame sequence that varies with time, according to the original rotation matrix of each video frame Rold;
assuming a smooth rotation matrix sequence obtained after smoothing the original rotation matrix xold is xnew=[R1new, R2new, . . . , Rnnew]T, then a geodesic distance between a smooth rotation matrix Rnnew and a corresponding original rotation matrix Rnold is dg2(Rnold, Rnnew), and a geodesic distance between two adjacent smooth rotation matrices is dg2(Rnnew, Rn+1new);
determining an objective function based on Riemann manifold architecture:




iteratively solving for the smooth rotation matrix Rnnew that minimizes the objective function according to Riemannian manifold constrained smoothing algorithm, and further obtaining the smooth rotation matrix sequence xnew; and
performing image stabilization on the video frame sequence, based on the smooth rotation matrix sequence xnew.

US Pat. No. 11,113,792

TEMPORAL-SPATIAL DENOISING IN RAY-TRACING APPLICATIONS

NVIDIA CORPORATION, Sant...


1. A method comprising:generating rendered frames of a scene using locations of filter taps of spatial filters that are jittered, wherein for each rendered frame of a plurality of the rendered frames, generating the rendered frame comprises:
determining a size of a spatial filter of the spatial filters for pixels of the rendered frame based at least in part on render data representative of ray-traced samples of the scene;
selecting the locations of the filter taps of the spatial filter that correspond to a subset of pixel positions of the spatial filter based at least in part on jittering at least one location corresponding to at least one selection parameter between the spatial filters; and
applying the spatial filter to the pixels using the filter taps to sparsely sample data values within the spatial filter that correspond to ray-traced samples of lighting conditions of the scene.

US Pat. No. 11,113,791

IMAGE NOISE REDUCTION USING SPECTRAL TRANSFORMS

FLIR SYSTEMS, INC., Wils...


1. A method comprising:determining row values for image frames comprising scene information and noise information;
performing first spectral transforms in a first domain on corresponding subsets of the row values to determine first spectral coefficients;
performing second spectral transforms in a second domain on corresponding subsets of the first spectral coefficients to determine second spectral coefficients;
selectively adjusting the second spectral coefficients;
performing reverse second spectral transforms in the second domain on corresponding subsets of the adjusted second spectral coefficients to determine adjusted first spectral coefficients;
performing reverse first spectral transforms in the first domain on corresponding subsets of the adjusted first spectral coefficients to determine adjusted row values; and
determining the row correction terms based on the adjusted row values.

US Pat. No. 11,113,790

ADDING GREATER REALISM TO A COMPUTER-GENERATED IMAGE BY SMOOTHING JAGGED EDGES

NVIDIA CORPORATION, Sant...


1. A method comprising:applying temporal antialiasing (TAA) to an image, wherein for each pixel of at least a subset of pixels, the TAA compares a historical value for the pixel in a previous frame with current values of neighboring pixels to the pixel in a current frame;
identifying failure pixels resulting from applying the TAA to the image, where each pixel of the at least a subset of pixels with the historical value that differs from the current values of the neighboring pixels by more than a predetermined amount is identified as a failure pixel; and
performing antialiasing on each of the failure pixels, utilizing a combination of ray tracing and fast approximate anti-aliasing (FXAA).

US Pat. No. 11,113,789

METHOD AND DEVICE FOR DIGITAL IMAGE RESTORATION


1. A method for restoring a digital image, the digital image to be restored being derived from an initial image acquired by an image acquisition device having an associated acquisition instrumental noise, the method including the steps of:obtaining an intermediate digital image with restitution of the associated acquisition instrumental noise;
denoising the intermediate digital image to obtain a denoised intermediate digital image; and
deconvoluting the denoised intermediate digital image to obtain a restored digital image, wherein the step of obtaining an intermediate digital image comprises sub-steps of:
obtaining, by applying a transformation called compression transformation, of a representation of the digital image to be restored by a plurality of coefficient blocks, each coefficients block of the plurality of coefficient blocks corresponding to a pixels block of the digital image to be restored;
for at least one processed coefficient of a coefficients block:
calculating a noise threshold as a function of a value representative of an image acquisition instrumental noise model;
comparing an absolute value of the at least one processed coefficient to the noise threshold; and
when the absolute value of the at least one processed coefficient is higher than or equal to the noise threshold, the at least one processed coefficient is left unchanged,
when the absolute value of the at least one processed coefficient is lower than the noise threshold, replacing the absolute value of the at least one processed coefficient with a noise value depending on the value representative of the image acquisition noise model.

US Pat. No. 11,113,788

MULTI-SPACE RENDERING WITH CONFIGURABLE TRANSFORMATION PARAMETERS

Apple Inc., Cupertino, C...


1. An apparatus, comprising:graphics circuitry configured to:access primitive data, including coordinates of primitives in a virtual space;
receive transformation parameters, based on execution of one or more instructions of a graphics program that specify different transformation parameters for different portions of a second space, including different scale factor values and different offset values for different portions of the second space;
store the received transformation parameters in respective sets of one or more registers corresponding to respective portions of the second space;
prior to rasterization of the primitives, transform coordinates of primitives in the virtual space into coordinates of primitives in the second space based on the stored transformation parameters, including using the different transformation parameters stored in the different sets of registers for different portions of the second space;
rasterize the primitives based on the primitive coordinates in the second space to generate fragment data, wherein use of the different transformation parameters during the transformation causes different portions of the virtual space to be sampled at different sample rates; and
process at least a portion of the fragment data to determine pixel attributes.


US Pat. No. 11,113,787

IMAGE DISTRIBUTION DEVICE, IMAGE DISTRIBUTION SYSTEM, IMAGE DISTRIBUTION METHOD, AND IMAGE DISTRIBUTION PROGRAM

AMATELUS INC., Tokyo (JP...


1. An image distribution device comprising:an acquisition unit that acquires a plurality of pieces of moving image data imaged at different points;
a data generating unit that generates still image data by extracting a frame for every predetermined time as a still image for each of the plurality of pieces of moving image data acquired by the acquisition unit;
a storage unit that stores the still image data in association with position data representing an imaging position at which a subject has been imaged in each of the plurality of pieces of moving image data and time data representing a time at which the still image data has been imaged;
a designated value accepting unit that accepts a position designation value for designating the position data in the still image data desired to be viewed by a user; and
a selection unit that selects the still image data in accordance with the time data on the basis of the position designation value accepted by the designated value accepting unit and transmits the selected still image data to an external display device via a communication network,
wherein the selection unit selects the still image data corresponding to the position designation value that has already been designated in a case in which the designated value accepting unit has not accepted the position designation value and selects the corresponding still image data on the basis of a change in the position designation value by using the time data of the still image data corresponding to a time at which the position designation value has been accepted as a reference in a case in which the designated value accepting unit has accepted the position designation value.

US Pat. No. 11,113,786

ASTC INTERPOLATION

Imagination Technologies ...


1. A binary logic circuit for performing an interpolation calculation between two endpoint values E0 and E1 using a weighting index i for generating an interpolated result P, the values E0 and E1 being formed from Adaptive Scalable Texture Compression (ASTC) colour endpoint values C0 and C1 respectively, the colour endpoint values C0 and C1 being low-dynamic range (LDR) or high dynamic range (HDR) values, the circuit comprising:an interpolation unit configured to perform an interpolation between the colour endpoint values C0 and C1 using the weighting index i to generate a first intermediate interpolated result C2;
combinational logic circuitry configured toreceive the first intermediate interpolated result C2;
determine whether the colour endpoint values are LDR values or HDR values;
in response to determining that the colour endpoint values are LDR values, output the interpolated result P calculated using one or more logical processing operations according to the equation: (1) P=?((C2«8)+C2+32)/64? when the interpolated result is not to be compatible with an sRGB colour space; (2) P=?((C2«8)+128.64+32)/64? when the interpolated result is to be compatible with an sRGB colour space; and
in response to determining that the colour endpoint values are HDR values, output the interpolated result P calculated using one or more logical processing operations according to the equation: (3) P=(C2+2)»2.


US Pat. No. 11,113,785

MITIGATING LATENCY-BASED DISPLAY DELAYS

International Business Ma...


1. A method comprising:receiving, from a display, a movement notification, wherein the movement notification corresponds to a movement;
rendering, by a graphical processing unit, a set of movement frames that reflect the movement;
transmitting, to the display, the set of movement frames;
receiving, from the display, a notification that the movement has ceased; and
transmitting, to the display, a stop command, wherein the stop command instructs the display to not display a first subset of frames in the set of movement frames, wherein the first subset of frames reflects the end of the movement.

US Pat. No. 11,113,784

SPARSE OPTIMIZATIONS FOR A MATRIX ACCELERATOR ARCHITECTURE

Intel Corporation, Santa...


1. A general-purpose graphics processor comprising:a compute cluster including multiple processing resources coupled with a cache memory, at least one processing resource including a matrix accelerator, the matrix accelerator configured to perform a matrix multiply operation on multiple elements of a first matrix and a second matrix, wherein the first matrix is a sparse matrix, wherein elements of the first matrix are compressed into a first compressed representation, and wherein the first compressed representation includes a set of non-zero value elements and metadata to identify the non-zero value elements;
wherein the compressed representation is to be stored to the cache memory in a second compressed representation that includes a compressed set of non-zero value elements; and
wherein the at least one processing resource is configured to:load the second compressed representation from the cache memory and store the second compressed representation to a memory within the at least one processing resource in the first compressed representation;
load selected elements of the second matrix from the cache memory and store the selected elements to the memory within the at least one processing resource, wherein the selected elements of the second matrix correspond with non-zero value elements of the first matrix stored within the first compressed representation and are selected based on the metadata for the non-zero value elements;
perform the matrix multiply operation on elements from the first compressed representation and the selected elements of the second matrix; and
write output of the matrix multiply operation to the memory within the at least one processing resource.


US Pat. No. 11,113,783

PROGRAMMABLE RE-ORDER BUFFER FOR DECOMPRESSION

Intel Corporation, Santa...


1. A graphics processing apparatus comprising:an interface to a memory device;
a reorder buffer system coupled to the interface to the memory device, the reorder buffer system comprising a random access memory and a tracker; and
an interface to couple the reorder buffer system to a decompressor, wherein:the random access memory is to store data prior to output to the interface coupled to the decompressor,
the tracker is to cause data to be provided to the interface to the decompressor in order of allocation,
an amount of memory resources in the random access memory allocated for a reorder buffer (ROB) to reorder received data is dynamically reconfigured based on a mode of operation,
the mode of operation is based on a profile of an application associated with use of the ROB, and
the profile of the application is to identify a percentage of compressed data transferrable over a memory bus using more than one clock cycle.


US Pat. No. 11,113,782

DYNAMIC KERNEL SLICING FOR VGPU SHARING IN SERVERLESS COMPUTING SYSTEMS

VMware, Inc., Palo Alto,...


1. A system for dynamic kernel slicing in a serverless computing service, comprising:at least one computing device;
program instructions stored in memory and executable in the at least one computing device that, when executed by the at least one computing device, direct the at least one computing device to:receive a request for execution of program code in the serverless computing service in which a plurality of virtual graphics processing units (vGPUs) are used in the execution of the program code on an underlying physical graphics processing unit (GPU);
in response to receipt of the request for execution of the program code, determine a slice size to partition a compute kernel of the program code into a plurality of sub-kernels for concurrent execution by the vGPUs, the slice size being determined for individual ones of the sub-kernels using an optimization function in accordance with a scheduling policy;
determine an execution schedule for executing the individual ones of the sub-kernels on the vGPUs in accordance with the scheduling policy; and
execute the sub-kernels on the vGPUs as partitioned in accordance with the execution schedule.


US Pat. No. 11,113,781

IMAGE-BASED POSE DETERMINATION

Digimarc Corporation, Be...


1. An image processing method that includes the acts: receiving a two-dimensional (2D) array of image values, and applying a 2D filter kernel to the received 2D array of image values to produce a filtered array of image values as output data, characterized in that the 2D filter kernel comprises a center coefficient and plural non-center coefficients, wherein (a) the center coefficient of the 2D filter kernel has a first polarity and all of the plural non-center coefficients of the 2D filter kernel have a second, opposite polarity; (b) two of said coefficients are real-valued rather than integer-valued; and (c) the 2D filter kernel comprises three non-center coefficients having different values.

US Pat. No. 11,113,780

WATERMARKING DIGITAL CONTENT

Hewlett-Packard Developme...


1. A method comprising:determining a digital quality of digital content received for watermarking;
retrieving, from a library of watermark tints comprising a plurality of preformed watermark tints of predefined sizes, a watermark tint set for watermarking the digital content, the watermark tint set comprising a plurality of watermark tints having a first size, wherein the first size of the plurality of watermark tints is determined based on the digital quality of the digital content; and
overlaying the plurality of watermark tints of the first size over the digital content to watermark the digital content.

US Pat. No. 11,113,779

DIGITAL WATERMARKING LEVERAGING ANOMALOUS MESH ELEMENTS

Microsoft Technology Lice...


1. One or more computing devices for creating a digital watermark, comprising:hardware logic circuitry, the hardware logic circuitry corresponding to: (a) one or more hardware processors that perform operations by executing machine-readable instructions stored in a memory; or (b) one or more other hardware logic components that perform the operations using a task-specific collection of logic gates; or (a) and (b), the operations including:
providing a file having a data structure that expresses an original mesh, the original mesh describing a three-dimensional object, the original mesh having:
a plurality of vertices that have respective locations in the original mesh;
a plurality of edges that connect the vertices together; and
a plurality of polygonal shapes defined by the vertices and the edges;
searching the data structure for at least one anomalous element of the original mesh that qualifies as a statistically atypical occurrence within the original mesh, based on a predetermined rule that defines what constitutes a statistically atypical occurrence;
subdividing one or more anomalous elements that are identified to produce subdivisions that are chosen to collectively encode values of a computer-readable code including the digital watermark, said subdividing producing a modified mesh file and comprising, for each anomalous element of the one or more anomalous elements, adding a new vertex on each existing edge, for a plurality of existing edges, wherein the adding comprises choosing a location at which the new vertex is placed on the each existing edge, and wherein the location defines a particular value of the values of the computer-readable code; and
storing the modified mesh file on a computer-readable medium, the computer-readable code being embedded in said one or more anomalous elements, and being extractable from said one or more anomalous elements by reading the values that are expressed by the subdivisions, said reading the values comprising, for the each anomalous element of the one or more anomalous elements, successively reading edges that include new vertices that are arrayed around a center vertex, starting with a chosen edge.

US Pat. No. 11,113,778

SYSTEM AND METHOD FOR INCORPORATING A WAGERING ACTIVITY INTO AN ELECTRONIC COMMERCE TRANSACTION


1. A system for incorporating at least one wager activity into an electronic commerce transaction, comprising:a merchant device associated with a merchant, said merchant device comprising at least one server device and at least one memory device for storing a first set of machine readable instructions; and
a host device associated with a host, said host device comprising at least one other server device and at least one other memory device for storing a second set of machine readable instructions;
wherein said first set of machine readable instructions are adapted to perform the steps of:receiving via a wide area network (WAN) a selection from a user device operated by a user, said selection selecting an item from a plurality of items available for purchase from said merchant;
receivng via said WAN a request from said user device to purchase said item, said request resulting in said item being placed into a virtual shopping cart on a website operated by said merchant, said virtual shopping cart being linked to a session identifier; and
receiving via said WAN a request from said user device to wager on at least a portion of a purchase price of said item in said virtual shopping cart, said request to wager resulting in said merchant device providing to said host device wagering information comprising a wager request, said session identifier, and said purchase price;

wherein said second set of machine readable instructions are adapted to perform the steps of:receiving via said WAN said wagering information from said merchant device;
receiving via said WAN purchase information, said purchase information comprising (i) payment information, (ii) a wager amount, and (iii) a predictive outcome, wherein at least said wager amount and said predictive outcome are received from said user device and said payment information comprises a first financial account of said user, said first financial account being used to transfer money from said user to said host;
using said payment information to secure payment of at least said wager amount from said user;
performing a wager activity resulting in an outcome;
comparing said outcome with said predictive outcome to determine whether there is a match therebetween;
using at least second payment information and said session identifier to purchase said item from said merchant when said outcome matches said predictive outcome, said second payment information comprising a second financial account of said host, said second financial account being used to transfer said amount of money from said host to said merchant, said second financial account being separate and distinct from said first financial account; and
using, at least said session identifier to instruct said merchant device to remove said item from said virtual shopping cart, returning said item to inventory, when said outcome differs from said predictive outcome.


