Machine Learning Patents (Class 706/12)
  • Patent number: 11507861
    Abstract: Methods and systems for collecting and analyzing sensor data to predict water fixture failure and water consumption are provided. In one embodiment, a method is provided that includes receiving sensor data regarding a water fixture. Changepoints may then be calculated within the sensor data and the sensor data may be split into intervals at the changepoints. A machine learning model may then be used to classify the intervals and a status of the water fixture and water consumption may be identified based on the classified intervals.
    Type: Grant
    Filed: February 26, 2020
    Date of Patent: November 22, 2022
    Assignee: SWEETSENSE, INC.
    Inventors: Daniel Wilson, Jeremy Coyle, Evan Thomas, Skot Croshere
  • Patent number: 11507865
    Abstract: An information handling system may be configured to: receive time-series data regarding measurements of a physical variable; determine that a missing data point is missing from the time-series data, wherein the missing data point corresponds to a particular day of the week; in response to a determination that earlier corresponding data from the particular day of the week of an earlier week is available, copy the earlier corresponding data to replace the missing data; in response to a determination that later corresponding data from the particular day of the week of a later week is available, copy the later corresponding data to replace the missing data; and in response to a determination that neither the earlier corresponding data nor the later corresponding data is available, perform interpolation to replace the missing data.
    Type: Grant
    Filed: July 30, 2020
    Date of Patent: November 22, 2022
    Assignee: Dell Products L.P.
    Inventor: Ally Junio Oliveira Barra
  • Patent number: 11507754
    Abstract: Methods and systems are presented for analyzing feedback data associated with a content and generating an interactive graphical representation of the feedback data. Upon receiving a request from a user, a feedback analysis system may access feedback data associated with a content from a content hosting server. The feedback data may include comments submitted by viewers of the content. The feedback analysis system may analyze the comments and generate an interactive graphical representation of the feedback data. The interactive graphical representation may include icons that represents keywords that are relevant to the comments and sentiments of the viewers derived based on the comments. Upon receiving a selection of an icon, the feedback analysis system may present a comment that corresponds to the keyword and/or sentiment represented by the icon.
    Type: Grant
    Filed: July 22, 2022
    Date of Patent: November 22, 2022
    Assignee: TYNTRE, LLC
    Inventor: Thomas Chen
  • Patent number: 11507963
    Abstract: The disclosure discloses a method and device of analysis based on a model, and a computer readable storage medium. The method includes: training various pre-determined models based on a preset number of customer information samples; combining the various trained models into a compound model according to a pre-determined combining rule, and after customer information to be analyzed is received, inputting the customer information to be analyzed into the compound model to output an analysis result. According to the disclosure, by the use of the compound model combined by the various models for analysis and prediction, the advantages of different models can be combined. Compared with a single model for prediction, the compound model effectively improves the accuracy of a prediction result.
    Type: Grant
    Filed: August 31, 2017
    Date of Patent: November 22, 2022
    Assignee: PING AN TECHNOLOGY (SHENZHEN) CO., LTD.
    Inventor: Yiyun Chen
  • Patent number: 11507785
    Abstract: A classifier network has at least two distinct sets of refined data, wherein the first two sets of refined data are sets of numbers representing the features values data received from sensors or a manufactured part. Performing, via at least two distinct types of support vector machines using an associated feature selection process for each classifier independently in a first layer, anomaly detection on the manufactured part. Then, using the stored data including refined data of at least two different types of data transforms and performing, via at least a two distinct types of support vector machines in a second layer, an associated feature selection process for each classifier independently. Forming at least four distinct compound classifier types for anomaly detection on the part using the stored data or coefficients. The ensemble of second layer support vector machine outputs compare the results to determine the presence of an anomaly.
    Type: Grant
    Filed: April 30, 2020
    Date of Patent: November 22, 2022
    Assignee: BAE Systems Information and Electronic Systems Integration Inc.
    Inventor: Martin S. Glassman
  • Patent number: 11507603
    Abstract: An improvement of the functionality of a computerized automatic recommendation engine is provided. In particular, a method for identifying uncertain classifications made by a computerized recommendation engine through the utilization of historical solution data, such that they can be flagged for subsequent human review, thereby improving the training process for the recommendation engine, is disclosed.
    Type: Grant
    Filed: July 11, 2020
    Date of Patent: November 22, 2022
    Assignee: BayesTree Intelligence Pvt Ltd.
    Inventors: Partha Pratim Ghosh, Vijay Giri, Girish Koppar, Avijit Biswas
  • Patent number: 11507217
    Abstract: A touch-based control device can include an exterior panel that includes a groove region and a surrounding region, one or more touch sensors for detecting touch inputs performed anywhere on a substantial portion of the exterior panel, and a sensing module comprising one or more processors to detect, via the one or more touch sensors, touch inputs performed by a user on the exterior panel. The sensing module can interpret the touch input based on at least one of (i) a region where the touch input occurred, or (ii) a type of the touch input, and control a connected device based on the interpreted touch input.
