US Pat. No. 10,460,254

SYSTEM AND METHOD FOR REDUCING STATE SPACE IN REINFORCED LEARNING BY USING DECISION TREE CLASSIFICATION

VMware, Inc., Palo Alto,...

1. A method for reducing state space in reinforced learning for automatic scaling of a multi-tier application, the method comprising:receiving a new state of the multi-tier application to be added to a state decision tree for the multi-tier application, the new state including a first attribute and a second attribute;
placing the new state in an existing node of the state decision tree only if the first attribute of the new state is same as the first attribute of any state contained in the existing node and a difference between a current statistical measure of values of the second attribute of each existing state contained in the existing node and a new statistical measure of the values of the second attribute of each existing state contained in the existing node with the values of the second attribute of the new state does not exceed a threshold to reduce a number of new states to consider for the reinforced learning; and
executing the reinforced learning using the state decision tree with the new state to automatically scale the multi-tier application.

US Pat. No. 10,460,253

SYSTEM AND METHOD FOR SOLVING 3SAT USING A QUANTUM COMPUTER

1. A quantum computer system, which includes: a program loaded on said quantum computer system, wherein the program includes:1) a defining function configured for defining decimation gates each including a corresponding decimation angle, a first density matrix and a second density matrix; 2) an altering function configured for altering one or more of the following control parameters: the identities of the decimation gates; the decimation angles corresponding to particular decimation gates; the order of application for the decimation gates; the number of times that particular decimation gates are applied between repetitions; and 3) an algorithm configured for altering the probability distribution for said quantum computer whereby the likelihood of obtaining a valid solution increases exponentially concentrating probability in solution states; said program configured for applying the altered physical operation to the quantum system; said program further defining a quantum computer mapping function mapping a first density matrix to a second density matrix; and said mapping function having no well-defined inverse mapping the final state of the system to the initial state.

US Pat. No. 10,460,252

SYSTEM AND METHOD OF CHAINING ALGORITHMS FOR GLOBAL OBJECT RECOGNITION TO IMPROVE PROBABILITY OF CORRECTNESS AND REDUCE PROCESSING LOAD

Raytheon Company, Waltha...

1. A computer-implemented method for global object recognition comprising:receiving, by the one or more hardware processors, object metadata including a plurality of characteristics that define an object to be detected;
receiving, by one or more hardware processors, search metadata including a plurality of context parameters that define a search for the object;
retrieving, based on the object and search metadata, a plurality of source data of a given data type;
selecting, from a plurality of algorithms, a subset of algorithms to be used in processing the retrieved source data based on a cumulative trained probability of correctness (Pc) that each of the algorithms, which are processed in a chain and conditioned upon the result of the preceding algorithms, produce a correct result;
ordering the algorithms in the subset based on algorithm metadata including a plurality of algorithm characteristics to reduce an expected processing load of the retrieved source data; and
processing the retrieved source data in order according to the chain of the selected subset of algorithms to obtain a plurality of results and to reduce the number of source data that is processed by the next algorithm in the chain, at least one result indicating whether the object was detected in corresponding source data output from the last algorithm in the chain.

US Pat. No. 10,460,251

CROSS-DOMAIN TIME SERIES DATA CONVERSION APPARATUS, METHODS, AND SYSTEMS

PREFERRED NETWORKS INC., ...

1. A method comprising:receiving a first time series of a first type of data;
storing the first time series of the first type of data;
encoding the first time series of the first type of data as a first distributed representation for the first type of data;
converting the first distributed representation to a second distributed representation for a second type of data which is different from the first type of data; and
decoding the second distributed representation for the second type of data as a second time series of the second type of data,
wherein a dimensionality of the first distributed representation is lower than a dimensionality of the first time series of the first type of data, and a dimensionality of the second distributed representation is lower than a dimensionality of the second first times series of the second type of data.

US Pat. No. 10,460,250

SCOPE IN DECISION TREES

Cavium, LLC, Santa Clara...

1. A method comprising:compiling a decision tree data structure including a plurality of nodes using a classifier table having a plurality of rules representing a search space for packet classification, the plurality of rules having at least one field, the plurality of nodes each covering a portion of the search space by representing subsets of the plurality of rules;
for each node of the decision tree data structure, computing a scope factor for the node based on (a) a node scope value computed for the node, the node scope value indicating a node portion of the search space covered by the node, the node scope value computed by determining a minimum number of bits for enumerating all values of the search space covered by the node on a per field basis and setting the node scope value to a sum of the minimum number of bits determined for each at least one field, and (b) a rule scope value computed for each rule intersecting the node, the rule scope value indicating a rule portion of the node portion covered by the node; and
using the scope factor computed for at least one node of the plurality of nodes as an input parameter to a decision for performing a compiler operation at the at least one node.

US Pat. No. 10,460,249

SYSTEM AND METHOD FOR PROJECTING A LIKELY PATH OF THE SUBJECT OF A SEQUENTIAL DECISION PROBLEM

SUPPORTED INTELLIGENCE, L...

1. A computer-aided decision making system, comprising:a user input device;
a user output device; and
a processor programmed to evaluate decision problems available to a user; the programmed processor:
(A) facilitating input of information from the user via the user input device, the information including
(i) a decision problem to be solved, the decision problem to be solved defined by
(ii) an action set, the action set has elements representing actions available to a subject, each element in the action set having a corresponding action cost, the corresponding action costs forming an action cost set,
(iii) at least one state dimension representing conditions relevant to the subject of the decision problem, each state dimension has elements representing values of a condition relevant to the decision problem,
(iv) each state dimension having a corresponding reward vector representing a reward to the subject associated with the elements of the state dimension, before consideration of the action cost set,
(v) each state dimension having a corresponding transition matrix containing, for each element in the state dimension, a probability of moving from each state in the state dimension to each state in the state dimension for each action in the action set,
(vi) a time index and a discount factor, the time index containing decision points available to the user, each decision point representing a point in time when the user selects from the action set, and the discount factor representing a subject's preference for rewards relative to time,
(B) the programmed processor combining the reward vectors with the action cost set to form a reward matrix and the programmed processor combining the transition matrices with the action set to form a total transition matrix;
(C) the programmed processor forming a functional equation from the at least one state dimension, the reward matrix, the total transition matrix, and the time index and the discount factor;
(D) the programmed processor evaluating the functional equation, including error-checking and validating the inputs and performing a convergence check to ensure that the functional equation will be solvable, and the programmed processor solving the functional equation;
(E) the programmed processor generating an optimal policy by using the solved functional equation to find, for every point in the time index, an overall value-maximizing action;
(F) the programmed processor generating at least one projected path beginning at a starting state by
(i) identifying a set of assumed actions by selecting the value-maximizing action for each potential state at an initial point in the time index, based upon the optimal policy
(ii) evaluating, for the assumed action, a transition to occur by comparing the probabilities in the total transition matrix for the combination of state dimensions;
(iii) generating the projected path for each decision point in the time index by selecting the transition from the possible transitions at each decision point based upon the current state, the reward in the current state given the assumed action and the transition at the next decision point in the decision index, where the selection is based on the transition probabilities, the decision advice, and the reward matrix;
(G) the programmed processor outputting the projected path to the user through the user output device.

US Pat. No. 10,460,248

AUTOMATIC ARTIST AND CONTENT BREAKOUT PREDICTION

SPOTIFY AB, Stockholm (S...

1. A computer-implemented method of using a selected cohort of content consumers to rate a media object to predict a breakout media object, the method comprising the steps of:defining, with a computer processing unit, a cohort of content consumers that have played one or more prior breakout media objects during a respective time period for each respective prior breakout media object of the one or more prior breakout media objects;
identifying, with the computer processing unit, a media object;
determining, with the computer processing unit, a first value, wherein the first value is equal to a number of members who belong to the cohort and who have played the media object;
determining, with the computer processing unit, a second value, wherein the second value is equal to a total number of content consumers who played the media object;
computing, with the computer processing unit, a rating using the first value and the second value, wherein the rating is calculated according to:

wherein x is a constant used to weight the rating in favor of popularity among total users and y is a constant used to weight the rating in favor of popularity among the cohort; and
identifying, with the computer processing unit, the media object as a breakout media object using the rating.

US Pat. No. 10,460,247

ATTRIBUTE WEIGHTING FOR MEDIA CONTENT-BASED RECOMMENDATION

ADOBE INC., San Jose, CA...

1. A computer-implemented method for generating content-based recommendations, the method comprising:determining, by a computer processor, a first similarity score based on a statistical measure of similarity between user preferences for each of a first content item and a second content item;
determining, by the computer processor, a second similarity score based on a statistical measure of similarity between a first content attribute and a second content attribute;
training a predictive model by assigning, by the computer processor, a weight to the first content attribute based on the first and second similarity scores, and a weight to the second content attribute based on the first and second similarity scores, wherein the same weight is assigned to a plurality of content items each having the same content attribute; and
generating, by the computer processor and using the predictive model, a content-based recommendation for at least one of the plurality of content items having both the first content attribute and the second content attribute based on the weights.

US Pat. No. 10,460,246

PERSONAL TASTE ASSESSMENT METHOD AND SYSTEM

RingIT, Inc., Syracuse, ...

11. A system for predicting a person's preference for a consumable item, comprising:one or more processors:
a database of trait values for a plurality of candidate consumable items;
a computer-readable memory storing a user profile for a first person; and
a computer-readable memory containing programming instructions that, when executed, cause one or more of the processors to:
receive, from the first person, ratings for each of a plurality of rated consumable items,
access a database to retrieve trait values of sensory traits that are associated with the rated consumable items,
develop a preference model for the first person based on the rating set, wherein the preference model represents associations between the person's ratings of consumable items and a plurality of consumable item traits, and wherein developing the preference model comprises:
identifying at least one association between at least one of the trait values for the rated consumable items and at least one of the received ratings, and
including the at least association in the preference model,
save the preference model in the user profile,
receive, from another person, a recommendation request for the first person, wherein the recommendation request comprises an identification of the person or of a group to which the person belongs,
access the database and the user profile for the first person, to identify a candidate consumable item in the database having trait values whose properties match traits that the preference model indicates are associated with rated consumable items that the person found to be appealing,
process the trait values of the candidate consumable item with the user profile to generate a predicted rating as a prediction of how the person would rate the identified candidate consumable item, and
cause an electronic device to output an identification of the identified candidate consumable item and the predicted rating.

US Pat. No. 10,460,245

FLEXIBLE, PERSONALIZED STUDENT SUCCESS MODELING FOR INSTITUTIONS WITH COMPLEX TERM STRUCTURES AND COMPETENCY-BASED EDUCATION

CIVITAS LEARNING, INC., ...

1. A method for building flexible persistence models for education institutions, the method comprising:translating units of academic progress of a non-traditional learning program of an education institution into states of a Markov model;
instantiating the Markov model to quantify transitions of students between the states as parameters of state transitions;
defining flexible persistence in terms of state-transitional characteristics of the students using the Markov model with the parameters of state transitions, wherein the flexible persistence indicate student enrollment from one collection of academic progress units to another collection of academic progress units;
extracting features from the Markov model with the parameters of state transitions that are related to the non-traditional learning program of the education institution using the defined flexible persistence; and
building at least one flexible persistence model using the extracted features for different segments of the students.

US Pat. No. 10,460,244

AUTOMATIC RESPONSE SYSTEM FOR WEARABLES

Intel Corporation, Santa...

1. An apparatus comprising:a wearable device comprising:
memory circuitry storing electronic data representing a knowledge base that comprises at least one data structure, each data structure comprising a plurality of ranked possible user responses;
user interface circuitry; and
automated response circuitry to:
select one data structure of the at least one data structure in response to one or more first electronic signals representing a communication received via a companion device communicatively coupled to the wearable device, wherein to select the one data structure is based at least in part on one or more of an event type associated with the received communication and a contact identifier associated with the received communication; and
provide, to a user via the user interface circuitry, one or more ranked possible user responses from the selected one data structure.

US Pat. No. 10,460,243

NETWORK DEVICE PREDICTIVE MODELING

Belkin International, Inc...

1. A computer-implemented method, comprising:generating, at a computing device, a prediction including a correlation between an interaction with a network device and a context, wherein the interaction is associated with a function performed by the network device;
determining confidence parameters associated with the prediction;
generating a testing outcome by testing the prediction, wherein testing includes analyzing received interaction data and contextual data, and wherein analyzing includes determining whether the interaction with the network device occurred in the context;
calculating a confidence value based on the testing outcome;
comparing the confidence value to the confidence parameters;
determining that the confidence value does not exceed at least one of the confidence parameters in response to comparing the confidence value to the confidence parameters;
transmitting a message that relates to a modification of the confidence parameters;
receiving, from a user at the computing device, input corresponding to an instruction to modify the confidence parameters;
modifying the confidence parameters based on the input;
comparing the confidence value to the modified confidence parameters;
determining that the confidence value exceeds the modified confidence parameters in response to comparing the confidence value to the modified confidence parameters;
detecting, by the computing device, the context associated with prediction;
transmitting, by the computing device and to the network device, an execution instruction associated with the function of the network device in response to detecting the context associated with the prediction; and
executing, by the network device, the function performed by the network device in response receiving the execution instruction.

US Pat. No. 10,460,242

SYSTEM AND METHOD FOR CLUSTERING INTEREST PATTERNS BASED ON A PLURALITY OF PRIORITY VALUES

Fulcrum Management Soluti...

1. A system for clustering interest for a plurality of participant objects and a plurality of thought objects based on priority values comprising:a network-connected interest clustering computer comprising a processor, a memory, and programming instructions, the programming instructions, when executed by the processor, cause the processor to cluster interest for a plurality of participant objects and thought objects comprising:
a device interface;
a plurality of user devices;
a project controller;
a matrix calculator;
a question object;
a plurality of participant objects;
a plurality of thought objects;
a score calculator;
a pattern analyzer;
wherein the device interface receives a plurality of connections from the plurality of user devices on a network;
wherein the project controller:
associates each user device to a participant object of the plurality of participant objects;
receives a question object comprising, at least, an arrangement of information from a first user device of the plurality of user devices;
sends the question object to at least a portion of the plurality of user devices;
receives the plurality of thought objects from at least a portion of the user devices;
sends the plurality of the thought objects to at least a portion of the user devices;
receives a plurality of priority value responses from a plurality of participant devices, each priority value response associated to a thought object of the plurality of thought objects and to a corresponding participant object of the plurality of participant objects;
wherein the matrix calculator:
computes a ratings matrix, the ratings matrix based on the plurality of priority values, the ratings matrix comprised of at least a portion of the plurality of participant devices and at least a portion of the plurality of thought objects;
permutes the ratings matrix into an interest-based submatrix, the permutation identifying a plurality of cohorts comprising at least a portion of the plurality of participant objects and at least a portion of the plurality of thought objects based on similar patterns of priority value responses;
wherein the participant devices are comprised from at least a portion of the user devices;
wherein each priority value fall within a predefined range;
wherein to compute the submatrix using a strict association level, the matrix calculator is operable to:
remove participant objects of the plurality of participant objects, that have no associated priority values;
remove thought objects of the plurality of thought objects, that have no associated priority values;
convert the plurality of priority values into a range centered around zero value;
filter at least a portion of the plurality of thought objects based on an associated polarization score, the polarization score calculated by summing the absolute values of the plurality of priority values assigned to an associated thought object and subtracting the absolute value of a sum of the plurality of priority values;
filter at least a portion of the plurality of participant objects based on an associated passion score, the passion score calculated by summing the absolute values of the plurality of priority values assigned by an associated participant object;
assign each participant object of the plurality of participant objects to its own cohort of a plurality of cohorts;
wherein the score calculator is operable to:
calculate a polarization score for each thought object of the plurality of thought objects;
calculate a passion score for each participant object of the plurality of participant objects;
wherein the pattern analyzer is operable to compare a plurality of assigned priority value responses associated to a first cohort, to a second plurality of assigned priority value responses associated to a second cohort, to determine an agreement, wherein if there is agreement, merging the first cohort with the second cohort;
wherein the agreement between the first priority value response and the second priority value response is determined by comparing, by the pattern analyzer, the signs associated to the first plurality of assigned priority value responses and the second plurality of assigned priority value responses;
wherein the predefined range is a zero-centered scale;
wherein if two cohorts, the matrix calculator is operable to assign a binarized label to each participant object and to each thought object based on associated priority values;
further wherein if other than two cohorts remain, the score calculator is further operable to calculate a passion score for each remaining cohort;
wherein if the passion score is less than a predefined threshold, matrix calculator is operable to iteratively remove at least a portion of participant objects, the at least portion of participant objects associated to one or more remaining cohorts with the lowest passion score,
wherein if the passion score is greater than the predefined threshold:
the score calculator is further operable to iteratively calculate a polarization score for the at least portion of thought objects;
the matrix calculator is further operable to iteratively remove at least a portion of the plurality of thought objects, the at least portion of the plurality of thought objects associated to one or more thought objects with the lowest polarization score.

US Pat. No. 10,460,241

SERVER AND CLOUD COMPUTING RESOURCE OPTIMIZATION METHOD THEREOF FOR CLOUD BIG DATA COMPUTING ARCHITECTURE

Institute For Information...

1. A server for big data cloud computing architecture, comprising:a transceiver connected to a network; and
a processor electrically connected to the transceiver, being configured to run a dynamic scaling system to execute the following operations:
receiving a task message via the transceiver, the task message recording a user-defined attribute, a program file and a plurality of data files of a to-be-executed task, the program file and the data files being stored in a data storage system which runs in a data storage server assembly in the big data cloud computing architecture;
executing a profiling procedure that comprises the following steps of:
sampling the data files recorded in the task message to choose a plurality of sampled data files and to generate an advance execution message which records the sampled data files and the program file of the to-be-executed task;
transmitting the advance execution message to a big data computing server assembly of the big data cloud computing architecture via the transceiver so that a sampled data computing system running in the big data computing server assembly executes the program file on the sampled data files and generates a profile according to an execution result of the program file; and
receiving the profile from the big data computing server assembly via the transceiver;
executing a classifying procedure that comprises the following step of:
based on a classification model, comparing the profile with the classification model to determine a task classification of the to-be-executed task;
executing a prediction procedure that comprises the following steps of:
based on a computing node type and a system parameter recorded in a prediction sub-model corresponding to the task classification in a prediction model, assigning the computing node type and the system parameter to the to-be-executed task; and
based on the prediction sub-model, generating an execution time prediction curve of the to-be-executed task according to the task classification and the profile to obtain a plurality of predicted execution times of the to-be-executed task corresponding to a plurality of computing node numbers, the computing node numbers corresponding to the predicted execution times in one-to-one correspondence;
executing an optimization procedure that comprises the following steps of:
determining whether there is at least one additional task;
when the at least one additional task exists, determining a practical computing node number of the to-be-executed task according to the user-defined attribute and the predicted execution times of the to-be-executed task, an additional user-defined attribute and a plurality of additional predicted execution times of each of the at least one additional task, and a maximum computing resource of the big data computing server assembly;
generating an optimization output message, which records the program file, the data files, the practical computing node number, the computing node type and the system parameter of the to-be-executed task; and
transmitting the optimization output message to a management server of the big data cloud computing architecture via the transceiver so that a management system run by the management server allocates at least one data computing system running in the big data computing server assembly to execute the program file on the data files of the to-be-executed task according to the optimization output message, wherein the number of the at least one data computing system is equal to the practical computing node number.

US Pat. No. 10,460,240

APPARATUS AND METHOD FOR TAG MAPPING WITH INDUSTRIAL MACHINES

General Electric Company,...

1. A method, comprising:operating one or more industrial devices at an industrial facility, wherein the industrial devices include a plurality of sensors;
receiving a list of equipment tag names and descriptions, each of the equipment tag names being associated with one or more of the plurality of sensors associated with one or more industrial devices;
obtaining a list of analytic tag names and descriptions, each of the analytic tag names being associated with one or more of the plurality of sensors that are associated with an analytic, the analytic being a computer program processing information from the one of the industrial machines;
normalizing the equipment tag descriptions to create normalized equipment tag descriptions and normalizing the analytic tag descriptions to create normalized analytic tag descriptions;
creating a first matrix of vectors that associates dictionary contents with aspects of the normalized equipment tag descriptions;
creating a second matrix of vectors that associates dictionary contents with aspects of the normalized analytic tag descriptions;
wherein the first matrix comprises an m by n matrix, each row of the first matrix being a vector having an normalized equipment tag name, each column of the first matrix being a different term, and each entry in the first matrix represents whether the normalized equipment tag name has the term;
wherein the second matrix comprises an s by t matrix, each row of the second matrix being a vector having a normalized analytic tag name, each column of the second matrix being a different term, and each entry in the second matrix represents whether the analytic tag name has the term;
comparing each vector in the second matrix to each of the vectors in the first matrix to obtain first similarity measures as between each normalized analytic tag name from the second matrix and each normalized equipment tag name from the first matrix;
based upon the comparing, creating an output, the output being a ranked list of normalized equipment tag names ordered according to the first similarity measures;
determining whether to associate a normalized equipment tag name to an input of the analytic having the normalized analytic tag name based upon an analysis of the list;
wherein the output is utilized by an automated learning circuit to improve a mathematical model that is utilized in future mappings between analytic tag names and equipment tag names.

US Pat. No. 10,460,239

GENERATION OF INFERRED QUESTIONS FOR A QUESTION ANSWERING SYSTEM

International Business Ma...

1. A computer implemented method for generating a set of inferred questions for a question answering system, the method comprising:determining, by a user monitoring system and based on context data a user state, wherein determining the user state includes comparing the context data with one or more user state profiles;
identifying, by the user monitoring system, an object satisfying an attention criterion, wherein the attention criterion is defined by an attention threshold value calculated by an attention synthesis algorithm;
extracting, by the user monitoring system using a data extraction algorithm, characterization information for the object satisfying the attention criterion, wherein the characterization information is configured to include sensory data of the object, wherein the characterization information includes data collected to describe or characterize the object;
determining, by the user monitoring system and using the characterization information for the object and a subset of the context data, a relationship between the object and the user state;
generating, by the user monitoring system based on the relationship between the object and the user state, a set of inferred questions for the question answering system; and
generating, using the question answering system, one or more answers for the set of inferred questions; and
using, by the user monitoring system, feedback from the user on the one or more answers generated for the set of inferred questions in one or more subsequent question answering sessions to refine the characterization information and the context data.

US Pat. No. 10,460,238

DATA QUALITY ISSUE DETECTION THROUGH ONTOLOGICAL INFERENCING

LEIDOS INNOVATIONS TECHNO...

1. A method for use in detecting data quality issues in one or more instances of an incoming set of data, the method comprising:determining a scope of an incoming data set to be receivable at a processor, wherein said determining a scope of the incoming data set comprises automatically perusing a plurality of instances of data structures comprising the incoming data set, and wherein each instance includes one or more entries;
obtaining, based on the determined scope, a domain ontology that includes a plurality of TBox statement collections that collectively comprise metadata describing desired or acceptable properties of data corresponding to the determined scope, and wherein the metadata in each TBox statement collection describes a) a plurality of data types, b) at least one format that each data type should have, and c) an indication of whether or not each format is required in order for the data to be considered compliant with the TBox statement collection, wherein at least one of the formats of at least one of the data types is indicated as being required in order for the data to be considered compliant with the TBox statement collection;
mapping, using the processor, the incoming data set to the domain ontology, wherein said mapping comprises linking specific data structures in the incoming data set to particular TBox statement collections of the obtained domain ontology; and
for each instance of the incoming data set:
identifying an anticipated TBox statement collection of the plurality of TBox statement collections of the domain ontology;
ascertaining, using the processor, whether the instance can be inferenced into the anticipated TBox statement collection of the domain ontology, wherein the instance can be inferenced into the anticipated TBox statement collection when the instance comprises an ABox statement that is compliant with the anticipated TBox statement collection, wherein the instance comprises an ABox statement that is compliant with the anticipated TBox statement collection when at least one data structure in the instance is the at least one of the data types having the at least one of the required formats;
determining, by the processor, that the instance is free of at least one data quality issue responsive to the instance being inferenced into the anticipated TBox statement collection; and
determining, by the processor, that the instance has at least one data quality issue responsive to the instance not being inferenced into the anticipated TBox statement collection, wherein when the processor determines that the instance has at least one data quality issue, the method further includes ascertaining whether the instance can be inferenced into any other TBox statement collections of the domain ontology, and wherein the processor:
determines that the at least one data quality issue comprises a structural and/or formatting issue associated with the instance when it is ascertained that the instance cannot be inferenced into any other TBox statement collections of the domain ontology; and
determines that the at least one data quality issue comprises a labeling issue associated with the instance when it is ascertained that the instance can be inferenced into another TBox statement collection of the domain ontology.