US Pat. No. 11,113,777

TECHNIQUES FOR DETECTING AND MANAGING CONGESTION WITHIN A WORKSPACE

Amazon Technologies, Inc....


1. A system, comprising:a plurality of mobile drive units located within a sortation facility and individually configured to move items within the sortation facility;
one or more data networks;
one or more processors; and
one or more memories storing computer-readable instructions that, upon execution by the one or more processors, cause the system to at least:obtain an electronic representation of an area of the sortation facility;
generate, utilizing the electronic representation, a set of volumes representing sub-areas of the area;
obtain navigational data corresponding to each of the plurality of mobile drive units, the navigational data corresponding to a plurality of historical time periods;
generate a plurality of density values for each of the set of volumes based at least in part on the navigational data corresponding to each of the plurality of historical time periods;
identify a congested volume from the set of volumes based at least in part on the plurality of density values;
generate supplemental data for the congested volume, wherein the supplemental data identifies attributes of congestion within the congested volume;
perform at least one remedial action based at least in part on the supplemental data;
obtain subsequent navigational data corresponding to at least one of the plurality of mobile drive units;
determine the congested volume remains congested; and
in response to determining the congested volume remains congested, forgo generation of subsequent supplemental data for the congested volume thereby reducing a processing burden of the system.


US Pat. No. 11,113,776

SYSTEMS AND METHODS FOR PROTECTING USER IDENTITY WITHIN ONLINE CONTENT PROVIDING ENVIRONMENTS

Google LLC, Mountain Vie...


1. A computer-implemented method for protecting user identity within online content providing environments, said method comprising:identifying a request for an online content item associated with an online device, wherein the request includes actual device data for the online device, wherein the actual device data includes actual values representing actual characteristics of the online device for a plurality of characteristic types;
identifying a particular characteristic type of the plurality of characteristic types utilized by a particular online content provider;
analyzing the actual device data to identify the actual value representing the actual characteristic of the online device for the particular characteristic type utilized by the particular online content provider;
generating a substitute value that also represents the actual characteristic of the online device for the particular characteristic type utilized by the particular online content provider, wherein the substitute value is different than the actual value contained in the actual device data from the request; and
providing the substitute value to the particular online content provider in place of the actual value to convey, without revealing the actual value, the actual characteristic of the online device for the particular characteristic type utilized by the particular online content provider.

US Pat. No. 11,113,775

SYSTEM AND METHOD FOR STANDARDIZED EVALUATION OF DRIVER'S LICENSE ELIGIBILITY

ALLSTATE INSURANCE COMPAN...


1. A driving license evaluation system comprising:at least one processor; and
memory storing computer-readable instructions, that when executed by the at least one processor, cause the driving license evaluation system to:detecting, using a first electronic sensor including at least one of a first acceleration sensor and a first geographic location sensor, first vehicle operation data indicating a manner in which a driver operates a vehicle;
dynamically construct a driver-specific written test for the driver by electronically generating or selecting questions for the driver-specific written test using the detected first vehicle operation data indicating the manner in which the driver operates the vehicle;
determine a written test result for the driver-specific written test that was dynamically constructed;
during a performance of a driving test comprising a specified driving route:detecting, using at least one of the first electronic sensor and a second electronic sensor, the second electronic sensor including at least one of a second acceleration sensor and a second geographic location sensor, second vehicle operation data associated with the vehicle during the performance of the driving test;
compare the second vehicle operation data to one or more requirements of the driving test;

determine a driving test result based, at least in part, on a comparison of at least a portion of the second vehicle operation data detected during the performance of the driving test to the specified driving route; and
communicate the written test result and the driving test result to a remote system.


US Pat. No. 11,113,774

SYSTEM, METHOD, AND APPARATUS FOR INDIVIDUAL INNOVATOR MARKETING AND RECOGNITION

Cummins, Inc., Columbus,...


1. A method, comprising:identifying a plurality of workspace locations, each of the workspace locations comprising a visual output device;
identifying a plurality of output devices;
interpreting a plurality of intellectual property asset display profiles corresponding to a plurality of intellectual property creative asset descriptions based on an associated intellectual property asset creator and a related person to the associated intellectual property asset creator, the related person being in a same business unit of a company as the associated intellectual property asset creator, being in a same group of the company as the associated intellectual property asset creator, or being at least one of a customer, a vendor, or a supplier associated with the associated intellectual property asset creator;
detecting a badge scan associated with a person;
determining a location and an identity of the person based on the detected badge scan associated with the person, the identity of the person being the related person or the associated intellectual property asset creator;
dynamically selecting an output device from the plurality of output devices and the visual output device of each workspace location based on the determined location from the detected badge scan;
determining an intellectual property asset display context based on the determined identity and location of the person; and
in response to the plurality of intellectual property asset display profiles and the intellectual property asset display context, providing an intellectual property asset display description to the selected output device that cycles through the plurality of intellectual property asset display profiles to change a display of the selected output device, wherein the selected output device includes a visual output device associated with an unassigned workspace.

US Pat. No. 11,113,773

SYSTEM AND METHOD FOR SHARING DIGITAL OBJECTS

SONY INTERACTIVE ENTERTAI...


1. A method of tracking and benefiting sources of components in transferred digital items in a digital gaming environment, the method comprising:receiving notification of a transfer of a digital item to a receiving user account, the digital item comprising a plurality of components in the digital gaming environment, wherein at least two of the components are associated with different respective sources, and wherein the notification is received by a server that hosts the digital gaming environment; and
executing instructions stored in memory of the server, wherein execution of the instructions by a processor of the server:compares the digital item associated with the received notification against a registry of digital items, wherein the comparison evaluates a degree of similarity between the digital item associated with the received notification and each of the digital items on the registry,
identifies at least one similarity between the digital item associated with the received notification and the respective digital item on the registry,
assigns a value to a set of similarities, the set of similarities including each identified similarity,
compares the assigned value with respect to a predetermined copying threshold, and
in response to the assigned value being identified as less than the predetermined copying threshold:allows the transfer of the digital item to the receiving user account,
constructs an authorized copy of the digital item from the components associated with the different respective sources based on an associated template, and
provides a benefit to the different respective sources upon completion of the transfer, the benefit for each source based on a difference between the assigned value and a predetermined benefits threshold for each source; and

in response to the assigned value being identified as at least meeting the predetermined copying threshold:prevents the transfer of the digital item to the receiving user account, wherein the receiving user account is not permitted to construct an authorized copy of the digital item from the components associated with the different respective sources based on the associated template.



US Pat. No. 11,113,772

METHOD AND APPARATUS FOR ACTIVITY NETWORKING


1. An apparatus for activity networking, comprising: a memory coupled to at least one processor, the processor being configured to:transmit, to a server, a request to form a crew, the request including an indication of an activity associated with the crew, an indication of a time for performing the activity, and an indication of a number of available spots on the crew;
receive, from the server, a message indicating that a predetermined number of spots on the crew is occupied by a plurality of users, the message including a unique identifier for conducting communications sessions;
initiate a communications session with the plurality of users by using the unique identifier, the initiating including displaying a graphical user interface for conducting the communications session;
receive a respective confirmation of membership in the crew from at least some of the plurality of users;
and provide at least those of the plurality of users who have confirmed their membership in the crew with a calendar appointment for the activity, the calendar appointment being provided while the communications session is being conducted, the calendar appointment being provided in response to an activation of first input component of the graphical user interface:
wherein the first input component of the graphical user interface is hidden or disabled before the respective confirmations of membership in the crew are received and the at least one processor is further configured to display or enable the first input component of the graphical user interface in response to receiving the respective confirmations of membership in the crew, the first input component being displayed or enable before the calendar appointment is provided.

US Pat. No. 11,113,771

SYSTEMS, METHODS AND ARTICLES FOR GENERATING SUB-GRAPHS OF A TAX CALCULATION GRAPH OF A TAX PREPARATION SYSTEM

Intuit Inc., Mountain Vi...


1. A system for preparing a tax return in which a granularity of tax questions presented to a user may be adjusted, comprising:a computing device having a computer processor, display and memory, and a non-transitory, computer-readable storage device having a software application stored thereon, the software application executable by the computer processor and comprising a tax calculation graph, a modular tax calculation engine, a plurality of decision tables, a sub-graph engine, a granularity control engine, a modular tax logic agent, a modular user interface manager, the modular tax logic agent when executed by the computer processor is detached from the modular user interface manager when executed by the computer processor;
a data store in communication with the computing device, the data store configured to store user-specific tax data therein;
the modular tax calculation engine when executed by the computer processor using the tax calculation graph to perform a plurality of tax calculation operations using the user-specific tax data read from the data store to calculate the tax return, the tax calculation graph comprising a plurality of interconnected nodes including one or more of input nodes, functional nodes, and function nodes, each input node being populated with user-specific tax data, each function node defines a tax calculation utilizing the populated input nodes, and each functional node is a result of a calculation performed by an interconnected function node when executed by the computer processor, a plurality of the functional nodes each including a user selectable tag configuring such node as a user enterable node having a value entered by the user;
the modular tax calculation engine when executed by the computer processor performs a plurality of tax calculation operations based on the tax calculation graph using the user-specific tax data read from the data store to calculate the tax return;
the plurality of decision tables collectively representing a completion graph for completing all required data fields for computing the tax return, each decision table representing a plurality of columns, each column corresponding to a tax question, and a plurality of rows, each row corresponding to a completion path for a tax rule, thereby forming a plurality of cells with each cell corresponding to a particular row and column, each cell in a respective row having a logic operator to be executed by the computer processor, the logic operator corresponding to the tax question of the each cell's respective column such that completion of each respective row is determined by the logic operators in the respective row;
the sub-graph engine when executed by the computer processor generating a sub-graph of the tax calculation graph based upon a target node and one or more user enterable nodes selected by the user from the nodes of the tax calculation graph, the sub-graph excluding: (a) all nodes of the tax calculation graph which only have a calculation path leading to only one or more user enterable nodes; and (b) all nodes which do not have a calculation path leading to the selected target node;
the granularity control engine when executed by the computer processor generating modified decision tables by modifying the decision tables such that cells in the decision tables directed to nodes excluded in the sub-graph by the sub-graph engine are configured in the decision tables as not needed to complete a particular tax topic;
the modular tax logic agent when executed by the computer processor analyzing user-specific tax data in the data store and the modified decision table to determine one or more suggested tax questions for obtaining missing tax data required for the tax calculation engine to complete a tax calculation of the sub-graph, the modular tax logic agent eliminating, based on the user-specific tax data, at least one row and its respective completion path to reduce possible suggested tax questions; and
the user interface manager when executed by the computer processor receiving the suggested tax questions from the modular tax logic agent and outputting on the display one or more questions based on the one or more suggestions via a user interface.

US Pat. No. 11,113,770

MACHINE-LEARNING DRIVEN DATA ANALYSIS BASED ON DEMOGRAPHICS, RISK, AND NEED

Nayya Health, Inc., New ...


1. A data processing system comprising:a processor; and
a computer-readable medium storing executable instructions that, when executed, cause the processor to perform operations comprising:obtaining an electronic copy of first demographic information associated with a user, wherein the first demographic information includes demographic information provided by the user, demographic information obtained from one or more third-party data sources, or both;
dynamically generating a plurality of questions to obtain second demographic information for the user by identifying additional demographic information relevant to the user for determining insurance coverage needs of the user using a first machine learning model trained to receive as an input the first demographic information for the user and to predict and output additional information demographic information relevant for determining insurance coverage needs of the user based on the first demographic information;
adding the second demographic information to the first demographic information to create cumulative demographic information for the user;
providing the cumulative demographic information as an input to a second machine learning model;
analyzing the cumulative demographic information with the second machine learning model, wherein the second machine learning model is trained to segment people into clusters of people having similar demographics, wherein the second machine learning model is configured to analyze the cumulative demographic information associated with the user to predict and output a cluster associated with the user and output predicted medical spending information associated with the predicted cluster;
providing the predicted medical spending information to a recommendation engine to generate a comprehensive insurance plan for the user comprising a plurality of insurance policies based on the predicted medical spending information;
customizing the comprehensive insurance plan based on the cumulative demographic information associated with the user to generate a customized bundle of insurance policies;
generating an insurance recommendation report that presents the customized bundle of insurance policies to the user; and
causing a user interface of a display of a computing device associated with the user to present the insurance recommendation report.


US Pat. No. 11,113,769

BLOCKCHAIN-BASED SERVICE EXECUTION METHOD AND APPARATUS, AND ELECTRONIC DEVICE

Advanced New Technologies...


1. A computer-implemented method for a blockchain-based service, comprising:collecting appearance data of a vehicle as collected appearance data, the vehicle capable of accessing, as a member, a blockchain;
registering, in a distributed database associated with the blockchain, the appearance data as an identity of the vehicle;
associating the appearance data with an account address of the vehicle in the blockchain;
detecting, by a member node device in the blockchain, a traffic congestion event that is related to the vehicle;
receiving a target transaction initiated by the member node device in the blockchain, wherein the target transaction comprises the appearance data of the vehicle that is collected by the member node device and traffic congestion event information that is related to the traffic congestion event;
invoking a smart contract that corresponds to the traffic congestion event information;
identifying the account address of the vehicle based on the appearance data of the vehicle that is collected by the member node device; and
executing, based on the account address of the vehicle, right-of-way yielding logic stated in the smart contract.

US Pat. No. 11,113,768

SYSTEMS AND METHODS FOR ENHANCED SITUATION VISUALIZATION

STATE FARM MUTUAL AUTOMOB...


1. An enhanced situation visualization (ESV) computing device comprising a memory and at least one processor communicatively coupled to the memory, wherein the at least one processor is programmed to:receive a reference request message from a user computing device, the reference request message including an image of a property in a current state;
retrieve, from a reference database, reference information that includes a historical image of the property in a prior state;
determine, based upon the reference request message and the reference information, situation information that includes at least one difference between the prior state and the current state of the property;
generate a virtual grid of the at least one difference between the current state and the prior state;
generate a reference response message including the situation information, the reference information, and the virtual grid; and
transmit the reference response message to the user computing device, wherein the reference response message causes the user computing device to display at least one of the situation information and the reference information as overlaid upon a current view of the user to provide an enhanced situation visualization of the property, including displaying the virtual grid over the current view of the property as a virtual grid overlay.

US Pat. No. 11,113,767

SYSTEMS AND METHODS FOR ENHANCED SITUATION VISUALIZATION

STATE FARM MUTUAL AUTOMOB...