    Type: Grant
    Filed: January 5, 2021
    Date of Patent: November 22, 2022
    Assignee: Brilliant Home Technology, Inc.
    Inventors: Aaron T. Emigh, Steven Stanek, Brian Cardanha, Bozhi See, Iris Yan, Gaurav Hardikar
  • Patent number: 11507430
    Abstract: Examples described herein can be used to determine and suggest a computing resource allocation for a workload request made from an edge gateway. The computing resource allocation can be suggested using computing resources provided by an edge server cluster. Telemetry data and performance indicators of the workload request can be tracked and used to determine the computing resource allocation. Artificial intelligence (AI) and machine learning (ML) techniques can be used in connection with a neural network to accelerate determinations of suggested computing resource allocations based on hundreds to thousands (or more) of telemetry data in order to suggest a computing resource allocation. Suggestions made can be accepted or rejected by a resource allocation manager for the edge gateway and the edge server cluster.
    Type: Grant
    Filed: September 27, 2018
    Date of Patent: November 22, 2022
    Assignee: Intel Corporation
    Inventors: Rasika Subramanian, Francesc Guim Bernat, David Zimmerman
  • Patent number: 11501477
    Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize glyph sets from predefined instances of variable fonts to customize font bounding boxes for custom instances of the variable fonts. The disclosed system customizes digital text including a variable font via one or more adjustable design axes. In response to a request to set a custom value of a design axis, the disclosed system determines a first and second predefined instances of the digital text. For example, the disclosed system determines a Euclidean distance between the custom value and corresponding values for the predefined instances. The disclosed systems determine sets of glyphs that contribute to the font bounding boxes of the first predefined instance and the second predefined instance. The disclosed systems generate a custom font bounding box for the digital text at the custom value of the design axis based on the glyph sets.
    Type: Grant
    Filed: March 22, 2021
    Date of Patent: November 15, 2022
    Assignee: Adobe Inc.
    Inventor: Nirmal Kumawat
  • Patent number: 11501015
    Abstract: A secure machine learning system of a database system can be implemented to use secure shared data to train a machine learning model. To manage the model, a first user of the database can share data in an encrypted view with a second user of the database, and further share one or more functions of an application that accesses the data while the data is encrypted. The second user can access functions of the application and can call the functions to generate a trained machine learning model and further generate machine learning outputs (e.g., predictions) from the trained model.
    Type: Grant
    Filed: December 16, 2021
    Date of Patent: November 15, 2022
    Assignee: Snowflake Inc.
    Inventors: Monica J. Holboke, Justin Langseth, Stuart Ozer, William L. Stratton, Jr.
  • Patent number: 11498212
    Abstract: A method for planning a manipulation task of an agent, particularly a robot. The method includes: learning a number of manipulation skills wherein a symbolic abstraction of the respective manipulation skill is generated; determining a concatenated sequence of manipulation skills selected from the number of learned manipulation skills based on their symbolic abstraction so that a given goal specification indicating a given complex manipulation task is satisfied; and executing the sequence of manipulation skills.
    Type: Grant
    Filed: June 4, 2020
    Date of Patent: November 15, 2022
    Assignee: Robert Bosch GmbH
    Inventors: Andras Gabor Kupcsik, Leonel Rozo, Marco Todescato, Markus Spies, Markus Giftthaler, Mathias Buerger, Meng Guo, Nicolai Waniek, Patrick Kesper, Philipp Christian Schillinger
  • Patent number: 11501192
    Abstract: Techniques for use in connection with performing optimization using an objective function that maps elements in a first domain to values in a range. The techniques include using at least one computer hardware processor to perform: identifying a first point at which to evaluate the objective function at least in part by using an acquisition utility function and a probabilistic model of the objective function, wherein the probabilistic model depends on a non-linear one-to-one mapping of elements in the first domain to elements in a second domain; evaluating the objective function at the identified first point to obtain a corresponding first value of the objective function; and updating the probabilistic model of the objective function using the first value to obtain an updated probabilistic model of the objective function.
    Type: Grant
    Filed: September 4, 2018
    Date of Patent: November 15, 2022
    Assignees: President and Fellows of Harvard College, The Governing Council of the University of Toronto
    Inventors: Ryan P. Adams, Roland Jasper Snoek, Kevin Swersky, Richard Zemel
  • Patent number: 11497988
    Abstract: Aspects of the subject technology include an event processing and prospect identifying platform. It accepts as input a set of storylines (a sequence of entities and their relationships) and processes them as follows: (1) uses different algorithms (LDA, SVM, information gain, rule sets) to identify themes from storylines; (2) identifies top locations and times in storylines and combines with themes to generate events that are meaningful in a specific scenario for categorizing storylines; and (3) extracts top prospects as people and organizations from data elements contained in storylines. The output comprises sets of events in different categories and storylines under them along with top prospects identified. Aspects use in-memory distributed processing that scales to high data volumes and categorizes generated storylines in near real-time.