US Pat. No. 10,460,237

NEURON-CENTRIC LOCAL LEARNING RATE FOR ARTIFICIAL NEURAL NETWORKS TO INCREASE PERFORMANCE, LEARNING RATE MARGIN, AND REDUCE POWER CONSUMPTION

International Business Ma...

1. An artificial neural network (ANN) comprising:a plurality of neurons arranged in layers with the outputs of one layer connected to the inputs of each neuron of the subsequent layer, where neurons are connected to each other via a synapse, each synapse having a synaptic weight encoding a connection strength between two connected neurons, the synaptic weight implemented using a non-volatile memory (NVM), where a plurality of training examples are serially input to the matrix while observing its output, where a backpropagation algorithm updates the synaptic weight in response to a difference between the output from a given layer and a desired output from said given layer,
a storage having computer readable program code embodied therein which implements a neuron-centric method to mitigate network freeze out, the computer readable program code:
(a) storing a local learning rate value in each neuron, where an effective learning rate applied to each synapse is determined jointly by local learning rates of two connected neurons;
(b) identifying two connected neurons whose synaptic weight dithers during the network freeze out;
(c) suppressing activity of the two connected neurons of (b) whose synaptic weight dithers, by decreasing the effective learning rate of it; and
(d) increasing local learning rates of at least one other connected neurons;
wherein the suppressing step (c) and the increasing step (d) stabilize network performance and mitigate the network freeze out.

US Pat. No. 10,460,236

NEURAL NETWORK LEARNING DEVICE

TOYOTA JIDOSHA KABUSHIKI ...

1. A neural network learning device that learns a hierarchical neural network having an input initial structure or a predetermined initial structure, comprising:a learning unit configured to perform a learning process that learns the neural network using a plurality of learning data sets,
wherein the learning process includes:
a data reading process that reads the learning data from a database;
a synaptic weight correction process that calculates a loss function of the neural network using the learning data and corrects a synaptic weight of the neural network according to the loss function, when the learning data is read by the data reading process;
a neuron generation process that newly generates a neuron in an intermediate layer of the neural network when the loss function is greater than a predetermined first threshold value after the synaptic weight correction process is performed; and
a neuron removal process that removes some of the neurons in the intermediate layer when the sum of the synaptic weights of a plurality of neurons in the intermediate layer of the neural network is less than a predetermined reference sum after the synaptic weight correction process is performed,
when the neuron is newly generated by the neuron generation process or when some of the neurons are removed by the neuron removal process, the synaptic weight correction process calculates the loss function again, using the learning data, and corrects the synaptic weight again according to the loss function,
the neural network learning device further includes an intermediate layer generation unit configured to perform an intermediate layer generation process that newly generates an additional intermediate layer including at least one neuron as the intermediate layer of the neural network when the loss function is greater than a predetermined second threshold value after the learning process is performed, and
when the additional intermediate layer is newly generated by the intermediate layer generation process, the learning unit performs the learning process again, using the neural network in which the additional intermediate layer has been generated.

US Pat. No. 10,460,235

DATA MODEL GENERATION USING GENERATIVE ADVERSARIAL NETWORKS

Capital One Services, LLC...

1. A method for generating data models, comprising:receiving, by a model optimizer from an interface, a data model generation request;
provisioning, by the model optimizer, computing resources with a data model;
generating, by a dataset generator, a synthetic dataset for training the data model using a generative network of a generative adversarial network, the generative network trained to generate output data differing at least a predetermined amount from a reference dataset according to a similarity metric;
generating, by the model optimizer, at least one of a statistical correlation score between the synthetic dataset and the reference dataset, a data similarity score between the synthetic dataset and the reference dataset, and a data quality score for the synthetic dataset;
training, by the computing resources, the data model using the synthetic dataset, wherein training the data model using the synthetic dataset comprises determining that the synthetic dataset satisfies a criterion concerning the at least one of the statistical correlation score between the synthetic dataset and the reference dataset, the data similarity score between the synthetic dataset and the reference dataset, and the data quality score for the synthetic dataset;
evaluating, by the model optimizer, performance criteria of the data model;
storing, by the model optimizer in a model storage, the data model and metadata of the data model based on the evaluation of the performance criteria of the data model; and
processing production data using the data model.

US Pat. No. 10,460,234

PRIVATE DEEP NEURAL NETWORK TRAINING

Microsoft Technology Lice...

1. A method comprising:storing first private values at a first machine and second private values at a second machine;
providing, to a third machine, a first share of the first private values and a first share of the second private values;
providing, to a fourth machine, a second share of the first private values and a second share of the second private values;
computing, at the third machine, a third machine value based on the first share of the first private values and the first share of the second private values;
computing, at the fourth machine, a fourth machine value based on the second share of the first private values and the second share of the second private values;
providing, to the first machine and the second machine, the third machine value and the fourth machine value;
computing, at the first machine, a mathematical function of the first private values and the second private values, the mathematical function being computed based on the first private values stored at the first machine, the third machine value, and the fourth machine value; and
providing an output of the computed mathematical function.

US Pat. No. 10,460,233

SELF-ADAPTIVE NEURAL NETWORKS

FUJITSU LIMITED, Kawasak...

1. A method of updating a neural network, comprising:computing gradients for an operating matrix of a current layer of the neural network based on data of at least one of:
the current layer; and
at least one other layer of the neural network;
updating the operating matrix of the current layer based on the computed gradients and the operating matrix of the current layer; and
updating an indexing matrix of the current layer based on matching the updated operating matrix of the current layer and a matching dictionary of the current layer.

US Pat. No. 10,460,232

METHOD AND APPARATUS FOR CLASSIFYING DATA, AND METHOD AND APPARATUS FOR SEGMENTING REGION OF INTEREST (ROI)

Samsung Electronics Co., ...

1. A processor-implemented method of classifying data, comprising:selecting a hypothesis class among entire classes;
generating output data with regard to the entire classes by applying a classification algorithm to input data;
modifying the input data to increase a value of the hypothesis class among the output data and setting the modified input data to be new input data in response to a determination that the re-classification condition is met; and
outputting the input data and the output data in response to a determination that the re-classification condition is not met.

US Pat. No. 10,460,231

METHOD AND APPARATUS OF NEURAL NETWORK BASED IMAGE SIGNAL PROCESSOR

SAMSUNG ELECTRONICS CO., ...

1. An image signal processing (ISP) system, comprising:a neural network that receives an input image and outputs a processed image, the input image including input image data, the neural network comprising a convolutional neural network having multiple parallel paths in which each path scales the input image data to separate the input image data into separate frequency bands of spatial resolution, a first path comprising a first convolutional layer having an output at a first frequency band of spatial resolution, the output of the first convolutional layer being pooled at a second frequency band of spatial resolution that is less than the first frequency band of spatial resolution, a second path being coupled to the pooled output of the first convolutional layer and comprising a second convolutional layer having an output at the second frequency band of spatial resolution, the output of the second convolutional layer being pooled at a third frequency band of spatial resolution that is less than the second frequency band of spatial resolution, a third path being coupled to the pooled output of the second convolutional layer and comprising a third convolutional layer having an output at the third frequency band of spatial resolution, an output of the third convolutional layer being upsampled to the second frequency band of spatial resolution and concatenated with the output of the second convolutional layer to form a first intermediate output, the first intermediate output being upsampled to the first frequency band of spatial resolution and concatenated with the output of the first convolutional layer to form a second intermediate output, the second intermediate output being input to a fourth convolutional layer to output the processed image, and the neural network adjusting the input image data for at least one image-quality attribute to generate the processed image; and
an image-processing chain that receives the processed image output from the neural network, the image-processing chain providing at least one of color correction, gamma correction, edge enhancement and contrast enhancement of the processed image to output a final image,
wherein the at least one adjusted image-quality attribute comprises an image size, an aspect ratio, a brightness, an intensity, a bit depth, a white value, a dynamic range, a gray level, a contouring, a smoothing, a speckle, a color space values, an interleaving, a gamma correction, a contrast enhancement, a sharpness and a demosaicing.

US Pat. No. 10,460,230

REDUCING COMPUTATIONS IN A NEURAL NETWORK

SAMSUNG ELECTRONICS CO., ...

1. A method, comprising:determining, using a processor, a group comprising a plurality of convolution kernels of a convolution stage of a neural network in which the convolution kernels of the group are similar to one another, the determining of the group by:
determining a similarity metric between a first convolution kernel and a second convolution kernel of the plurality of convolution kernels by calculating an element-wise ratio of the first convolution kernel to the second convolution kernel and calculating a standard deviation for the element-wise ratio of the first convolution kernel and the second convolution kernel; and
including the first convolution kernel and the second convolution kernel in the group responsive to determining that the similarity metric meets a similarity criterion;
determining a base convolution kernel for the group;
determining scaling factors based on the base convolution kernel for the group for a plurality of input feature maps processed by the group, each input feature map corresponding to a scaling factor and a convolution kernel; and
modifying the convolution stage of the neural network so that, when the neural network is executed, the convolution stage of the neural network performs:
scaling each of a plurality of input feature maps using the scaling factors,
generating a composite input feature map as a sum of the scaled input feature maps,
applying the base convolution kernel to the composite input feature map, and
summing the composite input feature map with any of a second plurality of input feature maps which are processed by a convolution kernel other than the base convolution kernel.

US Pat. No. 10,460,229

DETERMINING WORD SENSES USING NEURAL NETWORKS

Google LLC, Mountain Vie...

1. A method performed by one or more computers, the method comprising:generating a respective word sense numeric representation of each of a plurality of word senses of a particular word, the generating comprising, for each of the plurality of word senses:
obtaining a plurality of training text sequences for the word sense that each include the particular word and one or more respective training context words, wherein the particular word has been classified as having the particular word sense in each of the training text sequences,
determining a respective training text sequence numeric representation for each of the training text sequences for the word sense by processing each of the training context words in order using a recurrent neural network; and
determining the word sense numeric representation for the word sense from the respective training text sequence numeric representations for the training text sequences for the word sense;
receiving a request to determine the word sense of the particular word when included in a particular text sequence, the particular text sequence comprising one or more context words and the particular word;
determining a context numeric representation of the context words in the particular text sequence by processing each of the context words in the training text sequence in order using the recurrent neural network; and
selecting a word sense of the plurality of word senses having a word sense numeric representation that is closest to the context numeric representation as the word sense of the particular word when included in the particular text sequence.

US Pat. No. 10,460,228

SYNAPTIC, DENDRITIC, SOMATIC, AND AXONAL PLASTICITY IN A NETWORK OF NEURAL CORES USING A PLASTIC MULTI-STAGE CROSSBAR SWITCHING

International Business Ma...

1. A method comprising:interconnecting multiple board structures in a scalable neural network circuit via an event routing system comprising at least one inter-chip router, wherein each board structure comprises multiple functional neuronal core circuits, and each functional neural core circuit comprises a first neural core module and a second neural core module logically overlaid on one another such that electronic neurons and electronic axons of the first neural core module are paired together with electronic axons and electronic neurons of the second neural core module, respectively; and
routing one or more neuronal firing events via the event routing system.

US Pat. No. 10,460,227

VIRTUAL ASSISTANT IN A COMMUNICATION SESSION

Apple Inc., Cupertino, C...

1. A method comprising:receiving, by a first client device, as part of a communication session that takes place within a text-messaging communication application between a first user operating the first client device and at least a second user, a first message prepared by the first user;
determining, by a virtual assistant of the first client device based on a semantic analysis of the first message, whether the first message is directed to the virtual assistant or to the set of participant users;
determining, by the virtual assistant of the first client device, based on the semantic analysis of the first message, that the first message is directed to the virtual assistant and that the first message identifies a first task with which the virtual assistant can assist the first user; and
in response to determining that the first message is directed to the virtual assistant, assisting, by the first client device, the first user with the first task, wherein the first message is displayed within the text-messaging communication application of the first client device and the first message is not transmitted to at least the second user.

US Pat. No. 10,460,226

TIRE HAVING RADIO FREQUENCY IDENTIFICATION DEVICE FOR MONITORING STRUCTURAL HEALTH

Bridgestone Americas Tire...

1. A tire structural health monitoring assembly comprising:a tire having a plurality of components including:
a pair of annular beads,
a body ply extending between the annular beads,
a circumferential belt disposed above the body ply and extending axially across a portion of the body ply,
a circumferential tread disposed above the circumferential belt,
a pair of shoulders extending from opposite sides of the circumferential tread, and
a pair of sidewalls, each sidewall extending between one of the annular beads and one of the shoulders;
at least one radio frequency identification (RFID) tag disposed between two components of the tire, wherein the RFID tag is in contact with each of the two components; and
an RFID reader configured to receive a response signal from the RFID tag,
wherein, when no air is present in a region surrounding the RFID tag, the RFID reader receives a response signal at a first frequency and a first power level, and
wherein, when air is present in the region surrounding the RFID tag, the RFID reader receives a response signal at the first frequency and a second power level different from the first power level; and
a processor configured to identify the power level of a response signal received by the RFID reader at the first frequency, and further configured to transmit a notification when the power level of the response signal is outside a pre-determined range.

US Pat. No. 10,460,225

MARKING DEVICE AND MARKING METHOD

SATO HOLDINGS KABUSHIKI K...

1. A marking device to use with a sheet, comprising:a cut and raising part configured to make a cut to form a cut and raised section on the sheet having been found to have a defect and to press the cut and raised section in a bending direction as the sheet is conveyed to make the cut and raised section stand.

US Pat. No. 10,460,224

SYSTEMS AND METHODS FOR ENABLING RFID SESSIONS BASED ON IMAGER BASED OBJECT DETECTION

Zebra Technologies Corpor...

1. A scanning device for enabling radio frequency identification (RFID) sessions based on imager based object detection, the scanning device comprising:an optical imaging assembly having an optical field of view (FOV) and an effective reading range, the optical imaging assembly operable to capture one or more images corresponding to one or more product codes positioned within the effective reading range;
an RFID reader having an RFID antenna, the RFID reader configured to emit, via the RFID antenna, a radiation pattern, the radiation pattern configured to extend over at least the optical FOV and the effective reading range of the optical image assembly, the RFID reader operable to read one or more RFID tags; and
a processor communicatively coupled to the optical image assembly and the RFID reader, the processor configured to:
detect a product entering the effective reading range and within the optical FOV based on any of: image feature object detection, infrared (IR) proximity detection, or image scene detection, and
responsive to detecting the product:
switch the optical imaging assembly from a presentation mode to an active mode,
activate the RFID reader, and
terminate the scanning session upon the occurrence of at least one of: (1) the optical imaging assembly scanning a product code associated with the product, or (2) the RFID reader reading an RFID tag associated with the product.

US Pat. No. 10,460,223

ENCODED CELLS AND CELL ARRAYS

Gelliner Limited, Dougla...

1. A method comprising:receiving, by a computing device, a binary identifier comprising a plurality of bits;
determining, by the computing device, one or more encoded cells that encode the binary identifier in accordance with an encoding scheme, wherein each encoded cell indicates two or more bits of the binary identifier in a predetermined sequence, wherein each encoded cell includes a perimeter, an alignment mark within the perimeter, and a line pattern within the perimeter, and wherein the line pattern within the perimeter for each of at least one encoded cell includes a line positioned radially with respect to the alignment mark of the at least one encoded cell to represent at least two bits in the predetermined sequence of the at least one encoded cell;
generating, by the computing device, a cell array that includes the one or more encoded cells; and
outputting, by the computing device, data for producing a graphical representation of the cell array.

US Pat. No. 10,460,221

DISPLAYING A SEEDED, CONTINUOUSLY UPDATING IDENTIFIER IN A QR CODE

Ryan C. Tucker, Shorelin...

1. A non-transitory computer readable medium storing a program which, when executed by a micro-controller, displays a seeded, continuously updating identifier displayed in a QR code, said program comprising sets of instructions for:initializing QR code generation software on the micro-controller by a self-contained QR code display and replay attack prevention device in the absence of any external computing device;
initializing identifier generation software on the micro-controller by the self-contained QR code display and replay attack prevention device in the absence of any external computing device;
initializing an identifier seed on the micro-controller by the self-contained QR code display and replay attack prevention device in the absence of any external computing device;
generating a first identifier from the identifier seed by the micro-controller and turning the first identifier into a first QR code that refers to a particular information resource, said first QR code for display on a physical display medium by the self-contained QR code display and replay attack prevention device in the absence of any external computing device;
visually outputting the first identifier as the first QR code, by the micro-controller, for display on the physical display medium by the self-contained QR code display and replay attack prevention device in the absence of any external computing device;
generating a second identifier from the identifier seed by the micro-controller and turning the second identifier into a second QR code that refers to the particular information resource, said second QR code for display on the physical display medium by the self-contained QR code display and replay attack prevention device in the absence of any external computing device; and
visually outputting the second identifier as the second QR code, by the micro-controller, for display on the physical display medium by the self-contained QR code display and replay attack prevention device in the absence of any external computing device.

US Pat. No. 10,460,220

METHODS OF STORING INFORMATION USING NUCLEIC ACIDS

President and Fellows of ...

1. A method of making a medium for information storage using nucleotides comprisingconverting a format of information into a plurality of bit sequences of a bit stream,
converting the plurality of bit sequences to a plurality of corresponding oligonucleotide sequences using one bit per base encoding, and
synthesizing the plurality of corresponding oligonucleotide sequences.

US Pat. No. 10,460,219

GENERATING AN OBJECT MAP FROM A PLURALITY OF BINARY IMAGES

Hewlett-Packard Developme...

1. A method, comprising:dividing, by a processor element, an input image into a plurality of strips, where each strip of the plurality of strips is smaller than a whole of the input image;
generating, by the processor element, a plurality of binary images, where each binary image of the plurality of binary images corresponds to a strip of the plurality of strips, wherein the plurality of binary images comprises at least three binary images corresponding to each strip of the plurality of strips and wherein the at least three binary images each comprise a respective binary image in which edge magnitudes for all white pixels in the respective binary image are at least equal to at least one of: a strong edge threshold and a weak edge threshold;
executing, by the processor element, for a first binary image of the plurality of binary images,
a first pass in which foreground pixels of the first binary image are assigned labels that identify connected components in the first binary image; and
a second pass, subsequent to the first pass, in which:
any of the labels that correspond to connected components that exist entirely in the first binary image are freed in memory; and
any of the labels that correspond to connected components that are merged with other connected components are re-labeled to reduce a number of labels stored in a memory data structure; and
generating, by the processor element, an object map for the input image based on results of the connected component labeling for the plurality of binary images.

US Pat. No. 10,460,218

BITMAP PROCESSING OF DIGITAL DOCUMENTS

Broadridge Output Solutio...

1. A bitmap processing system for creating digital documents, comprising:a) a fulfiller operated raster image processor that:
i) receives customer application Page Description Language (PDL) job files containing information for creating the digital documents and ii)
generates bitmaps in accordance with said files;
b) a fulfiller operated editor that modifies said bitmaps so that the resulting documents process more efficiently in production steps downstream of a printing process, wherein said more efficient processing includes finishing and mailing; and
c) a PDL editor, upstream of said fulfiller operated raster image processor and said editor, that, using metadata extracted from said bitmaps, modifies an original customer application PDL for more efficient control of downstream processes.

US Pat. No. 10,460,217

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER-READABLE RECORDING MEDIUM

Ricoh Company, Ltd., Tok...

1. An information processing device configured to control an image forming part that forms a laminated image of a special color image using a special color material and a colored image using a colored color material through 2-path printing in which one of the special color image and the colored image is formed on a medium to be immobilized and the other one is laminated thereon, or 1-path printing in which one of the special color image and the colored image is formed on a medium and the other one is laminated thereon without performing immobilization, the information processing device comprising:a specification part configured to specify, by using image data for a correction chart defining a plurality of patch regions having different color values, a target characteristic indicating a relation between the color value and a first colorimetric value of a first patch image as the laminated image corresponding to each of the patch regions formed by the image forming part through the 2-path printing; and
a generation part configured to generate a correction table for correcting the color value so that a measured characteristic comes close to the target characteristic, the measured characteristic indicating a relation between the color value and a second colorimetric value of a second patch image as the laminated image corresponding to each of the patch regions formed by the image forming part through the 1-path printing using the image data for a correction chart.

US Pat. No. 10,460,216

COLLATION/RETRIEVAL SYSTEM, COLLATION/RETRIEVAL SERVER, IMAGE FEATURE EXTRACTION APPARATUS, COLLATION/RETRIEVAL METHOD, AND PROGRAM

NEC Corporation, Tokyo (...

1. A collation apparatus comprising:a storage device configured to store a plurality of image features of collation areas extracted from a plurality of objects and management information corresponding to the plurality of objects in a mutually associated manner;
a memory configured to store instructions; and
a processor coupled to the memory and configured to execute the instructions to:
obtain an image including a reference section and a collation area of an object to be collated;
retrieve, from the stored plurality of image features, an image feature having the highest similarity to an image feature of collation area of the object to be collated; and
output management information about an object stored in the storage device corresponding to the image feature having the highest similarity, wherein
the management information about the object is not used for collation of the object and includes at least one of a production site, a producer name, a lot number, a production date, a quality information, a shipping point, and a ship date of the object.

US Pat. No. 10,460,215

NATURAL LANGUAGE INTERACTION FOR SMART ASSISTANT

MICROSOFT TECHNOLOGY LICE...

1. A method for natural language interaction, comprising:recording speech provided by a human user;
translating the recorded speech into a machine-readable natural language input relating to an interaction topic;
maintaining an interaction timer tracking a length of time since a last machine-readable natural language input relating to the interaction topic;
based on a current value of the interaction timer being greater than an interaction engagement threshold, delivering a message relating to the interaction topic with a first natural language phrasing that includes an interaction topic reminder; or
based on the current value of the interaction timer being less than the interaction engagement threshold, delivering the message relating to the interaction topic with a second natural language phrasing that lacks the interaction topic reminder.

US Pat. No. 10,460,214

DEEP SALIENT CONTENT NEURAL NETWORKS FOR EFFICIENT DIGITAL OBJECT SEGMENTATION

Adobe Inc., San Jose, CA...

1. A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, cause a computer system to:receive, by a mobile device, a digital image portraying one or more salient objects;
select, by the mobile device, a neural network from a set of neural networks comprising a static salient content neural network and a real-time salient content neural network based on whether the digital image is static or is part of a real-time digital visual media feed;
identify, by the mobile device, the one or more salient objects portrayed in the digital image by applying the selected neural network to the digital image; and
generate a modified digital image based on the identified one or more salient objects portrayed in the digital image.

US Pat. No. 10,460,213

METHOD, APPARATUS AND COMPUTER PROGRAM STORED IN COMPUTER READABLE MEDIUM FOR STATE DECISION OF IMAGE DATA

SuaLab Co., Ltd., Seoul ...