1. An enhanced situation visualization (ESV) computing device comprising a memory and at least one processor communicatively coupled to the memory, wherein the at least one processor is programmed to:receive a reference request message from a user computing device, the reference request message including an image of a property in a current state and device data including geolocation data captured at the user computing device;
determine a first subject of the image, wherein the first subject is the property;
query a reference database to retrieve reference information associated with the property;
identify, based upon the reference information, a beacon associated with the property, wherein the beacon is coupled to an item of interest associated with the property;
transmit an interrogation signal to the beacon;
determine, based upon a response from the beacon and the device data, a location of the beacon relative to the user computing device;
generate instructions for overlay of an icon representative of the beacon location over the image of the property, the icon including an item tag identifying the item of interest to which the beacon is coupled, a direction indicator of a direction from a current, real-time view of the user computing device, and a distance indicator of a distance between the user computing device and the beacon; and
transmit a reference response message including the instructions to the user computing device, wherein the instructions, when executed by the user computing device, cause the user computing device to display the icon as overlaid upon the current, real-time view of the property, as displayed in real-time to the user on the user computing device, to provide an enhanced situation visualization of the property.

US Pat. No. 11,113,766

METHOD AND SYSTEM FOR AUTOMATICALLY DETECTING A FENCE

United Services Automobil...


1. A method of analyzing images of a premises by a computing device to determine whether a fence is present at the premises, the method comprising:retrieving, at the computing device, at least one image of the premises captured from a camera disposed proximally to the premises;
comparing, by the computing device, geotag information associated with the at least one image of the premises to a known location of the premises retrieved from an insurance policy associated with the premises;
upon confirming that the geotag information matches the known location of the premises, analyzing the at least one image of the premises using a machine learning system, wherein an output of the machine learning system includes a fence classification parameter;
determining, by the computing device, whether or not the premises has a fence based on the fence classification parameter; and
wherein, upon determining that a fence is present at the premises, modifying the insurance policy associated with the premises in response.

US Pat. No. 11,113,765

DETERMINING APPLIANCE INSURANCE COVERAGE/PRODUCTS USING INFORMATIC SENSOR DATA

United Services Automobil...


1. An electronic sensor system comprising:a plurality of sensor devices located within one or more appliances and is configured to capture data related to electricity usage of the one or more appliances, wherein the one or more appliances are located within a property, and wherein each sensor device of the plurality of sensor devices comprises a transmitter having an associated IP address to periodically capture and transmit data in accordance with a data capture interval value;
a data storage in communication with each sensor device of the plurality of sensor devices via a respective IP address, wherein the data storage is configured to aggregate the captured data related to the one or more appliances located in the property received from each sensor device of the plurality of sensor devices;
a communication device in communication with the data storage, wherein the communication device is configured to encrypt and transmit the aggregated captured data via a communications network;
a computer server in communication with the communication device via the communications network, the computer server programmed to:receive encrypted aggregated captured data from the communication device regarding the electricity usage of the one or more appliances located in the property;
analyze the encrypted aggregated captured data regarding the electricity usage of the one or more appliances located in the property to determine an appliance maintenance status for at least one appliance of the one or more appliances, wherein the appliance maintenance status is associated with at least one operating performance of the at least one appliance;
determine one or more repair needs for the at least one appliance based on the received encrypted aggregated captured data, wherein the one or more repair needs includes one or more immediate repair needs, one or more preventive maintenance needs, or both;
determine at least one performance degradation for the at least one appliance based on the appliance maintenance status;
upon determining that the at least one performance degradation is above a performance degradation threshold, determine a coverage value for repairing or replacing the at least one appliance based on a relationship between the at least one performance degradation and the performance degradation threshold;
upon the coverage value for the at least one appliance satisfying a second threshold, generate an electronic message comprising an identification of the at least one appliance, the appliance maintenance status, an insurance plan with the coverage value, and a recommendation for one or more insurance products related to an age value or the appliance maintenance status associated with the at least one appliance; and
transmit the electronic message to an electronic device of a user associated with the property.


US Pat. No. 11,113,764

METHOD AND SYSTEM FOR CREATING AND TRACKING LIFE INSURANCE POLICIES IN SEPARATE ACCOUNTS INCLUDING MODIFIED STABLE VALUE PROTECTED FUNDS

Addle Management, LLC, S...


1. A computer system for administering an investment comprising:at least one computer processor;
at least one non-transient memory for storing computer executable instructions, wherein execution of the computer executable instructions by the at least one computer processor causes, after a termination indication has been received that a contract holder of a life insurance contract including at least one stable value protected investment utilizing a surrender payment protocol option has requested termination of the life insurance contract, and in response to receiving the termination indication according to the surrender payment protocol option, the computer system to perform:(a) tracking a varying investment value of the at least one stable value protected investment utilizing the surrender payment protocol option after the termination indication is received;
(b) tracking a varying asset value of at least one underlying asset associated with the at least one stable value protected investment after the termination indication is received;
(c) determining, after the termination indication is received, whether a difference representing an extent to which the varying investment value exceeds the varying asset value is at most a predetermined threshold value; and
(d) providing a payment indication that the contract holder be paid an amount based on the varying investment value when the computer executable instructions (c) determine that the difference is at most the predetermined threshold value, wherein the surrender payment protocol option is an option associated with the at least one stable value protected investment to defer, after surrender, the payment of the proceeds due upon surrender of the life insurance contract if the varying investment value of the at least one stable value protected investment is greater than the varying asset value of the at least one underlying asset associated with the at least one stable value protected investment.


US Pat. No. 11,113,763

ADVISORY THRESHOLDS AND ALERTS FOR MANAGING POSITION CONCENTRATION RISK

Intercontinental Exchange...


1. A system comprising:one or more processors operatively coupled to a memory storing computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to:
generate an aggregate parameter value based on one or more first parameter values associated with a first customer account of a first independent computer system and one or more second parameter values associated with a second customer account of a second independent computer system;
determine that the aggregate parameter value has met or exceeded a threshold level for an aggregate trader position associated with the first customer account and the second customer account;
generate, in response to the determining, an advisory alert;
transmit the advisory alert to one or more authorized entity systems; and
remotely initiate one or more intervening measures.

US Pat. No. 11,113,762

SYSTEM AND METHOD FOR CREATING ON-DEMAND USER-CUSTOMIZED DEPOSIT STRATEGIES USING DATA EXTRACTED FROM ONE OR MORE INDEPENDENT SYSTEMS

Raisin Technology Europe,...


1. A system comprising:at least one computer server configured to communicate with one or more entity systems and at least one user device, the at least one computer server comprising at least one memory storing computer-readable code and at least one processor executing the computer-readable code, thereby causing the at least one computer server to:
receive, via one or more data feed interfaces, one or more baseline data structures from among the one or more entity systems, each of said one or more baseline data structures comprising a combination of one or more pre-defined components and one or more pre-defined parameters associated with one or more non-tradeable deposit products;
generate an interactive graphical user interface (GUI) on a display of the at least one user device, the interactive GUI comprising one or more screens;
apply one or more dynamic filter rules to the one or more baseline data structures to generate a list of baseline data structures that is based, at least in part, on a geographic characteristic that is associated with one or more of the at least one user device and a user of the at least one user device, said dynamic filter rules comprising said geographic characteristic;
display, via the interactive GUI, one or more combinations, each of which comprises a combination of one or more baseline data structures among the list of baseline data structures;
display, via the interactive GUI, one or more user adjustment tools for customizing variables of the one or more combinations, said variables comprising at least one of a deposit strategy and a customizable parameter among said pre-defined parameters;
receive, from the at least one user device via the interactive GUI, at least one adjustment indication via the one or more user adjustment tools;
adjust, responsive to the at least one adjustment indication, at least one of said variables, thereby forming a user-customized configuration of a user-customized combination;
dynamically update and display, via the interactive GUI, said adjusting and an impact of said adjusting on at least one other variable as said adjusting occurs;
receive, from the at least one user device via the interactive GUI, input comprising a confirmation indication of the user-customized configuration; and
create and issue the user-customized combination of baseline data structures responsive to the confirmation indication received from the at least one user device via the interactive GUI.

US Pat. No. 11,113,761

SYSTEMS AND METHODS FOR IMPLEMENTING A PLATFORM FOR INVESTING

THE BANK OF NEW YORK MELL...


6. A method comprising:receiving, by one or more processors, via an interface, a request from a customer, wherein the request indicates (i) a social media stream associated with the customer to be monitored for instances of investment triggering content (ITC);
configuring, by one or more processors, a customer account of the customer based on the request;
monitoring, by one or more processors, based on the customer account configuration, the social media stream for instances of ITC;
responsive to the monitoring detecting an instance of ITC, withdrawing, by one or more processors, a first amount from the customer account; and
executing, by one or more processors, on behalf of the customer, a purchase of a quantity of shares of an investment fund using the withdrawn first amount.

US Pat. No. 11,113,760

SPECIALIZED LIABILITY PAYMENT CALCULATOR WITH GRAPHICAL USER INTERFACE

HUG YOUR STUDENT DEBT, IN...


1. A computer-implemented method for financial liability payment calculation, the method comprising:receiving, by a processor, a source code for calculating a repayment schedule for a set of financial liabilities of a user;
revising, by the processor, a value assigned to a threshold duration in the source code, the threshold duration is for negative amortization calculation, wherein revising the value comprises:determining a type of the processor used to execute the source code, wherein the type of the processor indicates a data width that the processor uses; and
selecting the value of the threshold duration based on the type of the processor to prevent the negative amortization calculation from entering an unending loop;

detecting, by the processor, that a first financial liability is in negative amortization using the threshold duration that is based on the type of the processor;
computing, by the processor, using the source code, the repayment schedule for the set of financial liabilities using the threshold duration that is based on the type of the processor, wherein computing the repayment schedule comprises:computing priorities for each of the financial liabilities;
reordering the financial liabilities according to the priorities;
determining suggested payments for each of the financial liabilities using the threshold duration that is based on the type of the processor; and
determining a repayment timeline for the set of financial liabilities using the suggested payments; and
displaying, by the processor, the repayment schedule via a user interface.


US Pat. No. 11,113,759

ACCOUNT VULNERABILITY ALERTS

ConsumerInfo.com, Inc., ...


1. A computer system comprising:one or more computer processors configured to execute software instructions;
a non-transitory computer readable medium storing software instructions executable by the one or more computer processors to cause the computer system to:
scan one or more online networks for personal data associated with a user, wherein identification of personal data indicates a potential account takeover risk;
identify a second online account that uses a first online account in association with an account recovery option for the second online account;
based on the second online account using the first online account in association with the account recovery option, link the first online account with the second online account;
identify a first vulnerability for the first online account to hostile account takeover based at least in part on the potential account takeover risk associated with identification of personal data of the user;
identify a second vulnerability for the second online account based on the link;
determine one or more remedial actions that may be taken by the user with reference to one or more of the first or second vulnerabilities;
electronically provide the user with an alert regarding the one or more of the first or second vulnerabilities and an indication of the determined one or more remedial actions that may be taken by the user with reference to one or more of the first or second vulnerabilities;
receive a selection of a remedial action;
initiate the selected remedial action in response to user input,
monitor at least one of the first or second online account to identify a change corresponding to the selected remedial action;
identify the change based on the monitoring;
determine that the change addresses the remedial action; and
electronically provide the user with an updated alert including information indicative of the completion of the selected remedial action.

US Pat. No. 11,113,758

USER INTERFACE FOR DOCUMENT IMAGING

Wells Fargo Bank, N.A., ...


1. A system for facilitating image-based financial transactions, comprising:a computing device comprising a processor unit; an imaging device; and
a display, wherein the processor unit is programmed to perform actions comprising:displaying at the display a multi-mode launch icon, wherein the launch icon is alternately selectable by a user of the computing device in a first mode and in a second mode;
detecting a first user input that selects the launch icon in the first mode;
in response to the first user input, executing a first application at the computing device;
detecting a second user input that selects the launch icon in the second mode;
in response to the second user input, prompting the user to capture an image of a document with the imaging device;
receiving, from the imaging device, the image of the document;
determining, based at least in part on the image, that the document is of a first document type; and
executing a document-type routine to perform a first financial transaction based at least in part on the document.


US Pat. No. 11,113,757

SYSTEMS AND METHODS FOR FILTERING DIGITAL CONTENT HAVING A NEGATIVE FINANCIAL INFLUENCE

Wells Fargo Bank, N.A., ...


1. A computer-implemented method for tailoring information delivered via a social media service, the method comprising:receiving a restriction permission identifying one or more social media services for which content is allowed to be modified from a user device associated with a user;
receiving social media data of the user from a social media service of the one or more social media services at a social media computing system associated with a financial institution (“FI”);
analyzing the received social media data, wherein analyzing the received social media data comprises:determining if content within the received social media data should be categorized based on the restriction permission;
categorizing the content within the received social media data as at least one of restricted content elements and unrestricted content elements in response to the determination the content should be categorized, the restricted content elements and the unrestricted content elements determined based on one or more predetermined parameters associated with one or more goals of the user, at least one of the one or more goals of the user being a financial goal; and
determining, in response to the content being categorized as restricted content elements, that the restricted content elements can be modified by determining that the social media service is one of the one or more social media services identified by the restriction permission;

modifying, in response to the determination that the restricted content elements can be modified, at least a portion of the restricted content elements; and
transmitting the unrestricted content elements, the modified restricted content elements, and a notification that the modified restricted content elements have been modified to the user device associated with the user without transmitting unmodified restricted content elements.

US Pat. No. 11,113,756

METHOD FOR MAKING COGNITIVE BIDDING DECISION

International Business Ma...


1. A method for a provider to make a cognitive bidding decision comprising:using a processor and associated memory to
obtain information, including unstructured data and structured data, relating to a plurality of deals with a plurality of procuring organizations;
train a first machine learning prediction model based upon the structured data;
train a second machine learning prediction model based upon the unstructured data;
train a combined machine learning model, the combined machine learning model configured to provide a final output based upon at least one of an aggregation of an output of each of the first and second machine learning prediction models and a building of a model based upon the output of each of the first and second machine learning prediction models;
determine a respective predicted business growth of each procuring organization based upon the information;
determine a respective predicted growth of provider services for each procuring organization based upon the information;
determine a respective probability of winning each bid for each deal from each procuring organization;
determine a respective predicted revenue based upon winning each bid; and
determine whether to submit each bid based upon the respective predicted business growth of each procuring organization, the respective predicted growth of provider services for each procuring organization, the respective probability of winning each bid for each deal from each procuring organization, and the respective predicted revenue;
wherein one of the respective predicted business growth and the respective predicted growth of provider services is determined based upon the first machine learning prediction model based upon the structured data, the second machine learning prediction model based upon the unstructured data, and the combined machine learning model; and
wherein each respective predicted business growth is one of multiple levels of growth and wherein the first machine learning prediction model generates a prediction percentage for each of the multiple levels of growth.

US Pat. No. 11,113,755

SYSTEM AND METHOD FOR VISUALIZATION OF ITEMS IN AN ENVIRONMENT USING AUGMENTED REALITY

eBay Inc., San Jose, CA ...


1. A method implemented by a client device, the method comprising:receiving a selection of an item for placement into an image of an environment;
receiving environment image data containing the image of the environment;
scaling an item image for the selected item based on dimensions of the environment;
generating an augmented reality image that depicts the scaled item image disposed in the environment;
receiving a selection of the scaled item image in the augmented reality image; and
displaying item information in response to receiving the selection of the scaled item image.

US Pat. No. 11,113,754

EVENT-BASED DISTRIBUTION OF CRYPTOGRAPHICALLY SECURED DIGITAL ASSETS

NIKE, Inc., Beaverton, O...