    Type: Grant
    Filed: August 31, 2016
    Date of Patent: November 15, 2022
    Assignee: OMNISCIENCE CORPORATION
    Inventor: Manu Shukla
  • Patent number: 11501177
    Abstract: A model management tool is provided for performing analysis on data in a knowledge graph representation and enforcing data standardization to increase performance when reusing existing models to develop new artificial intelligence applications.
    Type: Grant
    Filed: June 12, 2020
    Date of Patent: November 15, 2022
    Assignee: Accenture Global Solutions Limited
    Inventors: Zhijie Wang, William Richard Gatehouse, Teresa Sheausan Tung
  • Patent number: 11501158
    Abstract: Aspects for vector operations in neural network are described herein. The aspects may include a controller unit configured to receive an instruction to generate a random vector that includes one or more elements. The instruction may include a predetermined distribution, a count of the elements, and an address of the random vector. The aspects may further include a computation module configured to generate the one or more elements, wherein the one or more elements are subject to the predetermined distribution.
    Type: Grant
    Filed: October 25, 2018
    Date of Patent: November 15, 2022
    Assignee: CAMBRICON (XI'AN) SEMICONDUCTOR CO., LTD.
    Inventors: Daofu Liu, Xiao Zhang, Shaoli Liu, Tianshi Chen, Yunji Chen
  • Patent number: 11501207
    Abstract: Systems and methods are described for a decision-making process that includes an increasing set of actions, compute a policy function for a Markov decision process (MDP) for the decision-making process, wherein the policy function is computed based on a state conditional function mapping states into an embedding space, an inverse dynamics function mapping state transitions into the embedding space, and an action selection function mapping the elements of the embedding space to actions, identify an additional set of actions in the increasing set of actions, update the inverse dynamics function based at least in part on the additional set of actions, update the policy function based on the updated inverse dynamics function and parameters learned during the computing the policy function, and select an action based on the updated policy function.
    Type: Grant
    Filed: September 23, 2019
    Date of Patent: November 15, 2022
    Assignee: ADOBE INC.
    Inventors: Georgios Theocharous, Yash Chandak
  • Patent number: 11500714
    Abstract: Apparatus, media, methods, and systems for data storage systems and methods for autonomously adapting data storage system performance, lifetime, capacity and/or operational requirements. A data storage system may comprise a controller and one or more non-volatile memory devices. The controller is configured to determine a category for a workload of one or more operations being processed by the data storage system using a machine-learned model. The controller is configured to determine an expected degradation of the one or more non-volatile memory devices. The controller is configured to adjust, based on the expected degradation and an actual usage of physical storage of the data storage system by a host system, an amount of physical storage of the data storage system available to the host system.
    Type: Grant
    Filed: February 22, 2021
    Date of Patent: November 15, 2022
    Assignee: WESTERN DIGITAL TECHNOLOGIES, INC.
    Inventors: Jay Sarkar, Cory Peterson
  • Patent number: 11501200
    Abstract: The present disclosure relates to system(s) and method(s) to generate alerts while monitoring a machine learning model in real time. The system is configured to receive, in response to a first input parameter, a first output parameter generated by a first function of a learning model corresponding to a machine learning model. The system is further configured to receive, in response to a second input parameter, a second output parameter generated by a second functionality of a real-time model corresponding to the machine learning model. Further, the system is configured to compare the first output parameter with the second output parameter and the first input parameter with the second input parameter to generate tuning and rebuilding alerts.
    Type: Grant
    Filed: June 19, 2017
    Date of Patent: November 15, 2022
    Assignee: HCL Technologies Limited
    Inventors: S U M Prasad Dhanyamraju, Satya Sai Prakash Kanakadandi
  • Patent number: 11501202
    Abstract: Querying databases may be performed with references to machine learning models. A database query may be received that references a machine learning model and database. In response to the query, the machine learning model may provide information which may be returned as part of a result of the query or may be used to generate a result of the query. The machine learning model may be generated in response to a request to generate a machine learning model that includes a database query that identifies the data upon which a machine learning technique may be applied to generate the machine learning model.
    Type: Grant
    Filed: April 17, 2018
    Date of Patent: November 15, 2022
    Assignee: Amazon Technologies, Inc.
    Inventor: Stefano Stefani
  • Patent number: 11501437
    Abstract: A system and a method for monitoring a brain CT scan image using ASPECTS score. The method includes receiving the brain CT scan image of a patient. Further, a basal ganglia region and a corona radiata level are identified in a plurality of slices in the brain CT scan image. Furthermore, a plurality of anatomical regions and a plurality of infarcts are segmented using deep learning. Subsequently, an overlapping region across the plurality of slices is determined based on the plurality of anatomical regions and the plurality of infarcts. The overlapping region and a predefined threshold are used to compute an ASPECTS score. The ASPECTS score is further used to recommend a course of action to the patient.
