Patents Issued in April 18, 2023
-
Patent number: 11631002Abstract: An information processing device includes: a processor configured to: calculate a combination of t and q minimizing a computation time when q computation cores compute convolution between first matrices and second matrices of t-row t-column with Winograd algorithm in parallel, where a total number of elements of the first and second matrices does not exceed a number of sets of data that can be stored in each of q storage areas of a register, and the q computation cores correspond to the q storage areas; and output a program for causing a computing machine including the q computation cores and the register to execute a process including: storing the first and second matrices in each of the q storage areas with a calculated combination of t and q, and computing convolution between the first matrix and the second matrix with the Winograd algorithm by each of the q computation cores.Type: GrantFiled: May 28, 2020Date of Patent: April 18, 2023Assignee: FUJITSU LIMITEDInventor: Toshihiro Shimizu
-
Patent number: 11631003Abstract: Techniques for predicting states may include: receiving data sets of counter values, wherein each counter values denotes a number of times a particular code flow point associated with the counter value is executed at runtime during a specified time period; receiving images generated from the data sets; labeling each of the images with state information, wherein first state information associated with a first image indicates that the first image is associated with a first error state of a system or an application; training a neural network using the images to recognize the first state; receiving a next image generated from another data set; and predicting, by the neural network and in accordance with the next image, whether the system or the application is expected to transition into the first state. In at least one embodiment, the foregoing processing may optionally use matrices generated from the data sets rather than images.Type: GrantFiled: June 30, 2020Date of Patent: April 18, 2023Assignee: EMC IP Holding Company LLCInventors: Owen Martin, Benjamin A. Randolph, Scott J. Romano, Hani Zaitoun, Abhilash Sanap
-
Patent number: 11631004Abstract: Techniques and mechanisms for determining the pruning of one or more channels from a convolutional neural network (CNN) based on a gradient descent analysis of a performance loss. In an embodiment, a mask layer selectively masks one or more channels which communicate data between layers of the CNN. The CNN provides an output, and calculations are performed to determine a relationship between the masking and a loss of the CNN. The various masking of different channels is based on respective random variables and on probability values each corresponding to a different respective channel In another embodiment, the masking is further based on a continuous mask function which approximates a binary step function.Type: GrantFiled: March 28, 2018Date of Patent: April 18, 2023Assignee: Intel CorporationInventor: Alexey Kruglov
-
Patent number: 11631005Abstract: Various methods are provided for training and subsequently utilizing a convolutional neural network (CNN) to detect small pedestrians (e.g., pedestrians located away a large distance). One example method may comprise performing a first training stage in which a first CNN is trained to detect objects of a first size, the first CNN trained using a first set of images comprised of objects of the first size, and configured to output a first set of parameters, performing a second training stage in which a second CNN is trained using a second set of images, the second set of images comprising objects of a second size, and the first CNN is initialized with the first set of parameters and is re-trained using the second set of images, and determining parameters of the first CNN by minimizing error between the first CNN and the second CNN.Type: GrantFiled: May 31, 2016Date of Patent: April 18, 2023Assignee: NOKIA TECHNOLOGIES OYInventor: Jiale Cao
-
Patent number: 11631006Abstract: An optimization device includes: a plurality of search parts; and a controller that controls the plurality of search parts, wherein, each of the plurality of search parts includes a state holding part configured to hold each of values of a plurality of state variables included in an evaluation function representing an energy value, an energy calculation part configured to calculate a change value of the energy value generated in a case where any one of the values of the plurality of state variables is changed, and a transition controller configured to stochastically determine whether or not to accept a state transition by a relative relation between the change value of the energy value and thermal excitation energy, based on a set temperature value, the change value, and a random number value.Type: GrantFiled: July 24, 2020Date of Patent: April 18, 2023Assignee: FUJITSU LIMITEDInventor: Jumpei Koyama
-