1. A method of event-based distribution of a cryptographically secured digital asset, the method comprising:receiving, from a computing device associated with a user, an indication that the computing device is located at a predetermined venue within a predetermined window of time;
receiving, from the computing device, a unique owner identification (ID) code associated with the user;
receiving, from the computing device, a unique code acquired by the user;
determining a unique digital asset ID code corresponding to the received unique code, the unique digital asset ID code representative of the cryptographically secured digital asset; and
transmitting a cryptographic block to a distributed blockchain ledger to record transfer of the cryptographically secured digital asset to the user, the cryptographic block comprising both the unique digital asset ID code and the unique owner ID code;
wherein determining the unique digital asset ID code comprises:directing an application or an internet browser running on the computing device to a virtual storefront display comprising a plurality of different displayed cryptographically secured digital assets;
receiving an indication of a selection of one of the plurality of different displayed cryptographically secured digital assets; and

wherein the determined unique digital asset ID code corresponds to both the received unique code and the selected one of the plurality of different displayed cryptographically secured digital assets.

US Pat. No. 11,113,753

NETWORK ACCESS SYSTEM FOR A SHOPPING APPLICATION AND RELATED METHODS

INMAR BRAND SOLUTIONS, IN...


1. A network access system comprising:a first WiFi network in a physical store defining a private network for wireless communications of a shopping application associated with the physical store,
a second WiFi network in the physical store defining a public network for wireless communications of at least one other application, the second WiFi network configured to provide slower speed than the first WiFi network; and
a mobile wireless communications device associated with a shopper and comprisingan input device,
a device wireless network interface, and
a controller coupled to the input device and associated with the device wireless network interface, the controller configured toexecute the shopping application associated with the physical store,
determine that the mobile wireless communications device is within the physical store based upon network identifiers associated with a plurality of available wireless networks available within the physical store,
enable the shopping application to communicate via the first WiFi network responsive to the mobile wireless communications device being geographically located within the physical store and without input to the input device, and
enable the at least one other application to communicate via the second WiFi network while the shopping application is enabled to communicate via the first WiFi network and responsive to the mobile wireless communications device being geographically located within the physical store and selection of the second WiFi network from among the plurality of available WiFi networks via the input device.



US Pat. No. 11,113,752

ON-LINE SESSION TRACE SYSTEM

eBay Inc., San Jose, CA ...


1. A method comprising:recording, via at least one hardware processor, in a course of an on-line shopping session associated with a user identification, one or more trace attributes indicative of activities of a user during the on-line shopping session, the one or more trace attributes comprising an attribute indicating a shopping cart web page that was last accessed via the on-line shopping session;
detecting, via the at least one hardware processor, a request from a client device to commence a second on-line shopping session associated with the user identification; and
subsequent to an interruption of the on-line shopping session and in response to the detected request to commence the second on-line shopping session:selecting, via the at least one hardware processor, the shopping cart web page based on the attribute indicating the shopping cart web page was last accessed during the on-line shopping session, and
causing display of the web page via the second on-line shopping session on the client device.


US Pat. No. 11,113,751

SYSTEMS AND METHODS FOR PREDICTING LOST DEMAND USING MACHINE LEARNING ARCHITECTURES

WALMART APOLLO, LLC, Ben...


1. A system comprising:one or more processors; and
one or more non-transitory computer-readable storage devices storing computing instructions configured to run on the one or more processors and perform:providing, via an electronic platform, access to one or more order placement user interfaces;
collecting order placement information associated with the one or more order placement user interfaces, the order placement information at least indicating (a) actual availability of order placement options during client sessions involving the one or more order placement user interfaces and (b) whether or not the client sessions were converted to actual orders;
analyzing, by a conversion determination network of a machine learning architecture, the order placement information;
generating, using the conversion determination network of the machine learning architecture, actual conversion information for the client sessions based on the actual availability of the order placement options during the client sessions;
generating, using the conversion determination network of the machine learning architecture, predicted conversion information for the client sessions based on a full availability of all of the order placement options during the client sessions; and
generating lost demand information based, at least in part, on the actual conversion information and the predicted conversion information.


US Pat. No. 11,113,750

SYSTEM AND METHOD FOR ELECTRONIC MANIFESTING IN A DISTRIBUTION NETWORK

United States Postal Serv...


1. A method of manifesting items comprising:sending a request, via a user interface, to access to an electronic manifesting system of a distribution network, wherein the request comprises a unique identifier associated with a user;
receiving, via a user interface, access to an electronic manifesting system based at least in part on the unique identifier associated with a user;
transmitting, via the user interface, to the distribution network, item information for a first item to the electronic manifesting system;
receiving, via the user interface, from the distribution network, first label information, wherein the label information contains a first computer readable code, wherein the first computer readable code comprises the unique identifier associated with the user and a unique identifier specific to the first item;
transmitting, via the user interface, to the distribution network, item information for a second item to the electronic manifesting system;
receiving, via the user interface, from the distribution network, second label information, wherein the label information contains a second computer readable code, wherein the second computer readable code comprises the unique identifier associated with the user and a unique identifier specific to the second item; and
providing, to the distribution network, the first item having the first computer readable code thereon and the second item having the second computer readable code thereon.

US Pat. No. 11,113,749

SYSTEM AND METHOD FOR GENERATING A PERSONALIZED CONCERT PLAYLIST

SPOTIFY AB, Stockholm (S...


1. A system for providing access to media content associated with an artist scheduled for performance, using a digital media content environment, comprising:a media device including a media application that enables display of a playlist personalized for a user based on a list of artists scheduled for performance, and a media consumption history of the user;
wherein an input action can be performed by the user to cause a media server to populate the playlist with media content accessible to the user via the playlist; and
wherein upon the user performing the input action, the media server:queries a database comprising listening profiles, to determine listening profiles for the user and for a plurality of other users having listening profiles similar to the user,
queries a database comprising media content consumption information including media consumption histories of users, to retrieve the media consumption history of the user, and aggregate delivery information indicative of media consumption by the plurality of other users having listening profiles similar to the user,
queries a database comprising performance listings to retrieve a plurality of performance listings filtered based on the retrieved media consumption history of the user, and the aggregate delivery information indicative of media consumption by the plurality of other users having listening profiles similar to the user, to obtain a set of artists having performance listings relevant to the user,
queries the database comprising media content consumption information to select a media content item associated with each artist from the set of artists, and
organizes and populates the playlist with the selected media content items.


US Pat. No. 11,113,748

ORDERING A TRANSPORTATION VEHICLE USING A NEAR-FIELD COMMUNICATION DEVICE

GT Gettaxi Systems Ltd, ...


1. A method comprising:receiving, by a processing device of a first client computing device, data from a first near-field communication (NFC) target device responsive to a first NFC device associated with the first client computing device being in physical proximity of the first NFC target device;
generating, by the processing device based on the data, an order request for a transportation vehicle; and
responsive to the order request not being placed and the first NFC device of the first client computing device being within a predetermined physical proximity of a second NFC device of a second client computing device, causing, by the processing device, information associated with the order request to be transmitted from the first client computing device to the second client computing device.

US Pat. No. 11,113,747

SYSTEMS AND METHODS FOR DISTRIBUTED GROCERY FULFILLMENT AND LOGISTICS

MI.T GASTRO MANAGEMENT GM...


1. A grocery preparation and fulfillment service management system, the system comprising:at least one ingredients database including product data and ingredient availability data that is received from a plurality of fulfillment servers;
a cloud computing environment including a public cloud space and a private cloud space, the private cloud space comprising a private computing space partitioned from within the cloud computing environment for access limited to an account of a user of a client device, wherein the private cloud space is configured to store private recipe data of the user from the client device;
a login interface configured to sign in the client device to the private cloud space with the account;
a search engine configured to receive from the user a search of the product data and retrieve the ingredient availability data from the at least one ingredients database based on the search;
an ordering interface coupled to the search engine and configured for access with the account by the user of the client device over a communication network, the ordering interface including a website configured to create purchase orders and add the purchase orders to an online shopping cart for the account, wherein the purchase order specifies a set of ingredients and a manner in which the set of ingredients are to be prepared based on ordering data templates corresponding to the private recipe data and the ingredient availability data, and wherein the private recipe data is linked to the product data in the ingredients database and is retrievable by the website from the private computing space;
a marketplace system configured to receive a request to sell units of purchase orders from the ordering interface to other users, generate a listing based on the request, receive listing orders corresponding to the listing, and forward the listing orders to a fulfillment manager system; and
the fulfillment manager system in communication with the plurality of fulfillment servers via the communication network, the fulfillment manager system configured to solicit the listing orders to the plurality of fulfillment servers, receive offers from the plurality of fulfillment servers to execute the listing orders, and confirm the offers, wherein the plurality of fulfillment servers are solicited based on an ability of fulfillment centers associated with the plurality of fulfillment servers to fulfill the listing orders, the plurality of fulfillment servers include corresponding inventory management systems that compute the ability of fulfillment centers to fulfill the listing orders based on inventory level data of the fulfillment centers.

US Pat. No. 11,113,746

METHOD, MEDIUM, AND SYSTEM FOR AUTOMATED PRODUCT IDENTIFICATION

International Business Ma...


1. An automated identification method comprising:receiving, by a processor of an identification hardware device from a plurality of users, permission to identify and monitor items associated with said plurality of users;
detecting, by said processor via a plurality of sensors in response to said receiving said permission, previously installed local devices located at a first geographical location, wherein said local devices comprise an autonomous robotic device and detected mobile devices, and wherein said detecting comprises sensing, via said plurality of sensors, said mobile devices and said robotic device autonomously performing operational functions with respect to an increased amount of speed and precision;
detecting, by said processor via said plurality of sensors, packet length attributes, cluster devices, and identification data identifying each device of the local devices;
storing, by said processor, said packet length attributes, said cluster devices, and said identification data within a network device;
detecting, by said processor via said plurality of sensors, a user and a user device, of said user, arriving at said first geographical location;
establishing, by said processor, communications between said user device and said local devices;
determining by said processor via said plurality of sensors, a travel path of said user and said user device traveling throughout said first geographical location;
additionally determining, by said processor via said plurality of sensors, that said user device is within a specified proximity with respect to said autonomous robotic device;
biometrically detecting, by said processor via a heart rate monitor, a blood pressure monitor, a temperature sensor, a pulse rate monitor, or an optical sensor of said plurality of sensors, current behavior interactions of said user;
retrieving for said user device and from said local devices, by said processor in response to said additionally determining and said biometrically detecting, said identification data and associated metadata describing said local devices;
detecting, by said processor, user movement causing said user to initiate motion and travel to a second geographical location differing from said first geographical location;
detecting, by said processor via said plurality of sensors, said user and said user device arriving at said second geographical location;
receiving, by said processor via said user device, a network-based request for locating a specified item;
analyzing, by said processor in response to said network-based request, said identification data and associated metadata; and
presenting, to said user in response based on results of said analyzing, network search results comprising a list of items and associated descriptions associated with said network-based request thereby causing said user to retrieve an item of said list of items, wherein said list of items and associated descriptions comprise an entry associated with at least one device of said local devices.

US Pat. No. 11,113,745

NEURAL CONTEXTUAL BANDIT BASED COMPUTATIONAL RECOMMENDATION METHOD AND APPARATUS

VERIZON MEDIA INC., New ...


1. A method comprising:receiving, at a computing device, a request for an item recommendation in connection with a user;
maintaining, via the computing device, a data store comprising information about the user and information about a plurality of items, the information about an item including feedback information corresponding to the user, the feedback information for use in grouping the plurality of items into at least three groups, a first group comprising each item previously recommended to the user and having positive feedback of the user, a second group comprising each item previously recommended to the user and having negative feedback of the user, and a third group comprising each unrecommended item without feedback of the user;
determining, via the computing device, a multi-dimensional feature vector user representation corresponding to the user using the information about the user;
determining, via the computing device, a plurality of item representations corresponding to the plurality of items, each item representation comprising a multi-dimensional feature vector item representation determined using information about the item from the item information store;
determining, via the computing device, a plurality of user-item pairs in a feature space, each user-item pair, in the feature space, relating the user with one of the items of the plurality of items, the determining comprising, for a user-item pair, determining a distance, in the feature space, between the feature vector item representation and the feature vector user representation, the feature vector item representation for each item in the first and third groups being more closely positioned, in the feature space, to the feature vector user representation than each item in the second group;
determining, via the computing device, a plurality of rewards for the plurality of user-item pairs, determination of a reward for a user-item pair comprising using a trained contextual bandit model to generate the reward using the feature space relating the user with each item of the plurality of items;
automatically selecting, via the computing device and using the plurality of rewards, at least one item from the plurality of items for the recommendation, each selected item having a greater reward than each unselected item of the plurality; and
communicating, via the computing device, the recommendation to a user for display on a device of the user.

US Pat. No. 11,113,744

PERSONALIZED ITEM RECOMMENDATIONS THROUGH LARGE-SCALE DEEP-EMBEDDING ARCHITECTURE WITH REAL-TIME INFERENCING

WALMART APOLLO, LLC, Ben...


1. A system comprising:one or more processors; and
one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform:training two sets of item embeddings for items in an item catalog and a set of user embeddings for users, using a triple embeddings model, with triplets, wherein the triplets each comprise a respective first user of the users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket;
generating an approximate nearest neighbor index for the two sets of item embeddings;
receiving a basket comprising basket items selected by a user from the item catalog;
grouping the basket items of the basket into categories based on a respective item category of each of the basket items;
randomly sampling a respective anchor item from each of the categories;
generating a respective list of complementary items for the respective anchor item for the each of the categories based on a respective lookup call to the approximate nearest neighbor index using a query vector associated with the user and the respective anchor item, wherein the query vector is generated for the user and the respective anchor item using the two sets of item embeddings and the set of user embeddings;
building a list of personalized recommended items for the user based on the respective lists of the complementary items for the categories; and
sending instructions to display, to the user on a user interface of a user device, at least a portion of the list of personalized recommended items.


US Pat. No. 11,113,743

INFORMATION RECOMMENDATION BASED ON RULE MATCHING

Advanced New Technologies...


1. A computer-implemented method comprising:retrieving, by one or more processors of an information recommendation client and from a data supply client, text data provided as text input in a graphical user interface of the data supply client, the text data comprising a message to be posted within a social network and being retrieved by the data supply client before receiving a user input that is configured to transmit the text data to the social network, and wherein the text data is prefiltered based on a feature of a recommendation information;
processing, by the one or more processors of the information recommendation client, the text data to determine a plurality of keywords and a subject;
retrieving, by the one or more processors of the information recommendation client, an information recommendation rule set corresponding to the subject;
determining, by the one or more processors of the information recommendation client, that the information recommendation rule set comprises an information recommendation rule matching the plurality of keywords and the subject of the text data, wherein matching the text data comprises searching the plurality of keywords in a trie associated to the information recommendation rule and generating a set of matched nodes;
in response to determining that the information recommendation rule set comprises the information recommendation rule matching the text data, retrieving, by the one or more processors of the information recommendation client, the recommendation information from a server;
transmitting, by the one or more processors of the information recommendation client, a recommendation based on the recommendation information to the graphical user interface of the data supply client; and
displaying, by the graphical user interface of the data supply client, the recommendation within the social network.

US Pat. No. 11,113,742

CAPTURING AND EXTRACTING FRAGMENTED DATA AND DATA PROCESSING USING MACHINE LEARNING

Bank of America Corporati...


1. A method comprising:generating a display associated with a user, the display including an option to upload data;
sending, to a user device associated with the user, the display including the option to upload data;
receiving, by a computing device, from the user device, and via the display first fragmented data associated with the user, the first fragmented data including metadata indicating a data type for the first fragmented data;
extracting, by the computing device, a plurality of data entries from the first fragmented data, the plurality of data entries being identified for extraction based on the metadata in the first fragmented data;
sending, to the user device, a request for data associated with a first data entry of the plurality of data entries;
determining, by the computing device and using machine learning, a data category for each data entry of the plurality of data entries; and
based on the determined data category for each data entry of the plurality of data entries, determining one or more of a number of entries in each data category or an amount associated with each data category.