1. A method for state decision of image data, processed by at least one computer processor, using a network function learned with respect to at least one pattern, the method comprising:acquiring first output data by the network function based on the image data;
acquiring second output data based on the image data by an algorithm that loses or modifies at least some of the image data and has a different effect from the network function; and
deciding state information of the image data based on the similarity of the first output data and the second output data.

US Pat. No. 10,460,212

BINNING DIGITAL IMAGES BY SOURCE CAMERA

U.S. Government as repres...

1. A computer-implemented method of using digital camera fingerprints to create, in a set of digital images generated by a plurality of digital cameras, bins of digital images, wherein each digital image in a particular bin was generated by the same digital camera as every other digital image in the same bin, the method comprising:determining, for each digital image in the set of digital images, a digital fingerprint;
sorting each digital image into one of a high-quality subset and a low-quality subset by evaluating each image according to an extreme pixel factor, wherein the extreme pixel factor is determined based on at least one of a) a number of pixels in the image having a pixel intensity greater than a brightness threshold, and b) a number of pixels in the image having a pixel intensity less than a darkness threshold;
sorting each digital image in the high-quality subset into one of a plurality of bins, wherein in each bin the images were determined, based on the digital fingerprints of the images in the bin, to have been generated by a single digital camera associated with the bin; and
sorting each digital image in the low-quality subset into one of the plurality of bins, the sorting being performed based on the digital fingerprint of the digital image.

US Pat. No. 10,460,211

IMAGE CLASSIFICATION NEURAL NETWORKS

Google LLC, Mountain Vie...

1. A neural network system implemented by one or more computers, wherein the neural network system is configured to receive an image and to generate a classification output for the input image, and wherein the neural network system comprises:a plurality of subnetworks arranged in a stack on top of each other, wherein each subnetwork is configured to process a subnetwork input to generate a subnetwork output and to provide the subnetwork output as input to another subnetwork above the subnetwork in the stack, and wherein the plurality of subnetworks includes:
a first subnetwork comprising a plurality of first modules, each first module comprising:
a first pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a first pass-through output;
a first average pooling stack of neural network layers, wherein the layers in the first average pooling stack are configured to collectively process the subnetwork input for the first subnetwork to generate a first average pooling output;
a first stack of convolutional neural network layers, wherein the layers in the first stack are configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output;
a second stack of convolutional neural network layers, wherein the second stack comprises a 1×1 convolutional layer immediately followed by a 3×3 convolutional layer immediately followed by a 3×3 convolutional layer, and wherein the layers in the second stack are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and
a first concatenation layer configured to concatenate the first pass-through output, the first average pooling output, the first stack output, and the second stack output to generate a first module output for the first module; and
a second subnetwork comprising second modules, each second module comprising:
a second pass-through convolutional layer configured to process the subnetwork input for the second subnetwork to generate a second pass-through output;
a second average pooling stack of neural network layers, wherein the layers in the second average pooling stack are configured to collectively process the subnetwork input for the second subnetwork to generate a second average pooling output;
a third stack of convolutional neural network layers, wherein the third stack includes a 1×1 convolutional layer followed by a 1×7 convolutional layer followed by a 1×7 convolutional layer, and wherein the layers in the third stack are configured to collectively process the subnetwork input for the second subnetwork to generate a third stack output;
a fourth stack of convolutional neural network layers, wherein the layers in the fourth stack are configured to collectively process the subnetwork input for the second subnetwork to generate a fourth stack output; and
a second concatenation layer configured to concatenate the second pass-through output, the second average pooling output, the third stack output, and the fourth stack output to generate a second module output for the second module.

US Pat. No. 10,460,210

METHOD AND DEVICE OF NEURAL NETWORK OPERATIONS USING A GRID GENERATOR FOR CONVERTING MODES ACCORDING TO CLASSES OF AREAS TO SATISFY LEVEL 4 OF AUTONOMOUS VEHICLES

STRADVISION, INC., Pohan...

1. A method for neural network operations by using a grid generator, comprising steps of:(a) a computing device, if a test image is acquired, instructing a non-object detector to acquire non-object location information for testing, including information on where non objects for testing are located on the test image, and class information of the non-objects for testing, including information on classes of the non-objects for testing, by detecting the non-objects for testing on the test image;
(b) the computing device instructing the grid generator to generate section information, which includes information on a plurality of subsections in the test image, by referring to the non-object location information for testing;
(c) the computing device instructing a neural network to determine parameters for testing, to be used for applying the neural network operations to either (i) at least part of the subsections including each of the objects for testing and each of non-objects for testing corresponding to said each of the objects for testing, or (ii) each of sub-regions, in each of said at least part of the subsections, where said each of the non-objects for testing is located, by referring to parameters for training which have been learned by using information on non-objects for training whose corresponding class information is same as or similar to that of the non-objects for testing; and
(d) the computing device instructing the neural network to apply the neural network operations to the test image by using each of the parameters for testing, corresponding to each of said at least part of the subsections, to thereby generate one or more neural network outputs.

US Pat. No. 10,460,209

METHOD AND SYSTEM FOR VEHICLE RECOGNITION

1. A method of recognizing a vehicle from an image, comprising:receiving, by a computing device, an image;
recognizing, by a computing device, features of vehicle brand from vehicle brand recognition region extracted from the image with a trained vehicle brand deep learning model;
recognizing, by a computing device, features of vehicle color from the image;
recognizing, by a computing device, the features of vehicle color from color recognition region extracted from the image with a trained color deep learning model;
identifying the vehicle based on a combination of the features of the vehicle brand and the features of vehicle color, wherein the identifying further comprises integrating, by the computing device, the features of the vehicle brand with the features of the vehicle color, and ranking color-vehicle brands; and
wherein the integrating is based on an integrated model:
Pt=?bPb?+Pc?c;
wherein Pf is the score after integrating vehicle color and vehicle brand,
Pb is the score of the vehicle brand in the features of vehicle brand;
Pc is the score of the vehicle color in the features of vehicle color; and
?b and ?c are defined by the formula below:
?*=arg max ?N(?bPb?+Pc?c);
wherein arg refers to taking parameters; max refers to maximum value, ?N refers to comparison correct rate of top N, ?* represents ?b and ?c, ? is a penalty factor.

US Pat. No. 10,460,208

SYSTEM AND METHOD FOR GENERATING LARGE SIMULATION DATA SETS FOR TESTING AN AUTONOMOUS DRIVER

Cognata Ltd., Rehovot (I...

1. A system for creating synthetic data for testing an autonomous system, comprising:at least one hardware processor adapted to execute a code for:
producing a plurality of synthetic training signals, each simulating one of a plurality of signals simultaneously captured from a common training scene by a plurality of sensors, and a plurality of training depth maps each qualifying one of the plurality of synthetic training signals according to the common training scene;
training a machine learning model based on the plurality of synthetic training signals and the plurality of training depth maps;
using the machine learning model to compute a plurality of computed depth maps based on a plurality of real signals, the plurality of real signals are captured simultaneously from a common physical scene, each of the plurality of real signals are captured by one of the plurality of sensors, each of the plurality of computed depth maps qualifies one of the plurality of real signals;
applying a point of view transformation to the plurality of real signals and the plurality of computed depth maps, to produce synthetic data simulating a possible signal captured from the common physical scene by a target sensor in an identified position relative to the plurality of sensors; and
providing the synthetic data to at least one testing engine to test an autonomous system comprising the target sensor.

US Pat. No. 10,460,207

IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND COMPUTER-READABLE NON-TRANSITORY MEDIUM

FUJITSU LIMITED, Kawasak...

1. An image processing device comprising:a memory; and
a processor coupled to the memory and the processor configured to execute a process, the process comprising:
acquiring a plurality of biometric images of a same biological body part of a same user from a biometric sensor;
generating, when a feature point appears at a corresponding position of the same biological body part in one or more of the plurality of biometric images and the feature point does not appear at the corresponding position in another of the plurality of biometric images, a pseudo feature point at the corresponding position of the another of the plurality of biometric images; and
storing information of the feature point of the plurality of biometric images and the pseudo feature point of the another of the plurality of biometric images as a biometric feature.

US Pat. No. 10,460,206

DIFFERENTIATING PHYSICAL AND NON-PHYSICAL EVENTS

Facebook, Inc., Menlo Pa...

1. A method comprising:receiving a set of starting content frames, each depicting a state of a plurality of objects at a starting time point;
applying a first model to generate a set of plausible ending content frames for each starting content frame, the first model trained to generate a subsequent content frame based on a starting content frame, each of the set of plausible ending content frames representing a plausible behavior of the plurality of objects based on physical phenomena;
applying a second model to generate a set of implausible ending content frames for each starting content frame, the second model trained to generate a subsequent content frame without using a starting content frame, each of the set of implausible ending content frames representing an implausible behavior of the plurality of objects based on physical phenomena; and
training a discriminator model using the set of starting content frames, the set of plausible ending content frames, and the set of implausible ending content, to predict a preferred ending frame conforming to plausible physical events from a first and second ending frame given a starting content frame, wherein the set of plausible ending content frames are a positive training set for plausible ending frames and the set of implausible ending frames are a negative training set for the set of plausible ending content frames.

US Pat. No. 10,460,205

CLUSTERING IMAGES BASED ON CAMERA FINGERPRINTS

Functional Technologies L...

1. A method of analysing a set of digital images each having been captured with a digital camera, the method comprising, using at least one processor:a) extracting a camera fingerprint from each image so as to form a set of camera fingerprints, each camera fingerprint being representative of the camera used to capture the image, and being of a first dimension;
b) forming a set of dimensionally reduced camera fingerprints from each camera fingerprint, the dimensionally reduced camera fingerprint being of a second dimension smaller than the first dimension;
c) forming a first subset of dimensionally reduced camera fingerprints and a second subset of dimensionally reduced camera fingerprints;
d) determining a level of similarity between every pairing of the dimensionally reduced camera fingerprints of the first subset;
e) determining a level of similarity between every pairing of the dimensionally reduced camera fingerprints of the second subset;
f) determining a level of similarity between every pairing of, on the one hand, the dimensionally reduced fingerprints of the first set and, on the other hand, the dimensionally reduced fingerprints of the second subset;
g) recording those pairings which indicate a comparatively higher level of similarity;
h) substituting for the contents of the first subset those dimensionally reduced camera fingerprints of the first and second subsets which have been recorded as part of a pairing showing a comparatively higher level of similarity;
i) substituting for the contents of the second subset a different subset of the set of the dimensionally reduced camera fingerprints;
j) repeating steps (e) to (i), typically until all of the dimensionally reduced camera fingerprints have been processed;
k) performing a clustering algorithm on all dimensionally reduced camera fingerprints based on the pairings having a comparatively higher level of similarity to produce a plurality of first clusters each comprising a set of dimensionally reduced camera fingerprints;
l) for each of the first clusters, determining a level of similarity between each of the camera fingerprints corresponding to the dimensionally reduced camera fingerprints of that cluster; and
m) splitting and merging the coarse clusters dependent upon the similarities between the camera fingerprints to form a plurality of second clusters.

US Pat. No. 10,460,204

METHOD AND SYSTEM FOR IMPROVED HEMODYNAMIC COMPUTATION IN CORONARY ARTERIES

Siemens Healthcare GmbH, ...

1. A method for non-invasive assessment of an arterial stenosis, comprising:segmenting a plurality of mesh candidates for an anatomical model of an artery including a stenosis region of a patient from medical imaging data, the plurality of mesh candidates representing different anatomical models of the artery resulting from variations in segmenting techniques, wherein segmenting the plurality of mesh candidates comprises:
determining one or more candidate locations for each vertex of the anatomical model,
assigning a confidence score to each of the plurality of mesh candidates by averaging a probability associated with each vertex in a respective mesh candidate, and
applying cluster analysis to reduce a number of the plurality of mesh candidates based on the confidence score;
computing a hemodynamic index for the stenosis region in each of the plurality of mesh candidates; and
determining whether a clinical decision for treatment of the stenosis region of the patient is ambiguous by determining whether a variation among values of the hemodynamic index for the stenosis region in each of the plurality of mesh candidates is entirely below a threshold for the clinical decision or is entirely above the threshold for the clinical decision.

US Pat. No. 10,460,203

JACCARD SIMILARITY ESTIMATION OF WEIGHTED SAMPLES: SCALING AND RANDOMIZED ROUNDING SAMPLE SELECTION WITH CIRCULAR SMEARING

salesforce.com, inc., Sa...

1. A method of pre-calculation, per object, of object feature bin values for identifying close matches between objects that have numerous weighted features, the method including:during min-hashing of an expanded set of weighted features into a predetermined number of feature bins, circularly smearing a feature that qualifies to be inserted by min-hashing into a particular feature bin across successive feature bins,
using a processor and memory coupled to the processor, the memory holding objects, sets of weighted features of the objects, and values placed in the feature bins by min-hashing,
for initial weighted features of an object and a predetermined number of the feature bins used to receive the values produced by the min-hashing of the weighted features, as part of calculating an estimated Jaccard similarity index among objects:
scaling initial weights to produce scaled-weighted features, using scaling factors automatically selected based on a sum of the initial weights divided by a number of features in a feature set, applying two or more of the selected scaling factors to scale the initial weights for min-hashing into one set of feature bins per scaling factor;
expanding the scaled-weighted features into two or more expanded sets of weighted features of the object, wherein each expanded set includes at least as many weighted features as the predetermined number of feature bins;
wherein expanding a particular scaled-weighted feature produces multiple instances of feature samples in proportion to respective scaled weight of the particular scaled-weighted feature; and
min-hashing the expanded sets, with circularly smearing the incremented fractional part of a min-hashed value under consideration, so that the incremented fractional part of the min-hashed value is considered as a candidate to be inserted into at least one successive bin after insertion into an initial min-hash selected bin; and
saving completed sets of the feature bins for each scaling of weights of the object together with a scaling factor or sum of feature weights for use in comparing sampled features of the object with sampled features of other objects by calculating an estimated Jaccard similarity index.

US Pat. No. 10,460,202

MULTI-CAMERA DEVICE

Intel Corporation, Santa...

1. A mobile computing device, comprising:a housing having:
a first edge;
a second edge;
a third edge opposite the first edge, the second edge extending between the first and third edges;
a fourth edge opposite the second edge, the first edge extending between the second and fourth edges, the first and third edges having a first length, the second and fourth edges having a second length greater than the first length;
a first face defined by the first, second, third, and fourth edges; and
a second face opposite the first face, the second face defined by the first, second, third, and fourth edges:
a touchscreen on the first face and facing in a first direction;
a first camera sensor on the second face, the first camera sensor facing in a second direction opposite the first direction;
a second camera sensor on the second face, the second camera sensor facing in the second direction;
a third camera sensor on the second face, the third camera sensor facing in the second direction, the first camera sensor having a higher resolution than either the second camera sensor or the third camera sensor, at least one of the second or third camera sensors to generate information relating to depth associated with an image to be captured by the first camera sensor, the first, second, and third camera sensors supported by the housing in a triangular pattern, the first, second, and third camera sensors being closer to the first edge than to the third edge, a portion of the second camera sensor exposed to an exterior of the housing being a first distance from the fourth edge, a portion of the third camera sensor exposed to the exterior of the housing being a second distance from the fourth edge, the second distance being greater than the first distance;
at least one storage device to store instructions; and
at least one processor to execute the instructions to provide a soft shutter button on the touchscreen, the soft shutter button to be in a corner of the touchscreen closer to the third edge than to the first edge the soft shutter button and the first camera sensor to be spaced apart from and on opposites sides of a line intersecting the second and third camera sensors.

US Pat. No. 10,460,201

STRUCTURE AND TRAINING FOR IMAGE CLASSIFICATION

Microsoft Technology Lice...

1. A computer implemented method of training an image classifier using training images data, comprising:receiving training images data, said training images data being labeled according to image classes;
constructing a set of voting convolutional tables and a set of binary features on two or more pixels of said training images data, for one of a plurality of nodes of a tree hierarchy structure, through:
creating a voting table to select a group of selected binary features by selecting candidate binary features having minimal global loss reduction; and
performing a split of the respective node using said voting table by selecting a candidate binary features group and creating a child-directing table, said candidate binary features group and child-directing table are used for a next of said plurality of nodes.

US Pat. No. 10,460,200

APPARATUS AND METHOD OF ANALYZING TOOL TRACE, AND COMPUTER PROGRAM FOR EXECUTING THE METHOD

Republic of Korea (Nation...

1. A method of analyzing a tool trace, the method being performed by a portable tool trace analyzing apparatus comprising a camera unit and comprising:obtaining a first image that is a three-dimensional (3D) image of the tool trace;
displaying the first image on a screen;
storing, in a database, second images that are 3D images of one or more tools and that correspond to a plurality of pieces of feature information of the one or more tools;
when a specific tool is selected based on a user input, searching for a second image from among the second images in the database, the second image corresponding to the specific tool, and displaying the second image on the screen;
matching the second image that is selected with the first image and thus generating a match image;
displaying the match image on the screen;
wherein the generating of the match image comprises:
calculating an error between the first image and the second image;
when the calculated error is greater than a preset reference value, the tool trace is not determined to match the specific tool, and when the calculated error is equal to or less than the preset reference value, the tool trace is determined to match the specific tool; and
displaying a result of the determination on the screen:
wherein the feature information of the one or more tools comprises at least a shape of a tool head; and
wherein the generating of the match image further comprises generating the match image by matching a head part of the tool in the second image, with the first image.

US Pat. No. 10,460,199

TEXTILE MATCHING USING COLOR AND PATTERN RECOGNITION AND METHODS OF USE

Terrence A. Carroll, The...

1. A non-transitory, computer-readable medium comprising program code that, when executed by one or more processors of a computer system, causes the one or more processors to:analyze a first image of a first article of clothing to obtain color and pattern information corresponding to the first article of clothing;
locate a second article of clothing for pairing with the first article of clothing to create a matched pair of articles of clothing, wherein the second article of clothing is located by:
obtaining a plurality of possible matching articles of clothing from one or more databases,
identifying, for each of the plurality of possible matching articles of clothing, color and pattern information; and
selecting one of the plurality of possible matching articles of clothing based on the color and pattern information corresponding to the first article of clothing and the color and pattern information corresponding to one or more the possible matching articles of clothing;
initiate display of images of the matched pair of articles of clothing, the images of the matched pair of articles of clothing comprising the first image of the first article of clothing and a second image of the second article of clothing, the second image displayed in association with a selectable feedback object that allows for input of feedback regarding the selection of the second article of clothing;
receive the feedback regarding the selection of the second article of clothing; and
based on the feedback being positive, calculate an updated probability value, wherein the updated probability value indicates that some of the plurality of possible matching articles with similar probability values to a probability value of the second article of clothing are more likely to be selected in a future pairing that others of the plurality of possible matching articles.

US Pat. No. 10,460,198

IMAGE PROCESSING SYSTEM

FotoNation Limited, Galw...

1. An image processing system comprising a template matching engine (TME) operatively connected to a memory storing image information, the TME being configured to:read at least a portion of an image from said memory using a raster scan; and
as each pixel of said image portion is being read, calculate a respective feature value of a plurality of feature maps as a function of said pixel value;
the TME further comprising:
a pre-filter responsive to a current pixel location corresponding to a node within a first limited detector cascade to be applied to a window within said portion of an image to:
compare a feature value from a selected one of said plurality of feature maps corresponding to said pixel location to a threshold value; and
responsive to pixels for all nodes within said first limited detector cascade to be applied to said window having been read, determine a score for said window based on the comparisons of said feature values and said threshold values for said nodes; and
a classifier, responsive to said pre-filter indicating that a score for a window is below a window threshold, not applying a second detector cascade longer than said first limited detector cascade to said window before indicating that said window does not comprise an object to be detected.

US Pat. No. 10,460,197

PROCESS FOR EVALUATING SKIN CARE PRODUCT EFFICACY AND SKIN CARE PRODUCT EFFICACY EVALUATION SYSTEM

1. A software as a service (SaaS) soft material applied product efficacy evaluation system to objectively evaluate the efficacy of a product as applied to a soft material, said SaaS soft material applied product efficacy evaluation system comprising:a first sample soft material treated with a product;
a second sample soft material without treatment by the product;
a phabrometer comprising a motor, a rod, and a weight plate; and
a cloud server computing device that hosts a soft material applied product efficacy service, said cloud server computing device comprising a processor, a memory storage, and a soft material applied product efficacy program that is stored in the memory storage and which, when running on the processor of the cloud server computing device launches the soft material applied product efficacy service to evaluate efficacy of a soft material product, said soft material applied product efficacy program comprising sets of instructions for (i) receiving a set of skin care product efficacy test project attribute data resulting from a first phabrometer-based test of the first sample soft material treated with the product and a second phabrometer-based test of the second sample soft material without treatment by the product, (ii) receiving a set of test condition settings that define a scope of testing by the phabrometer for each of the first phabrometer-based test of the first sample soft material treated with the product and the second phabrometer-based test of the second sample soft material without treatment by the product, (iii) calculating an efficacy value for each soft material attribute in the set of skin care product efficacy test project attribute data resulting from the first phabrometer-based test of the first sample soft material treated with the product, (iv) calculating baseline values for each soft material attribute in the set of skin care product efficacy test project attribute data resulting from the second phabrometer-based test of the second sample soft material without treatment by the product, and (v) demonstrating the efficacy of the soft material product in comparison with no soft material product by one or more displayed comparison charts.

US Pat. No. 10,460,196

SALIENT VIDEO FRAME ESTABLISHMENT

Adobe Inc., San Jose, CA...

1. In a digital medium environment to extract multiple salient frames from a video based at least partially on entities present in one or more photos, a method implemented by at least one computing device, the method comprising:obtaining, by the at least one computing device, a video including multiple frames;
obtaining, by the at least one computing device, multiple photos which are extrinsic to the video;
ascertaining, by the at least one computing device, multiple relevant entities in the video based on the multiple photos extrinsic to the video;
determining, by the at least one computing device, multiple candidate frames from the multiple frames of the video;
establishing, by the at least one computing device, multiple salient frames, in part, by:
filtering the multiple candidate frames based on the multiple relevant entities based on the multiple photos which are extrinsic to the video, and
computing multiple salient scores for the multiple candidate frames, each respective salient score corresponding to a respective candidate frame, each respective salient score is based on an image quality indicator of the each of the respective candidate frame and a relevancy score computed for at least one entity appearing in the respective candidate frame; and
controlling, by the at least one computing device, presentation of the multiple salient frames via a user interface.

US Pat. No. 10,460,195

IMAGING APPARATUS AND METHOD, OPERATION APPARATUS AND METHOD, AND PROGRAM AND RECORDING MEDIUM

Mitsubishi Electric Corpo...

1. An imaging apparatus comprising:one or more processors;
a memory storing a program that when executed by the one or more processors causes one or more processors to function as
an imaging/irradiating control unit for generating an illumination condition control signal for controlling an illumination condition, and an imaging condition control signal for controlling an imaging condition;
said illumination condition control signal causing a subject to be illuminated with a plurality of mutually different illumination conditions;
said imaging condition control signal causing a subject image to be captured with an imaging condition to generate captured images;
a luminance variation calculation unit for calculating, using a plurality of captured images obtained by capturing images under different illumination conditions, a luminance variation pertaining to each pixel between the plurality of captured images;
a texture variation calculation unit for calculating, using a plurality of captured images obtained by capturing images at different time points, a texture variation pertaining to each pixel between the plurality of captured images; and
a subject extraction unit for extracting a subject region based on the luminance variation and the texture variation, wherein
said texture variation calculation unit calculates, as the texture variation, a first texture variation using a plurality of captured images obtained by capturing images under identical illumination conditions at different time points, and a second texture variation using the plurality of captured images which are used for the calculation of the luminance variation.