Patent number: 11631007Abstract: The present invention relates to method and device for text-enhanced knowledge graph joint representation learning, the method at least comprises: learning a structure vector representation based on entity objects and their relation linking in a knowledge graph and forming structure representation vectors; discriminating credibility of reliable feature information and building an attention mechanism model, aggregating vectors of different sentences and obtain association-discriminated text representation vectors; and building a joint representation learning model, and using a dynamic parameter-generating strategy to perform joint learning for the text representation vectors and the structure representation vectors based on the joint representation learning model. The present invention selective enhances entity/relation vectors based on significance of associated texts, so as to provide improved semantic expressiveness, and uses 2D convolution operations to train joint representation vectors.Type: GrantFiled: February 8, 2021Date of Patent: April 18, 2023Assignee: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGYInventors: Feng Zhao, Tao Xu, Langjunqing Jin, Hai Jin
-
Patent number: 11631008Abstract: A system and method of creating electronic characters in one or more electronic formats, selectively customizing the characters, and presenting them via electronic channels in response to satisfaction of one or more programmable conditions is disclosed. The system enables entities to competitively bid to customize the personality and/or other attribute of a character. For example, a character may be presented via an electronic channel to an audience (e.g., one or more end users who view, listen to, or otherwise experience a character through an electronic channel). An entity may bid on altering that character's personality and/or other attribute. If the entity's bid is selected by the system (e.g., over other bids that also compete to alter one or more attributes of that character), the system customizes the character's personality and/or other attribute according to the winning bid's customization, and presents the customized character via the electronic channel to the audience.Type: GrantFiled: March 9, 2021Date of Patent: April 18, 2023Assignee: Pure Imagination Holdings, LLCInventors: Lisa Gai-Tzen Wong, Amit Tishler, Richard Paul Weeks
-
Patent number: 11631009Abstract: Approaches for multi-hop knowledge graph reasoning with reward shaping include a system and method of training a system to search relational paths in a knowledge graph. The method includes identifying, using an reasoning module, a plurality of first outgoing links from a current node in a knowledge graph, masking, using the reasoning module, one or more links from the plurality of first outgoing links to form a plurality of second outgoing links, rewarding the reasoning module with a reward of one when a node corresponding to an observed answer is reached, and rewarding the reasoning module with a reward identified by a reward shaping network when a node not corresponding to an observed answer is reached. In some embodiments, the reward shaping network is pre-trained.Type: GrantFiled: July 31, 2018Date of Patent: April 18, 2023Assignee: Salesforce.com, IncInventors: Xi Victoria Lin, Caiming Xiong, Richard Socher
-
Patent number: 11631010Abstract: The present application provides a system for use in a connected kitchen allowing a user to find and use traditional recipes as would be found in a recipe book but to have them automatically customized to their language, locality, dietary preferences and the appliances in their kitchen.Type: GrantFiled: April 19, 2019Date of Patent: April 18, 2023Assignee: ADAPTICS LIMITEDInventors: Tim Redfern, Ben Harris, Jack Phelan, Nicolas Nicolov Nicolov, Pablo Marti Gamboa
-
Patent number: 11631011Abstract: Methods, apparatus, and processor-readable storage media for automatically remediating storage device issues using machine learning techniques are provided herein. An example computer-implemented method includes obtaining performance-related information pertaining to one or more storage devices; automatically determining one or more workflows to be executed in connection with remediating at least one issue attributed to at least a portion of the one or more storage devices, wherein determining the one or more workflows comprises applying one or more machine learning techniques to the obtained performance-related information; and performing one or more automated actions based at least in part on the one or more workflows.Type: GrantFiled: January 31, 2020Date of Patent: April 18, 2023Assignee: EMC IP Holding Company LLCInventors: Ramya Ramachandran, Davidson Devasigamony, Jai Kumar, Sean Soltysik, Alik Saring
-
Patent number: 11631012Abstract: Described is an improved approach to implement an offline learning approach for machine learning that employs a window-based technique for predicting values within the window, and where outliers are identified and discarded from consideration. This approach efficiently permits offline learning to be employed in a manner that minimizes false positives, while also improving the quality of the data should retaining be required.Type: GrantFiled: June 30, 2020Date of Patent: April 18, 2023Assignee: Oracle International CorporationInventors: Zahra Khatami, Avneesh Pant
-
Patent number: 11631013Abstract: An actionable alert platform is provided. The platform may utilize artificial intelligence (“AI”) to formulate alert triggers that inform a user regarding unusual activity associated with a target transaction. The platform allows a user to enter customized criteria for an alert trigger and actionable responses for remediating the detected alert trigger. In response to detecting an alert trigger, the platform may formulate and transmit push notifications to a mobile device of user. The user may implement the actionable response directly from within the push notification. The platform may also provide push notifications to the user that advise on a status of the target transaction after applying the actionable response. An AI engine may generate additional alert triggers based on the criteria entered by the user. The AI engine may generate the actionable responses for any alert trigger.Type: GrantFiled: July 9, 2020Date of Patent: April 18, 2023Assignee: Bank of America CorporationInventors: Robert S. Mumma, Patrick Burgess, Trish Gillis