US Pat. No. 11,113,741

ARRANGING CONTENT ON A USER INTERFACE OF A COMPUTING DEVICE

INTERNATIONAL BUSINESS MA...


1. A computing device comprising:a processor;
a network interface coupled to the processor to enable communication over a network;
a storage device for content and programming coupled to the processor;
a program stored in the storage device, wherein an execution of the program by the processor configures the computing device to perform acts comprising:
receiving historical data comprising (i) data of a plurality of customers and (ii) data of a plurality of products;
creating a hybrid graph based on the received historical data, the hybrid graph comprising:one or more customer nodes and one or more product nodes;
for each product purchased, a directed edge between a corresponding customer node and a product node; and
for each product returned, a non-directed edge between a corresponding customer node and a product node; and

between each two customers of the plurality of customers, applying a customer weight factor on the hybrid graph, wherein the customer weight factor indicates a degree of similarity between the two customers;
between each two products of the plurality of products, applying a product weight factor on the hybrid graph, wherein the product weight factor indicates a degree of similarity between the two products;
receiving a request for a seed product from a computing device of a requestor customer;
identifying one or more products related to the seed product;
for each identified related product, determining a return affinity score towards the requestor customer by performing a random walk analysis initiated from the seed product to find a cluster around the seed product, wherein the return affinity score is a similarity function used to quantify the similarity between the two products and the two customers by evaluating a customer's return attribute probability for the products based on the hybrid graph;
ranking each related product based on their return affinity score; and
sending a representation of the related products to be displayed on the computing device of the requestor customer based on the ranking, where the related products are emphasized and/or suppressed based on the return affinity score.

US Pat. No. 11,113,740

SYSTEM AND METHODS FOR PERSONALIZATION AND ENHANCEMENT OF A MARKETPLACE

eBay Inc., San Jose, CA ...


1. A system comprising:one or more processors of at least one server machine;
a computer readable storage medium storing instructions that, when executed by the one or more processors, cause the at least one server machine to perform operations comprising:receiving one or more images from a user capture device depicting one or more products owned by a user;
identifying, based on a comparison of the one or more images to a product database using image recognition at an image recognition component of the at least one server machine, the one or more products owned by the user;
determining, at a product display component of the at least one server machine, a market value for each of the one or more products based at least in part on information obtained from the product database;
determining, at the product display component of the at least one server machine, the market value of at least one of the one or more products exceeds a predefined threshold value associated with at least one of the one or more products;
in response to determining the market value of at least one of the one or more products exceeds the predefined threshold value, transmitting, from a communication component of the at least one server machine, an alert to the user capture device, the alert including a notification that the market value of at least one of the one or more products exceeds the predefined threshold value; and
calculating a product sentiment score for each of the one or more products based on an aggregate of user reviews associated with each of the one or more products.


US Pat. No. 11,113,739

SYSTEM AND METHOD FOR AUTOMATIC FULFILLMENT

eBay Inc., San Jose, CA ...


1. A method, comprising:receiving, from a first computing device, a request to establish a collaborative shopping session with a second computing device on a network-based marketplace;
in response to receiving the request, transmitting information corresponding to the collaborative shopping session to the second computing device;
using the information to establish the collaborative shopping session between the first computing device and the second computing device;
when the collaborative shopping session is established, displaying a common interface associated with the collaborative shopping session on the first computing device and the second computing device;
granting control of a cursor provided in the common interface associated with the collaborative shopping session to the first computing device; and
in response to received input, alternating control of the cursor provided in the common interface associated with the collaborative shopping session.

US Pat. No. 11,113,738

PRESENTING ENDORSEMENTS USING ANALYTICS AND INSIGHTS

Microsoft Technology Lice...


1. A computer system comprising:a processor;
a storage device;
a memory device holding an instruction set executable by the processor to cause the computer system to perform operations comprising:
training a machine learned model using a machine learning algorithm, wherein the training includes calculating a plurality of coefficients using an optimization function;
responsive to receiving, via a computing device of a first member of a social networking service, a request to view a member profile of a second member of the social networking service:
accessing member profile data of the second member to identify a set of skills, each skill in the set of skills a skill for which the second member has received an endorsement from one or more endorsers;
deriving an endorsement quality score for each endorsement of a skill in the set of skills by the one or more endorsers, the endorsement quality score for each endorsement derived as a combination of sub-scores including an endorser value based on characteristics of the endorser and a recipient value based on characteristics of the second member, the combination calculated by passing one or more features of the endorser and one or more features of the second member to the trained machine learned model and applying the calculated coefficients to the subscores;
selecting from the set of skills a particular skill, shared in common between the first member profile and the second member profile, according to member profiles of the first member and the second member, and associated with an endorsement having an endorsement quality score that exceeds a predetermined threshold;
presenting in a user interface, via the computing device of the first member of the social networking service, the member profile of the second member and member information identifying the particular skill and the endorser associated with the endorsement of the particular skill; and
retraining the machine learning model based on input received from the first member in response to the presenting.

US Pat. No. 11,113,737

METHOD AND SYSTEM FOR MANAGING CONSTRAINT-BASED VIOLATIONS IN A PRODUCT DATA MANAGEMENT ENVIRONMENT

SIEMENS INDUSTRY SOFTWARE...


1. A method of managing constraint-based violations associated with a product in a computer-implemented Product Data Management (PDM) system, the method comprising:obtaining, using the computer-implemented PDM system, a set of constraints defined for the product from a product database, the set of constraints comprising one or more families with corresponding values, each family of the one or more families representing a single type of product design option and comprising a group of mutually exclusive values associated with the single type of product design option, wherein each constraint of the set of constraints is associated with a single family and a single corresponding value;
obtaining, by a processor of the computer-implemented PDM system, requirement data associated with the product, the requirement data being in the form of an input expression via a graphical user interface of the computer-implemented PDM system, the input expression containing one or more values associated with or more families of the set of constraints;
determining, by the processor of the computer-implemented PDM system, constraints from the set of constraints that are conflicting with the obtained requirement data associated with the product when the requirement data is not successfully validated with respect to the set of constraints, wherein a constraint is conflicting when a value of the input expression associated with the single family of the constraint does not match the single corresponding value of the constraint, and wherein at least one constraint from the set of constraints is responsible for causing a violation;
grouping, by the processor of the computer-implemented PDM system, the conflicting constraints into a plurality of logical groups based on a type of independent violation, the type of independent violation indicating a specific conflict between a value of a family of a single constraint and a value of a corresponding family of the requirement data for a type of family, wherein each logical group of the plurality of logical groups is associated with a single independent violation, such that the independent violation of a respective logical group represents a single conflict between a value of a family of the obtained requirement data and a value of a corresponding family of the constraint of the respective logical group;
outputting a multi-dimensional representation of the plurality of logical groups of conflicting constraints on a first view of the graphical user interface of the computer-implemented PDM system, such that a total number of independent violations for the obtained requirement data is determinable by a user from the first vie;
computing, by the processor of the computer-implemented PDM system, one or more solutions corresponding to each independent violation based on the logical groups;
automatically resolving conflicts between the constraints and requirement data corresponding to respective independent violations based on the corresponding one or more solutions; and
configuring the product based on the requirement data upon resolving the conflicts.

US Pat. No. 11,113,736

METHOD, APPARATUS, AND COMPUTER PROGRAM PRODUCT FOR ESTIMATING INVENTORY BASED ON DISTRIBUTION DATA

MCKESSON CORPORATION, Ir...


1. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:receive, from a prescriber computer, an indication of an order request comprising at least (a) a product identifier and (b) at least one merchant attribute describing at least one merchant at which a product is requested to be obtained;
access distribution data relating to the distribution of product to at least one merchant associated with the at least one merchant attribute;
access prescription claims received via a communication interface and associated with the product identifier and the at least one merchant;
generate estimated inventory information, based on the distribution data and the prescription claims associated with the product identifier and the at least one merchant, wherein the estimated inventory information describes an estimated inventory of the product of at least one merchant associated with the at least one merchant attribute;
transmit a message, comprising at least the estimated inventory information and cost information, to the prescriber computer;
cause display of the message at the prescribing computer;
receive, from the prescriber computer, an indication of a selected merchant to which to route the order request; and
in response to the indication of the selected merchant, transmit the order request to a pharmacy computer associated with the selected merchant.

US Pat. No. 11,113,735

MEDIUM FOR CREATING STANDARDIZED SHARED SERVICE OFFERINGS WITH TEMPLATE FOR CUSTOM UNIQUE PRICES


1. A computer program product for generating customized pricing of in-common business service offerings through an online marketplace platform for direct comparison of the in-common business services by consumers, the computer program product comprising a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code being configured, when executed by a processor, to:store within a host server of the platform, a database of business services and service tiers associated with each of the business services, and service providers by geographic location;
generate a service provider electronic user interface template for display on a first computing device, accessible to a plurality of service providers through a network connection to the platform, wherein the service provider electronic user interface template displays,a first tier of business services, wherein each business service is a service type performed in-common by service providers of the same business service,
a second tier of service tiers, each service tier being a subcategory of a respective business service, wherein each service tier includes a description of service details performed in-common by service providers in the same business service, and
a pricing field;

generate a selectable toggle on/off feature, displayed on the service provider electronic user interface template, for each service tier, enabling one or more service tiers associated with the business service, for one service provider to be selectably displayed in association with the one service provider in a customer electronic user interface, wherein the pricing field is configured to receive a custom price associated with enabled service tiers;
store in the host server platform, for each service provider, selected service tiers enabled by the toggle on/off feature;
store in the database, the geographic location of each service provider; and
generate for display on a second computing device, the customer electronic user interface displaying a list of service providers, with the enabled service tiers available within each business service and the custom price of enabled service tiers for each service provider, in response to a customer service request query by a consumer for a selected business service and associated service tier.

US Pat. No. 11,113,734

GENERATING LEADS USING INTERNET OF THINGS DEVICES AT BRICK-AND-MORTAR STORES

ADOBE INC., San Jose, CA...


1. A computer-implemented method for generating a lead for a consumer and a product comprising:receiving detected sensor data from at least one of one or more consumer devices or one or more IoT devices at a brick-and-mortar store, the detected sensor data indicative of the consumer interacting with the product at the brick-and-mortar store, wherein the one or more IoT devices comprises a camera, and wherein the detected sensor data from the camera comprises an indication of a facial expression of the consumer;
determining one or more interactions of the consumer with the product based on a comparison between the detected sensor data and stored sensor data, wherein the stored sensor data is included within mapping information, and wherein the mapping information comprises the stored sensor data that is mapped to sets of predefined interactions, each set of predefined interactions comprising a first predefined interaction and a second predefined interaction, wherein the first predefined interaction and the second predefined interaction correspond to a first precomputed score and a second precomputed score, each indicating corresponding conversion rates;
based on the set of predefined interactions, calculating a leads score based on the first precomputed score of the first predefined interaction and the second precomputed score of the second predefined interaction, the calculated leads score indicating an interest level of the consumer in the product; and
generating a lead for the consumer based on determining the leads score exceeds a threshold.

US Pat. No. 11,113,733

INTEGRATED ARCHITECTURE FOR PERFORMING ONLINE ADVERTISING ALLOCATIONS

OpenX Technologies, Inc.,...


1. A method implemented by a plurality of integrated processors to implement a multi-layer bid structure by executing instructions including executable code stored in a non-transitory memory for placement of advertising on publisher content accessible online by a network, the method comprising:loading, by at least one of the plurality of integrated processors, a web page with the publisher content viewable on a user device when the web page renders on the user device by a browser;
executing within the web page, by at least one of the plurality of integrated processors, an instruction set including a snippet of HTML adapted to write one or more scripts into the web page in the process of attempting to deliver advertising on the publisher content for an advertisement space on the web page, including an ad-exchange header code soliciting responsive bid data from a plurality of bidding participants coupled by the network to the plurality of integrated processors;
normalizing, by at least one of the plurality of integrated processors, respective bids from the bidding participants;
determining, by at least one of the plurality of integrated processors, a highest bid and passing the highest bid by one or more ad exchanges as a key value bid; and
performing advertisement selection by the one or more advertisement exchanges, by at least one of the one or more processors, to determine a winning bid.

US Pat. No. 11,113,732

CONTROLLING USE OF NEGATIVE FEATURES IN A MATCHING OPERATION

Microsoft Technology Lice...


1. A system, implemented by one or more computing devices, for providing information items to end users, comprising:a trigger-identifying system, including:a user interface component configured to receive input from an administrative user, and to provide output to the administrative user;
a trigger-generating component configured to extract content from a web resource identified by the administrative user via the user interface component and then generate positive trigger information based on content that is extracted, the positive trigger information serving as a basis for determining when an input query, provided by an end user, qualifies as a match with a part of the web resource, the web resource corresponding to a web site that includes one or more web pages;
a negative feature-providing component configured to supply negative feature information, the negative feature information serving as a basis for determining when the input query is explicitly disqualified as a match with a part of the web resource;
a data store for storing filtering information that includes the positive trigger information and the negative feature information; and
an impact-managing component including:a conflict-assessing component configured to determine an impact of the negative feature information in disqualifying matching between input queries provided by end users and the positive trigger information, when the input queries contain the negative feature information input by the end users, to provide conflict output information; and
a control mechanism configured to instruct the negative feature-providing component to modify the negative feature information based on the conflict output information;


an item-matching system configured to deliver information items to end users based on matching between the input queries and the positive trigger information, and based on consideration of the negative feature information; and
a performance-monitoring system configured to monitor performance of the item-matching system, to generate performance information, and to supply the performance information to the trigger-identifying system for use thereby in generating the filtering information.

US Pat. No. 11,113,731

SYSTEMS AND METHODS FOR CUSTOMER VALUATION AND MERCHANT BIDDING

eBay Inc., San Jose, CA ...


1. A method performed by hardware processing circuitry, comprising:identifying a location of a mobile device;
identifying a plurality of merchants within a threshold distance of the location of the mobile device;
determining different first valuations based on the location, each of the different first valuations determined based on a different respective one of the plurality of merchants and a distance of the mobile device relative to each of the plurality of merchants;
providing the different first valuations to a first valuation's respective merchant: including a first merchant of the plurality of merchants;
detecting a change in the location of the mobile device;
determining different second valuations based on the changed location, each of the different second valuations further based on a different respective one of the plurality of merchants including the first merchant; and
providing the different second valuations to a second valuation's respective merchant, including the first merchant of the plurality of merchants.

US Pat. No. 11,113,730

PARALLEL DATA POOL PROCESSING AND INTELLIGENT ITEM SELECTION

Amazon Technologies, Inc....


1. A method comprising:receiving, by one or more computer processors coupled to at least one memory, a first bid request for a content delivery slot, wherein the first bid request comprises a first user identifier for a first user;
determining clickstream data for the first user using the first user identifier;
determining a first set of product identifiers that the first user interacted with using the clickstream data;
deduplicating the first set of product identifiers to remove duplicate product identifiers;
selecting a random subset of the first set of product identifiers, wherein the random subset comprises at most twenty product identifiers;
sending a first evaluation request comprising the random subset to a model evaluator component, wherein the model evaluator component is configured to determine an estimated value for one or more of the random subset, wherein the estimated value comprises a first bid amount for a first product identifier of the one or more of the random subset;
receiving a second bid request comprising a second user identifier for a second user;
determining that the second user interacted with one product identifier;
sending a second evaluation request comprising the one product identifier to the model evaluator component;
determining that a first timer for the for a first response to the first bid request;
determining, based on the model evaluator component, a first set of estimated values for the one or more of the random;
pausing determination of bid amounts for unevaluated product identifiers in the random set based on at least one of a timer value associated with the first timer, a number of unevaluated product identifiers associated with the first bid request, or a number of evaluated product identifiers associated with the first bid request;
determining, during the pausing, an estimated value for the one product identifier;
determining, after the pausing, an estimated value for at least one of unevaluated product identifiers in the random subset;
selecting a highest ranked product identifier from the first set of estimated values and the estimated value for the at least one of unevaluated product identifiers using respective estimated values;
sending the first response to the first bid request using the highest ranked product identifier; and
sending a second response to the second bid request using the estimated value for the one product identifier.