US Pat. No. 10,460,194

SYSTEM AND METHOD FOR THE DETECTION AND COUNTING OF REPETITIONS OF REPETITIVE ACTIVITY VIA A TRAINED NETWORK

1. A system for detecting and counting repetitive activity over time, comprising:a signal input to transfer, from outside to inside the system, signal information from which repetitive activity is detected and counted;
one or more detectors for detecting repetitive activity from a plurality of time windows of fixed length, where the time windows contain said signal information;
a processor that utilizes a trained deep neural network classifier for determination of and outputting an estimation of a cycle length of each repetition of the repetitive activity within each time window; and
at least two registers to integrate the estimation provided by the processor between a count-start and a count-stop and to produce a count of the number of the repetitions.

US Pat. No. 10,460,193

IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND COMPUTER-READABLE STORAGE MEDIUM

FUJITSU LIMITED, Kawasak...

1. An image processing apparatus comprising:a storage configured to store a program; and
a processor configured to execute the program and perform a process including
fitting data of a three-dimensional shape of a target object in an image of the target object to a quadric surface, to approximate the three-dimensional shape by the quadric surface,
performing a plane expansion process on data of the image, to expand the quadric surface onto an expansion plane,
computing corresponding points of the image before and after the plane expansion process, and
correcting at least one of inclination and rotation of the target object, to generate normalized data of the image using the corresponding points that are computed,
wherein the computing the corresponding points computes the corresponding points including a point on a straight line located on the expansion plane that is in contact with a point on a quadratic curve of the quadric surface, a reference point on the target object, and an intersection point of a first imaginary straight line that passes through the point on the straight line and extends in a direction of a first normal vector that is perpendicular to the straight line, and
wherein the corresponding points respectively on the straight line located on the expansion plane and on the quadric curve located on the quadric surface are equidistant from an expansion center of the expansion plane, the expansion center of the expansion plane having coordinates corresponding to coordinates of a center of the target object.

US Pat. No. 10,460,192

METHOD AND SYSTEM FOR OPTICAL CHARACTER RECOGNITION (OCR) OF MULTI-LANGUAGE CONTENT

XEROX Corporation, Norwa...

1. A method for optical character recognition (OCR) of multi-language content, the method comprising:extracting, by a data processor in a computing device, at least a text portion from an image received from a user-computing device associated with a user, over a communication network, wherein the text portion comprises a plurality of keywords associated with a plurality of languages;
segmenting, by a data segmentation processor in the computing device, the plurality of keywords into a plurality of isolated virtual layers, wherein each isolated virtual layer of the plurality of isolated virtual layers comprises one or more keywords, from the plurality of keywords, the one or more keywords in each layer are associated with a specific language from the plurality of languages, the specific language corresponds to a common language for the one or more keywords in a given isolated virtual layer, and the given isolated layer is dedicated to the common, specific language;
generating, by a multi-language OCR processor in the computing device, an OCR output of each of the plurality of isolated virtual layers based on the language associated with the one or more keywords in each of the plurality of isolated virtual layers;
generating, by a document generating processor in the computing device, an electronic document corresponding to the received image based on the OCR output of each of the plurality of isolated virtual layers, wherein the electronic document comprises a background portion comprising the OCR output and a foreground portion comprising the text portion, and the OCR output in the background portion comprises searchable layers corresponding to the plurality of layers, enabling the user to perform one or more operations; and
transmitting the electronic document to the user-computing device, over the communication network.

US Pat. No. 10,460,191

DYNAMICALLY OPTIMIZING PHOTO CAPTURE FOR MULTIPLE SUBJECTS

Capital One Services, LLC...

1. A method, comprising:determining, by a user device, a plurality of image resolutions supported by a camera of the user device;
determining, by the use device, a screen aspect ratio of a display of the user device;
capturing, by the camera of the user device, a first preview image;
processing, by the user device, the first preview image using a first computer vision technique;
detecting, by the user device and based on processing the first preview image, a first side of a document;
determining, by the user device and based on processing the first preview image, first information associated with the first side of the document;
selecting, by the user device and based on the first information, a first image resolution of the plurality of image resolutions;
capturing, by the camera of the user device, a first image of the first side of the document according to the first image resolution;
capturing, by the camera of the user device, a second preview image;
processing, by the user device, the second preview image using a second computer vision technique;
detecting, by the user device and based on processing the second preview image, a second side of the document;
determining, by the user device and based on processing the second preview image, second information associated with the second side of the document;
determining, by the user device, a threshold image resolution based on the second information;
determining, by the user device and based on the screen aspect ratio, a set of image resolutions of the plurality of image resolutions that fit the display of the user device;
selecting, by the user device and based on the second information, a second image resolution from the set of image resolutions,
wherein the second image resolution corresponds to a different quality of image than the first image resolution, and
wherein the second image resolution satisfies the threshold image resolution;
capturing, by the camera of the user device, a second image of the second side of the document according to the second image resolution; and
performing, by the user device, an action related to the first image and the second image.

US Pat. No. 10,460,190

ARTICLE RECOGNITION APPARATUS AND ARTICLE RECOGNITION METHOD

TOSHIBA TEC KABUSHIKI KAI...

1. A settlement apparatus for commodities, comprising:an image interface configured to acquire an image captured by photographing a predetermined place where a plurality of commodities are disposed;
a weight interface configured to acquire a weight of the commodities measured by a weight scale, the weight scale being configured to measure the weight of the commodities disposed at the predetermined place; and
a processor configured to:
acquire a first image through the image interface;
acquire a second image through the image interface after detecting a predetermined event;
recognize which one or more commodities out of the plurality of commodities have been taken out based on the first and the second image;
acquire registered weights of the recognized one or more commodities from a commodity database;
output an error if a total of the registered weights disagrees with a difference between a first weight which the weight scale measures at a time of photographing the first image, and a second weight which the weight scale measures at a time of photographing the second image;
acquire a price corresponding to the recognized one or more commodities; and
complete settlement of the commodities based on the acquired price when the weight scale does not detect any commodity.

US Pat. No. 10,460,189

METHOD AND APPARATUS FOR DETERMINING SUMMATION OF PIXEL CHARACTERISTICS FOR RECTANGULAR REGION OF DIGITAL IMAGE AVOIDING NON-ALIGNED LOADS USING MULTIPLE COPIES OF INPUT DATA

TEXAS INSTRUMENTS INCORPO...

1. An electronic assembly, comprising:at least one processor; and
a non-transitory computer readable storage medium storing a program for execution by the at least one processor, the program including instructions to:
load a first data element from an integral image buffer, to the at least one processor, in response to determining that a first base address is aligned for a first single instruction multiple data (SIMD) operation by the at least one processor; and
load an offset first data element of an offset integral image from an offset integral buffer on a storage device, to the at least one processor, in response to determining that the first base address is non-aligned for the first SIMD operation;
wherein the offset first data element represents a first corner of a rectangular region of a digital image, wherein the first data element represents the first corner of the rectangular region of an integral image, wherein the integral image is a representation of the digital image, and wherein the integral image is formed by data elements stored in the integral image buffer on the storage device; and
wherein the offset first data element of the offset integral image is defined by corresponding data elements of the integral image and stored at address locations in the offset integral buffer that are offset by one address location such that a select data element in the integral image buffer at a select address that is non-aligned for a select SIMD operation by the at least one processor is located at a select offset address in the offset integral buffer that is aligned for the select SIMD operation.

US Pat. No. 10,460,188

BIO-SENSING APPARATUS

Gingy Technology Inc., H...

1. A bio-sensing apparatus, adapted to sense a biopolymer, the bio-sensing apparatus comprising:a sensing element, having a sensing surface;
a spatial filter element disposed on the sensing surface and comprising spatial filter sheets, wherein each of the spatial filter sheets comprising:
a light-transmitting layer; and
a spatial filter layer, disposed on the light-transmitting layer and having light-transmitting portions and light-blocking portions, each of the light-transmitting portions is surrounded by light-blocking portions of the light-blocking portions, wherein light-transmitting layers of the spatial filter sheets and spatial filter layers of the spatial filter sheets are stacked alternately in a normal direction of the sensing surface;
a light-transmitting element disposed on the spatial filter element, the spatial filter element is disposed between the light-transmitting element and the sensing element; and
a surface plasma resonance layer disposed on the light-transmitting element and adapted to receive the biopolymer, the light-transmitting element is disposed between the surface plasma resonance layer and the spatial filter element.

US Pat. No. 10,460,187

BIOMETRIC AUTHENTICATION DEVICE AND SYSTEM

Hitachi, Ltd., Tokyo (JP...

1. A biometric authentication device comprising:a housing having a front side surface, a rear side surface, a passage side surface and an upper surface;
a light source array that is installed on the upper surface of the housing and includes a plurality of light sources;
an opening that is provided in the upper surface of the housing and located between the light source array and an intersection of the front side surface and the upper surface;
an infrared camera that is disposed inside the housing below the opening in the upper surface; and
a processor, wherein
an optical axis of a majority of the light sources intersects with the upper surface of the housing at an angle less than 90 degrees,
a plane formed by the light source array intersects with the passage side surface of the housing at an angle of less than 90 degrees, and
the processor is programmed to perform authentication of a biometric feature of a user irradiated with an irradiation light from the light sources and imaged by the infrared camera through the opening.

US Pat. No. 10,460,186

ARRANGEMENT FOR CREATING AN IMAGE OF A SCENE

Robert Bosch GmbH, Stutt...

1. A system for creating at least one image of a scene and/or object, comprising:at least one device for recording the at least one image of the scene and/or object, which is of a surrounding of the at least one user;
a device for acquiring a behavior of at least one user in viewing the scene and/or object, which is of the surrounding of the at least one user; and
a control unit for evaluating the behavior of the at least one user and for obtaining therefrom at least one control signal for a controlling of the device, including a selection of a recording direction and of image segments or objects that are to be recorded, for recording the at least one image in accordance with the behavior of the at least one user;
wherein the control unit is configured to evaluate at least one of the following features of the behavior of the at least one user: i) a pupil size or a temporal change in this pupil size of the at least one user, ii) a vocalization or speech expression of the at least one user, and iii) a gesture of the at least one user, and wherein the control unit is configured to evaluate a facial expression of the at least one user, the facial expressions excluding sleepiness,
wherein a change of the at least one user's direction of view from a route to be followed to a differing direction results in a control signal for taking a picture of the scene viewed by the at least one user, and
wherein the control unit is configured to evaluate a pupil size or a temporal change in this pupil size of the at least one user.

US Pat. No. 10,460,185

ROADSIDE IMAGE TRACKING SYSTEM

1. A system for roadside image tracing comprising:a camera mounted on a vehicle configured to capture images of objects around the vehicle while driving along a route of a plurality of routes;
processing circuitry configured to
receive the captured images from the camera and vehicle parameters including speed, a fuel level, and a mileage;
extract objects and locations of the objects within the captured images including information related to driving;
determine an average driving distance of the vehicle along each route of the plurality of routes;
predict a fueling time and a fueling location along each route of the plurality of routes based on the average driving distance, the vehicle parameters including the fuel level, and the information extracted from captured images including fuel prices, discounts, and road closures;
determine a route ranking based on the information collected from the objects during one or more trips along each route of the plurality of routes and the predicted fueling time and a predicted fueling location;
generate route options based on the route ranking and the vehicle parameters; and
transmit route options to a display.

US Pat. No. 10,460,184

IMAGE INFORMATION ACQUIRING APPARATUS, VEHICLE, AND CONTROL METHOD THEREOF

Hyundai Motor Company, S...

1. A vehicle comprising:a display;
a photographing device configured to acquire image information of a road on which the vehicle currently travels; and
a main controller configured to: i) detect first speed limit information based on the acquired image information, ii) calculate a difference between the detected first speed limit information and pre-stored second speed limit information corresponding to the road on which the vehicle currently travels, iii) display the first speed limit information when the calculated difference is less than a predetermined level or when the vehicle enters a branch road, and iv) display the second speed limit information when the calculated difference exceeds the predetermined level and when the vehicle does not enter the branch road.

US Pat. No. 10,460,183

METHOD AND SYSTEM FOR PROVIDING BEHAVIOR OF VEHICLE OPERATOR USING VIRTUOUS CYCLE

Xevo Inc., Bellevue, WA ...

1. A method configured to detecting operator behavior (“OB”) utilizing a plurality of sensors, machine learning center, and cloud based network, comprising:monitoring operator body language of an operator captured by a set of interior sensors and capturing surrounding information observed by a set of exterior sensors onboard a vehicle as the vehicle is in motion;
selectively recording data relating to the operator body language and the surrounding information in accordance with a containerized OB model generated by a machine learning center (“MLC”);
detecting an abnormal OB (“AOB”) in accordance with vehicular status signals received by the OB model while the vehicle is in operating;
rewinding recorded operator body language and the surrounding information leading up to detection of the AOB and generating labeled data associated with the AOB;
uploading the labeled data to the cloud based network for facilitating OB model training at the MLC via a virtuous cycle; and
correlating the labeled data with location information, time stamp, and vicinity traffic condition obtained from the cloud based network to update correlated labeled data relating to the AOB.

US Pat. No. 10,460,181

PROCESSING OF SENSOR DATA FOR A DRIVER ASSISTANCE SYSTEM

Bayerische Motoren Werke ...

1. A method for processing sensor data for a comfort driver assistance system for a motor vehicle, in which sensor data describing respective locations of a plurality of objects are acquired, the method comprising the acts of:extracting coordinates of the plurality of objects from the sensor data, wherein an inner side of an object of the plurality of objects, on which the motor vehicle is intended to drive past the object, is determined;
distinguishing a region which can be traveled on and is in front of and/or behind each of the plurality of objects in a direction of travel of the motor vehicle from a region which cannot be traveled on, wherein the region which can be traveled on is an object travel region and wherein a boundary between the object travel region and the region which cannot be traveled on is a boundary line which extends beyond the object to a front and/or to a rear along the inner side of the object in the direction of travel; and
determining the boundary line and forwarding data relating to the boundary line from a sensor device to a central control device of the comfort driver assistance system instead of the sensor data describing the object, wherein the boundary line is a trajectory which describes a path of the motor vehicle which, coming from an outer side in front of the object in the direction of travel, leads past the inner side of the object at a minimum distance with a maximum steering angle, and/or describes a path which leads outward from the object with a maximum steering angle for a current driving speed after the object, the maximum steering angle being determined based on a speed of the motor vehicle.

US Pat. No. 10,460,180

SYSTEMS AND METHODS FOR VISUAL CLASSIFICATION WITH REGION PROPOSALS

GM GLOBAL TECHNOLOGY OPER...

1. A method for classifying objects in an environment, the method comprising:(a) processing, ranging information from depth sensors to identify a set of bounding box region proposals for an image from a camera, wherein the ranging information comprises point cloud data provided from lidar devices, wherein the bounding box region proposals are selected areas of the image that include objects to be classified, wherein each of the bounding box region proposals comprises: a set of two-dimensional bounding box coordinates that correspond to a region of a rectified image that includes one or more objects to be classified, wherein the set of bounding box region proposals collectively specify which objects are in the rectified image and where those objects are in the rectified image, wherein the processing comprises:
(a1) generating segmented objects based on the ranging information, wherein the segmented objects define three-dimensional locations and dimensions of objects in vicinity of a vehicle;
(a2) determining a subset of segmented objects to be classified that: meet a size constraint, are within a certain height range above the ground and are within a driveable area of the vehicle, and wherein other segmented objects that are not to be classified are those that the vehicle cannot hit and are disregarded when generating the object state information;
(a3) generating object state information that indicates the three-dimensional locations of the subset of segmented objects to be classified; and
(a4) translating the three-dimensional locations of objects as specified by the object state information into the set of bounding box region proposal; and
(b) classifying, via a neural network executed by the hardware based processor, only the objects from the image that are within one of the bounding box region proposals and generating an object classification result for each object from the rectified image that is within one of the bounding box region proposals;
(c) processing image data received from cameras to generate the rectified images; and
(d) generating a regressed bounding box for each object that is classified, wherein each regressed bounding box for each object is the bounding box that the neural network has determined to be a best bounding box encompassing that object, wherein steps (a1) through (a4), (b), (c) and (d) are performed iteratively such that the object classification result and the regressed bounding box for each object being classified are fed back on each iteration to refine the bounding box region proposal for each object during each subsequent iteration so that the bounding box region proposal for each object more closely describes actual geometry of that object.

US Pat. No. 10,460,179

SYSTEM AND METHOD FOR RECOGNIZING A LANE

MANDO HELLA ELECTRONICS C...

1. A lane recognition system comprising:an image sensor for capturing an image comprising a lane;
a neuromorphic system in which a plurality of neurons in which pattern vectors related to a lane information are stored are connected by a parallel bus, wherein the plurality of neurons storing the pattern vectors including information related to a lane color and a lane shape; and
a lane recognition unit configured to generate [1×N] size input vectors of a predetermined size for a region of interest of the input image frame input from the image sensor, to input the generated vector having [1×N] size to the neuromorphic system, and to recognize a lane in the input image based on lane information of a neuron having a pattern vector most similar to an input vector among a plurality of neurons stored in the neuromorphic system by comparing the input vector with the pattern vectors stored in the plurality of neurons to obtain one neuron having the smallest relative distance value.

US Pat. No. 10,460,178

AUTOMATED PRODUCTION OF CHAPTER FILE FOR VIDEO PLAYER

STUDY SOCIAL INC., Gaine...

1. A method of creating a chapter file, said method comprising:inputting a video file into audio-visual software and splitting said video file into a plurality of still images at a predefined frame rate, each of said still images having a corresponding timestamp;
inputting said still images into optical character recognition (OCR) software and producing a machine-readable file or files corresponding to said still images;
inputting said machine-readable file or files into a computer program and identifying an index of said each of said still images; and
writing each identified index along with its corresponding timestamp into a chapter file in chronological order and saving said chapter file into persistent storage of a computer.

US Pat. No. 10,460,177

METHODS AND SYSTEMS OF SPATIOTEMPORAL PATTERN RECOGNITION FOR VIDEO CONTENT DEVELOPMENT

Second Spectrum, Inc., L...

1. A method comprising:receiving a first broadcast video teed capturing a filmed occurrence, the first broadcast video feed comprising a plurality of broadcast video frames captured by a broadcast camera, wherein the first broadcast video teed is a video feed that is consumable by a client device;
receiving a tracking camera video feed corresponding to the filmed occurrence, the tracking camera video feed comprising a plurality of tracking video frames and being captured by a tracking camera having a position that is calibrated to a frame of reference;
tracking one or more respective pixel locations of an object detected in one or more respective broadcast video frames of the first broadcast video feed;
tracking one or more respective spatial locations of the object based on one or more respective tracking video frames where the object is detected in the tracking video feed;
time-aligning the first broadcast video feed with the tracking video feed based on the one or more respective pixel locations and the one or more respective spatial locations;
generating a spatio-temporal index corresponding to the filmed occurrence based on the time-alignment of the first broadcast video feed with the tracking video feed, wherein the spatio-temporal index indexes spatio-temporal information relating to objects detected in the broadcast video feed and/or the tracking video feed;
spatially aligning an augmentation item with respect to the object in a subset of the one or more broadcast video frames based on the spatio-temporal index; and
generating an augmented video stream having one or more augmented video frames based on the subset of the one or more broadcast video frames and the spatial alignment of the augmentation item with respect to the object, wherein the augmentation item and the object are spatially aligned in the augmented video stream.

US Pat. No. 10,460,176

METHODS AND SYSTEMS OF SPATIOTEMPORAL PATTERN RECOGNITION FOR VIDEO CONTENT DEVELOPMENT

Second Spectrum, Inc., L...

1. A method for delivering personalized video content, comprising:processing at least one video feed through at least one spatiotemporal pattern recognition algorithm that uses machine learning to develop an understanding of at least one event within the at least one video feed of a professional game, wherein the understanding developed by the machine learning includes an entry in a relationship library at least detailing a relationship between two visible features of the at least one video feed;
capturing 3D video of a non-professional player as a data feed;
developing an understanding using the machine learning of at least one event within the data feed relating to motion of the non-professional player; and
automatically, under computer control, providing an enhanced video feed that mixes video of the non-professional player with the at least one video feed of the professional game and represents the nonprofessional player as an animation having attributes based on the data feed relating to motion of the non-professional player playing within a context of the professional game based on the understanding of the at least one event within the at least one video feed of the professional game and the data feed relating to the motion of the non-professional player.

US Pat. No. 10,460,175

DEEP LEARNING PROCESSING OF VIDEO

Amazon Technologies, Inc....

1. A method comprising:performing a first processing of a first frame of a video by a neural network, wherein the first processing comprises application of a first layer and a second layer of the neural network; and
performing a second processing of a second frame of the video by the neural network, wherein application of the second layer of the neural network is skipped in the second processing if the first frame and the second frame are substantially similar.

US Pat. No. 10,460,174

SYSTEM AND METHODS FOR ANALYSIS OF USER-ASSOCIATED IMAGES TO GENERATE NON-USER GENERATED LABELS AND UTILIZATION OF THE GENERATED LABELS

THE HONG KONG UNIVERSITY ...

1. A system for using images generated or shared by a plurality of entities to output associations between entities of the plurality of entities, comprising:one or more processor-readable media, configured to store processor-executable instructions; and
one or more processors, configured, based on execution of the stored processor-executable instructions, to facilitate:
extracting visual features of the images generated or shared by the plurality of entities, wherein each image is generated or shared by a respective entity of the plurality of entities;
annotating the images generated or shared by the plurality of entities with non-user-generated labels based on the extracted visual features, wherein the non-user-generated labels are machine-generated based on a machine analysis of the extracted visual features;
generating a label-based representation for a first entity based on a plurality of non-user-generated labels associated with images generated or shared by the first entity;
generating a label-based representation for a second entity based on a plurality of non-user-generated labels associated with images generated or shared by the second entity;
comparing the label-based representation for the first entity and the label-based representation for the second entity to determine whether or not they are similar;
determining an association between the first entity and the second entity in response to determining that the label-based representation for the first entity and the label-based representation for the second entity are similar; and
outputting the determined association between the first entity and the second entity.

US Pat. No. 10,460,173

SYSTEM AND METHOD FOR PROVIDING INFORMATION BASED ON CONSTRUCTION SITE IMAGES

CONSTRU LTD, Tel Aviv (I...

1. A method for providing information based on construction site images, the method comprising:obtaining image data captured from a construction site using at least one image sensor;
obtaining at least one electronic record associated with the construction site;
analyzing the image data to identify at least one discrepancy between the at least one electronic record and the construction site;
analyzing the image data to identify at least one construction error;
analyzing the image data to identify a type of the at least one construction error;
providing information to a user based on the identified at least one discrepancy, the provided information comprises an indication of the at least one construction error; and
based on the identified type, forgoing providing at least part of the information.

US Pat. No. 10,460,171

SYSTEMS AND METHODS FOR PROCESSING MEDIA CONTENT THAT DEPICT OBJECTS

Facebook, Inc., Menlo Pa...

1. A computer-implemented method comprising:providing, by a computing system, a live camera view for a camera of the computing system;
performing, by the computing system, as one or more background processes, object recognition with respect to one or more representations of the live camera view;
receiving, by the computing system, a first command to acquire a first image represented via the live camera view at a first time,
determining, by the computing system, that a first face associated with a first recognized user is depicted in the first image; and
identifying, by the computing system, a first location associated with the first image;
receiving, by the computing system, a second command to acquire a second image represented via the live camera view at a second time;
determining, by the computing system, that a second face associated with a second recognized user is depicted in the second image;
identifying, by the computing system, a second location associated with the second image;
determining, by the computing system, that the first location and the second location are within a specified allowable proximity from each other;
presenting, by the computing system, an interface portion overlaying the live camera view, the interface portion providing at least a first identifier for the first recognized user in the first image; and
enabling, by the computing system, both the first image and the second image to be shared with both the first recognized user and the second recognized user.