-
Patent number: 11631014Abstract: Systems and methods of the present disclosure include at least one processor that receives a data set of a data stream from a data source, where the data set includes a time-varying data points. The processor determines event observations associated with data points of the time-varying data points based on a detection model to identify types of the event observations, including: i) anomalies, ii) change-points, iii) patterns, or iv) outliers. The processor generates anomaly records in an event data store based on the event observations and automatically generates event records for at least one of the anomaly records based on variables of at least one dimension of the time-varying data points, where the event record links one or more event observations. The processor automatically applies changes in the event record to each event observation of the one or more event observations based on the linking by the event record.Type: GrantFiled: July 31, 2020Date of Patent: April 18, 2023Assignee: Capital One Services, LLCInventors: John C. Stocker, Parth Shrotri, Luke Botti, Scott Jemielity, Diana Yoo, Mark Roberts, Naga V. Gumpina, Daniel Snipes, Alan Rozet
-
Patent number: 11631015Abstract: An IP-to-Domain (IP2D) resolution system predicts which domain is most likely associated with an IP address. The resolution system generates unique source vote features (FSV) from (IP, domain, source) data. The FSV features are used to train a computer learning model that predicts which domain is most likely associated with an IP address. The domain predictions can then be used to more efficiently process events, more accurately calculate consumption scores, and more accurately detect associated company surges.Type: GrantFiled: September 10, 2020Date of Patent: April 18, 2023Assignee: Bombora, Inc.Inventors: Erik G. Matlick, Nicholaus Eugene Halecky, Benny Lin
-
Patent number: 11631016Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving training data, the training data being based upon interactions between a user and a cognitive learning and inference system; performing a hierarchical topic machine learning operation on the training data; generating a cognitive profile based upon the information generated by performing the hierarchical topic machine learning operation; and, generating a cognitive insight based upon the cognitive profile generated using the hierarchical topic machine learning operation.Type: GrantFiled: May 3, 2021Date of Patent: April 18, 2023Assignee: Tecnotree Technologies, Inc.Inventors: Ayan Acharya, Matthew Sanchez
-
Patent number: 11631017Abstract: Because digital assistants tend to have different areas of expertise and/or different abilities to fulfill a given request, it is sometimes difficult for a user to know which digital assistant is best able to fulfill a request. Representative embodiments disclose mechanisms to increase federate digital assistants so that a user's request can be funneled to the digital assistant best able to fulfill the user's request. A meta-assistant gathers information on skills provided by a set of digital assistants. The meta-assistant also gathers completion data for requests for different digital assistants and user satisfaction information. A user submits a request to the meta-assistant. The meta-assistant extracts user intent from the request and redirects the user's request to the digital assistant best able to fulfill the request. Embodiments can utilize trained machine learning models or scored algorithmic approaches to select the digital assistant.Type: GrantFiled: January 9, 2018Date of Patent: April 18, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Ryen White, Girish Sthanu Nathan
-
Patent number: 11631018Abstract: Aspects of the disclosure relate to performing enhanced exception processing using cognitive automation tools. In some embodiments, a computing platform may receive interaction data identifying one or more actions performed by one or more users in resolving a plurality of exception items associated with an exception queue. Subsequently, the computing platform may train, using a learning engine, a machine learning model to resolve a first exception and a second exception of one or more exceptions based on the interaction data. Based on training the machine learning model, the computing platform may generate one or more configuration commands directing a processing module to implement the machine learning model to process additional exception items associated with the exception queue. The computing platform then may send the one or more configuration commands to the processing module.Type: GrantFiled: June 1, 2020Date of Patent: April 18, 2023Assignee: Bank of America CorporationInventors: Christine Malabad, Jeffrey R. Goertz, Letishia R. Hunt, Clement Chellaraj, Eric Dryer, Clarence E. Lee, Charles Christopher Harbinson, Verlon S. Watson
-