US Pat. No. 11,113,729

REAL-TIME ONLINE ADVERTISEMENT TYPE OVERRIDES

Xandr Inc., New York, NY...


1. A method comprising:performing by one or more computers:receiving, by a processing system including a processor, from a client device, a first notification of an ad space from a seller over a communication network, the ad space being for presentation in a user interface of an application executing on the client device;
identifying, by the processing system, a first creative for the ad space;
identifying, by the processing system, a first plurality of ad conditions in a global ad profile corresponding to an ad space inventory to which the ad space belongs comprising a first condition that identifies an allowed creative media type for the ad space inventory, wherein the allowed creative media type comprises a fixed image, an expandable image, an animation, video, or audio, wherein the allowed creative media type comprises a first subject matter;
identifying, by the processing system, a second plurality of ad conditions in a seller's ad profile corresponding to the seller;
sending, by the processing system, a second notification requesting a bid on the ad space to a plurality of bidders over the communication network, each bidder representing a respective buyer;
receiving, by the processing system, bids from the bidders over the communication network, each bid corresponding to a respective bid price, buyer, and a creative;
determining, by the processing system, that a first bid of the bids corresponds to the first creative having a media type comprising a second subject matter different from the first subject matter, wherein the media type of the first creative comprises a fixed image, an expandable image, an animation, video, or audio;

identifying, by the processing system, a preexisting arrangement between a first buyer corresponding to the first bid and the seller, wherein the preexisting arrangement and the second plurality of ad conditions take priority over the first plurality of ad conditions in the global ad profile, wherein the preexisting arrangement and the second plurality of ad conditions allow the first creative to be served to the ad space, wherein the client device receives a uniform resource locator (URL) for the first creative over the communication network, wherein the client device obtained the first creative over the communication network according to the URL and presents the first creative on the ad space on a graphical user interface (GUI), wherein the preexisting arrangement includes a floor price between the first buyer and the seller;
determining, by the processing system, that the first creative does not satisfy the first plurality of ad conditions based on the first creative not comprising the allowed creative media type;
determining, by the processing system, that the first creative does satisfy the second plurality of ad conditions;
determining, by the processing system, that a first bid price of the first bid exceeds the floor price;
selecting, by the processing system, the first creative for the ad space based on the second plurality of ad conditions taking priority over the first plurality of ad conditions and the first bid price exceeding the floor price; and
storing, by the processing system and based on the selecting of the first creative for the ad space, a transaction record that includes the seller, the first buyer, and a second bid price of a second bid included in the bids, wherein the second bid price corresponds to a second buyer that is different from the first buyer and the second bid price is different from the first bid price.

US Pat. No. 11,113,728

SYSTEM AND METHOD FOR MARKETING OVER AN ELECTRONIC NETWORK

Tamiras Per Pte. Ltd., LL...


1. A method comprising:displaying at least one program display of a computer program configured to request and receive information and an interactive advertisement on a user interface of a user device, the user device configured to request and receive information from a distributor computing device, the user interface comprising a banner window and a browser window;
transmitting a signal from the user device to access at least one commands configuration file that comprises:speech-to-text commands related to the interactive advertisement,
at least one commands parameter for the speech-to-text commands, and
at least one of a URL link to be accessed via the browser window for each speech-to-text command and at least one graphic to be displayed via the banner window for each speech-to-text command,
wherein the at least one commands configuration file is hosted by the distributor computing device remotely located from the user device;

presenting a message associated with the interactive advertisement via the user interface to facilitate user interaction with the displayed interactive advertisement, the message received at the user device from the distributor computing device;
receiving a speech-to-text command;
recognizing the received speech-to-text command as corresponding to at least one of the speech-to-text commands of the commands configuration file related to the interactive advertisement;
responsive to the recognized speech-to-text command, updating the banner window of the user interface with the at least one graphic for the speech-to text command in the at least one commands configuration file and updating the browser window with the URL link for the speech-to-text command in the at least one commands configuration file; and
identifying an advertising sponsor of the displayed interactive advertisement by specifying a path for the at least one commands configuration file used by the distributor computing device to facilitate collection of revenue to subsidize costs related to the computer program.

US Pat. No. 11,113,727

SYSTEMS AND METHODS FOR DYNAMIC ROAD SIGN PERSONALIZATION


1. A method for presenting to a vehicle, personalized and generalized information on a road sign, the method comprising:a processor receiving sensor data from a sensor and using the sensor data to determine proximity of the vehicle to the road sign;
receiving data regarding at least one of operating characteristics of the vehicle and characteristics of one or more occupants of the vehicle;
determining road conditions proximate to the road sign, wherein the road conditions proximate to the road sign comprise a quantity of vehicles forming roadway congestion;
determining whether or not to present information on the road sign based on the quantity of vehicles forming the roadway congestion;
upon a determination that the quantity of vehicles exceeds the vehicle threshold, presenting generalized information on the road sign;
and
upon a determination that the quantity of vehicles does not exceed the vehicle threshold, presenting the personalized information on the road sign.

US Pat. No. 11,113,726

METHODS, APPARATUSES, AND COMPUTER PROGRAM PRODUCTS FOR PROVIDING A PLATFORM FOR NEGOTIATION AND PROVISION OF PROMOTIONS

Groupon, Inc., Chicago, ...


1. A method for generating promotion impressions comprising:receiving, via a processor and from a consumer device, a consumer request for a promotion, wherein the consumer request comprises one or more indications of consumer preferences for the promotion;
determining, via the processor, a potential merchant list comprising one or more potential merchants, based in part on the consumer request, the potential merchant list associated with a plurality of merchant devices, each of the plurality of merchant devices located remotely from other merchant devices of the plurality of merchant devices and located remotely from the consumer device;
for each potential merchant in the potential merchant list, determining, via the processor, whether the potential merchant is associated with pre-established promotion criteria that meets the consumer request;
for a first potential merchant set of the potential merchant list, the first potential merchant set comprising each potential merchant determined not to be associated with the pre-established promotion criteria that meets the consumer request:generating, via the processor, transmission information comprising the consumer request for providing to a merchant device of the plurality of merchant devices, the merchant device associated with the potential merchant; and
providing, via the processor in real-time to the merchant device associated with the potential merchant, the transmission information comprising the consumer request; and

for a second potential merchant set, the second potential merchant set comprising at least one potential merchant determined not to be associated with the pre-established promotion criteria that meets the consumer request:receiving, via the processor in real-time, a response from the merchant device associated with the potential merchant, the response comprising promotion data; and
storing, via the processor, the promotion data associated with the potential merchant in a promotion data list; and

determining, based on electronic marketing information corresponding to the consumer device and from the promotion data list associated with the second potential merchant set, a relevant promotion data subset associated with a consumer profile corresponding to the consumer device, the electronic marketing information comprising a first electronic marketing information portion generated by the processor in response to first user interaction with the processor via the consumer device associated with the consumer profile or an additional consumer device associated with the consumer profile, and the electronic marketing information comprising a second electronic marketing information portion received from at least one server external from the processor via the consumer device associated with the consumer profile or the additional consumer device associated with the consumer profile, and wherein the relevant promotion data subset comprises the promotion data stored in the promotion data list for at least one promotion determined as relevant to the consumer profile; and
generating, via the processor in real-time, an impression comprising the relevant promotion data subset from the promotion data list.

US Pat. No. 11,113,725

METHOD AND SYSTEM FOR RECOMMENDING PROMOTIONS TO CONSUMERS

Groupon, Inc., Chicago, ...


1. A computer-executable method comprising:receiving user clickstream data input, from a first graphical user interface (GUI), attached to a first consumer device associated with a first consumer, the user clickstream data input comprising an interest indication relating to a first promotion, the interest indication indicative of an interaction between the first consumer and the first promotion, wherein the interest indication is at least one of click data indicative of a viewing activity, an accessing activity, an editing activity, a retrieving activity, a purchase activity, or a promotion rating activity;
identifying, from a promotion sharing database, a second consumer with which the first consumer is related via a promotion sharing association, the promotion sharing association comprised of a plurality of association scores, each of the plurality of association scores indicative of a particular characteristic shared by the first consumer and the second consumer,
wherein the second consumer with which the first consumer is related via a promotion sharing association is related by a process comprising;
programmatically generating an association and an association score for the association between the first consumer and the second consumer based on prior activity data of the first consumer related to a prior promotion and prior activity data of the second consumer related to the prior promotion,
wherein programmatically generating the association between the first consumer and the second consumer comprises:analyzing a social graph to identify one or more edges connecting a first node representing the first consumer and a second node representing the second consumer, each edge of the one or more edges connecting the two nodes being associated with a particular category or characteristic of the prior promotion;
retrieving a connection score for a connection path, the connection score representing an estimated strength of connection between the first consumer and the second consumer, the connection score based on the prior activity data of the first consumer related to the prior promotion and the prior activity data of the second consumer related to the prior promotion;
analyzing a taste graph to identify a path connecting a first node representing the first consumer and a second node representing the second consumer;
retrieving a relevancy score for the path, the relevancy score representing an estimated relevancy of promotion interests between the first consumer and the second consumer, the relevancy score based on a one or more profile data features and one or more activities performed by the first consumer and the second consumer in connection with a common set of promotions;
generating, via a machine learning model, the association score related to the association between the first consumer and the second consumer based on the connection score and the relevancy score, wherein the generation of the machine learning model comprises generating a multidimensional vector for an example first consumer and an example second consumer and comparing the multidimensional vector for the example first consumer and the multidimensional vector for the example second consumer to determine a measure of similarity and programmatically executing a machine learning algorithm to relate the measure of similarity to a probability that the association score between the example first consumer and the example second consumer is positive or negative; and
generating the association between the first consumer and the second consumer if the association score exceeds a predetermined threshold score;

programmatically retrieving, from a consumer association database stored on a non-transitory computer-readable medium, the association between the first consumer and the second consumer, the association score associated with characteristics of the first promotion, and prior activity data of the first consumer related to the first promotion and prior activity data of the second consumer related to the first promotion;
upon retrieval of the association from the consumer association database, determining if the association score related to the association between the first consumer and the second consumer associated with characteristics of the first promotion meets a predetermined threshold; and
causing a second impression of the first promotion to be generated, configured for display, wherein the second impression of the first promotion comprises data indicative of the prior activity data of the second consumer related to the first promotion, at a second consumer interface, attached to a second consumer device, the second consumer device associated with the second consumer.

US Pat. No. 11,113,724

CONTENT SELECTION ASSOCIATED WITH WEBVIEW BROWSERS

Google LLC, Mountain Vie...


1. A method for expanding a cookie space of a webview comprising:obtaining, by a content management system and from a first webview of a first application that is executing a script at a resident device, a URL that includes a unique identifier of the resident device;
responsive to receipt of the unique identifier by the content management system:dropping, by the content management system, a cookie in a first temporary cookie space of the first webview; and
storing, in a repository of the content management system, an entry that links the cookie and the unique identifier;

after the first temporary cookie space of the first webview has been cleared at the resident device, receiving, by the content management system and from a second different webview generated by the resident device, the unique identifier of the resident device;
retrieving, by the content management system, the cookie from the entry using the unique identifier of the resident device that is received from the second different webview;
dropping, by the content management system, the retrieved cookie in a second temporary cookie space of the second different webview;
selecting, by the content management system and in response to the request, a content item for presentation in a publisher page presented by the second different webview using interaction information that (i) was received from the first webview and (ii) was stored in the entry that links the cookie and the unique identifier based on the the retrieved cookie being included in a content request; and
providing the selected content item to the second different webview at the resident device.

US Pat. No. 11,113,723

EXPLICIT USER HISTORY INPUT

Sprint Communications Com...


1. A method of selectively modifying user history, comprising:receiving an advertisement by a user equipment (UE);
determining by the UE a subject of the advertisement, wherein the UE determines a subject of the advertisement by reading metadata that is appended to the advertisement;
receiving by the UE an input to disassociate the subject of the advertisement from a user history of the UE maintained remote from the UE; and
transmitting a user history modification request to a history moderator server by the UE, wherein the user history of the UE is maintained remotely by a history manager server that, after the history moderator server validates a user history modification request and the history manager server receives the user history modification request from the history moderator server, removes the subject of the user history modification request from the user history of the UE to disassociate the subject of the advertisement from the user history of the UE, wherein the history moderator server determines a validity of the user history modification request by checking the percentage of clicks or views of the subject in the user history modification request the subject has over a predefined period of time.

US Pat. No. 11,113,722

PROVIDING CONTENT RELATED TO SENTIMENT OF PRODUCT FEATURE

ADOBE INC., San Jose, CA...


1. One or more computer storage media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations to provide targeted content related to sentiment associated with products, the operations comprising:in accordance with an abandonment of an item in an electronic shopping cart, identifying a referral source from which a user navigated to arrive at a product page having the item in an electronic shopping cart;
determining that the referral source and the product page were visited during a browsing session;
determining a negative sentiment of a product feature associated with the item, wherein the negative sentiment of the product feature is determined using content of the referral source, wherein the content of the referral source includes a negative description of the product feature;
based on the negative sentiment of the product feature, selecting positive targeted content related to the product feature associated with the item, wherein the positive targeted content includes a positive description of the product feature which is contrary to the negative description of the product feature in the content of the referral source, the targeted content intended to address the negative sentiment of the product feature associated with the item; and
providing the positive targeted content for the user to view in an effort to entice the user to complete a purchase of the item in the shopping cart.

US Pat. No. 11,113,721

DYNAMIC SENTIMENT-BASED MAPPING OF USER JOURNEYS

ADOBE INC., San Jose, CA...


1. In a digital medium environment for collecting and analyzing analytics data, a computer-implemented method for aggregating interaction information and presenting a user journey comprising:collecting, by a server device, analytics data for a plurality of online user interactions for a plurality of users with respect to an online entity;
analyzing the analytics data to identify attributes of the plurality of online user interactions;
determining sentiment scores for each of the plurality of online user interactions based on the identified attributes of the plurality of user interactions, each sentiment score indicating a measurement of sentiment of a user of the plurality of users associated with an online user interaction;
aggregating the plurality of online user interactions to identify an interaction path comprising a plurality of different types of online user interactions experienced by a threshold number of the plurality of users associated with a target metric;
aggregating the sentiment scores for each type of online user interaction of the plurality of different types of online user interactions to generate a general sentiment score indicating a measurement of sentiment of users who experienced a corresponding type of online user interaction;
generating an interactive presentation comprising a visualization of the interaction path, the visualization of the interaction path comprising:a sequence of interaction icons representing the different types of online user interactions;
sentiment icons indicating a range of the determined general sentiment scores for the respective different types of online user interactions in the interaction path, wherein the range of the determined general sentiment scores comprises a lowest sentiment score to a highest sentiment score; and
segment icons corresponding to segments of users from the plurality of users, the segments of users comprising subsets of the plurality of users;

generating a sentiment window corresponding to a sentiment icon of the sentiment icons, the sentiment window comprising a notification of an abnormal sentiment icon and description of factors contributing to the abnormality;
providing the sentiment window within the interactive presentation; and
in response to detecting a selection of a segment icon corresponding to a segment of users, modifying the visualization of the interaction path to reflect interactions experienced by the selected segment of users by modifying a size of the sentiment icons to indicate a range of segment sentiment scores for the segment of users for the respective different types of online user interactions in the interaction path.