US Pat. No. 10,460,170

IMAGE PROCESSING OF AERIAL IMAGERY FOR ENERGY INFRASTRUCTURE SITE STATUS ANALYSIS

SOURCEWATER, INC., Houst...

1. A computer-implemented method for processing images to determine Energy Infrastructure (EI) site status, the method to be carried out by at least one processor executing computer instructions, the method comprising:receiving a working image including at least one aerial image of a portion of global terrain;
applying a first EI feature recognition model to the working image to generate information on a first EI feature at a first geographical location in the portion of global terrain at a first confidence level according to image content of the working image;
applying a second EI feature recognition model to the working image to generate information on a second EI feature at a second geographical location in the portion of global terrain at a second confidence level according to image content of the working image;
determining a composite indication of an EI site status based on at least the information on the first EI feature, the information on the second EI feature, the first confidence level and the second confidence level.

US Pat. No. 10,460,169

IMAGE PROCESSING OF AERIAL IMAGERY FOR ENERGY INFRASTRUCTURE ANALYSIS USING JOINT IMAGE IDENTIFICATION

SOURCEWATER, INC., Houst...

1. A computer-implemented method for processing images to identify Energy Infrastructure (EI) features, the method to be carried out by at least one processor executing computer instructions, the method comprising:receiving a working image comprising at least one aerial image of a portion of global terrain;
applying an EI feature recognition model to the working image to identify a first EI feature at a first confidence level according to image content of the working image;
associating the first EI feature with a first EI feature type and a first location within the portion of the global terrain;
retrieving an identification of a second EI feature in the portion of the global terrain;
associating the second EI feature associated with a second EI feature type and a second location within the global terrain;
updating the identification of the first EI feature to a second confidence level based at least on the first confidence level, the identification of the second EI feature, and information on a relationship between the first EI feature and the second EI feature.

US Pat. No. 10,460,168

INTERFACES FOR IMPROVING DATA ACCURACY IN A POSITIONING SYSTEM DATABASE

Verizon Patent and Licens...

1. A method comprising:obtaining, by a device, a first two-dimensional image providing an aerial perspective of a building,
a business being located within the building;
receiving by the device, a path identifier indicative of a virtual roadway proximal to the building;
receiving, by the device, a first identifier in the first two-dimensional image of a first edge of the business relative to the building, a second identifier of a second edge of the business relative to the building, and a third identifier of an entrance to the business relative to the building;
determining by the device, a first latitude and longitude pairing on a map for the first identifier, a second latitude and longitude pairing on the map for the second identifier, and a third latitude and longitude pairing on a map for the third identifier;
providing, by the device and for display in the first two-dimensional image, an identification of the first edge of the business based on the first identifier, an identification of the second edge of the business based on the second identifier, and an identification of the entrance of the business based on the third identifier; and
obtaining, by the device, a second two-dimensional image based on the virtual roadway,
the second two-dimensional image providing a first person perspective of the building.

US Pat. No. 10,460,167

EXTENDED DEPTH-OF-FIELD BIOMETRIC SYSTEM

Global Bionic Optics Ltd....

1. A method of processing an extended depth-of-field (EDOF) image of an iris at an imaging wavelength km, comprising:capturing a raw image of the iris, wherein the raw image has a reduced modulation transfer function (MTF) based on an optical system having an amount of spherical aberration (SA) of 0.2?IM?SA?2?IM;
processing the raw image;
accessing a wavelet base function, wherein the wavelet base function has a plurality of wavelet coefficients;
projecting at least a portion of the processed raw image on the wavelet base function;
identifying a plurality of modulated equalization coefficients from the projection; and
generating an iris code based on the plurality of modulated equalization coefficients.

US Pat. No. 10,460,166

ROBUST SEGMENTATION OF RETINAL PIGMENT EPITHELIUM LAYER

CANON KABUSHIKI KAISHA, ...

1. A computer implemented method for determining a retinal pigment epithelium, the method comprising:identifying a plurality of regions by calculating a degree of polarization uniformity value using captured image data of an eye, the captured image data being polarization-sensitive OCT data of the eye;
fitting, by a processor, a plurality of curves to at least some of the identified regions, each fitted curve defining at least one first depolarising region at a predetermined distance above the fitted curve and at least one second depolarising region at the predetermined distance below the fitted curve;
for each of the fitted curves, determining, by the processor, a curve score, wherein contribution of a corresponding at least one second depolarizing region is weighted higher than contribution of a corresponding at least one first depolarizing region;
comparing, by the processor, the determined curve scores;
selecting, by the processor, one of the fitted curves using a result of the comparing to determine a position of a healthy retinal pigment epithelium (RPE) of the eye;
generating an en face RPE thickness map using the determined position of the healthy retinal pigment epithelium; and
evaluating at least one of size and the number of at least one of diseased regions in the en face RPE thickness map.

US Pat. No. 10,460,165

HEAD MOUNTED DISPLAY

FOVE, Inc., Tokyo (JP)

1. An eyesight detection device comprising:a lens to be disposed at a position facing a user's cornea when the device is used by the user;
a plurality of infrared light sources disposed in a periphery of the lens that emit infrared light toward the user's cornea; and
a camera that captures an image including the user's cornea;
wherein, when the periphery of the lens is equally divided into four regions of a first region corresponding to the outer corner side of the eye of the user, a second region corresponding to the inner corner side of the eye, a third region corresponding to the top side of the head, and a fourth region corresponding to the jaw side, the plurality of infrared light sources are disposed in the first region and the second region wherein the plurality of infrared light sources are disposed asymmetrically with respect to an axis extending through a center of the first region and a center of the second region.

US Pat. No. 10,460,164

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, EYEWEAR TERMINAL, AND AUTHENTICATION SYSTEM

SONY CORPORATION, Tokyo ...

1. An information processing apparatus comprising:circuitry configured to:
when a first authentication image including an iris of an eye of a user is obtained, display an object on a display screen to perform iris authentication;
measure a size of a pupil in the eye of the obtained first authentication image;
change a shape of the object displayed on the display screen and obtain a second authentication image based on a measured brightness of an environment at a time of obtaining the first authentication image and the measured size of the pupil in the obtained first authentication image; and
perform the iris authentication using at least one of the first authentication image and the second authentication image according to the user's current situation.

US Pat. No. 10,460,163

SYSTEM AND METHOD FOR DIGITALLY WATERMARKING DIGITAL FACIAL PORTRAITS

MorphoTrust USA, LLC, Bi...

1. A computer implemented identification method executed by one or more processors, the method comprising:obtaining, from a mobile computing device of a device user, data encoding a digital facial portrait that portrays a person, the digital facial portrait embedded with at least one digital watermark identifying payload data linking the digital facial portrait to the person portrayed by the digital facial portrait;
obtaining an image representing a facial portrait of the device user;
receiving results of a comparison between the digital facial portrait and the image representing the facial portrait of the device user, the results indicating that the device user is the person portrayed by the digital facial portrait;
in response to the results indicating that the device user is the person portrayed by the digital facial portrait, decoding the at least one digital watermark to obtain the payload data from the at least one digital watermark;
retrieving personally identifiable information based on the payload data; and
determining that the digital facial portrait is authentic based on the decoded at least one digital watermark by authenticating the digital facial portrait based on the personally identifiable information.

US Pat. No. 10,460,162

METHOD, DEVICE, AND SYSTEM, FOR IDENTIFYING DATA ELEMENTS IN DATA STRUCTURES

Handycontract, LLC, Reno...

1. A computer-implemented method for determining document structure of a document, the method comprising:generating a document string corresponding to the document;
identifying a first candidate marker at a first position in the document string;
based on determining that the first candidate marker is in a predefined first-element form, adding the first candidate marker to a set of marker sequences associated with the document as a first marker sequence, wherein the first marker sequence corresponds to a first candidate hierarchy for the document structure;
identifying a second candidate marker occurring at a second position in the document string subsequent to the first position;
based on determining that the second candidate marker is in the predefined first-element form, adding the second candidate marker to the set of marker sequences as a second marker sequence, wherein the second marker sequence corresponds to a second candidate hierarchy for the document structure;
identifying a third candidate marker occurring at a third position in the document string subsequent to the second position;
based on determining that the third candidate marker is not in the predefined first-element form, iteratively determining whether the third candidate marker is consecutively congruent to a last element in each respective marker sequence of the set of marker sequences;
based on determining that the third candidate marker is consecutively congruent to the last element in the first marker sequence, adding the third candidate marker to the first marker sequence;
determining at least one eligible marker sequence based on evaluating each marker sequence of the set of marker sequences using at least one marker sequence eligibility criteria; and
generating a display of the document comprising visual indicia associated with a determined document structure, wherein the visual indicia correspond to a determined hierarchy for the document structure based on the at least one eligible marker sequence.

US Pat. No. 10,460,161

METHODS AND SYSTEMS FOR ENSURING CORRECT PRINTING PLATE USAGE AND SIGNAL TOLERANCES

Digimarc Corporation, Be...

1. A method of monitoring a spectral difference between a substrate and one or more colors, the one or more colors configured to carry an encoded signal, said method comprising:determining a minimum ink value and a maximum ink value of an encoded signal carrier;
determining a spectral reflectance difference at or around 660 nm between: i) the substrate without any ink and the minimum ink value, and ii) the substrate without any ink and the maximum ink value;
based on the difference of i and ii, determining a tolerance range;
printing the minimum ink value and the maximum ink value in a control strip area;
measuring the spectral reflectance of the substrate, the printed minimum ink and the printed maximum ink to yield measurements, and using the measurements to determine whether the printing press is maintaining printing within the determining tolerance range.

US Pat. No. 10,460,160

E-PAPER IMAGER

Hewlett-Packard Developme...

1. An imager comprising:an ion-emitting unit;
a conveying structure to move a passive e-paper display medium in a first orientation along a travel path and to releasably support the display medium in spaced relation to receive airborne ions from the ion-emitting unit for imaging operations;
a validation arrangement to permit target-content imaging operations via the ion-emitting unit upon a determination the display medium is valid and to prevent target-content imaging operations upon a determination that the display medium is invalid, and
a machine-readable-code reader;
wherein the ion-emitting unit comprises:
an erasing unit spaced apart, and located downstream, from the machine-readable-code reader; and
a writing unit spaced apart, and located downstream, from the erasing unit.

US Pat. No. 10,460,159

VIDEO ENDPOINT, COMMUNICATION SYSTEM, AND RELATED METHOD FOR AUTOMATIC FRAMING A SIGNING AREA OF A SIGN LANGUAGE USER

SORENSON IP HOLDINGS, LLC...

1. A communication system, comprising:a video endpoint having a camera, the video endpoint configured to:
determine dimensions of an initial signing area of an audibly-impaired user during a setup procedure prior to engaging in a communication session by analyzing a range of motion for the audibly-impaired user to sign a predetermined word or set of words, wherein the video endpoint is configured to determine the dimensions of the initial signing area of the audibly-impaired user by taking measurements of at least a portion of the audibly-impaired user's body and automatically framing the camera to include a region including the initial signing area based on the measurements; and
automatically frame a field of view of the camera to include the initial signing area or a determined adjusted signing area of the audibly-impaired user having updated dimensions based, at least in part, on a range of motion for the audibly-impaired user's signing motions during the communication session; and
a relay service configured to provide sign language translation services during a communication session with the audibly-impaired user at the video endpoint and a far-end user at a communication device.

US Pat. No. 10,460,158

METHODS AND SYSTEMS FOR GENERATING A THREE DIMENSIONAL REPRESENTATION OF A HUMAN BODY SHAPE

KABUSHIKI KAISHA TOSHIBA,...

1. A method of generating a three dimensional representation of a human body shape from a depth image of a clothed human subject, the method comprising:identifying at least one representative sample from a plurality of pre-calculated representative samples, each pre-calculated representative sample comprising a three dimensional representation of a human body shape and a corresponding depth map, by comparing depth maps of the pre-calculated representative samples with the depth image of the clothed human subject, the depth maps corresponding to unclothed human body shapes;
determining a neighbourhood of first data space of possible depth images of unclothed human body shapes from the depth map of the at least one representative sample;
generating a parametric model for the human body shape from a neighbourhood of second data space of human body shapes, the neighbourhood of the second data space of human body shapes corresponding to the neighbourhood of the first data space of possible depth images of the unclothed human body shapes; and
generating the three dimensional representation of the human body shape by fitting the parametric model to the depth image of the clothed human subject.

US Pat. No. 10,460,157

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING SYSTEM, AND PROGRAM

Sony Corporation, (JP)

1. An information processing device comprising:a communication device configured to wirelessly receive sensor information from a sensor device; and
a processor configured
to generate play event information using the sensor information,
to determine from the play event information whether a detected behavior of a user is a predetermined play event,
to control an imaging device to capture play images based on the predetermined play event, and
identify a type of play event based on the play event information and a sport associated with a play event.

US Pat. No. 10,460,156

AUTOMATED TRACKING AND RETAINING OF AN ARTICULATED OBJECT IN A SEQUENCE OF IMAGE FRAMES

SONY CORPORATION, Tokyo ...

1. An image-processing apparatus, comprising:at least one image processor configured to:
segment each image frame in a sequence of image frames into different segmented regions that corresponds to different super-pixels;
detect an articulated object in a first motion state by non-zero temporal derivatives between a first image frame and a second image frame that succeeds said first image frame in said sequence of image frames;
construct a first connectivity graph of a first set of super-pixels of said first image frame;
construct a second connectivity graph of a second set of super-pixels of said second image frame; and
generate a complete object mask of said articulated object in a second motion state based on said first connectivity graph and said second connectivity graph, wherein at least a portion of said articulated object is stationary in said second motion state.

US Pat. No. 10,460,155

FACIAL IDENTIFICATION TECHNIQUES

AWARE, INC., Bedford, MA...

1. A method of electronically assisted facial identification of a person comprising:displaying, for a human facial examiner on at least one display, at least two facial images of the person;
electronically maintaining, by a processor and storage, a predefined list of facial components to be examined by the human facial examiner in the at least two facial images, the predefined list of facial components assisting the human facial examiner with determining whether the at least two facial images are of different persons or of a same person; and
automatically guiding through information presented on at least one display the human facial examiner through the facial identification process using the electronically maintained list of facial components, wherein the automatic guiding includes providing one or more of instructions, guidelines and anatomical definitions to the human facial examiner and storing a record of which facial components have been examined.

US Pat. No. 10,460,154

IDENTIFYING UNKNOWN PERSON INSTANCES IN IMAGES

Adobe Inc., San Jose, CA...

1. A method of identifying people in digital images using cluster-based person recognition comprising:dividing, by at least one processor, images of an image gallery into a plurality of image clusters, each image cluster comprising a plurality of images from the image gallery that share one or more common characteristics, the one or more common characteristics comprising one or more characteristics other than identities of the plurality of person instances in the images;
training, by the at least one processor, a cluster classifier for each image cluster of the plurality of image clusters based on a plurality of known person instances;
determining, by the at least one processor, an image cluster of the plurality of image clusters to which an image comprising an unknown person instance most corresponds based on one or more characteristics of the image and common characteristics of the determined image cluster of the plurality of image clusters, the one or more characteristics of the image comprising one or more characteristics other than an identity of the unknown person instance; and
determining, by the at least one processor, a probability that the unknown person instance is each known person instance in the determined image cluster using the cluster classifier of the determined image cluster.

US Pat. No. 10,460,153

AUTOMATIC IDENTITY DETECTION

Futurewei Technologies, I...

1. A method for detecting identification, comprising:obtaining, by an object detecting device of a network, a first picture comprising a first object at a first time instant and a second picture comprising a second object at a second time instant;
generating, by the object detecting device, a first feature vector of the first object based on the first picture and a second feature vector of the second object based on the second picture;
sending, by the object detecting device, the first feature vector and the second feature vector to a server;
obtaining, by the object detection device, basic pattern information of the first object and basic pattern information of the second object;
determining, by the object detecting device, that the first feature vector and the second feature vector are associated with a same object, based on the basic pattern information of the first object and the basic pattern information of the second object;
receiving, by a server of the network, a message from the object detecting device, wherein the message indicates that the first feature vector and the second feature vector are associated with the same object; and
recognizing, by the server of the network, the second object without recognizing the second feature vector based on the received message.

US Pat. No. 10,460,152

METHOD AND APPARATUS FOR PUSHING INFORMATION

BAIDU ONLINE NETWORK TECH...

1. A method for pushing information, comprising:detecting face information by a smart device;
detecting, by the smart device, at least one hand of a user;
recognizing, by the smart device, the at least one hand of the user to acquire a hand gesture;
determining, by the smart device, whether the hand gesture matches with a preset hand gesture;
when determining that the hand gesture matches with the preset hand gesture, acquiring, by the smart device, a control instruction based on the hand gesture, wherein a correspondence between the preset hand gesture and the control instruction is preset;
acquiring pushing information by the smart device according to the face information and the control instruction, wherein a relationship of the face information, control instruction, and the pushing information is pre-determined; and
presenting the pushing information by the smart device in one or more forms of text, an image, and voice;
after detecting the face information by the smart device, the method further comprises:
when detecting by the smart device that the face information meets a preset condition, controlling the intelligent household electrical appliance to perform a corresponding operation by the smart device according to the face information.

US Pat. No. 10,460,151

PRIVATE PHOTO SHARING SYSTEM, METHOD AND NETWORK

CloudSpotter Technologies...

1. A photograph network sharing process comprising the steps of:processing one or more photographs taken by a photographer at an event, to a server generally controlled by a photographer, and wherein the step of processing one or more photographs includes the steps of:
uploading the one or more photographs to the server; extracting facial metrics on any face depicted within each photograph, of the one or more photographs; and creating a database on the server that links each photograph, of the one or more photographs to corresponding extracted facial metrics;
registering a user attending the event, wherein the step of registering a user includes:
providing the user attending the event with an option to consent to receiving one or more photographs taken during the event and that contain an image of the user; extracting primary facial metrics from a photograph of the user, when the user consents to receiving the one or more photographs, defined as a registered user; creating a secure access to an event photo gallery uniquely associated to the registered user and stored on the server generally controlled by the photographer; storing the primary facial metrics on the server and linking the primary facial metrics of the registered user to the event photo gallery; and providing the registered user with an unique subject identifier or unique link for access into the event photo gallery uniquely associated to the registered user; and
matching and linking a photograph, of the one or more photographs uploaded to the server, to the registered user, wherein the step of matching and linking a photograph includes:
automatically comparing the primary facial metrics with the extracted facial metrics stored on the database and corresponding to any and all photographs, of the one or more photographs, uploaded to the server; identifying a photograph, when comparing the primary facial recognition metrics to the extracted facial metrics contains a predetermined level of certainty that the photograph contains an image of the registered user; and automatically linking the identified photograph to the event photo gallery uniquely associated to the registered user, whereby the registered user accessing the event photo gallery uniquely matched to the registered user gains access only to all identified photographs taken during the event and which contain the image of the registered user.

US Pat. No. 10,460,150

DEEP LEARNING AUTOMATED DERMATOPATHOLOGY

PROSCIA INC., Haverford,...

1. An at least partially computer implemented method of classifying a human cutaneous tissue specimen, the method comprising:obtaining a computer readable image of the human tissue sample;
preprocessing the image;
applying a trained deep learning model to the image to label each of a plurality of image pixels with at least one probability representing a particular diagnosis, such that a labeled plurality of image pixels is obtained;
applying a trained discriminative classifier to contiguous regions of pixels defined at least in part by the labeled plurality of image pixels to obtain a specimen level diagnosis, wherein the specimen level diagnosis comprises at least one of:basal cell carcinoma, dermal nevus, or seborrheic keratosis; andoutputting the specimen level diagnosis.

US Pat. No. 10,460,149

METHOD AND APPARATUS FOR UPDATING FINGERPRINT TEMPLATES, AND MOBILE TERMINAL

Guangdong Oppo Mobile Tel...

1. A method for updating fingerprint templates, comprising:acquiring a fingerprint image input by a user;
comparing the fingerprint image with fingerprint templates pre-stored in a fingerprint template set, wherein the fingerprint template set comprises N fingerprint templates and N is a positive integer;
determining whether a match value between the fingerprint image and an ith fingerprint template of the fingerprint template set is greater than a second preset threshold, wherein i is a positive number and is less than or equal to N;
generating a new fingerprint template based on the fingerprint image and adding the new fingerprint template to the fingerprint template set, if the match value is greater than the second preset threshold;
wherein comparing the fingerprint image with the fingerprint templates comprises:
determining a matching order of each of the fingerprint templates; and
comparing, based on the matching order, the fingerprint image with the fingerprint templates;
wherein each of the fingerprint templates in the fingerprint template set comprises corresponding weight information, wherein determining the matching order of each of the fingerprint templates comprises:
acquiring a matching frequency corresponding to each of the fingerprint templates in the fingerprint template set, wherein the matching frequency relates to a number of match times between a fingerprint template and the fingerprint image input by the user; and
determining the weight information of each of the fingerprint templates based on the matching frequency corresponding to each of the fingerprint templates; and
determining the matching order of each of the fingerprint templates according to the weight information of each of the fingerprint templates.

US Pat. No. 10,460,148

METHOD FOR CONTROLLING UNLOCKING AND MOBILE TERMINAL

Guangdong Oppo Mobile Tel...

8. A mobile terminal, comprising:a memory configured to store computer-readable program codes; and
a processor configured to invoke the computer-readable program codes to perform:
acquiring number of all feature points in a current feature point set of a user finger, the current feature point set being formed by a mobile terminal scanning and processing the user finger according to a current sensing electrode set, the current sensing electrode set comprising sensing electrodes in lines from the [M/2]?k11th to [M/2]+k12th row in a sensing electrode array of M-lines N-rows, the sensing electrode array being arranged in a fingerprint identification sensor of the mobile terminal, and M, N, k11 and k12 being positive integers;
unlocking the mobile terminal when the number of all the feature points in the current feature point set is greater than or equal to a first preset threshold and the current feature point set matches with a pre-saved fingerprint template, and
adding sensing electrodes with X lines to the current sensing electrode set so as to update the current feature point set when the number of all the feature points in the current feature point set is smaller than the first preset threshold, the X lines comprising X1 adjacent lines before the [M/2]?k11 line and X2 adjacent lines after the [M/2]+k12, X1, X2 and X being positive integers, and X equals to a sum of X1 and X2.

US Pat. No. 10,460,147

DISPLAY SCREEN, DISPLAY DEVICE AND MOBILE TERMINAL

GUANGDONG OPPO MOBILE TEL...

1. A display screen, comprising a display layer and a first light shielding layer, the display layer having a display surface towards a user, the first light shielding layer being arranged on the display surface, the first light shielding layer having a fingerprint recognition area, the fingerprint recognition area comprising a plurality of first through holes and a plurality of light shielding portions among the plurality of first through holes, the plurality of the first through holes being configured so that sensing signals emitted and received by a fingerprint unit located below the display screen can be transmitted through the plurality of the first through holes;wherein the display layer comprises a light-reflecting layer, and the first light shielding layer is a polarizing layer configured to block a reflected light signal of the light-reflecting layer from being emitted; and within an orthographic projection area of the fingerprint recognition area in the display layer, an orthographic projection of the plurality of the light shielding portions in the display layer completely covers an orthographic projection of the light-reflecting layer in the display layer.

US Pat. No. 10,460,146

IMAGE CAPTURE APPARATUS

Gingy Technology Inc., H...

