Country
Full text data for US,EP,CN
Type
Legal Validity
Legal Status
Filing Date
Publication Date
Inventor
Assignee
Click to expand
IPC(Section)
IPC(Class)
IPC(Subclass)
IPC(Group)
IPC(Subgroup)
Agent
Agency
Claims Number
Figures Number
Citation Number of Times
Assignee Number
No. Publication Number Title Publication/Patent Number Publication/Patent Number Publication Date Publication Date
Application Number Application Number Filing Date Filing Date
Inventor Inventor Assignee Assignee IPC IPC
1
US2021001482A1
MACHINE LEARNING DEVICE, ROBOT CONTROLLER, ROBOT SYSTEM, AND MACHINE LEARNING METHOD FOR LEARNING ACTION PATTERN OF HUMAN
Publication/Patent Number: US2021001482A1 Publication Date: 2021-01-07 Application Number: 17/023,376 Filing Date: 2020-09-17 Inventor: Tsuda, Taketsugu   Okanohara, Daisuke   Okuta, Ryosuke   Matsumoto, Eiichi   Kawaai, Keigo   Assignee: FANUC CORPORATION   Preferred Networks, Inc.   IPC: B25J9/16 Abstract: A machine learning device for a robot that allows a human and the robot to work cooperatively, the machine learning device including a state observation unit that observes a state variable representing a state of the robot during a period in that the human and the robot work cooperatively; a determination data obtaining unit that obtains determination data for at least one of a level of burden on the human and a working efficiency; and a learning unit that learns a training data set for setting an action of the robot, based on the state variable and the determination data.
2
US2021004247A1
Suggesting Actions Based on Machine Learning
Publication/Patent Number: US2021004247A1 Publication Date: 2021-01-07 Application Number: 17/027,255 Filing Date: 2020-09-21 Inventor: Krishna, Golden Gopal   Borg, Carl Magnus   Bojic, Miroslav   Newton-dunn, Henry Owen   Klinker, Jacob M.   Pereira, Mindy   Mancuso, Devin   Park, Daniel June Hyung   Sin, Lily   Assignee: Google LLC   IPC: G06F9/451 Abstract: This document describes techniques for suggesting actions based on machine learning. These techniques determine a task that a user desires to perform, and presents a user interface through which to perform the task. To determine this task, the techniques can analyze content displayed on the user device or analyze contexts of the user and user device. With this determined task, the techniques determine an action that may assist the user in performing the task. This action is further determined to be performable through analysis of functionalities of an application, which may or may not be executing or installed on the user device. With some subset of the application's functionalities determined, the techniques presents the subset of functionalities via the user interface. By so doing, the techniques enable a user to complete a task more easily, quickly, or using fewer computing resources.
3
US2021004712A1
Machine Learning Performance and Workload Management
Publication/Patent Number: US2021004712A1 Publication Date: 2021-01-07 Application Number: 16/460,311 Filing Date: 2019-07-02 Inventor: Sarferaz, Siar   Assignee: SAP SE   IPC: G06N20/00 Abstract: Systems and methods are described herein for reducing resource consumption of a database system and a machine learning (ML) system. Data is received from an ML application of a database system. The data includes a first inference call for a predicted response to the received data. The first inference call is a request to a ML model to generate one or more predictions for which a response is unknown. An ML model using the received data generates an output comprising the predicted response to the data. The output for future inference calls is cached in an inference cache so as to bypass the ML model. The generated output to the ML application is provided by the ML model. A second inference call is received which includes the data of the first inference call. The cached output is retrieved from the inference cache. The retrieving bypasses the ML model.
4
US2021006949A1
MACHINE LEARNING COORDINATED WIRELESS NETWORKING
Publication/Patent Number: US2021006949A1 Publication Date: 2021-01-07 Application Number: 17/029,737 Filing Date: 2020-09-23 Inventor: Amini, Peiman   Emmanuel, Joseph Amalan Arul   Assignee: NETGEAR, INC.   IPC: H04W4/30 Abstract: The disclosed methods and systems use artificial intelligence (AI) and machine learning (ML) technologies to model the usage and interference on each channel. For example, units of the system can measure channel interference regularly over the time of day on all radios. The interference information is communicated to the base unit or a cloud server for pattern analysis. Interference measurements include interference from units within the system as well as interference from nearby devices. The base unit or the cloud server can recognize the pattern of the interference. Further, connected devices have a number of network usage characteristics observed and modeled including bitrate, and network behavior. These characteristics are used to assign channels to connected devices.