US Pat. No. 11,113,720

SYSTEM AND A METHOD FOR SURVEYING ADVERTISEMENTS IN MOBILE APPLICATIONS


1. A computer-implemented method executed by an internet server, the method comprising the actions of:receiving at the internet server, data comprising:at least one particular mobile application, wherein the at least one particular mobile application comprises executable code configured to be executed by a processor of a mobile communications device, and wherein the executable code comprises at least one advertisement related code;
at least one user location for a particular virtual user, the user location comprising a selected geographical location; and
personal data for simulating the particular virtual user on the internet server;

monitoring, by the internet server, in real-time, processing of the executable code, the executable code being processed by an emulated mobile communications device on the internet server;
intercepting, by the internet server, in real-time, a communication generated by the emulated mobile device processing the at least one advertisement related code;
communicating, by the internet server, in real-time, the intercepted communication to an ad network server via a proxy server, wherein the proxy server is associated with the received user location of the particular virtual user;
receiving, by the internet server, advertisement data from the ad network server; and
recording, by the internet server, at least one of:advertisement information included in the advertisement data to be displayed by the at least one particular mobile application; and
parameters associated with the advertisement data.


US Pat. No. 11,113,719

CONTENT DEMOTION

International Business Ma...


1. A computer-implemented method comprising:receiving promoted content for display at a primary device that is a node of a cloud network and a user device;
detecting and profiling a user's cognitive state by monitoring the user's interactions with the primary device using at least one of: eye tracking sensors, motion tracking sensors, audio/speech sensors, and a camera and monitoring the user's interactions with one or more applications using at least one of: typing characteristics, mouse movement, analysis of typed content, and an application profile;
predicting the user's behavior with respect to the promoted content by inferring the user's context and preferences from the detected profile of the user's cognitive state, using a neural network;
prompting the user for feedback via the primary device;
retraining the neural network using the feedback; and
in response to the prediction of the user's behavior that the user may attempt to purchase promoted content, automatically demoting the promoted content, wherein demoting the promoted content includes blocking transfer of the promoted content that is displayed at the primary device from the primary device to one or more secondary devices via a peer-to-peer network that is established between the primary device and the one or more secondary devices.

US Pat. No. 11,113,718

ITERATIVELY IMPROVING AN ADVERTISEMENT RESPONSE MODEL

PAYPAL, INC., San Jose, ...


1. A method, comprising:electronically scanning, by a computer comprising one or more hardware processors, websites of a plurality of merchants;
determining, by the computer, a frequency of usage of one or more terms on the websites, a placement of the one or more terms on the websites, or a visual appearance of the one or more terms on the websites;
determining, by the computer based on the frequency, the placement, or the visual appearance of the one or more terms on the websites, a dictionary of terms associated with the websites;
correlating the terms in the dictionary of terms with types of merchants from the plurality of merchants or with payment services used by plurality of merchants;
retrieving website data from a website of a first merchant from the plurality of merchants;
determining, based on the retrieved website data, whether any terms appearing on the website of the first merchant match the terms in the dictionary of terms;
selecting, based on the determining whether any terms appearing on the website of the first merchant match the terms in the dictionary of terms, one or more payment provider services to advertise to the first merchant;
training, by the computer, an advertisement response model using a training data set that indicates a respective response to an advertising campaign for each unit in the training data set, wherein units of the training data set correspond to a first subset of the plurality of merchants;
determining, by the computer based on the training the advertisement response model using the training data set, that a first accuracy value corresponding to the advertisement response model is less than an accuracy value threshold;
determining, by the computer using the dictionary of terms, a target data set that is different from the training data set, wherein units of the target data set correspond to a second subset of the plurality of merchants, the second subset being different from the first subset;
identifying, by the computer based on executing the advertisement response model using the target data set, one or more units from the target data set for which to run the advertising campaign;
receiving, by the computer, one or more responses corresponding to a run of the advertising campaign with respect to the identified one or more units from the target data set;
updating, by the computer, the training data set based on the one or more responses; and
determining, by the computer based on training the advertisement response model using the updated training data set, whether a second accuracy value corresponding to the advertisement response model is greater than the accuracy value threshold.

US Pat. No. 11,113,717

CUSTOMER ENGAGEMENT PLATFORM EXPERIMENTATION FRAMEWORK

MICROSOFT TECHNOLOGY LICE...


1. A method of creating a customer engagement platform experimentation framework, comprising:creating, based on selections made by a user at a user interface, an experiment based on an original promotion to determine customer engagement, the experiment including conditions selected by the user;
computing user bucket assignments for the experiment, the user bucket assignments utilizing numberlines to compute the user bucket assignments and group users of the experiment into a control or a treatment group, the numberlines computing the user bucket assignments similarly for related experiments to ensure the users are in either the control or the treatment group for all the related experiments;
creating experiment bookings for the experiment in accordance with the user bucket assignments;
detecting parameters at runtime during a client content request, the parameters including operating system version or screen resolution;
and
upon the detected parameters being satisfied, delivering the experiment to the users in accordance with the conditions and the experiment bookings.

US Pat. No. 11,113,716

ATTRIBUTION THAT ACCOUNTS FOR EXTERNAL VIEWING CONDITIONS

ADOBE INC., San Jose, CA...


1. A method for attributing credit to one or more online consumer touchpoints for a consumer performing an action, the method comprising:detecting an external viewing condition for the one or more online consumer touchpoints, wherein the one or more online consumer touchpoints include an advertisement received through an electronic network and wherein the external viewing condition indicates whether the consumer is in a distracting environment during the one or more online consumer touchpoints;
determining that the consumer performed the action following the one or more online consumer touchpoints;
determining an effectiveness of the one or more online consumer touchpoints by applying a machine learning technique to the external viewing condition and touchpoint data associated with the one or more online consumer touchpoints, wherein the machine learning technique accounts for the effectiveness of particular consumer touchpoints in particular external viewing conditions and types of environments created by the particular external viewing conditions, and wherein the machine learning technique accounts for combinations of external viewing conditions and types of environments under which consumers interacted with a product without converting the interaction into a purchase; and
attributing relative credit to the one or more online consumer touchpoints for the consumer performing the action based on the effectiveness of the one or more online consumer touchpoints.

US Pat. No. 11,113,715

DYNAMIC CONTENT SELECTION AND OPTIMIZATION

AMAZON TECHNOLOGIES, INC....


1. A computer-implemented method, comprising:obtaining creative content including a plurality of image and textual elements, the image and textual elements having a plurality of variable parameters;
selecting initial permutations of the creative content, based at least in part on application of a random number;
displaying, on a computing device display, the initial permutations of the creative content;
generating a plurality of creative content permutations, corresponding to the creative content, using the plurality of image and textual elements and parameter settings from among the variable parameters, the creative content permutations having respective selection probabilities;
automatically selecting display content, from the plurality of creative content permutations, based on a highest selection probability for a corresponding creative content permutation, the highest selection probability based at least in part on one or more multi-armed bandit algorithms processing the content permutations' respective selection probabilities;
rendering the display content for display;
obtaining user interaction data corresponding to the display content;
recalculating at least one of the respective selection probabilities based at least in part upon the user interaction data;
generating updated display content, based at least in part on the recalculating at least one of the respective selection probabilities; and
displaying, on the computing device display, the display content.

US Pat. No. 11,113,714

FILTERING MACHINE FOR SPONSORED CONTENT

Verizon Media Inc., New ...


10. A machine comprising:communication circuitry coupled to at least one network and configured to receive first sponsored content from a first client device;
quality model circuitry; and
filtering circuitry coupled to the communication circuitry and to the quality model circuitry, the filtering circuitry configured to:receive the first sponsored content from the communication circuitry;
input at least a portion of the first sponsored content into the quality model circuitry;
receive from the quality model circuitry a quality metric for the first sponsored content;
compare the quality metric to a quality threshold; and
effect provision of the first sponsored content to a second client device for display on the second client device when the quality metric exceeds the quality threshold;
wherein the quality model circuitry is configured to generate the quality metric for the first sponsored content based upon (i) historical feedback associated with other sponsored content and (ii) a trustworthiness factor of the first sponsored content determined based upon an analysis of coherence corresponding to textual features of the first sponsored content, wherein the coherence is determined based upon a cosine similarity between bag of word vectors of a title of the first sponsored content and a description of the first sponsored content.


US Pat. No. 11,113,713

LINKING A TRANSACTION WITH A MERCHANT TO AN INTERACTION WITH AN AUGMENTED REALITY ADVERTISEMENT

EDATANETWORKS INC., Calg...


1. A computer-network implemented method for promoting one or more merchants of a marketing program to one or more members of the marketing program, each of the one or more merchants having a corresponding merchant profile that includes a geographical location and each of the one or more members having a corresponding member profile that includes a geographical location, wherein the one or more member profiles and the one or more merchant profiles of the marketing program are stored on a data storage device, each of the one or more member profiles including a participant identifier of the corresponding member, the method comprising:monitoring, receiving, and storing in the data storage device, electronic signals representing data related to incidences, for the one or more members, of rendering on respective display screens of an augmented reality (AR) view of a corresponding product advertisement containing an AR triggering symbol, wherein the stored data related to each said AR view of the product advertisement activity of the one or more members is indexed by the participant identifier of the corresponding member of the one or more members;
detecting an occurrence of a transaction associated with a merchant of the one or more merchants;
receiving or accessing data associated with the transaction;
determining a participant identifier of the one or more members from the data associated with the transaction;
determining a length of elapsed time between the occurrence of the transaction and the occurrence of the AR view of the product advertisement activity of the one or more members;
triggering, as a result of detecting the occurrence of the transaction associated with the participant identifier, a determination of whether:the transaction is linked to any AR view of the product advertisement activity of the one or more members with the participant identifier; and
the respective geographical locations of the one or more members and the merchant of the one or more merchants are in the same vicinity;
and
if so, then:determining with a level of certainty whether the transaction is linked to the AR view of the product advertisement activity of the one or more members with the participant identifier, wherein the determined level of certainty varies based on:the length of the elapsed time;
the data related to the AR view of the product advertisement activity of the one or more members; and
the data associated with the transaction;

and
based on the determined level of certainty and the data related to the AR view of the product advertisement activity of the one or more members, generating one or more incentives.



US Pat. No. 11,113,712

AUTOMATIC REDEMPTION OF DIGITAL OFFERS WITH DEFERRED PAYMENT

Quotient Technology Inc.,...


1. A computer-implemented method for improving computer processing efficiency using a distributed system to transfer, store, monitor, and apply a set of rules to process rebates using contextual transaction data and post-sale rebate criteria to automatically determine rebate eligibility and deliver refunds, the method comprising:receiving, at a server computer that is used by multiple retailers, each of which operates a different retail data center comprising one or more computing devices and one or more databases that collectively operate as a retail server, each retail data center being communicatively coupled to one or more brick-and-mortar stores and/or online stores, and independent of a request for an offer recommendation, contextual transaction data via an application programming interface (API) from a retailer terminal in real time with respect to a transaction at the terminal, the contextual transaction data comprising at least basket-level transaction details comprising universal product codes (UPCs) and quantities purchased;
receiving, at the server computer from a transaction aggregator via APIs of the transaction aggregators, the contextual transaction data comprising historical transaction records that were generated for previous transactions with the multiple retailers;
receiving, at a product data store that is communicatively coupled to the server computer, Universal Product Codes (UPCs) and/or stock-keeping unit (SKU) numbers and descriptions of products from the multiple retailers in periodic batch synchronizations of retailer product databases and from the historical transaction records;
receiving, at the server computer, offer activation request data, the offer activation request data including a loyalty card number and an identification of a digital offer, the digital offer associated with a discount amount, the digital offer being associated with digital metadata specifying one or more post-sale product rebate availability criteria comprising that a post-sale product rebate is available for the digital offer during a specified time frame and/or for certain geographic locations;
querying, by the server computer, a digital data repository to seek a data record matching the loyalty card number;
in response to determining that the data repository has a record matching the loyalty card number, electronically activating the digital offer associated with the identification of the digital offer and associating the activated digital offer with the loyalty card number in the digital data repository;
determining, based on the contextual transaction data and based on querying the product data store, that a consumer entity associated with the loyalty card number purchased a product associated with the activated digital offer and identified in the product data store;
determining, by the server computer, that a post-sale product rebate is available for the consumer entity associated with the loyalty card number based on the digital metadata and the post-sale product rebate availability criteria, the post-sale rebate being a rebate that is available for the consumer entity after the consumer entity has purchased the product associated with the activated digital offer;
in response to determining that the post-sale product rebate is available for the consumer entity after the purchase of the product, generating, by the server computer, a digital payment file based on the discount amount associated with the activated digital offer, the digital payment file specifying a refund amount to be electronically transmitted to the consumer entity associated with the loyalty card, the refund amount resulting after the purchase of the product associated with the activated digital offer; and
using the server computer, transmitting the digital payment file to a third-party payment system that causes the refund amount specified in the digital payment file and resulting after the purchase of the particular product to be transmitted electronically to the consumer entity associated with the loyalty card, the refund amount being transmitted automatically to the consumer entity without an explicit input from the consumer entity to avail the post-sale product rebate.

US Pat. No. 11,113,711

INTRA-TRANSACTION ACCOUNT GENERATION

Capital One Services, LLC...


1. A method, comprising:receiving, by a device, transaction information related to a transaction that is being completed at a transaction terminal;
determining, by the device and based on data from a sensor of the transaction terminal or from a user device, that a benefit account was not used in association with completing the transaction;
interrupting, by the device and based on determining that the benefit account was not used in association with completing the transaction, completion of the transaction;
activating, by the device and based on interrupting completion of the transaction, the sensor,the sensor being configured to receive information associated with the benefit account from the user device or a transaction card; and

completing, by the device and after interrupting completion of the transaction, the transaction based on receiving an indication from the transaction terminal that the benefit account was applied.

US Pat. No. 11,113,710

MODEL-BASED PROMOTION AND PRICE COMPUTATION SYSTEM AND METHOD

PHILIP MORRIS USA INC., ...


1. A method for monitoring a contractual agreement between a retailer and a manufacturer over a network via a processing device configured to execute a model-based promotion and price computation model, the method comprising:in a processor of the processing devicemonitoring, in real-time, a plurality of sales parameters and promotion information, the plurality of sales parameters associated with the retailer and received in real-time over the network, and the promotion information associated with the manufacturer;
receiving, over the network and upon occurrence of a triggering event, a key for decrypting a data segment among a plurality of data segments, wherein a plurality of encrypted sales promotions are stored as the plurality of data segments;
decrypting at least one of the plurality of encrypted sales promotions based on the triggering event and the key; and
determining whether a current sales promotion identified in the promotion information should be implemented by comparing at least one of the plurality of sales parameters to a threshold, wherein the current sales promotion is included in the at least one of a plurality of encrypted sales promotions that are decrypted;

in response to determining that the current sales promotion is to be implementedevaluating retailer parameters for implementing the current sales promotion and calculating, in real-time, an adjusted retail price of goods for the current sales promotion to be implemented based on the promotion information,
transmitting the adjusted retail price of goods over the network for immediate price adjustment at the retailer, and
auditing the plurality of sales parameters in real-time to determine whether the retailer has implemented the current sales promotion and whether the implementation is under manufacturer-specified criteria.