    Type: Grant
    Filed: July 6, 2022
    Date of Patent: November 15, 2022
    Assignee: Qure.ai Technologies Private Limited
    Inventors: Ujjwal Upadhyay, Satish Kumar Golla, Swetha Tanamala, Sasank Chilamkurthy, Preetham Putha
  • Patent number: 11501216
    Abstract: A computer system has a first machine learning module configured to predict a probability of a respective option being selected by a particular user if presented to that user via a computer app. A second machine learning module is configured to determine a respective confidence value associated with the probability. A third module uses the predicted probabilities and confidence values to determine at least one option to be presented to the particular user.
    Type: Grant
    Filed: February 21, 2020
    Date of Patent: November 15, 2022
    Assignee: KING.COM LTD.
    Inventors: Lele Cao, Sahar Asadi
  • Patent number: 11503052
    Abstract: A system and method for detecting anomalous hypertext transfer protocol secure (HTTPS) traffic are provided. The method includes receiving samples of at least rate-based features, wherein the rate-based features demonstrate a normal behavior of at least HTTPS traffic directed to a protected entity; computing a short-term baseline and a long-term baseline based on the received samples, wherein the short-term baseline is adapted to relatively rapid changes in the HTTPS traffic and the long-term baseline is adapted to relatively slow changes in the HTTPS traffic; computing at least one short-term threshold respective of the short-term baseline and at least one long-term threshold respective of the long-term baseline; evaluating each of the at least one threshold against real-time samples of HTTPS traffic to determine whether behavior of the HTTPS traffic is anomalous; and generating alarm when anomaly is detected.
    Type: Grant
    Filed: December 19, 2019
    Date of Patent: November 15, 2022
    Assignee: Radware, Ltd.
    Inventors: Lev Medvedovsky, David Aviv, Ehud Doron
  • Patent number: 11494294
    Abstract: Certain aspects involve models for generating code executed on data-processing platforms. One example involves receiving an electronic data-processing model, which generates an analytical output from input attributes weighted with respective modeling coefficients. A target data-processing platform is identified that requires bin ranges for the modeling coefficients and reason codes for the input attributes. Modeling code is generated that implements the electronic data-processing model with the bin ranges and the reason codes. The processor outputs executable code that implements the electronic data-processing model.
    Type: Grant
    Filed: February 2, 2021
    Date of Patent: November 8, 2022
    Assignee: EQUIFAX INC.
    Inventors: Rajesh Indurthivenkata, Lalithadevi Venkataramani, Aparna Somaka, Xingjun Zhang, Matthew Turner, Bhawana Koshyari, Vijay Nagarajan, James Reid, Nandita Thakur
  • Patent number: 11494415
    Abstract: A method and system for a feature subset-classifier pair for a classification task. The classification task corresponds to automatically classifying data associated with a subject(s) or object(s) of interest into an appropriate class based on a feature subset selected among a plurality of features extracted from the data and a classifier selected from a set of classifier types. The method proposed includes simultaneously determining the feature subset-classifier pair based on a relax-greedy {feature subset, classifier} approach utilizing sub-greedy search process based on a patience function, wherein the feature subset-classifier pair provides an optimal combination for more accurate classification. The automatic joint selection is time efficient solution, effectively speeding up the classification task.
    Type: Grant
    Filed: May 23, 2019
    Date of Patent: November 8, 2022
    Assignee: TATA CONSULTANCY SERVICES LIMITED
    Inventors: Ishan Sahu, Ayan Mukherjee, Arijit Ukil, Soma Bandyopadhyay, Chetanya Puri, Rituraj Singh, Arpan Pal, Rohan Banerjee
  • Patent number: 11494612
    Abstract: A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.
    Type: Grant
    Filed: October 31, 2018
    Date of Patent: November 8, 2022
    Assignee: Sony Interactive Entertainment Inc.
    Inventors: Ruxin Chen, Min-Hung Chen, Jaekwon Yoo, Xiaoyu Liu
  • Patent number: 11494587
    Abstract: In an embodiment, a method includes receiving a trigger of machine learning model generation. In addition, the method includes algorithmically eliminating at least some of rows and at least some of columns of a training dataset, the algorithmically eliminating yielding a size-reduced training dataset. The method additionally includes generating, for a prediction target, a plurality of machine learning models via a plurality of machine learning algorithms. The method also includes measuring prediction accuracies of the plurality of machine learning models relative to the prediction target. Furthermore, the method includes selecting a particular machine learning model. Moreover, the method includes applying the particular machine learning model to a data source.