1. An image capture apparatus, comprising:an imaging unit, comprising:
an electrode;
a light emitting layer, disposed on the electrode; and
a dielectric layer, disposed on the light emitting layer;
a light receiving device, wherein at least a portion of an object is in contact with a portion of the dielectric layer so that the light emitting layer emits an image light beam corresponding to the portion of the dielectric layer, and the light receiving device is disposed on a transmission path of the image light beam;
a conductive element, disposed on the dielectric layer of the imaging unit and having an opening exposing the dielectric layer, wherein a power supply is electrically connected with the conductive element, and the object is electrically connected with the power supply via the conductive element; and
an indicating unit, disposed on the imaging unit, comprising:
a first conductive pattern;
a first dielectric pattern;
a light emitting pattern;
a second dielectric pattern;
a second conductive pattern; and
an insulation pattern, wherein the first conductive pattern, the first dielectric pattern, the light emitting pattern, the second dielectric pattern, the second conductive pattern and the insulation pattern are stacked sequentially in a direction away from the imaging unit.

US Pat. No. 10,460,145

DEVICE FOR CAPTURING IMPRINTS

1. A device for capturing an image of a imprint of a body part, comprisingan image-acquiring module having an optical field covering an acquisition zone through which the body part may move,
a light source that produces a spatially uniform illumination of the body part and
a sight-projecting module that projects a luminous sight onto said body part perpendicularly to a direction of movement of the body part, wherein:
the luminous sight is a repetitive pattern of lower light intensity than the uniform illumination; and
said device comprises circuitry adapted to:
simultaneously activate the light source, the sight-projecting module and the image-acquiring module in order to allow an image of the imprint, called the acquired image, to be acquired;
model the variations in light intensity of the projection of the sight on the body part by determining parameters of a preset parametric mathematical model;
generate an image of the projection of the sight on the body part, called the synthetic image, on the basis of said model and using the parameters determined beforehand, and to subtract the synthetic image from the acquired image in order to obtain a sight-free image of the body part, said sight-free image of the body part being able to be used to carry out an identification or an authentication.

US Pat. No. 10,460,144

NON-FINGER OBJECT REJECTION FOR FINGERPRINT SENSORS

Cypress Semiconductor Cor...

1. A method, comprising:detecting a presence of an object at a fingerprint sensor;
in response to detecting the presence of the object, acquiring image data for the object based on signals from the fingerprint sensor; and
for each subset of one or more subsets of the image data,
calculating a magnitude value for a spatial frequency of the subset; and
identifying the object as a finger based on comparing the magnitude value to a threshold and comparing ridge directions of a plurality of regions of a surface of the object captured in the image data.

US Pat. No. 10,460,143

SENSOR AND SENSOR-EQUIPPED DISPLAY DEVICE

Japan Display Inc., Toky...

1. A sensor-equipped display device comprising:a scanning line;
a signal line;
a pixel switch connected to the scanning line and the signal line;
a pixel electrode connected to the pixel switch;
a first common electrode;
a detection electrode;
a current mirror circuit including a first transistor and a second transistor, the first transistor including a first gate electrode, a first electrode connected to a first power supply and a second electrode electrically connected to the detection electrode and the first gate electrode, the second transistor including a second gate electrode connected to the first gate electrode, a third electrode connected to the first power supply, and a fourth electrode; and
an integrator including an operational amplifier and a capacitor, the operational amplifier including an inverting input terminal electrically connected to the fourth electrode and a noninverting input terminal connected to a second power supply, the capacitor being connected between an output terminal and the inverting input terminal of the operational amplifier.

US Pat. No. 10,460,142

BARCODE IDENTIFICATION METHOD FOR IMPROVING DECODING RELIABILITY BY CORRECTING IMAGE DISTORTION

Qisda Corporation, Taoyu...

1. A barcode identification method comprising:generating a binarization barcode by using a binarization process from a sampled barcode;
acquiring a first region from the binarization barcode;
acquiring a first narrow element width from the first region;
acquiring a second region from the binarization barcode;
acquiring a second narrow element width from the second region;
generating an extension region by extending the second region when the second narrow element width is smaller than the first narrow element width;
generating a plurality of binarization sequences corresponding to the extension region;
eliminating a binarization sequence of the plurality of binarization sequences when at least one value of the binarization sequence is inconsistent with the first narrow element width;
decoding at least one of the binarization sequences for generating at least one decoded sequence by using a lookup table; and
verifying the at least one decoded sequence for generating a verified sequence by using a checksum code.

US Pat. No. 10,460,141

PER-CHANNEL COLOR BARCODES FOR DISPLAYS

University of Rochester, ...

1. A method of decoding a coherent RGB color barcode captured by a mobile device RGB camera by imaging the coherent RGB color barcode displayed by a RGB display comprising:displaying a coherent RGB color barcode on said RGB display to provide a displayed coherent RGB color barcode;
capturing an image of said displayed coherent RGB color barcode by said mobile device RGB camera to provide a captured image of said coherent RGB color barcode displayed on said RGB display;
localizing synchronization patterns in said captured image to determine a geometric layout of the coherent color barcode and an alignment of the geometric layout to the captured image of the coherent RGB color barcode;
estimating parameters of an RGB cross-channel interference in said captured image by using regions of said captured image that comprise synchronization pattern regions and known predetermined pilot block values for these regions set during the coherent barcode encoding process;
using said estimated parameters to apply a per pixel color interference cancellation process to said image of said displayed coherent RGB color barcode to extract two or three separate monochrome grey images of each barcode of said coherent RGB color barcode; and
decoding said two or three separate monochrome grey images to provide a decoded data for corresponding barcode of said coherent RGB color barcode displayed on said RGB display.

US Pat. No. 10,460,140

READING AND WRITING CODES USING OPTICAL DEVICES

ILLUMINA, INC., San Dieg...

1. A method for tracking an item, comprising:(a) providing an item comprising a solid polymer material;
(b) irradiating the item to create a spatial pattern of optical modifications in the polymer material, wherein the spatial pattern of optical modifications comprises a code that indicates information; and
(c) detecting the pattern of optical modifications, thereby determining the information; wherein the polymer material comprises (1) a polyimide material; or (2) a silicon-based polymer.

US Pat. No. 10,460,139

SYSTEM AND METHOD FOR UNIQUE IDENTIFIER DETECTION BASED ON INVISIBLE LIGHT

Intuit Inc., Mountain Vi...

1. A unique identifier detection system, comprising:a first object comprising a first object housing;
a first invisible light source coupled to the first object housing and configured to emit first invisible light;
a first opaque substrate coupled to the first object housing, the first opaque substrate comprising material opaque to invisible light emitted by the first invisible light source, the first opaque substrate defining a first aperture design configured to receive the first invisible light from the first invisible light source and to form a first identification pattern, wherein the first aperture design comprises a first one or more apertures defined by the first opaque substrate;
a second object comprising a second object housing;
a second invisible light source coupled to the second object housing and configured to emit second invisible light;
a second opaque substrate coupled to the second object housing, the second opaque substrate comprising material opaque to invisible light emitted by the second invisible light source, the second opaque substrate defining a second aperture design configured to receive the second invisible light from the second invisible light source and to form a second identification pattern distinct from the first identification pattern, wherein the second aperture design comprises a second one or more apertures defined by the second opaque substrate;
a device comprising a device housing;
an invisible light sensor coupled to the device housing and configured to sense the first invisible light and to sense the second invisible light; and
a device control circuit coupled to the device housing and electronically coupled to the invisible light sensor, the device control circuit configured to detect the first identification pattern of the first invisible light and to determine a first object unique identifier based on the first identification pattern, and configured to detect the second identification pattern of the second invisible light and to determine a second object unique identifier based on the second identification pattern.

US Pat. No. 10,460,138

SYSTEMS AND METHODS FOR GENERATING AND READING INTRINSIC MATRIXED BAR CODES

Capital One Services, LLC...

1. A system for embedding an intrinsic matrixed bar code within a video, comprising:at least one processor configured to execute instructions; and
at least one memory storing the instructions to perform operations comprising:
receiving a video having plurality of frames;
selecting a subset of the frames for embedding one or more intrinsic matrixed bar codes;
selecting at least one frame preceding the subset of frames;
generating a first set of registration marks for the selected at least one preceding frame;
selecting coordinates on frames of the subset of frames;
overlaying the one or more bar codes on the selected coordinates;
generating a second set registration marks with the selected coordinates; and
overlaying the first set of registration marks on corresponding frames of the selected at least one preceding frame and the second set of registration marks on corresponding frames of the subset of frames.

US Pat. No. 10,460,137

DYNAMIC RFID TAG SINGULATION USING STATE INFORMATION MASKING

Amazon Technologies, Inc....

1. A method comprising:using a radio frequency identification (RFID) reader, interrogating at least a first RFID tag with a read command comprising a masking value for a predefined portion of a User Memory Bank included in a non-volatile memory (NVM) of the first RFID tag, wherein the predefined portion of the User Memory Bank stores state information for the first RFID tag, wherein the masking value corresponds to a non-quiesced state relative to the read command interrogation;
receiving, responsive to the read command interrogation, a response from the first RFID tag that indicates that the first RFID tag is in the non-quiesced state;
receiving identification information for the first RFID tag;
updating a listing of identified tags using the identification information for the first RFID tag; and
using the RFID reader, interrogating the first RFID tag with a write command that instructs the first RFID tag to write a predefined value to the predefined portion of the User Memory Bank,
wherein writing the predefined value to the predefined portion places the first RFID tag in a quiesced state relative to a subsequent read command interrogation comprising the masking value.

US Pat. No. 10,460,136

TERMINAL FOR MAGNETIC SECURE TRANSMISSION (MST) AND ELECTROMAGNETIC WAVE SHIELDING STRUCTURE

WITS Co., Ltd., Gyeonggi...

1. A magnetic secure transmission (MST) terminal comprising:a body configured to receive a magnetic flux, and comprising a magnetic head and a coil member wound around the magnetic head; and
an electromagnetic wave shielding structure configured to focus the magnetic flux toward the magnetic head, having a surface area increases or decreases in proportion to a distance from the head, and being formed of a magnetic material.

US Pat. No. 10,460,135

FOLDABLE ORGANIC LIGHT EMITTING DIODE (“OLED”) PURCHASING INSTRUMENT READER

Bank of America Corporati...

1. A foldable circuit board comprising:an array of organic light emitting diodes (“OLEDs”) forming a foldable OLED display, the foldable OLED display comprising:
a magnetic read surface area;
a swipe surface area; and
a fold axis;
a magnetic read head embedded within the magnetic read surface area;
a communication circuit;
a processor circuit comprising a non-transitory memory and a processor; and
a power source for powering the OLED display, the communication circuit, the magnetic read head and the processor circuit;wherein, in operation:the foldable OLED display is configured to bend about the fold axis and position the magnetic read surface area adjacent to the swipe surface area to form a swipe channel;
the non-transitory memory stores machine readable instructions that when executed by the processor detect formation of the swipe channel and activate the magnetic read head;
the magnetic read head is positioned to extract information from a purchasing instrument inserted into the swipe channel; and
the communication circuit is configured to transmit the information extracted from the purchasing instrument to a remote server.

US Pat. No. 10,460,134

SMARTCARD AND COMPUTER QUICK CONNECT AND RELEASE SYSTEM

IALL-TECH LLC, Philadelp...

1. An identification system comprising:a smartcard unit having a length, a width and a thickness less than the length and the width,
the smartcard unit having an internal compartment for receipt of a smartcard so that the smartcard is accessible for reading by an external reader; and
a reader unit comprising a smartcard reader operative to engage the smartcard unit so as to interface communicatively with the smartcard and operative to interface with a computer to enable the computer to communicate with the smartcard;
wherein the reader unit includes a reader unit alignment structure or a portion of the reader unit engages with a corresponding smartcard unit alignment structure to align the reader unit and the smartcard unit in an alignment for communicative interfacing;
wherein the reader unit including a reader head with a plurality if contacts on an external surface of the reader head, the reader head having internal wiring connected to the contacts, the contacts defining a reader interface that is configured to contact with corresponding contacts on an external surface of the smartcard unit when the reader unit and the smartcard unit are in said alignment thereby effecting said communicative interfacing;
the reader unit including a flexible cable with a first end attached to the reader head and a second end connectable to another component in the system for providing a path for communication between the internal wiring in the reader head and the other component, the flexible cable including a computer connector adapted to removably attach to the computer and;
wherein at least one of the reader unit and the smartcard unit has a retainer operative to secure the reader unit to the smartcard unit with sufficient pressure that when the smartcard unit is being worn by a user the alignment for communicative interfacing is maintained, and
wherein the retainer includes a magnet for attaching the reader head to the smartcard unit by a magnetic force such that the reader head is separable from the smartcard unit by application of a separation force acting along the flexible cable in one of a plurality of directions relative to the retainer, the separation force being greater than the magnetic force;
wherein the retainer is configured to make the reader unit and the smartcard unit reversibly separable in a plurality of directions without damaging the reader head, the flexible cable and the smartcard unit.

US Pat. No. 10,460,133

SYSTEMS AND METHODS FOR CORRECTION OF ON-STRIP CODING

Trividia Health, Inc., F...

1. A diagnostic test strip comprising:a base code comprising information that allows a meter designed to work with a plurality of diagnostic test strips to convert raw signal data from one or more electrodes on the plurality of diagnostic test strips into a meaningful concentration value for an analyte of interest; and
a modified code being different from the base code of the plurality of diagnostic test strips,
wherein the modified code modifies information encoded by the base code based on a difference in an average value for the plurality of diagnostic test strips of one or more strip geometry parameters, one or more chemistry parameters, or both the one or more strip geometry parameters and the one or more chemistry parameters and a corresponding value for the diagnostic test strip.

US Pat. No. 10,460,132

SECURITY KEYS ASSOCIATED WITH IDENTIFICATION OF PHYSICAL USB PROTECTION DEVICES

HIGH SEC LABS LTD, Yokne...

1. A method of protecting a protected computing device comprising:A) a preparation stage comprising:
providing a plurality of USB protection devices, wherein each of the protection devices comprises an authentication chip for interacting with a security software;
obtaining identification of said plurality of USB protection devices;
entering said identification of said plurality of USB protection devices into an organization database;
installing said security application in the protected computing device;
loading security keys associated with each of said identification of said plurality of USB protection devices from said organization database to said security application in the protected computing device;
installing said plurality of USB protection devices into USB connectors of the protected device; and
qualifying said plurality of USB protection devices by said security application; and
B) an operation stage comprising:
monitoring said plurality of USB protection devices by said security application;
detecting at least one security event associated with at least one of said USB protection devices by said security application; and
disabling the normal operation of the protected computing device by said security application.

US Pat. No. 10,460,131

PREVENTING ACCESS OF A HOST DEVICE TO MALICIOUS DATA IN A PORTABLE DEVICE

SANDISK TECHNOLOGIES LLC,...

1. A method for protecting a host device, comprising:performing a mutual authentication between a storage device and the host device using a key exchange mechanism, the storage device contains a read only partition and a removable partition;
copying a protection application from the read only partition of the storage device to a memory in the host device, wherein the storage device is connected to the host device;
running the protection application on the host device, wherein the protection application restricts access from the removable partition of the storage device by the host device;
then requesting, by the protection application, access to a file allocation table data of the removable partition for analyzing information stored therein;
then sending the file allocation table data to the protection application on the host device;
then analyzing the file allocation table data;
determining if the protection application on the host device has finished a scanning of the file allocation table data; and
pursuant to the finishing of the scanning of the file allocation table data, sending an expose command to a controller of the storage device to notify that the data in the removable partition of the storage device is safe and available for use by the host device.

US Pat. No. 10,460,130

MECHANISM TO PROTECT A DISTRIBUTED REPLICATED STATE MACHINE

Amazon Technologies, Inc....

1. A computer-implemented method, comprising:obtaining:
a first checksum generated by a first computer system based at least in part on a first set of ordered database operations on a database; and
a second checksum generated by a second computer system based at least in part on a second set of ordered database operations on the database;
determining that a sequence of database operations comprising operations associated with the first set and the second set is obtained in order by at least:
parsing the sequence of database operations to obtain a first set of ordered operations, the first set associated with the first computer system;
generating a first output based at least in part on the first set, wherein the first output matches the first checksum;
parsing the sequence of database operations to obtain a second set of ordered operations, the second set associated with the second computer system; and
generating a second output based at least in part on the second set, wherein the second output matches the second checksum; and
generating a third checksum based at least in part on the first set and the second set to indicate the sequence is in order, wherein the third checksum indicates whether the sequence has been altered, and further wherein a different sequence of database operations can be parsed to generate outputs that match the first checksum and the second checksum.

US Pat. No. 10,460,129

SYSTEM AND METHOD FOR MANAGING COOPERATIVE SYNTHETIC IDENTITIES FOR PRIVACY PROTECTION THROUGH IDENTITY OBFUSCATION AND SYNTHESIS

CA, Inc., New York, NY (...

1. A method, comprising:receiving, from a first requestor, a request to create a cooperative synthetic identity case for an original identity;
determining whether a cooperative synthetic identity case has already been created for the original identity;
in response to determining that the cooperative synthetic identity case has not already been created for the original identity, generating the cooperative synthetic identity case by replacing all personally identifiable information associated with the original identity with corresponding synthetic information;
generating a case identifier that uniquely identifies the cooperative synthetic identity case;
associating the case identifier with an expiration period;
storing the cooperative synthetic identity case, the case identifier, and the expiration period to a single memory;
associating the cooperative synthetic identity case with the personally identifiable information of the original identity;
storing the association between the cooperative synthetic identity case and the personally identifiable information of the original identity to the single memory; and
sending the case identifier to the first requestor.

US Pat. No. 10,460,128

COLLECTION FLOW FOR CONFIDENTIAL DATA

Microsoft Technology Lice...

1. A computerized method comprising:in a training phase:
obtaining a plurality of pieces of sample labeled information with sample missing attribute values identifying attribute values missing from the sample labeled information;
for each of the plurality of pieces of sample labeled information:
extracting one or more features from the piece of sample labeled information;
feeding the extracted one or more features and the sample missing attribute values into a machine learning algorithm to train an attribute inference model to output missing attribute values for the sample missing attribute values based on the extracted one or more features;
in an attribute inference phase:
obtaining information about a user;
passing the information to the attribute inference model to generate one or more attribute values for attribute values missing in the information;
modifying a collection flow, defined in a user interface of a computing device, based on the generated one or more missing attribute values, the collection flow defining a sequence of screens; and
presenting the modified collection flow to the user in the user interface.

US Pat. No. 10,460,127

SYSTEM AND METHOD USING A DATABASE FOR ENHANCED USER INITIATED REQUESTS OF MATERIAL OR INFORMATION

United States Postal Serv...

1. A method of providing material based on a user-initiated request in a system including at least a plurality of computing devices, a server, a network and an electronic database, the method comprising:receiving, at a server via a network, a data structure from each business of a plurality of businesses, wherein the data structure maps selected keyword combinations to corresponding icons and/or links, and to particular information or material corresponding to each keyword combination;
storing each of the received data structures in an electronic database;
presenting one or more icons and/or links associated with search results having at least a portion of corresponding selected keywords using the stored data structures, wherein the icons and/or links are displayed adjacent to associated search result items on an electronic display of a computing device of the plurality of computing devices corresponding to a particular user;
receiving click event data of a particular icon or link selected by the particular user;
presenting an application or form requesting contact data of the particular user;
receiving the contact data of the particular user;
storing the contact data of the particular user in a record of an initial table of an electronic database;
transforming data in at least one or more fields of the record for the particular user in the initial table to generate a record for the particular user in a sanitized table of the electronic database; and
causing the sending of particular material received from one of the businesses of the plurality of businesses, the particular material corresponding to the user-initiated request using the selected icon and/or link and contact data for the particular user obtained from the sanitized table.

US Pat. No. 10,460,126

PROVIDING USER CONTROL OF SHARED PERSONAL INFORMATION

Adobe Inc., San Jose, CA...

1. In a digital environment for allowing users to control sharing of personal information, a method of verifying a digital transaction history of users, the method comprising:receiving, from a client device associated with a user, an encoded verification request to provide a lifetime value verification of the user to a third-party provider, wherein the encoded verification request is encoded with a private security token at the client device and directly authorized by the user at the client device associated with the user;
determining whether the user satisfies the lifetime value verification based on:
decoding the encoded verification request;
identifying, within the verification request, a threshold value to verify;
analyzing transaction records within a blockchain associated with the user to generate a user lifetime value; and
comparing the user lifetime value to the threshold value; and
providing, to a computing device associated with the third-party provider, a verification result indicating that the user satisfies the lifetime value verification or indicating that the user does not satisfy the lifetime value verification.

US Pat. No. 10,460,125

APPARATUS AND METHOD FOR AUTOMATIC QUERY PROCESSING

Samsung Electronics Co., ...

1. An apparatus for automatic query processing comprising:a processor configured to:
extract a query condition from an input query;
create one or more first sub-queries based on the input query;
determine whether the one or more first sub-queries is required to be executed recursively based on the query condition;
based on the one or more first sub-queries being required to be executed recursively, determine a search interval for executing the one or more first sub-queries recursively based on characteristics of primary information required for executing the one or more first sub-queries and update rules for the primary information;
execute the one or more first sub-queries at the determined search interval, recursively;
verify whether the query condition is satisfied based on each of results of executing the one or more first sub-queries recursively; and
based on verifying that the query condition is satisfied, provide searched information of the input query based on the results of executing the one or more first sub-queries.

US Pat. No. 10,460,124

PER-VOLUME TENANT ENCRYPTION AND EXTERNAL KEY MANAGER

NetApp, Inc., Sunnyvale,...

1. A server node comprising:a processor; and
a computer-readable medium having program code stored therein, the program code executable by the processor to cause the server node to, based on receipt of a request from a client: write data to a storage volume, compress the data;
calculate a first tweak value based on identification of the storage volume; vary the compressed data according to the first tweak value; select one of a plurality of encryption schemes based on the request, wherein the selected encryption scheme uses an encryption key stored on the server;
encrypt the compressed, varied data according to the encryption key to yield compressed, varied and encrypted data to prevent identification of the data by unauthorized decryption from another client;
hash the compressed, varied and encrypted data to yield one or more hash values as one or more block identifiers; and
communicate the compressed, varied and encrypted data to a set of one or more server nodes based, at least in part, on the one or more block identifiers for the set of one or more server nodes to store the compressed, varied and encrypted data.

US Pat. No. 10,460,123

SYSTEM AND METHOD FOR AUTOMATICALLY SECURING SENSITIVE DATA IN PUBLIC CLOUD USING A SERVERLESS ARCHITECTURE

Capital One Services, LLC...

15. A method for executing jobs immediately upon receipt of a notification, the method comprising:receiving a notification that a sensitive file comprising sensitive data has been received at a file receipt location;
generating a first container instance in response to the notification;
receiving, from the first container instance, a report to the cloud compute service terminating the first container instance based on the report; and
generating a second container instance in response to the notification.

US Pat. No. 10,460,122

DYNAMIC PERMISSION MODES

Qumulo, Inc., Seattle, W...

1. A method for managing data in a file system over a network using one or more processors that execute instructions to perform actions, comprising:instantiating a file system engine to perform actions including:
providing a file system that includes one or more file system objects, wherein the one or more file system objects are accessible by two or more clients that use different native permission schemes;
receiving, from a client, an access request that is associated with the one or more file system objects, wherein the access request includes one or more native permission values that are supported by the client;
providing one or more other requested permission values included in another access request from another client, wherein the other access request is associated with the one or more file system objects, and wherein the one or more other requested permission values are unsupported by the native permission scheme used by the client; and
associating the one or more requested permission values and the one or more other permission values with the one or more file system objects; and
instantiating a permissions engine to perform actions including:
determining one or more map rules based on one or more characteristics of the access request, wherein the one or more map rules include computer readable instructions that map native permission values to platform permission values from a platform permission scheme;
executing the one or more map rules to provide one or more platform permission values based on the one or more native permission values, wherein the one or more platform permission values are associated with the one or more file system objects, and wherein the platform permission scheme reduces latency and improves efficiency of computing resources employed to access the one or more file system objects by replacing use of the two or more different native permission schemes to define access rights to the one or more file system objects;
comparing one or more requested platform permission values to the platform permission values associated with the one or more file system objects; and
providing the access rights to the one or more file system objects based on an affirmative result of the comparison.