Patent number: 11631019Abstract: A computing network has a sensor, a first processor in a first computing network location, and a second processor in a second computing network location, the second computing network location further from the sensor than the first computing network location. The first processor is configured to receive sensor data from the sensor and configured to operate a first machine learning model to make a first inference based on the sensor data. The second processor is configured to receive the sensor data and to operate a second machine learning model to make a second inference based on the sensor data in response to a trigger. The computing network is configured to collate and process the first and second inferences to make an aggregated inference.Type: GrantFiled: March 30, 2020Date of Patent: April 18, 2023Assignee: SEECHANGE TECHNOLOGIES LIMITEDInventor: David Packwood
-
Patent number: 11631020Abstract: Some embodiments of the present invention relate to systems and methods for estimating validation time that use an estimation of the amount of data fulfilling a rule or a set of rules. This estimation method may be more accurate because it considers how much data will match the rule versus how much data can be discarded. The disclosed systems and methods give visibility into how much time a rule set validation will take and how long the computer system will be unavailable due to the rule set being evaluated. This allows users to make better decisions about whether and when a rule set should be evaluated, and/or whether and how to modify implementation of the rule set.Type: GrantFiled: August 25, 2021Date of Patent: April 18, 2023Assignee: Visa International Service AssociationInventors: Gajanan Chinchwadkar, Navendu Misra, Sam Hamilton, Juharasha Shaik, Durga Kala, Ram Miryala
-
Patent number: 11631021Abstract: A method for identifying and ranking potentially privileged documents using a machine learning topic model may include receiving a set of documents. The method may also include, for each of two or more documents in the set of documents, extracting a set of spans from the document, generating, using a machine learning topic model, a set of topics and a subset of legal topics for the set of spans, generating a vector of probabilities for each span with a probability being assigned to each topic in the set of topics for the span, assigning a score to one or more spans in the set of spans by summing the probabilities in the vector that are assigned to a topic in the subset of legal topics, and assigning a score to the document. The method may further include ranking the two or more documents by their assigned scores.Type: GrantFiled: October 2, 2019Date of Patent: April 18, 2023Assignee: Text IQ, Inc.Inventors: Ethan Benjamin, Apoorv Agarwal
-
Patent number: 11631022Abstract: Soil and groundwater contamination migration are forecasted according to instructions stored in a memory and executable by a processor to facilitate prompt and accurate remediation efforts. In embodiments, an environmental machine learning model is employed, and analysis and determination of contaminant plume distances, sources and destinations are made. A database stores raw environmental site data, from which relevant data can be extracted for a site of interest, and the environmental machine learning model can be trained on the extracted relevant data to predict the spatial and cross-section probability distribution of a contaminant plume at the site of interest.Type: GrantFiled: March 13, 2019Date of Patent: April 18, 2023Assignee: Daybreak, LLCInventors: Jason R. Dalton, Anna M. Harrington
-
Patent number: 11631023Abstract: A quantum-mechanics station (?-station) and a cloud-based server cooperate to provide quantum mechanics as a service (?aaS) including real-time, exclusive, interactive sessions. The ?-station serves as a system for implementing “recipes” for producing, manipulating, and/or using quantum-state carriers, e.g., rubidium 87 atoms. The cloud-based server acts as an interface between the station (or stations) and authorized users of account holders. To this end, the server hosts an account manager and a session manager. The account manager manages accounts and associated account-based and user-specific permissions that define what actions any given authorized user for an account may perform with respect to a ?-station. The session manager controls (e.g., in real-time) interactions between a user and a ?-station, some interactions allowing a user to select a recipe based on wavefunction characterizations returned earlier in the same session.Type: GrantFiled: June 29, 2020Date of Patent: April 18, 2023Assignee: ColdQuanta, Inc.Inventors: Dana Zachary Anderson, Seth Charles Caliga, Farhad Majdeteimouri
-
Patent number: 11631024Abstract: An apparatus useful for creating and measuring states of an entangled system, comprising a pair of interacting multi-level systems, each of systems comprising a state |g>; a state |r>, and state |r*>. One or more first electromagnetic fields excite a first transition between the ground state |g> and the state |r> to create an entangled system. One or more second electromagnetic fields are tuned between the state |r> and the intermediate state |r*> so that any population of the systems in |r*> are dark to a subsequent detection of a population in the systems in |g>, providing a means to distinguish the entangled system in the state |g> and the entangled system in the state |r>. In one or more examples, the systems comprise neutral Rydberg atoms.Type: GrantFiled: February 10, 2021Date of Patent: April 18, 2023Assignee: California Institute of TechnologyInventors: Manuel Endres, Alexandre Cooper-Roy, Jacob P. Covey, Ivaylo S. Madjarov, Adam L. Shaw, Vladimir Schkolnik, Jason R. Williams, Joonhee Choi
-