US Pat. No. 11,113,709

DISTRIBUTION OF FRACTIONAL EQUITY REWARDS BASED ON PURCHASE BEHAVIOR

Bumped, Inc., Portland, ...


1. A method comprising:aggregating, with an equity allocation system of a loyalty platform comprising one or more computing systems, a plurality of dollar reward amounts, wherein the plurality of dollar reward amounts are based on a plurality of tracked user loyalty purchases tracked automatically by the loyalty platform, and wherein the equity allocation system comprises instructions executable by one or more processors to direct an inventory account to aggregate the plurality of dollar reward amounts;
displaying, via the loyalty platform, an equity reward status to one or more user computing devices associated with one or more of the plurality of tracked user loyalty purchases;
executing, with the equity allocation system, a whole share purchase based on the aggregated dollar reward amounts exceeding a pending reward threshold, wherein the equity allocation system directs an average price account to perform the whole share purchase from a clearing house;
automatically adding, with the equity allocation system, a number of whole shares purchased in the whole share purchase to the inventory account to form a pre-purchased supply of shares of stock, wherein the equity allocation system directs the average price account to transfer the number of whole shares to the inventory account;
determining, with the equity allocation system, a plurality of fractional share amounts based on an execution price of the whole share purchase and the plurality of dollar reward amounts;
automatically distributing, with the equity allocation system, the plurality of fractional share amounts to a plurality of user accounts from the pre-purchased supply of shares of stock in the inventory account, wherein the equity allocation system directs the inventory account to transfer each fractional share amount of the plurality of fractional share amounts to a corresponding user account of the plurality of user accounts;
responsive to distributing the plurality of fractional share amounts, automatically displaying, via the loyalty platform, an updated equity reward status via the one or more user computing devices; and
dynamically adjusting, automatically with the equity allocation system and in real time, the pre-purchased supply of shares of stock to maintain the pre-purchased supply between an upper supply threshold and a lower supply threshold that are each dynamically adjusted based at least on a running average rate of fractional equity reward distribution.

US Pat. No. 11,113,708

SYSTEM FOR GENERATING A DIGITAL COUPON BASED UPON COLLECTED USER CARD EXCHANGE INFORMATION AND RELATED METHODS

INMAR CLEARING, INC., Wi...


1. A system comprising:a buyer wireless communications device associated with a buyer;
a seller wireless communications device associated with a seller;
a gift card generation server configured to generate a plurality of electronic gift cards each having a retailer associated therewith; and
a gift card exchange server cooperating with said gift card generation server and configured toobtain buyer and seller financial account information associated with the buyer and seller, respectively, for funding an electronic gift card exchange transaction between the buyer and the seller,
provide a user exchange marketplace between the buyer and the seller for the plurality of electronic gift cards and collect user card exchange information based thereon, the user card exchange information comprising a current value, a buyer acquisition value associated with a given one of the plurality of electronic gift cards, a geographic location of the corresponding retailer, and a seller geographic location,
match the buyer and the seller based upon the collected user card exchange information, and communicate the given electronic gift card to the buyer mobile wireless communications device based upon the matching as part of the electronic gift card exchange transaction,
process payment of the electronic gift card exchange transaction between the buyer and the seller by causing transfer of funds between the buyer and the seller based upon the buyer and seller financial account information,
generate at least one buyer digital coupon redeemable at a retailer different than the retailer corresponding to the given electronic gift card and based upon the user card exchange information, the at least one buyer digital coupon having a buyer redemption value based upon the buyer acquisition value relative to the current value at a time of exchange of the given one of the plurality of electronic gift cards between the buyer and the seller,
generate at least one seller digital coupon redeemable at the retailer corresponding to the given electronic gift card and based upon the user card exchange information, the at least one seller digital coupon having a seller redemption value based upon the buyer acquisition value relative to the current value at a time of the exchange of the given one of the plurality of electronic gift cards between the buyer and the seller, and a relative distance between the geographic location of the corresponding retailer and the seller geographic location,
communicate the at least one buyer and seller digital coupons to the buyer and the seller mobile wireless communications devices, respectively, and
store the at least one buyer and seller digital coupons in respective digital wallets associated with the buyer and seller, respectively.


US Pat. No. 11,113,707

ARTIFICIAL INTELLIGENCE IDENTIFICATION OF HIGH-VALUE AUDIENCES FOR MARKETING CAMPAIGNS

Isolation Network, Inc., ...


1. A method for authorizing execution of targeted marketing campaigns for streaming media intellectual property (IP) assets, the method comprising:streaming, by media asset consumers, of media IP assets distributed to digital service providers (DSPs) via a media asset distributor, for which the consumers have obtained streaming access through subscription or agreement to other terms of use from the DSPs;
documenting and compiling the streaming interactions of the consumer into a transaction-level trend data report, wherein items in the report comprise specific media IP assets;
implementing a marketing analytics pipeline that:receives the transaction-level trend data report,
compiles the streaming interactions of individual consumers from the transaction-level trend data report into specific geodemographic groups including geographic regions, genders, ages and DSP subscription status, and without identification of individual consumers,
creates a ranked list of media IP assets and corresponding marketing actions,
retrieves links on the DSPs for the media IP assets in the ranked list of media IP assets, the links being retrieved by use of APIs of the DSP and/or a smartlink API,
creates for each media IP asset in the ranked list of media IP assets, using the smartlink API, one or more landing pages comprising the associated links on the DSPs, and
creates marketing campaigns for media IP asset managers/owners including the one or more landing pages comprising the links on the DSPs for each of the one or more media IP assets in the ranked list;

presenting the ranked list of media IP assets and corresponding marketing actions and marketing campaigns to the media IP asset managers/owners in a graphical user interface (GUI), wherein the GUI includes a media IP asset and a corresponding listing of marketing campaigns, and wherein the GUI enables the media IP asset managers/owners to manage funds, set territory specific budgets and store promotional advertisement material for the marketing campaigns;
receiving modifications made via the GUI by the media IP asset managers/owners; and
receiving authorization to execute the marketing campaigns from the media IP asset managers/owners,
wherein the marketing analytics pipeline comprises:
a marketing action analytics hub configured to receive the growth and re-engagement opportunities from an opportunity detection analytics hub or from a marketing platform directly and to identify high growth potential audiences using predictive models of engagement; and
a marketing platform configured to interact with the marketing action analytics hub and to create targeted marketing campaigns based around the high growth potential audiences, the marketing platform further being configured to suggest specific marketing actions to the media IP asset managers/owners, wherein the marketing actions are designed for delivery to the high growth potential audiences on appropriate marketing channels via the targeted marketing campaigns;
wherein the marketing action analytics hub is comprised of an offline model generation component and an online audience generation component and uses a targeting method based on the specific geodemographic group data compiled from the streaming interactions of individual consumers and the interests of these groups for generating descriptions of high growth potential audiences,
wherein the offline model generation component is configured to use the compiled streaming interactions of geodemographic groups contained in a consumption database to fit statistical models based on consumption patterns of an entirety of distributed media IP assets on a regular cadence by clustering media IP assets into categories and employing an alternating least squares framework to generate a specific matrix factorization for each category by approximating an engagement matrix E as a product of two latent factor matrices Eest:=XY?, where Y? is the matrix transpose of Y;
wherein the choice of the rows and columns of E are informed by the truncation of media IP assets and geodemographic groups based on consumption thresholds, and the values of the entries of E are evaluations of a scalar valued multivariable function ƒ on vectors in a consumption tensor whose dimensions correspond to media IP assets, geodemographic groups, and streaming channels, X is an m×k matrix, Y is an n×k matrix and Eest is itself an approximation of the best rank k?min(m,n) approximation of E that minimizes a cost function




over all possible choices of X and Y such that Strain and Stest form a partition (disjoint nonempty subsets that cover the whole set) of indices of E, Xi and Yj respectively denote the i-th and j-th rows of the matrices X and Y and I and J are truncated sets of media IP assets and geodemographic groups respectively;
wherein ? and k are two hyperparameters for each category determined by a cross validation scheme that minimizes the sum of squared errors SSE(k, ?):=?(i,j)?Stest(Eij(k,?)?Eij)2 using an adaptive grid search where Eij(k,?) is the (i, j)-entry in the matrix Eest(k,?) denoting the estimate obtained from the alternating least squares component for a given hyperparameter pair (k, ?), where the chosen k and ? are then used to train the model on the combined train and test dataset, i.e. Strain is now I×J, to minimize the cost(X,Y) to fit Eest=XY?;
wherein ?Xi? and ?Yj? are the l2 norms of Xi and Yj respectively, where the analytic expressions that minimize the cost function for Xi and Yj for a fixed Y and a fixed X respectively are approximated by iteratively applying Xi=(ED(i)Y((Y?Y+?·Id)?1)?)i and Yj=(E?D(j)X((X?X+?·Id)?1)?)j, where Id is the appropriately sized identity matrix, D(i) is an n×n diagonal matrix with the j-th diagonal element one if (i, j)?Strain and zero otherwise, and similarly for the m×m matrix D(j).

US Pat. No. 11,113,706

SCORING INFORMATION MATCHING METHOD AND DEVICE, STORAGE MEDIUM AND SERVER

PING AN TECHNOLOGY (SHENZ...


1. A method for obtaining an accurate target service record in a database of service records, comprising:obtaining a first electronic target scoring message which corresponds to a first telephone number and includes first target scoring information, wherein the first telephone number comprises a first identity number;
storing the first target scoring information and first telephone number in a first record of the database of service records;
obtaining a second electronic target scoring message which corresponds to a second telephone number and includes second target scoring information, wherein the second telephone number comprises a second identity number, and wherein the first identity number and the second identity number can be the same;
storing the second target scoring information and second telephone number in a second record of the database of service records;
extracting the first identity number from the first telephone number;
searching the database of service records for a service record which includes the first identity number and the second telephone number, thereby obtaining a searched service record;
determining that a transmission time of an electronic target scoring message corresponding to the searched service record satisfies a preset condition; and
determining that the searched service record is the target service record that matches with the first target scoring information.

US Pat. No. 11,113,705

BUSINESS FORECASTING USING PREDICTIVE METADATA

International Business Ma...


1. A method for comprising:receiving, by one or more processors, one or more sets of data for projection;
identifying, by the one or more processors, a first metadata value associated with a first set of the one or more sets of data, wherein the first metadata descriptor indicates that the first set is associated with a non-predetermined trend;
identifying, by the one or more processors, a second metadata value is associated with a second set of the one or more sets of data, wherein (i) the second metadata descriptor indicates that the second set is associated with a predetermined trend, and (ii) the second metadata value includes an expression indicating the predetermined trend;
in response to the first metadata descriptor indicating that the first set is associated with the non-predetermined trend, determining, by the one or more processors, one or more projected values of the first set of data based, at least in part, on one or more statistical models;
in response to the second metadata descriptor indicating that the second set is associated with the predetermined trend, generating, by the one or more processors, one or more projected values of the second set of data based, at least in part, on the expression indicating the predetermined trend;
displaying, by the one or more processors, the one or more projected values of the first and second sets of data;
displaying, by the one or more processors, an override protection interface element associated with the first set of data; and
in response to the override protection interface element being enabled during the display of the one or more projected values of the first set of data, updating, by the one or more processors, the display of the one or more projected values of the first set of data based on at least one local setting associated with the first set of data, wherein the updated projection of the first set of data overrides at least one global setting of a dashboard interface with the at least one local setting.

US Pat. No. 11,113,704

SYSTEMS AND METHODS FOR INTERACTIVE ANNUITY PRODUCT SERVICES USING MACHINE LEARNING MODELING


1. A system comprising:a server computing device communicably coupled to a database computing device and having a machine learning processor programmed with an instruction to execute
an artificial intelligence algorithm, the server computing device programmed to:generate an input data set by:determining a set of user information associated with a user, including user demographics, user risk preferences, and user objectives;
determining a set of market index information, including historical market index information, current market index information, and forecast market index information; and
determining one or more available annuity products using the set of user information;

execute, by the machine learning processor, a price optimization module to traverse a computer-generated annuity matching model using the input data set to select a subset of the available annuity products that are associated with product characteristics that match one or more of the user objectives and generate one or more annuity product recommendations for the user based upon the subset of annuity products; and
execute, by the machine learning processor, a market simulation module to traverse a computer-generated annuity performance prediction model using the subset of annuity products selected by the price optimization module and one or more predictions of market performance, the market simulation module generating one or more simulated outcomes for
each of the annuity products in the subset of annuity products;

the system further comprising a client computing device communicably coupled to the server computing device, the client computing device configured to:generate a graphical user interface for display to the user via a display device, the graphical user interface including one or more visual representations of each of: the one or more annuity product recommendations and the one or more simulated outcomes,


wherein the machine learning processor and the modules execute the artificial intelligence algorithm to improve the computer-generated models by automatically assimilating newly-collected input data elements from an external data source into the computer-generated models without relying on manual intervention, and
wherein the server computing device further configured to build, by the machine learning processor, the computer-generated annuity matching model by training a machine learning algorithm programmed on the machine learning processor against a training data set.

US Pat. No. 11,113,702

ONLINE PRODUCT SUBSCRIPTION RECOMMENDATIONS BASED ON A CUSTOMERS FAILURE TO PERFORM A COMPUTER-BASED ACTION AND A MONETARY VALUE THRESHOLD

Amazon Technologies, Inc....


1. A method, comprising:receiving, by at least one processor coupled to memory of a server machine, a plurality of purchase requests, over a network, for a set of user accounts of an online-purchasing system hosted by the server machine;
storing, in a database, purchase histories for the set of user accounts based on the plurality of purchase requests;
determining, by the at least one processor, a subset of the set of user accounts of the online-purchasing system, wherein the subset of user accounts is defined based on users accounts of the subset being associated with performance of a first computer-based transaction associated with an online-purchasing resource, wherein the first computer-based transaction comprises a first online purchase or subscription;
determining, by the at least one processor, one or more user account pairs in which one user account of the subset of user accounts performed a second computer-based transaction associated with the online-purchasing resource, wherein the second computer-based transaction comprises a second online purchase or subscription and another user account of the subset of user accounts did not perform the second computer-based transaction; and
for a user account pair of the one or more user account pairs:determining, by the at least one processor and using the database, that a first user account of the user account pair spent a first amount of money using the online purchasing resource during a first time period, wherein the first user account is associated with performance of the second computer-based transaction;
determining, by the at least one processor and using the database, that a second user account of the user account pair spent a second amount of money using the online purchasing resource during the first time period, wherein the second user account is associated with failure to perform the second computer-based transaction;
determining, by the at least one processor, based on the first amount of money and the second amount of money, that the first user account and the second user account are similar accounts;
determining, by the at least one processor, a first monetary value associated with the first user account, wherein the first monetary value is based on the performance of the second computer-based transaction during a second time period;
determining, by the at least one processor, a second monetary value associated with the second user account, wherein the second monetary value is based on the failure to perform the second computer-based transaction during the second time period;
determining, by the at least one processor, based on the first monetary value and the second monetary value, an impact analysis value for the second computer-based transaction representing a difference between performance of the second computer-based transaction and non-performance of the second computer-based transaction;
determining, by the at least one processor, that the impact analysis value exceeds a threshold monetary value, thereby indicating the second computer-based transaction is a high-value action;
generating, by the at least one processor, a graphical notification associated with the high-value action;
sending, by the at least one processor, the graphical notification to the second user account via the network to a device associated to the second user account, wherein the graphical notification provides the device with access to an online purchase interface that allows the second user to perform the second computer-based transaction; and
receiving, by the at least one processor, an indication via the network from the device associated with the second user account that the second user accessed the online purchase interface via the graphical notification.