US Pat. No. 10,460,121

ELECTRONIC AUTHORIZATION DEVICE

Robert Bosch GmbH, Stutt...

1. A method for authorizing use of at least one power tool with an electronic authorization device having a sensor unit and an evaluation unit, the method comprising:sensing with the sensor unit a body parameter of a user that includes at least one of a blood pressure, a pulse rate, and a body temperature of the user;
evaluating the sensed body parameter with the evaluation unit;
determining authorization information based on the evaluated body parameter with the evaluation unit; and
enabling or disabling operation of the power tool based on the determined authorization information with the electronic authorization device.

US Pat. No. 10,460,120

POLICY MEDIATED HIERARCHICAL STRUCTURES IN KEY VALUE STORES

Amazon Technologies, Inc....

1. A computer-implemented method, comprising:simulating a multi-level hierarchy in a keyspace having a flat hierarchy and being represented in a key-value store, the keyspace including a plurality of key-value pairs associated with a plurality of objects stored in connection with a computer system, by at least:
generating a redirecting key-value pair for storage in the key-value store, the redirecting key-value pair having:
a key that indicates a redirect name for a subset of the plurality of key-value pairs directed to an indicator of a directory to be represented comprising a set of more than one object including a subset of the plurality of objects other than the redirecting key-value pair, and
a value that indicates a namespace associated with the subset of the plurality of key-value pairs directed to the subset of the plurality of objects;
assigning a delimiter that, when invoked, activates a redirect for requests associated with the redirecting key-value pair; and
associating, to the multi-level hierarchy, a policy that applies to the multi-level hierarchy so as to control a requestor's access to the multi-level hierarchy; and
in response to a request invoking the delimiter,
processing the policy, based at least in part on verifying that a requested redirect name in the request matches the key of the redirecting key-value pair, to perform one or more actions in accordance with the request.

US Pat. No. 10,460,119

IDPS ACCESS-CONTROLLED AND ENCRYPTED FILE SYSTEM DESIGN

Intuit Inc., Mountain Vi...

1. A method comprising: managing, with a resource management module of a computing system, a storage container including data, the storage container being configured to ensure that a managed file system of the storage container is able to launch on a second computing entity after having been removed from a first computing entity, the resource management module being a component of a kernel of an operating system of the computing system;hosting, with the resource management module, a virtual file system including a plurality of files representing the data;
generating, with an access control and encryption module, a plurality of application containers, including individual application containers for each respective user each application container including a user-specific list of files of the virtual file system a particular user associated with a particular application container is authorized to access and a list of processes authorized for the particular user, the user-specific list of files of the virtual file system further mapping one or more specific files to authorized processes authorized to access files of the one or more specific files, wherein each application container only has access to encryption keys for files stored therein and each user only has access to files of the application container, and only processes, programs, applications and other executables listed in a process list of the application container are allowed to access files of the application container;
creating an access control scenario wherein access to the plurality of application containers is governed by an agent whereas all real data is written directly to the virtual file system, the agent depending on a user-defined policy including access-control entities and rules denying access to root users, and wherein if a file, process, user application is not associated with a given user, the given user is denied access to the file, process or user application;
encrypting, with the access control and encryption module, each file of the virtual file system with unique randomly-generated file encryption keys specific to individual files, wherein there is a one-to-one correspondence between the unique randomly-generated file encryption keys and files in the virtual file system;
encrypting the unique randomly-generated file encryption keys;
receiving, with the access control and encryption module, a request from an application program process of a user to access data within a particular file in the virtual file system;
determining whether the application program process of the request is mapped in the list of processes to the particular file, and further determining whether the user is also authorized access to the data of the particular file, and if either the application program process of the request is not mapped in the list of processes to the particular file or the user is not authorized access to the data of the particular file, denying the access request;
decrypting, responsive to determining that the application program process of the request is mapped in the list of processes to the particular file and determining that the user is also authorized access to the data of the particular file, with the access control and encryption module, the unique encryption key for the particular file; and
outputting, with the access control and encryption module, the decrypted particular file to the user.

US Pat. No. 10,460,118

SECURE STORAGE AUDIT VERIFICATION SYSTEM

Workday, Inc., Pleasanto...

1. A system for secure storage audit verification comprising:a transaction pool; and
a processor configured to:
verify a transaction stored in the transaction pool, wherein the transaction comprises one of the following: a key request by a Key Management System (KMS), a consumption of a released key by the KMS, a key released by the KMS, or a key released by a Key Release System (KRS);
sign a proposed block, wherein the proposed block is based at least in part on the transaction;
receive a counter signed proposed block;
add the counter signed proposed block to a blockchain;
determine whether the transaction has occurred based at least in part on the blockchain;
in response to a determination that the transaction has occurred, indicate that secure storage associated with the transaction is verified, and
in response to a determination that the transaction has not occurred, indicate that secure storage processing is suspended.

US Pat. No. 10,460,117

SYSTEM AND METHOD FOR REMOVING INTERNET ATTACK SURFACE FROM INTERNET CONNECTED DEVICES

1. A system for removing attack surface between data isolated devices that share their input output means comprising:User device configured to connect to a network and interact with a user through shared input output means wherein said input output means comprising at least a user display and a user input means;
Secure device coupled to said user device for processing data and interacting with said user at least partly using said shared input output means wherein said secure device is configured to prevent any data communication and data access from said user device and wherein data from said shared input output means is at least partially inaccessible to said user device when used by said secure device;
Remote secure device for communicating with said secure device over the network said secure device configured to use said user device network connection at least partly for communicating with said remote secure device wherein at least part of said remote secure device communication data with said secure device is not accessible to said user device whereby said secure device interacts with said user using said shared input output means and communicates data based on said interaction with said remote device with no attack surface from said coupled user device.

US Pat. No. 10,460,116

ACCESS CONTROL METHOD, SYSTEM AND STORAGE MEDIUM

SUMITOMO MITSUI BANKING C...

1. A control method for access to information, the method being executed by a global credit management system, the global credit management system comprising at least one information management unit, at least one corresponding database storing information to be provided by the at least one information management unit and an accessibility determination unit, and the method comprising:receiving, by the accessibility determination unit, a login ID of a user;
determining, by the accessibility determination unit, roles & responsibilities associated with the login ID and an entity to which the user belongs;
receiving, by at least one information management unit, a request for access to an information stored in the at least one corresponding database;
extracting, by the at least one information management unit from the at least one corresponding database, conditions necessary for accessing information stored in the at least corresponding database, and providing, by the at least one information management unit, the extracted conditions to the accessibility determination unit; and
determining, by the accessibility determination unit based on the conditions, accessibility of information that the user attempts to access, wherein determining the accessibility is executed based on:
a) determining an entity managing information that the user attempts to access;
b) determining an access control pattern based on laws and regulations associated with the entity managing the information that the user attempts to access;
c) determining whether the access control pattern based on the laws and regulations is satisfied based on a relation between the entity to which the user belongs and the entity managing the information that the user attempts to access, wherein determining by the global credit management system that access is enabled only when the entity to which the user belongs, belongs to the same entity group to which the entity managing the access control pattern of the requested information belongs and is located in the same country where the entity managing the access control pattern of the requested information is located;
d) determining whether the information that the user attempts to access is accessible with the roles & responsibilities associated with the login ID.

US Pat. No. 10,460,115

DATA ANONYMITY

International Business Ma...

1. A system, comprising:a memory storing a program which, when executed on a processor, performs an operation for ensuring anonymity of data, the operation comprising:
determining a number of members of each of a plurality of clusters, based on one or more features of members leaving the cluster; and
anonymizing the data in the database, easing the determined number of members of each cluster, wherein the one or more features of the leaving members from the cluster are selected from the group consisting of a ratio of leaving, a period for leaving, a cause of leaving, or a combination thereof; wherein the database has the period for leaving for each member; wherein the determination is made by calculating a required minimum number, N, for the members in each cluster, based on the ratio of leaving; wherein the anonymization is performed using k-anonymization with k being the retired minimum number, N, and wherein, in the database, assuming that the value, k, for the k-anonymization is Y after a passage of a first predefined term, X, the required minimum number, N, is calculated based on Y.

US Pat. No. 10,460,114

IDENTIFYING VISUALLY SIMILAR TEXT

Amazon Technologies, Inc....

1. A computer-implemented method, comprising:receiving a request to access a uniform resource locator (URL);
performing optical character recognition (OCR) on an at least a portion of the image of the URL to extract text;
determining whether extracted text from the performed OCR matches a second domain name in a list of domain names;
performing a bitwise comparison of the domain name in the URL to the second domain name in the list of domain names upon determining that the extracted text matches the second domain name;
preventing the request to access the URL from proceeding upon determining that the bitwise comparison does not match the second domain name in the list of domain names.

US Pat. No. 10,460,113

SECURITY FIX OF A CONTAINER IN A VIRTUAL MACHINE ENVIRONMENT

International Business Ma...

1. A method for a security fix of a container in a VM (virtual machine) environment, the method comprising:detecting, by a computer, a container in a container environment, wherein in the container environment the container shares a single kernel with other one or more containers;
determining, by the computer, whether the container in the container environment has a security issue;
creating, by the computer, a virtual machine in a VM (virtual machine) environment, wherein in the VM environment the virtual machine is isolated from other one or more virtual machines;
migrating, by the computer, the container from the container environment to the virtual machine in the VM environment, in response to determining that the container has the security issue;
fixing, by the computer, the security issue of the container in the virtual machine in the VM environment;
determining, by the computer, whether the security issue is fixed in the virtual machine in the VM environment; and
migrating, by the computer, a snapshot of the virtual machine in the VM environment to a new container in the container environment, in response to determining that the security issue is fixed in the virtual machine in the VM environment.

US Pat. No. 10,460,112

SYSTEM AND METHOD FOR PRIVACY LEAKAGE DETECTION AND PREVENTION SYSTEM WITHOUT OPERATING SYSTEM MODIFICATION

Northwestern University, ...

1. A taint-tracking system using a taint-storage data-structure, the taint-tracking system comprising:a hashtable configured to operate in multi-threaded applications, a taint stored in the hashtable;
a key of the hashtable including a weak reference to objects so that taint-storage does not interfere with garbage collection of an underlying runtime;
values of the hashtable comprising records containing the taint and a set of objects that may point to containing objects referred to by the key; and
an instrumentation module comprising a processor and memory, configured to handle taint propagation through framework code using a policy based application programming interface summarization, combined with storing relationships of containing objects so that changes in taints in an object may trigger taint changes in containing objects in keeping with the policy, where the instrumentation module is static to prune code paths that are proven to not carry sensitive information and to instrument only paths along which privacy leakage may happen, and the framework code is not modified, and where the instrumentation module is configured to dynamically track a flow of privacy-sensitive information along the path.

US Pat. No. 10,460,111

SYSTEM AND METHOD TO ISOLATE HOST AND SYSTEM MANAGEMENT IN AN INFORMATION HANDLING SYSTEM

Dell Products, LP, Round...

1. An information handling system comprising:a central processing unit to execute an operating system of the information handling system;
a memory to store a boot image for a boot process of the information handling system; and
a service processor to execute the boot image to perform the boot process, and the execution of the boot image to cause the service processor to:
detect whether an isolation profile is enabled within the boot process, wherein the isolation profile is enabled in response to a signal provided by a host device external to the information handling system based on the operating system being compromised; and
in response to the isolation profile being enabled, to disable Intelligent Platform Management Interface system management from the operating system to prevent system management access by the compromised operating system to the service processor.

US Pat. No. 10,460,110

SYSTEMS AND METHODS FOR UNLOCKING SELF-ENCRYPTING DATA STORAGE DEVICES

Seagate Technology LLC, ...

1. An apparatus comprising:a data storage device configured to:
removably connect to a first server having a first operating system configured to perform native operating system functions of the first server;
load a second operating system stored locally in the data storage device into the memory of the first server, the second operating system configured to execute security functions of the data storage device, including:
unlocking a first secure area of the data storage device;
retrieving a first access key from the first secure area;
unlocking a second secure area of the data storage device with the first access key;
determining a second access key based on information stored to the second secure area; and
unlocking a secure storage area of another data storage device with the second access key.

US Pat. No. 10,460,109

MALICIOUS PROGRAM IDENTIFICATION BASED ON PROGRAM BEHAVIOR

iboss, Inc., San Diego, ...

1. A method performed by data processing apparatus, the method comprising:receiving, by a network gateway, a message from outside of a network addressed to a device inside the network, the message containing a data object;
replacing instructions in the data object that request sensitive actions with corresponding instructions that pass requests for sensitive actions to an execution manager, the execution manager configured to examine the requests for sensitive actions before they are provided to the computing device;
executing the data object by the network gateway;
in response to the execution of the data object, determining that the data object has requested a sensitive action before the data object has attempted an interaction with a user; and
in response to determining that the data object has requested the sensitive action, classifying the data object as a high-risk data object.

US Pat. No. 10,460,108

METHOD AND SYSTEM TO IDENTIFY AND RECTIFY INPUT DEPENDENCY BASED EVASION IN DYNAMIC ANALYSIS

Trend Micro Incorporated,...

1. A computer-implemented method to counteract evasive code, the method comprising:executing a code sample by a sample process under control of an analysis platform; and
performing a recursive and iterative procedure to determine a significant path from a conditional value evaluation statement and avoid execution flow of the sample process from deviating from the significant path,
wherein the recursive and iterative procedure comprises:
triggering a checkpoint during the execution of the code sample;
determining whether the checkpoint is in an image space of the sample process or an image space of an external procedure; and
when the checkpoint is in the image space of the external procedure, setting a return checkpoint on a return address for the external procedure.

US Pat. No. 10,460,107

SYSTEMS AND METHODS FOR AUTOMATIC SNAPSHOTTING OF BACKUPS BASED ON MALICIOUS MODIFICATION DETECTION

Carbonite, Inc., Boston,...

1. A method comprising: detecting, by a backup system in communication with multiple computing devices, legitimate file activity occurring on the multiple computing devices, wherein the legitimate file activity comprises sharing a file;calculating, by the backup system, at least one file activity threshold based on patterns of the legitimate file activity occurring over time on different ones of the multiple computing devices;
detecting, by a backup agent in communication with the backup system, a plurality of client file activities occurring over time on a client device of the multiple computing devices;
and preventing, by the backup agent, modification of previously backed up data of the client device responsive to the client file activities exceeding the file activity threshold wherein the calculating of the file activity threshold comprises:
aggregating, by the backup system, file activity rates received from the computing devices;
and setting, by the backup system, the file activity threshold by multiplying the file activity rates by a percentage based on statistical confidence of the file activity rates.

US Pat. No. 10,460,106

METHOD AND DEVICE FOR IDENTIFYING COMPUTER VIRUS VARIANTS

ALIBABA GROUP HOLDING LIM...

1. A method of identifying computer virus variants, the method comprising:running a virus sample to be tested;
generating and recording a sample application program interface (API) call sequence that represents runtime characteristic behavior performed by the virus sample produced during the running of the virus sample;
obtaining a plurality of characteristic API call sequences and a plurality of key API call sequences, the plurality of characteristic API call sequences respectively correspond to and respectively represent runtime characteristic behavior performed by a plurality of virus families, each characteristic API call sequence having a corresponding key API call sequence in the plurality of key API call sequences, wherein each of the corresponding key API call sequences comprises API calls that represent impactful key APIs used in operation by a respective virus family of the plurality of virus families;
for each of the plurality of characteristic API call sequences, determining a number of characteristic API calls that are in the sample API call sequences;
when the number of characteristic API calls that are in the sample API call sequences reaches a first set limit, generating an indication that the virus sample is likely virus;
when the number of characteristic API calls that are in the sample API call sequences lies below the first set limit, for each of the plurality of key API call sequences, determining a number of key API calls that are in the sample API call sequence; and
when the number of key API calls that are in the sample API call sequence reaches a second set limit, generating an indication that the virus sample may be a virus.

US Pat. No. 10,460,105

ENDPOINT MALWARE DETECTION USING AN EVENT GRAPH

Sophos Limited, Abingdon...

5. A method for malware detection comprising:instrumenting a first endpoint to monitor a number of causal relationships among a number of computing objects at a first set of logical locations within a computing environment related to the first endpoint;
excluding, from the first set of logical locations, at least one logical location associated with a known, good process;
recording a sequence of events causally relating the number of computing objects at the first set of logical locations excluding the at least one logical location associated with the known, good process;
creating an event graph based on the sequence of events;
applying a malware detection rule to the event graph; and
remediating the first endpoint when the malware detection rule and the event graph indicate a compromised security state.

US Pat. No. 10,460,104

CONTINUOUS MALICIOUS SOFTWARE IDENTIFICATION THROUGH RESPONSIVE MACHINE LEARNING

Alert Logic, Inc., Houst...

1. A security system for securing and responding to security threats in a computer having a Central Processing Unit (CPU), a Kernel/Operating System, and a plurality of software applications, the system including:a data collector module in the form of a hypervisor and/or kernel module implemented with the CPU, configured to intermediate a predetermined selection of first tier calls between the CPU and the Kernel/Operating System and/or second tier calls between the Kernel/Operating System and the applications, and to store information pertaining to the intermediated first tier calls (first tier call IDs) and/or to the intermediated second tier calls (second tier call IDs) in a data store, the data collector module being configurable in real-time to selectively enlarge or contract the predetermined selection of first tier calls;
an Analytic Engine, implemented in user space of the computer, configured to aggregate and map the stored first tier call IDs and/or second tier call IDs to a machine learning (ML) Model to generate a threat analysis, the ML Model including patterns of first tier call IDs associated with identifiable security threats;
the Analytic Engine being configured to selectively enlarge or contract the predetermined selection of first tier calls and/or second tier calls to respectively increase or decrease specificity of said threat analysis;
the Analytic Engine being further configured to implement one of more of a plurality of responsive actions in response to said threat analysis; and
a Management Module communicably coupled to the ML Model and/or to the kernel module, the collector module, and the Analytic Engine, the Management Module configured to generate a plurality of user interfaces accessible by a user computer communicably couplable to the system, the user interfaces configured to enable a user to update the ML Model and configure the collector module and the Analytic Engine.

US Pat. No. 10,460,103

SECURITY FOR DEVICES CONNECTED TO A NETWORK

International Business Ma...

1. A system of providing security for a device comprising:at least one hardware processor configured to:
monitor a plurality of networked devices for a security risk, wherein each networked device is associated with a corresponding security risk tolerance for initiating actions to alleviate the security risk and a corresponding remediation risk tolerance indicating a risk level associated with performance of the actions to alleviate the security risk on that networked device;
determine the risk level associated with performing the actions on the plurality of networked devices based on outcomes of prior performance of the actions to alleviate security risks, wherein the risk level associated with performing the actions on the plurality of networked devices is further based on a trust level of a source providing the actions, and wherein a greater trust level of the source produces a lower risk level relative to the risk level produced from a lower trust level of the source; and
in response to a monitored security risk for one or more of the plurality of networked devices exceeding the corresponding security risk tolerance:
determine one or more actions with a risk level from performance satisfying the corresponding remediation risk tolerance for each of the one or more networked devices; and
initiate at the system a network service provided to the one or more networked devices to perform the determined one or more actions on each of the one or more networked devices to alleviate the monitored security risk.

US Pat. No. 10,460,102

COGNITIVE LEARNING TO COUNTER SECURITY THREATS FOR KINEMATIC ACTIONS IN ROBOTS

International Business Ma...

1. A method of countering security threats for kinematic actions in robots comprising:receiving input instructions for a kinematic robot, by executing first instructions in a computer system;
conducting an analysis of the input instructions using a cognitive system which maps proposed instructions to either legitimate behavioral actions or illegitimate behavioral actions based on contextual variables relating to a context of the input instructions, by executing second instructions in the computer system;
computing a security anomaly index score based on the analysis wherein the security anomaly index score represents a variance of a likely kinematic action of the kinematic robot in response to the input instructions compared to acceptable actions, by executing third instructions in the computer system, wherein different numeric weights are applied to the contextual variables and said computing begins with a default value for the security anomaly index score and thereafter increments or decrements the security anomaly index score based on the weights;
determining that the security anomaly index score exceeds a predetermined threshold, by executing fourth instructions in the computer system; and
responsive to said determining, generating a security alert for an administrator of the kinematic robot, by executing fifth instructions in the computer system.

US Pat. No. 10,460,101

ENRICHING NETFLOW DATA WITH PASSIVE DNS DATA FOR BOTNET DETECTION

Microsoft Technology Lice...

1. A system comprising:a processor;
memory; and
a botnet detection application that is stored in the memory and executed by the processor and that is configured to:
obtain Netflow data indicating one or more IP addresses accessed by a computer;
obtain passive Domain Name System (DNS) data indicating respective one or more domains associated with each of the one or more IP addresses;
generate features associated with the computer based on the Netflow data and passive DNS data;
generate probability data based on the Netflow data and passive DNS data, wherein the probability data indicates a probability that the computer accessed the one or more domains, and wherein, in one or more instances, the probability is determined using a computed probability distribution over the one or more IP addresses and/or the one or more domains;
assign weights to the features based on the probability data to provide weighted features; and
determine whether the computer is likely to be part of a botnet based on the weighted features.

US Pat. No. 10,460,100

INJECTION OF DATA FLOW CONTROL OBJECTS INTO APPLICATION PROCESSES

Hewlett-Packard Developme...

1. A non-transitory computer readable storage medium including executable instructions that, when executed by a processor, cause the processor to:execute a callback that is assigned, using at least one of a kernel module and management instrumentation of an operating system, to a creation event of an application process; and
in response to the execution, inject a data flow control object into the application process prior to the application process having any chance of making system calls to the operating system, the data flow control object to intercept a system call made by the application process and to control flow of data being handled by the system call wherein data is not exported out of the operating system unprocessed by the data flow control object prior to the injection.

US Pat. No. 10,460,099

SYSTEM AND METHOD OF DETECTING MALICIOUS CODE IN FILES

AO Kaspersky Lab, Moscow...

1. A computer-implemented method for detecting malicious code in files, the method comprising:intercepting, by a processor, one or more application program interface (API) calls during an execution of a process launched from a file of a computing device;
detecting, by the processor, a fulfillment of an exit condition of the process, wherein the exit condition is based on weights assigned to types of suspicious events;
in response to detecting the exit condition, identifying one or more signatures of a first type and transferring one or more saved memory dumps of the computing device to an emulator for execution, wherein the execution of the transferred one or more saved memory dumps of the computing device in the emulator comprises disassembling one or more executable codes contained in the one or more saved memory dumps and maintaining in succession in a second log records of the intercepted API calls, wherein each record in the second log contains information for an API function called, the information including a unique identifier (PID) of a process launched from a corresponding file; and
identifying a malicious code in the file in response to detecting one or more signatures of a second type based at least upon execution results of the transferred memory dumps of the computing device.

US Pat. No. 10,460,098

LINKING DEVICES USING ENCRYPTED ACCOUNT IDENTIFIERS

Google LLC, Mountain Vie...

1. A method comprising:providing an application to a plurality of devices, the application configured to gather account information for services accessed by a given device;
receiving, by a server from a first device, a data package including a first device identifier and a first one-way encrypted account identifier for accounts associated with the first device, wherein account information from the accounts is used, by the first device, to generate the first one-way encrypted account identifier, and wherein the server is unable to decrypt the first one-way encrypted account identifier;
receiving, by the server from a second different device, a data package including a second different device identifier and a second one-way encrypted account identifier generated by the second different device, and wherein the server is unable to decrypt the second one-way encrypted account identifier;
comparing, by the server, the first one-way encrypted account identifier to the second one-way encrypted account identifier;
responsive to the first one-way encrypted account identifier matching the second one-way encrypted account identifier, determining, by the server based on the comparison, that the first device and the second different device are associated with a same user; and
linking, by the server, cookies associated with account-related services of the first device with cookies associated with account-related services of the second different device based on the determination that the first device and the second different device are associated with the same user.