Patent number: 11631025Abstract: A learning apparatus includes: an update unit which updates a dictionary used by a classifier; a calculation unit which calculates, by using a dictionary updated and one or more samples with labeling being samples assigned with labels, a ratio to a number of the samples with labeling as a loss with respect to all the samples with labeling; and a determination unit which determines whether to update the dictionary, by using the loss, wherein, when the determination unit determines to update the dictionary, the update unit updates the dictionary by using the samples with labeling added with a new sample with labeling, and wherein the determination unit determines whether to update the dictionary, by using a loss calculated by using the updated dictionary and a loss calculated by using the dictionary before updating with respect to all the samples with labeling before adding the new sample with labeling.Type: GrantFiled: January 5, 2016Date of Patent: April 18, 2023Assignee: NEC CORPORATIONInventor: Atsushi Sato
-
Patent number: 11631026Abstract: Systems, methods, and non-transitory computer readable media are configured to train a machine learning model. The training can be based on a training set of embeddings of a first type and a training set of embeddings of a second type. The machine learning model can be trained to receive an embedding of a second type and to output a corresponding embedding of the first type. A given embedding of the second type can be provided as input to the machine learning model. An embedding of the first type can be obtained from the machine learning model. The embedding of the first type can correspond to the given embedding of the second type.Type: GrantFiled: July 13, 2017Date of Patent: April 18, 2023Assignee: Meta Platforms, Inc.Inventors: Martin Schatz, Bradley Ray Green
-
Patent number: 11631027Abstract: The present disclosure relates to systems and methods for providing Online-to-Offline services. The method may include obtain first information associated with a first service request having been allocated to a service provider and having been accepted by the service provider. The method may also include obtaining second information associated with a second service request initiated via an application executed by a second requester terminal. The method may also include determining a matching parameter based on the first information and the second information by using at least one trained matching model and determining whether the matching parameter is larger than a threshold. The method may also include transmitting data associated with the second service request based on a result of the determination that the matching parameter is larger than the threshold.Type: GrantFiled: December 25, 2018Date of Patent: April 18, 2023Assignee: BEIJING INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.Inventors: Junqiang Fu, Xianyue Zeng, Yangbiao Liu, Zang Li
-
Patent number: 11631028Abstract: A tendency of an action of a robot may vary based on learning data used for training. The learning data may be generated by an agent performing an identical or similar task to a task of the robot. An apparatus and method for updating a policy for controlling an action of a robot may update the policy of the robot using a plurality of learning data sets generated by a plurality of heterogeneous agents, such that the robot may appropriately act even in an unpredicted environment.Type: GrantFiled: June 13, 2019Date of Patent: April 18, 2023Assignee: Samsung Electronics Co.. Ltd.Inventors: Jun-Won Jang, Kyung-Rock Kim, Taesin Ha
-
Patent number: 11631029Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for generating combined feature embeddings for minority class upsampling in training machine learning models with imbalanced training samples. For example, the disclosed systems can select training sample values from a set of training samples and a combination ratio value from a continuous probability distribution. Additionally, the disclosed systems can generate a combined synthetic training sample value by modifying the selected training sample values using the combination ratio value and combining the modified training sample values. Moreover, the disclosed systems can generate a combined synthetic ground truth label based on the combination ratio value. In addition, the disclosed systems can utilize the combined synthetic training sample value and the combined synthetic ground truth label to generate a combined synthetic training sample and utilize the combined synthetic training sample to train a machine learning model.Type: GrantFiled: September 9, 2019Date of Patent: April 18, 2023Assignee: Adobe Inc.Inventors: Nikaash Puri, Balaji Krishnamurthy, Ayush Chopra
-
Patent number: 11631030Abstract: A technique for training a model includes obtaining a training example for a model having model parameters stored on one or more computer readable storage mediums operably coupled to the hardware processor. The training example includes an outcome and features to explain the outcome. A gradient is calculated with respect to the model parameters of the model using the training example. Two estimates of a moment of the gradient with two different time constants are computed for the same type of the moment using the gradient. Using a hardware processor, the model parameters of the model are updated using the two estimates of the moment with the two different time constants to reduce errors while calculating the at least two estimates of the moment of the gradient.Type: GrantFiled: February 11, 2020Date of Patent: April 18, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventor: Tetsuro Morimura