    Type: Grant
    Filed: October 23, 2018
    Date of Patent: November 8, 2022
    Inventors: Dhurai Ganesan, Aananthanarayanan Pandian, Tanvir Khan
  • Patent number: 11494693
    Abstract: Machine learning model re-training based on distributed feedback received from a plurality of edge computing devices is provided. A trained instance of a machine learning model is transmitted, via one or more communications networks, to the plurality of edge computing devices. Feedback data is collected, via the one or more communications networks, from the plurality of edge computing devices. The feedback data includes labeled observations generated by the execution of the trained instance of the machine learning model at the plurality of edge computing devices on unlabeled observations captured by the plurality of edge computing devices. A re-trained instance of the machine learning model is generated from the trained instance using the collected feedback data. The re-trained instance of the machine learning model is transmitted, via the one or more communications networks, to the plurality of edge computing devices.
    Type: Grant
    Filed: May 31, 2019
    Date of Patent: November 8, 2022
    Assignee: NAMI ML INC.
    Inventors: Joseph D. Pezzillo, Daniel Burcaw
  • Patent number: 11496590
    Abstract: In one embodiment, a method includes generating predicted locations of each of a plurality of network addresses, wherein each predicted location is associated with a time stamp representing an age of the predicted location, determining a weighting factor representing a probability that at least one of the predicted locations of the network address corresponds to a true location of the network address based on location-related features associated with each network address and the time stamps, determining a weight for each predicted location based on at least the weighting factor, wherein the weight represents a probability that the predicted location corresponds to the true location of the network address, and providing one or more of the predicted locations that correspond to a particular network address based on the respective weights of the predicted locations in response to a request to identify a geographic location for the particular network address.
    Type: Grant
    Filed: February 11, 2021
    Date of Patent: November 8, 2022
    Assignee: Meta Platforms, Inc.
    Inventor: William Bullock
  • Patent number: 11494691
    Abstract: Systems and methods are provided for training a model using machine learning. An exemplary method may include providing, by the model in a training session, an action to an environment to receive feedback from the environment. The method may also include generating, by a behavior simulator, a plurality of predicted outcomes from the environment resulting from the action. The method may further include training the model, using at least a subset of the predicted outcomes, to generate a set of candidate models. The method may include receiving actual feedback from the environment and determining whether the actual feedback matches one of the predicted outcomes in the subset. Responsive to the determination that the actual feedback matches one of the predicted outcomes in the subset, the method may include using, in a new training session, the candidate model in the set corresponding to the matched predicted outcome.
    Type: Grant
    Filed: March 15, 2019
    Date of Patent: November 8, 2022
    Assignee: Capital One Services, LLC
    Inventors: Fardin Abdi Taghi Abad, Jeremy Goodsitt, Austin Walters, Reza Farivar, Mark Watson, Anh Truong
  • Patent number: 11494632
    Abstract: Implementations are directed to generating simulated training examples for training of a machine learning model, training the machine learning model based at least in part on the simulated training examples, and/or using the trained machine learning model in control of at least one real-world physical robot. Implementations are additionally or alternatively directed to performing one or more iterations of quantifying a “reality gap” for a robotic simulator and adapting parameter(s) for the robotic simulator based on the determined reality gap. The robotic simulator with the adapted parameter(s) can further be utilized to generate simulated training examples when the reality gap of one or more iterations satisfies one or more criteria.
    Type: Grant
    Filed: December 7, 2017
    Date of Patent: November 8, 2022
    Assignee: X DEVELOPMENT LLC
    Inventor: Yunfei Bai
  • Patent number: 11494704
    Abstract: An information processing method includes acquiring a first prediction result by inputting evaluation data to a first model; determining an anomaly in the first prediction result based on the first prediction result and reference information; acquiring a second model based on the determination result; acquiring a second prediction result by inputting the evaluation data to the second model; determining an anomaly in the second prediction result based on the second prediction result and the reference information; acquiring a third model based on the determination result; acquiring a third prediction result by inputting the evaluation data to the third model; determining an anomaly in the third prediction result based on the third prediction result and the reference information; and if the anomaly in the third prediction result is recognized as being identical to the anomaly in the first prediction result, outputting information about a training limit of the first model.
    Type: Grant
    Filed: July 15, 2020
    Date of Patent: November 8, 2022
    Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA
    Inventors: Yusuke Tsukamoto, Kazunobu Ishikawa, Sotaro Tsukizawa
  • Patent number: 11494689
    Abstract: There is provided systems and methods for training a classifier. The method comprises: obtaining a classifier for classifying data into one of a plurality of classes; retrieving training data comprising a set of observations and a set of corresponding labels, each label representing an assigned class for a corresponding observation; and applying an agent trained by a reinforcement learning system to generate labeled data from unlabeled observations and train the classifier using the training data and the labeled data according to a policy determined by the reinforcement learning system.