5
US10885039B2
Machine learning based search improvement
Publication/Patent Number: US10885039B2 Publication Date: 2021-01-05 Application Number: 14/721,945 Filing Date: 2015-05-26 Inventor: Hornkvist, John M.   Kapoor, Gaurav   Assignee: Apple Inc.   IPC: G06F16/2457 Abstract: Systems and methods are disclosed for improving search results returned to a user from one or more search domains, utilizing query features learned locally on the user's device. A search engine can receive, analyze and forward query results from multiple search domains and pass the query results to a client device. A search engine can determine a feature by analyzing query results, generate a predictor for the feature, instruct a client device to use the predictor to train on the feature, and report back to the search engine on training progress. A search engine can instruct a first and second set of client devices to train on set A and B of predictors, respectively, and report back training progress to the search engine. A client device can store search session context and share the context with a search engine between sessions with one or more search engines. A synchronization system can synchronize local predictors between multiple client devices of a user.
6
US2021005280A1
VARIANT CALLING USING MACHINE LEARNING
Publication/Patent Number: US2021005280A1 Publication Date: 2021-01-07 Application Number: 17/028,303 Filing Date: 2020-09-22 Inventor: Beauchamp, Kyle   Muzzey, Dale   Ganesh, Adithya C.   Hong, Sun Hae   Assignee: MYRIAD WOMEN'S HEALTH, INC.   IPC: G16B20/20 Abstract: Methods for determining a respective carrier status of an individual are disclosed. In some examples, the method includes determining the respective carrier status based on copy number data for a gene in a genome of the individual and SNP data for the gene using a machine learning algorithm. In some examples, the machine learning algorithm is configured to receive, as inputs, the copy number data and the SNP data, and output the respective carrier status of the individual.
7
US10884893B2
Detecting software build errors using machine learning
Publication/Patent Number: US10884893B2 Publication Date: 2021-01-05 Application Number: 16/112,506 Filing Date: 2018-08-24 Inventor: Sobran, Alexander   Zhang, Bo   Herrin, Bradley C.   Assignee: International Business Machines Corporation   IPC: G06F11/36 Abstract: A method, system and computer program product for detecting software build errors. A classification system is created that identifies users' questions in crowdsource data pertaining to errors in computer programs that are associated with a log report. A model is built to classify log data as bug-related or not bug-related based on the classification system. Log reports from log data obtained from crowdsource data are identified as being bug-related based on the model. After vectorizing such log reports and storing the vectorized log reports, the language of a new build log report for a software product is vectorized upon completion of the build of the software product. If the vectorized log report is within a threshold amount of distance to a stored vectorized log report, then a copy of the log report (bug-related) and a source of the log report associated with the stored vectorized log report is provided.
8
US2021003974A1
POWER GRID AWARE MACHINE LEARNING DEVICE
Publication/Patent Number: US2021003974A1 Publication Date: 2021-01-07 Application Number: 16/814,596 Filing Date: 2020-03-10 Inventor: Yang, Weiwei   White, Christopher Miles   Lytvynets, Kateryna   Edge, Darren Keith   Hoak, Amber D.   Assignee: Microsoft Technology Licensing, LLC   IPC: G05B13/02 Abstract: A system and method for managing operation of electrical devices includes a control module that monitors status of multiple sources of electrical power to one or more electrical devices and electrical usage of the one or more electrical devices that receive electricity from the source of electrical power. The operation of the one or more electrical devices is managed using a machine learning model that forecasts status of the at least one source of electrical power and generates operational rules for the one or more electrical devices from historical values of control parameters of the one or more electrical devices, the status of the source of electrical power, and the electrical usage of the one or more electrical devices. The system may optimize renewable energy utilization, power grid stabilization, cost of electrical power usage, and the like.
9
US2021004726A1
Machine learning model abstraction layer for runtime efficiency
Publication/Patent Number: US2021004726A1 Publication Date: 2021-01-07 Application Number: 17/024,762 Filing Date: 2020-09-18 Inventor: Shang, Rex   Lin, Dianhuan   Ma, Changsha   Koch, Douglas A.   Gupta, Shashank   Sainion, Parnit   Thothathri, Visvanathan   Paul, Narinder   Xu, Howie   Assignee: Zscaler, Inc.   IPC: G06N20/00 Abstract: Systems and methods include training a machine learning model with data for identifying features in monitored traffic in a network; analyzing the trained machine learning model to identify information overhead therein, wherein the information overhead is utilized in part for the training; removing the information overhead in the machine learning model; and providing the machine learning model for runtime use for identifying the features in the monitored traffic, with the removed information overhead from the machine learning model.
10
US10884409B2
Training of machine learning sensor data classification system
Publication/Patent Number: US10884409B2 Publication Date: 2021-01-05 Application Number: 15/872,275 Filing Date: 2018-01-16 Inventor: Mercep, Ljubo   Pollach, Matthias   Assignee: Mentor Graphics (Deutschland) GmbH   IPC: G05D1/00 Abstract: This application discloses training of a classification system for an assisted or automated driving system of a vehicle. A processing system can label sensor measurement data collected by sensors mounted in the vehicle with classifications, which can include a type of an object associated with the sensor measurement data and a confidence level of the classification. A training system can utilize the classifications labeled to the sensor measurement data to train a classification graph utilized by the classification system. The training system can select a node in a classification graph based, at least in part, on a classification labeled to sensor measurement data. The training system can compare the sensor measurement data to matchable data in the selected node, and modify the classification graph based, at least in part, on differences between the sensor measurement data and the matchable data in the selected node.