US Pat. No. 10,460,097

MALICIOUS CLIENT DETECTION BASED ON USAGE OF NEGOTIABLE PROTOCOLS

Amazon Technologies, Inc....

1. A computer-implemented method comprising:communicating, via a cryptographically protected communications session with a computer system, using cryptographically protected communications utilizing a first negotiable feature;
detecting, during the cryptographically protected communications with the computer system utilizing the first negotiable feature, a triggering event;
in response to the triggering event, causing the cryptographically protected communications with the computer system to change from the first negotiable feature to a second negotiable feature during the cryptographically protected communications session; and
initiating a security measure as a result of stored data indicating that the computer system fails to support the second negotiable feature.

US Pat. No. 10,460,096

MOTION-BASED IDENTITY AUTHENTICATION OF AN INDIVIDUAL

Ohio University, Athens,...

1. A method for securely authenticating an identity of an individual based on a pattern that is traced by the individual, comprising:prompting the individual with a three-dimension authentication template that includes a defined three-dimension pattern for the individual to trace, the tracing of the defined pattern including a plurality of motions;
receiving the traced pattern from the individual generated from tracing wherein the plurality of motions generates input motion-based behavior data including behaviometric data associated with behaviometric characteristics of the individual;
obtaining previously captured motion-based behavior data associated with tracing of the defined three-dimension pattern by the individual as reference motion-based behavior data;
determining an inter-relationship of the input motion-based behavior data and an inter-relationship of the reference motion-based behavior data including generating a matrix for the input motion-based behavior data set and a matrix for the reference motion-based behavior data set, the matrices each reflecting the impact of pieces of data in the set on other pieces of data in the same set;
adjusting the input motion-based behavior data to account for the inter-relationship thereof using the matrices; and
comparing the adjusted input motion-based behavior data with the previously captured motion-based behavior data while maintaining the inter-relationship of both the input and reference motion-based behavior data to thereby authenticate the identity of the individual.

US Pat. No. 10,460,095

EARPIECE WITH BIOMETRIC IDENTIFIERS

1. A method of verifying an identity of a user using a set of earpieces comprising a left earpiece and a right earpiece, the method comprising:transducing sound at a speaker of the left earpiece to direct the sound towards a left external auditory canal of the user;
receiving reflected sound at a microphone of the left earpiece, the microphone of the left earpiece positioned to receive reflections from the sound transduced at the speaker of the left earpiece and reflected from the left external auditory canal of the user;
transducing sound at a speaker of the right earpiece to direct the sound towards a right external auditory canal of the user;
receiving reflected sound at a microphone of the right earpiece, the microphone of the right earpiece positioned to receive reflections from the sound transduced at the speaker of the right earpiece and reflected from the right external auditory canal of the user;
processing the reflected sound received at the microphone of the left earpiece to determine a property of the left external auditory canal of the user and processing the reflected sound received at the microphone of the right earpiece to determine a property of the right external auditory canal of the user;
determining if both the property of the left external auditory canal of the user and the property of the right external auditory canal of the user match known properties for a user identity and if so, verifying the identity of the user;
wherein the reflected sound received at the microphone of the left earpiece is conveyed to the processor disposed in the left earpiece over a magnetic inductance linkage between the left earpiece and the right earpiece;
wherein the sound transduced at the speaker of the left earpiece is based on a sound signal generated at the left earpiece which includes one or more randomized components;
wherein the sound transduced at the speaker of the right earpiece is based on a sound signal generated at the left earpiece which includes one or more randomized components and wherein the sound signal is communicated from the left earpiece to the right earpiece over the magnetic inductance linkage between the right earpiece and the left earpiece; and
wherein the sound transduced at the speaker of the left earpiece is different from the sound transduced at the speaker of the right earpiece.

US Pat. No. 10,460,094

METHOD, APPARATUS, AND STORAGE MEDIUM FOR DATA PROCESSING

TENCENT TECHNOLOGY (SHENZ...

1. A data processing method, comprising:outputting a character key entry prompt information on a first user interface of a terminal to carry out a character key access method;
obtaining a character key entered though the first user interface;
performing a configuration permission authentication by comparing the character key with a reference character key stored in the terminal;
only in response to determining that the configuration permission authentication succeeds, configuring a biometric key access method for an encrypted data to obtain a reference biometric key, and the encrypted data being subsequently accessible through the biometric key access method;
obtaining an access configuration of the encrypted data in the terminal when receiving an access request for the encrypted data, the access configuration comprising the biometric key access method;
outputting a biometric key entry prompt information according to the access configuration;
performing a verification by calling a system application programming interface (API) of the terminal to collect a biometric key, when a biometric key entry operation performed according to the key entry prompt information is detected;
obtaining a verification result by comparing the collected biometric key with the reference biometric key; and
responding to the access request according to the verification result when the collected biometric key matches the reference biometric key.

US Pat. No. 10,460,093

TERMINAL DEVICE, METHOD, AND PROGRAM

SONY CORPORATION, Tokyo ...

1. A terminal device comprising:a detector configured to detect a touch operation, the touch operation corresponding to a start of an authentication process for authenticating a user; and
a display controller configured to
display, during the authentication process, an authentication process screen by using a first image included in a first display screen that is displayed after the authentication process succeeds, the authentication process screen having a degree of blurring,
display a second display screen that is displayed before the authentication starts in addition to the first image, the second display screen having a color,
during the authentication process, move the second display screen in a same direction as a direction of the touch operation, reduce the degree of blurring of the authentication process screen, and lighten the color of the second display screen,
in response to the authentication process failing,
deform at least a portion of a shape displayed in the authentication process screen and the second display screen during the authentication process, the shape representing an occurrence of the authentication process, and
move the second display screen in an opposite direction of the direction of the touch operation, and
in response to the authentication process succeeding, further reduce the degree of blurring of the authentication process screen and further lighten the color of the second display screen.

US Pat. No. 10,460,092

FINGERPRINT IDENTIFICATION SYSTEM AND METHOD AND DISPLAY DEVICE

BOE TECHNOLOGY GROUP CO.,...

1. A fingerprint identification system connected with a touch screen, comprising:a fingerprint identification region arranged on the touch screen to acquire an input fingerprint;
a fingerprint verification module connected with the fingerprint identification region and configured to verify whether the input fingerprint is a fingerprint of a user and to unlock the touch screen if it is determined that the input fingerprint is the fingerprint of the user; and
an application start control module connected with the fingerprint identification region and the fingerprint verification module, respectively, and configured to obtain a finger press direction from the input fingerprint and start an application corresponding to the finger press direction when the input fingerprint is the fingerprint of the user, wherein the finger press direction is a direction formed according to an order in which the respective points on the fingertip of the finger contact the fingerprint identification region when the finger presses the fingerprint identification region or a direction opposite thereto; and the finger press direction corresponds to at least one application,
wherein the application start control module comprises:
a direction obtaining unit connected with the fingerprint identification region and the fingerprint verification module, respectively, and configured to obtain the finger press direction based on the input fingerprint when the input fingerprint is the fingerprint of the user;
an angle calculation unit connected with the direction obtaining unit and configured to calculate an angle formed between the finger press direction and a reference direction, the angle being positive in an anticlockwise direction;
a storage unit storing correspondences between preset angle ranges and applications, wherein the preset angle ranges are within a range of 360 degrees in the anticlockwise direction from the reference direction as a starting direction, and each of the preset angle ranges corresponds to at least one application; and
a determination unit connected with the angle calculation unit and the storage unit, respectively, and configured to determine the preset angle range within which the calculated angle falls, retrieve an application corresponding to the calculated angle based on the correspondences between the preset angle ranges and the applications, and start the application.

US Pat. No. 10,460,091

SUPPLEMENTAL HAND GESTURE AUTHENTICATION

International Business Ma...

1. A method of supplemental authentication based on hand gesture activity of a user with an application of a device computer comprising the steps of:after a user has completed a successful authentication challenge to initially access at least the device computer,
the device computer recording hand gesture activity of the user during current use of the application of the device computer at a time other than during an authentication challenge provided to the user for user input;
the device computer comparing the recorded hand gesture activity of the user during current use of the application of the device computer at a time other than during an authentication challenge provided to the user for user input to previously recorded hand gesture activity during use of a same application of the device computer to provide a supplemental authentication of the user of the device computer; and
when the recorded hand gesture activity of the user does not match the previously recorded hand gesture activity during use of the same application, the use of the application of the device computer is halted and an additional authentication challenge requiring input from the user is presented to the user; and
when the additional authentication challenge is passed, resuming the use of the application of the device computer for the user, and updating a hand gesture representation associated with the application of the user with the device computer which is used to compare to current user usage of the application.

US Pat. No. 10,460,090

METHODS AND SYSTEM FOR PASSIVE AUTHENTICATION THROUGH USER ATTRIBUTES

NCR Corporation, Atlanta...

1. A method, comprising:collecting, on a device, data relevant to attributes of a user;
passively authenticating the user based on the data by computing a value based on the data, wherein computing further includes chaining a first instance of a confidence calculator that executes on the device within a first processing environment with a second instance of the confidence calculator that executes on a second and different device within a second and different processing environment to produce the value by computing, by the first instance, a first portion of the value, providing, by the first instance, the first portion to the second instance as input data, computing, by the second instance, a second portion of the value from the first portion, and combining the first portion and the second portion as the value; and
automatically providing the user access to an electronic resource at a particular access level selected from a plurality of access levels based on a difference between a predetermined value and the value.

US Pat. No. 10,460,089

DISPLAY DYNAMIC CONTENTS ON LOCKED SCREENS

Facebook, Inc., Menlo Pa...

1. A method comprising:by a computing device, obtaining a plurality of dynamic information items relevant to a user of the computing device;
by the computing device, ranking the plurality of dynamic information items based at least in part on one or more social factors of the user stored on a social-networking system;
by the computing device, displaying, based at least in part on the ranking, at least one of the plurality of dynamic information items on a locked screen of the computing device; and
by the computing device, in response to user input selecting the at least one displayed dynamic information item being received at the computing device, displaying, on the locked screen of the computing device, detailed content associated with the respective dynamic information item and a user-interface component for performing one or more actions with respect to the displayed dynamic information item, the locked screen being configured to:
allow the user to perform the actions via the user-interface component without unlocking the locked screen if the selected actions are in a first set of actions; and
prevent the user from performing the actions via the user-interface component without unlocking the locked screen if the selected actions are in a second set of actions.

US Pat. No. 10,460,088

ELECTRONIC DEVICE AND CONNECTION METHOD

RICOH COMPANY, LTD., Tok...

1. An electronic device configured to be used with a recording medium, the recording medium having a security-lock function in which a security lock is activated by setting a recording medium password, the electronic device comprising:a communication interface configured to connect with an external device; and
processing circuitry configured to
determine whether or not the communication interface detects that the electronic device and the external device are connected via a cable,
in response to determining that the electronic device is connected to the external device via the cable, display a password input screen and receive an input password,
send, to the recording medium, the input password, and
when the recording medium determines that the input password matches the set recording medium password, receive, from the recording medium, an indication to release the security lock and inform the external device that the recording medium is accessible.

US Pat. No. 10,460,087

METHOD AND APPARATUS TO SECURE AND PROTECT DATA-CENTERS AND GENERALIZED UTILITY-BASED CLOUD COMPUTING ENVIRONMENTS FROM UNINVITED GUESTS IN THE FORM OF BOTH HARDWARE AND SOFTWARE

TELEFONAKTIEBOLAGET LM ER...

1. A method implemented by a network device communicatively coupled to a datacenter to detect a presence of unauthorized software and hardware in the datacenter, the method comprising:initiating deployment of a virtual agent on a node in the datacenter, wherein the virtual agent is to perform a security scan of the node and store results of the security scan in a memory allocated to the virtual agent at the node, and wherein the results of the security scan are to be encrypted by the virtual agent using a data encryption key; and
initiating migration of the virtual agent to a preconfigured location that has been previously configured with a data decryption key for decrypting the results of the security scan prior to the migration of the virtual agent to the preconfigured location, wherein the results of the security scan are to be extracted from the virtual agent and decrypted at the preconfigured location using the data decryption key.

US Pat. No. 10,460,086

MANAGING APPLICATION ACCESS TO CERTIFICATES AND KEYS

BlackBerry Limited, Wate...

1. A method of handling, at a resource manager, a file system request for a data item in a store, the method comprising:receiving, from an application, the file system request, the file system request specifying a path;
parsing the path to isolate a store identifier for the store;
detecting an identity for the application;
determining, based on the identity and the store identifier, that the store is in a namespace of the application, wherein the namespace comprises a list of all stores to which the application has access; and
responsive to the determining, obtaining the data item from a manager of the data item.

US Pat. No. 10,460,085

TABLET COMPUTER

MATTEL, INC., El Segundo...

1. A tablet computer, comprising:a touch screen display, one or more processors, a storage media, a wireless data communication interface, an operating system comprising an application framework layer and an application layer, an adaptive learning system, and an overlay system and an access control stored in the storage media and configured to be executed by the one or more processors, the overlay system comprising:
instructions for controlling access to one or more application programs in the application layer;
instructions for providing a first user interface that receives input through the touch screen display;
instructions for providing a second operating environment associated with a second user interface that receives input through the touch screen display;
instructions for requiring input of an authentication code through the touch screen display to access the first user interface from the second operating environment; and
instructions for accepting, in the first user interface, a configuration of the access control configured to permit or deny a request for access in the second operating environment to one or more of a system setting, an application program, an audio file by a media player app, a video file by the media player app, a hardware resource, an internet resource, a text file, an image file, and an electronic book;
the adaptive learning system comprising:
instructions for executing at least one direct instructional component comprising at least one of a definition of a desired skill, a skill acquisition exercise, and a configuration and evaluation interface;
instructions for executing at least one indirect instructional component comprising one or more reinforcements designed to encourage one or more behaviors associated with acquisition or reinforcement of the desired skill;
instructions for executing at least one technological enabler to support at least one of the direct instructional component and the indirect instructional component;
instructions for analyzing data captured regarding the skill acquisition exercise;
instructions for determining an assessment regarding the skill acquisition exercise based on one or more predetermined criteria, wherein the one or more predetermined criteria comprise one or more of a user proficiency in the desired skill and a user learning style; and
instructions for personalizing a subsequent instance of a skill acquisition exercise automatically based on the assessment.

US Pat. No. 10,460,084

PROTECTING MEDIA ITEMS USING A MEDIA SECURITY CONTROLLER

Cryptography Research, In...

1. A method comprising:receiving, by a media security controller circuit of a media storage device from a rendering device, a request to render a media item that is stored in a memory of the media storage device;
sending to the rendering device, by the media security controller circuit in response to receiving the request, an authorization file stored in memory of the media storage device, the authorization file comprising first instructions to be executed by the media security controller circuit and second instructions to be executed by the rendering device to render the media item;
receiving, by the media security controller circuit, at least a portion of the authorization file from the rendering device, wherein the portion of the authorization file comprises the first instructions;
executing, by the media security controller circuit, the first instructions to send to the rendering device a message for the rendering device to obtain a portion of data from the memory of the media storage device and to provide the portion of the data to the media security controller circuit, wherein the data in the memory of the media storage device relates to the media item to be rendered by the rendering device;
receiving from the rendering device, by the media security controller circuit, the portion of the data obtained by the rendering device from the memory of the media storage device;
transforming, by the media security controller circuit, the portion of the data obtained by the rendering device from the memory of the media storage device; and
sending to the rendering device, by the media security controller circuit, the transformed portion of the data.

US Pat. No. 10,460,083

DIGITAL CREDENTIAL SYSTEM

Screening Room Media, Inc...

1. A method comprising:receiving, by a digital content delivery system, a request to rent a first digital movie;
in response to receiving the request, assigning, by the digital content delivery system, a digital content license to a user account associated with a client-side digital delivery device, the digital content license permitting a user of the user account to:
attend a scheduled presentation of the first digital movie at an exhibitor location, and
stream the first digital movie from the client-side digital delivery device associated with the user account;
in response to receiving a request associated with the user account to attend a selected scheduled presentation of the first digital movie at a first selected exhibitor location, assigning, by the digital content delivery system, a digital credential to the user account, the digital credential being redeemable at the selected exhibitor location to view the selected scheduled presentation of the digital movie;
receiving, from a mobile computing device associated with the user account, a first request to display the digital credential on a display of the mobile computing device;
in response to receiving the first request, determining that either a current location of the mobile computing device is outside of a predetermined geographic distance of the selected exhibitor location, or a remaining amount of time until a scheduled start time of the selected scheduled presentation is greater than a threshold amount of time, yielding a first determination;
in response to the first determination, denying the first request;
after denying the first request, receiving a second request to display the digital credential on the display of the mobile computing device,
in response to receiving the second request, determining that the current location of the mobile computing device is within the predetermined geographic distance of the selected exhibitor location and the remaining amount of time until the scheduled start time of the selected scheduled presentation is less than the threshold amount of time, yielding a second determination; and
in response to the second determination, causing presentation of the digital credential on the display of the mobile computing device.

US Pat. No. 10,460,082

DIGITAL RIGHTS MANAGEMENT PROGRESSIVE CONTROL AND BACKGROUND PROCESSING

Adobe Inc., San Jose, CA...

1. In a digital medium environment, a method implemented by a client computing device, the method comprising:downloading, by the client computing device, content that includes a plurality of items and a digital rights management module embedded as part of the content;
monitoring, by the client computing device, user interaction with other content that is executable on the client computing device independent of the content, the monitoring performed via background processing of the digital rights management module such that the embedded digital rights management module is not directly accessible to a user of the client computing device;
forming, by the client computing device, a model, as a function of progressively learned traits observed during the interaction with the other content through use of the digital rights management module; and
progressively controlling access, by the client computing device, to individual ones of the plurality of items of the content through use of a digital rights management module embedded as part of the content, the controlling based on updates to the progressively learned traits of the model through continued said monitoring of the user interaction with the other content and whether the progressively learned traits meet specified traits of a behavior of a digital rights management policy enforced by the digital rights management module for the content.

US Pat. No. 10,460,081

METHOD AND APPARATUS FOR PORTABLY BINDING LICENSE RIGHTS TO CONTENT STORED ON OPTICAL MEDIA

FOX BROADCASTING COMPANY,...

1. A method of conditionally enabling a playback of content stored in read-only memory removable from a playback module, comprising:accepting a read-only memory (ROM) having the content encrypted so as to be decryptable according to one or more content keys, wherein the ROM includes globally unique ROM identifier (ROM ID);
reading the ROM identifier by a ROM controller, the ROM controller having an unalterable ROM controller identifier (ROM controller ID);
transmitting a ROM playback license request from the ROM controller to a license server, the ROM playback license request comprising the ROM controller ID, the ROM ID and a request for a license to play back the content from the ROM using the ROM controller;
receiving a content license enabling one or more rights to the content including a right for the playback of the encrypted content from the ROM using the ROM controller, the content license including the one or more content keys and being encrypted to be decryptable according to a ROM controller secret associated with the ROM controller ID;
decrypting the content license in the ROM controller to recover the one or more content keys;
providing the encrypted content from the ROM and the one or more content keys to the playback module for use in decrypting the encrypted content;
accepting a command to copy the encrypted content from the ROM to a random access memory (RAM), the RAM written to and read from under the control of a RAM controller having an unalterable RAM controller ID;
copying the encrypted content from the ROM to the RAM; and
copying the ROM ID to a memory accessible to the RAM controller.

US Pat. No. 10,460,080

ACCESSING PREDICTIVE DATA

Gearbox, LLC, Bellevue, ...

1. A system comprising:at least one processing device;
an interface device operatively coupled to the at least one processing device; and
a memory operatively coupled to the at least one processing device and bearing one or more instructions that, when executed by the at least one processing device, perform operations including at least:
receiving an input via the interface device identifying at least one treatment agent;
providing an indication of a first possible outcome of a use of the at least one treatment agent with respect to at least one direct end target, the first possible outcome based at least partly on at least one dataset associated with at least one first predictive basis;
receiving input via the interface device pertaining to at least one differential gene expression associated with at least one subpopulation;
applying filter criteria using the at least one processing device to the at least one dataset associated with the at one first predictive basis, the filter criteria including at least one second predictive basis to provide a second possible outcome of the use of the treatment agent, the second predictive basis based at least partly on the at least one differential gene expression associated with the at least one subpopulation; and
outputting a representation of at least the second possible outcome of the use of the treatment agent.

US Pat. No. 10,460,079

METHOD AND MEDICAL APPARATUS FOR OPTIMIZATION OF THE PERFORMANCE OF A PROCEDURE INVOLVING MEDICAL IMAGING ON A PATIENT

Siemens Healthcare GmbH, ...

1. A method for operating a medical system in order to perform a procedure on a patient, said procedure comprising a plurality of successively-performed steps, said method comprising:in a computer, determining target values for each of said steps of the procedure;
during performance of said procedure, detecting actual values for each of said steps of the procedure and providing said actual values to said computer;
in said computer, comparing the target values respectively to actual values for each of said steps of said procedure, in order to determine a deviation between each of the target values and each of the actual values, respectively; and
in said computer, generating an electrical signal that represents said deviation between each target value and each actual value and providing said electrical signal representing the deviation as an output from said computer if an amount of said deviation is above a predetermined threshold value.

US Pat. No. 10,460,078

SYSTEMS AND METHODS FOR REMOTE DEMAND BASED DATA MANAGEMENT OF CLINICAL LOCATIONS

Parallel 6, Inc., San Di...

1. A system for managing one or more clinical protocols across multiple locations, comprising:a processor;
a data store configured to store workflow items with information for clinical trials employing the one or more clinical protocols; and
a memory communicatively coupled with the processor, the memory configured to store instructions, the instructions configured to cause the processor to:
determine a geo-fence around a first geographic location, wherein the first geographic location is a clinical research location;
receive, from a mobile device, a second geographic location of the mobile device;
determine that the mobile device is associated with a clinical trial based at least in part on the first geographic location and the second geographic location;
determine a plurality of clinical protocol activities associated with the clinical trial and the mobile device;
determine that the second geographic location of the mobile device satisfies a first clinical protocol activity of the plurality of clinical protocol activities associated with the clinical trial;
capture a second type of content from the mobile device, wherein the second type of content is associated with a second clinical protocol activity of the plurality of clinical protocol activities;
determine an additional workflow step for the second clinical protocol activity of the plurality of clinical protocol activities; and
enable a mobile control interface to display the additional workflow step for the second clinical protocol activity of the plurality of clinical protocol activities, wherein the mobile control interface is located at the first geographic location of the clinical research location.

US Pat. No. 10,460,077

SECURELY COLLECTING AND PROCESSING MEDICAL IMAGERY

1. A system for recording HIPAA compliant medical imagery comprising:a first medical imaging system comprising a medical imaging device;
the first medical imaging system configured to capture imagery and transmit that imagery as medical files to a second medical imaging system;
the second medical imaging system comprising:
a special purpose computer;
the special purpose computer comprising:
a first processor, a second processor, a permanently installed hard drive, and a random access memory;
wherein the first processor is a GPU;
wherein the second processor is a CPU;
wherein the permanently installed hard drive is configured such that it stores all instructions necessary for the first processor to process medical files transmitted from the first medical system;
wherein the permanently installed hard drive is further configured such that it stores all instructions necessary for the second processor to encrypt and store all medical files, as they are created, on a removable drive only; and
wherein the removable drive is an encrypted removable flash storage drive.