    Type: Grant
    Filed: June 5, 2018
    Date of Patent: November 8, 2022
    Assignee: Chatterbox Labs Limited
    Inventors: Ioannis Efstathiou, Stuart Battersby, Henrique Nunes, Zheng Yuan
  • Patent number: 11496608
    Abstract: Systems and methods for managing a Network Based Media Processing (NBMP) workflow are provided. A method includes obtaining, by a workflow manager, a network based media processing (NBMP) workflow including a plurality of workflow tasks and a plurality of proximity parameters which indicate a plurality of desired distances between the plurality of workflow tasks and at least one of a media source and a media sink; assigning the plurality of workflow tasks to the media sink, the media source, and at least one cloud element or network element, based on the plurality of desired distances; and managing the NBMP workflow according to the assigned plurality of workflow tasks.
    Type: Grant
    Filed: June 22, 2021
    Date of Patent: November 8, 2022
    Assignee: TENCENT AMERICA LLC
    Inventor: Iraj Sodagar
  • Patent number: 11494720
    Abstract: Techniques are provided for the automated risk assessment of a document. In one embodiment, the techniques involve mapping, via a risk assessment engine, one or more sentences in a first document to one or more risk categories, identifying, via a classification engine, risk-associated language of the one or more sentences based on the one or more risk categories, mapping, via a risk assessment engine, the risk-associated language of the one or more sentences to one or more risk criterion of a risk criterion document, and generating, via a risk assessment engine, a first risk assessment based on the one or more risk criterion of the risk criterion document.
    Type: Grant
    Filed: June 30, 2020
    Date of Patent: November 8, 2022
    Assignee: International Business Machines Corporation
    Inventors: Raji Lakshmi Akella, Xuan-Hong Dang, Syed Yousaf Shah, Petros Zerfos, Milton Orlando Laverde Echeverria, Ashley Potter
  • Patent number: 11494703
    Abstract: Systems and methods to utilize a machine learning model registry are described. The system deploys a first version of a machine learning model and a first version of an access module to server machines. Each of the server machines utilizes the model and the access module to provide a prediction service. The system retrains the machine learning model to generate a second version. The system performs an acceptance test of the second version of the machine learning model to identify it as deployable. The system promotes the second version of the machine learning model by identifying the first version of the access module as being interoperable with the second version of the machine learning model and by automatically deploying the first version of the access module and the second version of the machine learning model to the plurality of server machines to provide the prediction service.
    Type: Grant
    Filed: March 31, 2020
    Date of Patent: November 8, 2022
    Assignee: Opendoor Labs Inc.
    Inventor: Chongyuan Xiang
  • Patent number: 11488056
    Abstract: A non-transitory computer-readable storage medium storing therein a learning program that causes a computer to execute a process includes: determining whether or not there is a discontinuity point at which a variation in a learning time relative to a variation in a learning parameter is discontinuous; specifying, when the discontinuity point is present, ranges of the learning parameter in which the variation in the learning time relative to the variation in the learning parameter is continuous, based on the discontinuity point; calculating, for each of the specified ranges, an estimated value of performance of trials using a trial parameter learned by machine learning per a learning time of machine learning using a learning parameter included in the range; and specifying a learning parameter which enables any of the estimated values selected in accordance with a magnitude of the estimated value among the calculated estimated values.
    Type: Grant
    Filed: September 18, 2018
    Date of Patent: November 1, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Teruya Kobayashi, Ryuichi Takagi
  • Patent number: 11484685
    Abstract: Techniques for robotic control using profiles are disclosed. Cognitive state data for an individual is obtained. A cognitive state profile for the individual is learned using the cognitive state data that was obtained. Further cognitive state data for the individual is collected. The further cognitive state data is compared with the cognitive state profile. Stimuli are provided by a robot to the individual based on the comparing. The robot can be a smart toy. The cognitive state data can include facial image data for the individual. The further cognitive state data can include audio data for the individual. The audio data can be voice data. The voice data augments the cognitive state data. Cognitive state data for the individual is obtained using another robot. The cognitive state profile is updated based on input from either of the robots.
    Type: Grant
    Filed: June 29, 2020
    Date of Patent: November 1, 2022
    Assignee: Affectiva, Inc.
    Inventors: Rana el Kaliouby, Jason Krupat
  • Patent number: 11488060
    Abstract: Provided is a learning method, a learning program, a learning device, and a learning system, for training a classification model, to further raise the correct answer rate of classification by the classification model. The learning method includes execution of generating one piece of composite data by compositing a plurality of pieces of training data of which classification has each been set, or a plurality of pieces of converted data obtained by converting the plurality of pieces of training data, at a predetermined ratio, inputting one or a plurality of pieces of the composite data into the classification model, and updating a parameter of the classification model so that classification of the plurality of pieces of training data included in the composite data is replicated at the predetermined ratio by output of the classification model, by a computer provided with at least one hardware processor and at least one memory.