11
US10885343B1
Repairing missing frames in recorded video with machine learning
Publication/Patent Number: US10885343B1 Publication Date: 2021-01-05 Application Number: 16/556,489 Filing Date: 2019-08-30 Inventor: Harkness, Kevin   Assignee: Amazon Technologies, Inc.   IPC: G06N3/08 Abstract: Repairing missing frames in a video includes obtaining video data from an image capture system, applying a first neural network model to the video data to detect that one or more frames are missing, where the first neural network model has been trained to detect missing frames based on training data in which an artificial gap has been introduced. In response to detecting that the one or more frames are missing, a second model is applied to the video data to generate one or more replacement frames. The one or more replacement frames are based on at least a first frame prior to the detected dropped one or more frames, and a second frame after the detected dropped one or more frames. Modified video data is generated using the plurality of frames and the replacement frames.
12
US2021004703A1
TEMPORAL EXPLANATIONS OF MACHINE LEARNING MODEL OUTCOMES
Publication/Patent Number: US2021004703A1 Publication Date: 2021-01-07 Application Number: 16/460,934 Filing Date: 2019-07-02 Inventor: Zoldi, Scott Michael   Rahman, Shafi Ur   Assignee: FAIR ISAAC CORPORATION   IPC: G06N5/04 Abstract: In transactional systems where past transactions can have impact on the current score of a machine learning based decision model, the transactions that are most responsible for the score and the associated reasons are determined by the transactional system. A system and method identifies such past transactions that maximally impact the current score and allow for a more effective understanding of the scores generated by a model in a transactional system and explanation of specific transactions for automated decisioning, to explain the scores in terms of past transactions. Further an existing instance-based explanation system is used to identify the reasons for the score, and how the identified transactions influence these reasons. A combination of impact on score and impact on reasons determines the most impactful past transaction with respect to the most recent score being explained.
13
US2021004707A1
QUANTUM PULSE OPTIMIZATION USING MACHINE LEARNING
Publication/Patent Number: US2021004707A1 Publication Date: 2021-01-07 Application Number: 16/458,586 Filing Date: 2019-07-01 Inventor: Gambetta, Jay M.   Faro, Sertage Ismael   Nation, Paul   Martin, Fernandez Francisco Jose   Assignee: International Business Machines Corporation   IPC: G06N10/00 Abstract: Techniques for facilitating quantum pulse optimization using machine learning are provided. In one example, a system includes a classical processor and a quantum processor. The classical processor employs a quantum pulse optimizer to generate a quantum pulse based on a machine learning technique associated with one or more quantum computing processes. The quantum processor executes a quantum computing process based on the quantum pulse.
14
US2021004723A1
LEARNING DEVICE, LEARNING METHOD, AND LEARNING PROGRAM
Publication/Patent Number: US2021004723A1 Publication Date: 2021-01-07 Application Number: 16/982,798 Filing Date: 2019-01-29 Inventor: Kanno, Go   Assignee: NEC Corporation   IPC: G06N20/00 Abstract: Provided is a learning device that can accurately exclude training data inappropriate for learning a model from training data and can learn the model. A selecting means 73 selects first training data and second training data. Using the first training data and the second training data, a second learning means 74 learns a second model for evaluating training data by machine learning. In a case where the second model has been generated at the time of learning a first model, a first learning means evaluates each of the training data by applying each of the training data to the second model, excludes training data of a prescribed evaluation, and learns the first model.
15
US10885463B2
Metadata-driven machine learning for systems
Publication/Patent Number: US10885463B2 Publication Date: 2021-01-05 Application Number: 15/288,978 Filing Date: 2016-10-07 Inventor: Hansen, Klaus Marius   Botez, Andreea-bogdana   Panko, Andrei S.   Hejlsberg, Thomas   Perisic, Marko   Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC   IPC: G06N20/00 Abstract: Training prediction models and applying machine learning prediction to data is illustrated herein. A prediction instance comprising a set of data and metadata associated with the set of data identifying a prediction type is obtained. The data and metadata are used to determine an entity to train a prediction model using the prediction type. A trained prediction model is obtained from the entity. A notification system may be configured to react to monitor contextual information and apply the prediction. A workflow system may automatically perform a function in a workflow based on prediction.