-
Patent number: 11631031Abstract: Aspects of the disclosure relate to an automated model generation platform for recursive model building. A computing platform may receive a request for automated machine learning model building, and may identify a service offering corresponding to the request. Based on the identified service offering and using machine learning algorithms, the computing platform may select machine learning models and a corresponding sequence of model application (e.g., machine learning model information). The computing platform may store the machine learning model information along with a corresponding indication of the identified service offering. The computing platform may receive a request for model information corresponding to a service access request, and may identify that the service access request corresponds to a problem within the identified service offering.Type: GrantFiled: February 20, 2020Date of Patent: April 18, 2023Assignee: Bank of America CorporationInventor: Maharaj Mukherjee
-
Patent number: 11631032Abstract: An exemplary system, method, and computer-accessible medium can include, for example, (a) receiving a dataset(s), (b) determining if a misclassification(s) is generated during a training of a model(s) on the dataset(s), (c) generating a synthetic dataset(s) based on the misclassification(s), and (d) determining if the misclassification(s) is generated during the training of the model(s) on the synthetic dataset(s). The dataset(s) can include a plurality of data types. The misclassification(s) can be determined by determining if one of the data types is misclassified. The dataset(s) can include an identification of each of the data types in the dataset(s).Type: GrantFiled: May 11, 2020Date of Patent: April 18, 2023Assignee: CAPITAL ONE SERVICES, LLCInventors: Jeremy Goodsitt, Anh Truong, Reza Farivar, Fardin Abdi Taghi Abad, Mark Watson, Vincent Pham, Austin Walters
-
Patent number: 11631033Abstract: Methods related to a model training scheme performed on a computing device are described. The computing device may include a display module and a memory module storing multiple prediction models and item data that includes data of multiple items. Example methods may include displaying, on the display module, a first representation of at least one modality of one or more items among the multiple items; detecting an activity of a user of the computing device in response to displaying of the at least one modality of the one or more items to generate user activity log data; and evaluating at least one first prediction model of the multiple prediction models based on the user activity log data to generate an evaluation value of the at least one first prediction model. The at least one first prediction model may be related to a prediction of the one or more items.Type: GrantFiled: July 3, 2020Date of Patent: April 18, 2023Assignee: MERCARI, INC.Inventor: Yusuke Shibui
-
Patent number: 11631034Abstract: Techniques to generate a flavor profile using artificial intelligence are disclosed. A flavor classifier classifies flavors for a given set of ingredients of a recipe from a set of possible classes of flavors. The flavor classifier may use different deep learning models to allow for different granularity levels corresponding to each flavor based on desired preciseness with classification of a particular flavor. A respective flavor predictor may or may not be used for each granularity level based on output of a certainty level classifier used for determining a preceding level of granularity.Type: GrantFiled: April 2, 2021Date of Patent: April 18, 2023Assignee: NotCo Delaware, LLCInventors: Karim Pichara, Pablo Zamora, Matias Muchnick, Antonia Larranaga
-
Patent number: 11631035Abstract: Disclosed embodiments are a computing system and a computer-implemented method for distributed training of a machine learning model over a plurality of computing nodes, in a plurality of iterations, characterized by gradient gap based mitigation of the gradient staleness problem. The disclosed method evaluates the staleness of the gradient based on the difference in gradients between a central point, for example an iteration's common starting point, and the points reached by the respective computing node during one or more iterations, and aggregates the update steps from the plurality of computing nodes, while giving more weight to computing nodes having a lesser change in the gradient.Type: GrantFiled: November 5, 2020Date of Patent: April 18, 2023Assignee: Technion Research & Development Foundation LimitedInventors: Assaf Schuster, Saar Barkai, Ido Hakimi
-
Patent number: 11631036Abstract: According to an aspect of an embodiment, operations include controlling a user device to display a plurality of task-specific questions onto an electronic user interface (UI) of the user device. Each task-specific question corresponds to a check for presence of a bias in one of a sequence of development phases of a machine learning (ML) model. The operations further include receiving a first input comprising a plurality of user responses corresponding to the displayed plurality of task-specific questions and determining a set of biases associated with the ML model based on the received first input. The operations further include controlling the user device to display the determined set of biases and a set of plausible actions to mitigate an effect of the determined set of biases on the ML model.Type: GrantFiled: May 11, 2020Date of Patent: April 18, 2023Assignee: FUJITSU LIMITEDInventors: Ramya Malur Srinivasan, Ajay Chander