    Type: Grant
    Filed: July 25, 2018
    Date of Patent: November 1, 2022
    Assignee: The University of Tokyo
    Inventors: Tatsuya Harada, Yuji Tokozume
  • Patent number: 11488378
    Abstract: Apparatus, systems, and methods for analyzing data are described. The data can be analyzed using a hierarchical structure. One such hierarchical structure can comprise a plurality of layers, where each layer performs an analysis on input data and provides an output based on the analysis. The output from lower layers in the hierarchical structure can be provided as inputs to higher layers. In this manner, lower layers can perform a lower level of analysis (e.g., more basic/fundamental analysis), while a higher layer can perform a higher level of analysis (e.g., more complex analysis) using the outputs from one or more lower layers. In an example, the hierarchical structure performs pattern recognition.
    Type: Grant
    Filed: October 9, 2017
    Date of Patent: November 1, 2022
    Assignee: Micron Technology, Inc.
    Inventor: Paul Dlugosch
  • Patent number: 11487909
    Abstract: Systems, methods, and non-transitory computer readable media are configured to determine a likelihood of a user choosing to reveal a given content item when contents of the content item are obscured. The likelihood can be determined based at least in part on a trained machine learning model. An extent by which to obscure the content item based at least in part on the likelihood can be determined. Subsequently, an obscured version of the content item can be provided for display. The content item can be obscured based at least in part on the determined extent.
    Type: Grant
    Filed: February 1, 2021
    Date of Patent: November 1, 2022
    Assignee: Meta Platforms, Inc.
    Inventors: Fabiana Meira Pires de Azevedo, Marc Thomas Cruz, Matthew Miklasevich, Arvin Aminpour, Bonan Dong, Jason Rose
  • Patent number: 11490163
    Abstract: Systems and methods for generating a content item based on a difference between a user confidence score and a confidence score are disclosed. For example, a system generates for output a first content item. While the first content item is being outputted, the system receives user data via sensors of a device. The system determines a user confidence score based on the user data and metadata of the first content item. The user confidence score indicates a user's perceived probability of an event occurring in the future. The system calculates a prediction score which estimates the likelihood of the event occurring in the future. In response to determining that the difference between the user confidence score and the prediction score exceeds a threshold, the system selects a second content item related to the event and generates for output a recommendation comprising an identifier of the second content item.
    Type: Grant
    Filed: July 8, 2021
    Date of Patent: November 1, 2022
    Assignee: Rovi Guides, Inc.
    Inventors: Shyak Das, Vikram Makam Gupta, Muthukumar Lakshmipathi, Madhusudhan Seetharam
  • Patent number: 11488317
    Abstract: A system is provided that stores a neural network model trained on a training dataset which indicates an association between first graphic information associated with one or more first objects and corresponding first plurality of depth images. The system receives second graphic information that corresponds to the one or more first objects. The system further applies the trained neural network model received on the second graphic information. The system predicts a first depth image from the first plurality of depth images based on the application of the trained neural network model on the received second graphic information. The system extracts first depth information from the predicted first depth image. The first depth information corresponds to the one or more first objects indicated by the second graphic information.
    Type: Grant
    Filed: November 23, 2020
    Date of Patent: November 1, 2022
    Assignee: SONY GROUP CORPORATION
    Inventors: Jong Hwa Lee, Gareth White, Antti Myllykoski, Edward Theodore Winter
  • Patent number: 11481680
    Abstract: Methods, systems, and computer program products for verifying confidential machine learning models are provided herein. A computer-implemented method includes obtaining (i) a set of training data and (ii) a request, from a requestor, for a machine learning model, wherein the request is accompanied by at least a set of test data; obtaining a commitment from a provider in response to the request, the commitment comprising a special hash corresponding to parameters of a candidate machine learning model trained on the set of training data; revealing the set of test data to the requestor; obtaining, from the requestor, (i) a claim of performance of the candidate machine learning model for the test data and (ii) a proof of the performance of the candidate machine learning model; and verifying the claimed performance for the requestor based on (i) the special hash and (ii) the proof of the claimed performance.
    Type: Grant
    Filed: April 17, 2020
    Date of Patent: October 25, 2022
    Assignee: International Business Machines Corporation
    Inventors: Pankaj S. Dayama, Nitin Singh, Dhinakaran Vinayagamurthy, Vinayaka Pandit
  • Patent number: 11481571
    Abstract: Techniques for generating a machine learning model to detect event instances from physical sensor data, including applying a first machine learning model to first sensor data from a first physical sensor at a location to detect an event instance, determining that a performance metric for use of the first machine learning model is not within an expected parameter, obtaining second sensor data from a second physical sensor during a period of time at the same location as the first physical sensor, obtaining third sensor data from the first physical sensor during the period of time, generating location-specific training data by selecting portions of the third sensor data based on training event instances detected using the second sensor data, training a second ML model using the location-specific training data, and applying the second ML model instead of the first ML model for detecting event instances.