16
US2021004649A1
Centroid for Improving Machine Learning Classification and Info Retrieval
Publication/Patent Number: US2021004649A1 Publication Date: 2021-01-07 Application Number: 17/024,439 Filing Date: 2020-09-17 Inventor: Luan, Jian   Wolff, Matthew   Wallace, Brian Michael   Assignee: Cylance Inc.   IPC: G06K9/62 Abstract: Centroids are used for improving machine learning classification and information retrieval. A plurality of files are classified as malicious or not malicious based on a function dividing a coordinate space into at least a first portion and a second portion such that the first portion includes a first subset of the plurality of files classified as malicious. One or more first centroids are defined in the first portion that classify files from the first subset as not malicious. A file is determined to be malicious based on whether the file is located within the one or more first centroids.
17
US10885558B2
Generating personalized banner images using machine learning
Publication/Patent Number: US10885558B2 Publication Date: 2021-01-05 Application Number: 16/155,255 Filing Date: 2018-10-09 Inventor: Zheng, Shuai   Kiapour, Mohammadhadi   Ramakrishnan, Nandini   Boudet, Christophe   Zaw, Jr. Fred Aye   Assignee: eBay Inc.   IPC: G06Q30/00 Abstract: A machine is configured to generate in real time personalized online banner images for users based on data pertaining to user behavior in relation to an image of a product. For example, the machine receives a user selection indicating one or more data features associated with the user. The one or more data features include a data feature pertaining to user behavior in relation to an image of a product. The machine generates, using a machine learning algorithm, a data representation of the machine learning algorithm based on the one or more data features including the data feature pertaining to user behavior in relation to the image of the product. The data representation includes one or more data features pertaining to one or more characteristics of online banner images. The machine generates an online banner image for the user based on the data representation.
18
US10885092B2
Media selection based on learning past behaviors
Publication/Patent Number: US10885092B2 Publication Date: 2021-01-05 Application Number: 15/954,866 Filing Date: 2018-04-17 Inventor: Cruz, Huertas Luis Carlos   Hamilton, Ii Rick A.   Narasimhamurthy, Hari K.   Zamora, Duran Edgar A.   Assignee: International Business Machines Corporation   IPC: G06F16/00 Abstract: A method, computer system, and a computer program product for selecting a media playlist based on learning past behaviors of a user is provided. The present invention may include receiving a plurality of current user data. The present invention may then include receiving a plurality of current external conditions data. The present invention may also include enriching a plurality of current raw data associated with the plurality of current user data, the plurality of user reactions to the media selections and the plurality of current external conditions data. The present invention may further include determining the plurality of current user data exceeds a threshold. The present invention may also include, in response to determining the threshold is exceeded, creating a dataset. The present invention may then include retrieving a media playlist. The present invention may further include sending the retrieved media playlist to a media device.
19
US10885332B2
Data labeling for deep-learning models
Publication/Patent Number: US10885332B2 Publication Date: 2021-01-05 Application Number: 16/354,352 Filing Date: 2019-03-15 Inventor: Bigaj, Rafal   Cmielowski, Lukasz G.   Oszajec, Marek   Erazmus, Maksymilian   Assignee: International Business Machines Corporation   IPC: G06K9/62 Abstract: A first and second scoring endpoint with payload logging are deployed. At the second scoring endpoint, native data and a user-generated score for the native data are received, the native data is pre-processed into readable data for the deep-learning model, and the user-generated score and the readable data are output to the first scoring endpoint, which is associated directly with the deep-learning model. A raw payload that includes the native data is output to a payload store. At the first scoring endpoint, the readable data and the user-generated score are processed by the deep-learning model, which outputs a transformed payload and a prediction, respectively, to the payload store. The raw payload is matched with the transformed payload and the prediction to produce a comprehensive data set, which is evaluated to describe a set of transformation parameters. The deep-learning model is retrained to account for the set of transformation parameters.
20
US10884795B2
Dynamic accelerator scheduling and grouping for deep learning jobs in a computing cluster
Publication/Patent Number: US10884795B2 Publication Date: 2021-01-05 Application Number: 15/963,331 Filing Date: 2018-04-26 Inventor: Liu, Junfeng   Feng, Kuan   Xu, Qing   Su, Zhichao   Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION   IPC: G06F9/46 Abstract: Embodiments for dynamic accelerator scheduling and grouping for deep learning jobs in a computing cluster. An efficiency metric of each job executing in the computing cluster is calculated to generate a prioritized job queue. Accelerator re-grouping execution plans are then generated based on the prioritized job queue, the accelerator re-grouping execution plans associated with a target cluster topology to be achieved according to the placement of selected jobs from the prioritized job queue in relation to a location of respective ones of a plurality of accelerators within the computing cluster. One of the accelerator re-grouping execution plans is executed to allocate the selected jobs to the respective ones of the plurality of accelerators to thereby shift the computing cluster to the target cluster topology.