    Type: Grant
    Filed: January 12, 2018
    Date of Patent: October 25, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Kenneth Liam Kiemele, John Benjamin Hesketh, Evan Lewis Jones, James Lewis Nance, LaSean Tee Smith
  • Patent number: 11481692
    Abstract: A validity of a prediction model can be evaluated comprehensively. A machine learning program verification apparatus 100 includes a calculation device 104. The calculation device 104 obtains a decision tree logical expression by logically combining path logical expressions indicating decision tree paths indecision trees for a program created by machine learning, creates a combined logical expression by logically combining a verification property logical expression and an objective variable calculation logical expression with the decision tree logical expression, performs satisfiability determination by inputting the combined logical expression to a satisfiability determiner, and when a result of the determination indicates satisfaction, obtains, from a satisfaction solution of the satisfiability determination, a violation input value that is a value of an explanatory variable that violates a verification property and a violation output value that is a value of an objective variable.
    Type: Grant
    Filed: February 7, 2020
    Date of Patent: October 25, 2022
    Assignee: HITACHI, LTD.
    Inventors: Naoto Sato, Yuichiroh Nakagawa, Hironobu Kuruma, Hideto Noguchi
  • Patent number: 11481452
    Abstract: Implementations include providing a first set of tags by processing a document using generic entity extraction based on one or more external taxonomies, providing a second set of tags by processing the electronic document using specific entity extraction based on internal taxonomies specific to the enterprise, determining a relevance score for each tag in the first set of tags, and the second set of tags, defining a set of tags including one or more tags of the first set of tags, and one or more tags of the second set of tags, tags of the set of tags being in rank order based on respective relevance scores, receiving user input to the set of tags, and performing one or more of adjusting a ranking of tags based on the user input, and editing at least one internal taxonomy of the one or more internal taxonomies based on the user feedback.
    Type: Grant
    Filed: November 27, 2018
    Date of Patent: October 25, 2022
    Assignee: Accenture Global Solutions Limited
    Inventors: Riccardo Mattivi, Xin Zuo, Ian Hook, Aonghus McGovern, Thomas A. Hsu, Bijay Kumar
  • Patent number: 11481729
    Abstract: Trusted, privacy-protected systems and methods are disclosed for processing, handling, and performing tests on human genomic and other information. According to some embodiments, a system is disclosed that is a cloud-based system for the trusted storage and analysis of genetic and other information. Some embodiments of the system may include or support some or all of authenticated and certified data sources; authenticated and certified diagnostic tests; and policy-based access to data.
    Type: Grant
    Filed: April 10, 2020
    Date of Patent: October 25, 2022
    Assignee: Intertrust Technologies Corporation
    Inventors: W. Knox Carey, David P. Maher, Michael G. Manente, Jarl Nilsson, Talal G. Shamoon
  • Patent number: 11481210
    Abstract: Implementations are described herein for using machine learning to perform various tasks related to migrating source code based on relatively few (“few shots”) demonstrations. In various implementations, an autoregressive language model may be conditioned based on demonstration tuple(s). In some implementations, a demonstration tuple may include a pre-migration version of a first source code snippet and a post-migration version of the first source code snippet. In other implementations, demonstration tuples may include other data, such as intermediate forms (e.g., natural language descriptions or pseudocode), input-output pairs demonstrating intended behavior, etc. The autoregressive language model may be trained on corpora of source code and natural language documentation on the subject of computer programming.
    Type: Grant
    Filed: December 29, 2020
    Date of Patent: October 25, 2022
    Assignee: X DEVELOPMENT LLC
    Inventors: Rishabh Singh, David Andre, Bin Ni, Owen Lewis
  • Patent number: 11481671
    Abstract: Provided is a system for verifying integrity of a machine learning model, the system includes at least one processor programmed or configured to determine whether an output of a machine learning model based on an input corresponds to a reference output of the machine learning model based on the input, serialize the machine learning model into a file, calculate a file integrity value of the file using a file integrity detection function, determine whether the file integrity value corresponds to a reference file integrity value of the file, and perform an operation with the machine learning model based on determining that the file integrity value corresponds to the reference file integrity value of the file. A method and computer program product are also disclosed.
    Type: Grant
    Filed: May 16, 2019
    Date of Patent: October 25, 2022
    Assignee: Visa International Service Association
    Inventors: Vishwas Siravara, Peijie Li, Yu Gu
  • Patent number: 11482307
    Abstract: An incremental author disambiguation framework may create new clusters to accommodate new data based on the existing cluster results and newly added data. The proposed system may provide frequent update of taxonomic classification, name disambiguation and many other applications because it takes less time to generate new results. In addition, the proposed methods may reduce the time needed for updating the model and help improve the performance with the limited computational resource.
    Type: Grant
    Filed: March 2, 2018
    Date of Patent: October 25, 2022
    Assignee: Drexel University
    Inventors: Zhengqiao Zhao, Gail Rosen