-
Patent number: 11631037Abstract: A System, Method, and Apparatus for Predicting Medical No-Shows and for Scheduling is provided. The system is based on a patient appointment schedule and indicators including office type, practice area, appointment type, engagement with the office leading up to appointment, and a variety of other characteristics of each patient and appointment. The indicators can be selected, weighted proportionately, and input into an algorithm for analysis and processing. The algorithm can then predict the likelihood of a no-show for the respective patient and appointment. The likelihood can then be used for scheduling to minimize the negative impact on the medical professional of the no-show. The algorithm can be used in conjunction with machine learning to improve its accuracy as it informs itself with experience and additional data points. The likelihood of a no-show can be incorporated into scheduling programs and made accessible on mobile devices, computers, and other monitoring devices.Type: GrantFiled: March 20, 2020Date of Patent: April 18, 2023Assignee: Mend VIP, Inc.Inventors: Matthew McBride, Brandon Lassiter, Paul Senzee, Zach Firestone, Nils Elde
-
Patent number: 11631038Abstract: A system and method for dispatching haul trucks includes a production planner configured to operate based on a production plan. The production planner computationally defines production arcs for transferring material from loading tools to dump sites, computationally develops one or more possible return arcs for each production arc, compiles a set of possible return arcs, and computationally selects a sub-set of the possible return arcs to command a real time dispatcher.Type: GrantFiled: April 22, 2020Date of Patent: April 18, 2023Assignee: Caterpillar Inc.Inventors: Russell A. Brockhurst, Kevin E. Gates
-
Patent number: 11631039Abstract: System trains machine learning model to determine content data, metadata, and context data for support ticket communications, in response to receiving support ticket communications. Machine learning model receives communication associated with support ticket, and determines content data, metadata, and context data for communication. System converts content data, metadata, and context data for communication into first impulse for first channel and second impulse for second channel. System determines first channel value based on first type of conversion of first impulse and any impulses for first channel that are converted from data that is determined for support ticket event. System determines second channel value based on second type of conversion of second impulse and any impulses for second channel that are converted from data that is determined for support ticket event. System uses first channel value and second channel value to generate priority associated with support ticket, and outputs priority.Type: GrantFiled: February 11, 2020Date of Patent: April 18, 2023Assignee: SupportLogic, Inc.Inventors: Charles Monnett, Carl Waldspurger, Lawrence Spracklen, Krishna Raj Raja
-
Patent number: 11631040Abstract: A system for implementing a trial in one or more fields is provided. In an embodiment, an agricultural intelligence computing system receives field data for a plurality of agricultural fields. Based, at least in part, on the field data for the plurality of agricultural fields, the agricultural intelligence computing system identifies one or more target agricultural fields. The agricultural intelligence computing system sends, to a field manager computing device associated with the one or more target agricultural fields, a trial participation request. The server receives data indicating acceptance of the trial participation request from the field manager computing device. The server determines one or more locations on the one or more target agricultural fields for implementing a trial and sends data identifying the one or more locations to the field manager computing device.Type: GrantFiled: February 21, 2020Date of Patent: April 18, 2023Assignee: CLIMATE LLCInventors: Thomas Gene Ruff, Jason Kendrick Bull, Nicholas Charles Cizek, Brandon Rinkenberger, Doug Sauder, Aaron E. Robinson, Timothy Reich, Hunter Merrill, Allan Trapp, Morrison Jacobs, Tonya Ehlmann, Daniel Williams, Christina Bogdan, Moslem Ladoni
-
Patent number: 11631041Abstract: Systems and methods as disclosed herein are provided for generating a research study application. A request to generate a research study is received from a user. A plurality of task generation options are presented on a graphical user interface of an electronic device. The plurality of task generation options are selected from the group consisting of a consent survey, an eligibility survey, a medical history survey, and a medical tracking survey. Input regarding the plurality of task generation options is received from the user. Additionally, a research study application is generated based on information received from the user.Type: GrantFiled: May 24, 2017Date of Patent: April 18, 2023Assignee: Medable Inc.Inventors: Michelle Rae Longmire, Ingrid Oakley-Girvan, Timothy Robert Smith, James Marcel Sas, Niraj Patel, Guillermo Biset, Fernando Waigandt, Matthew Lean, Analia Gigena
-
Patent number: 11631042Abstract: Systems and methods for assessing, tracking and improving security maturity of an organization are provided. Described is a system for assessing security maturity of an organization. The system receives a list of data sources located across multiple jurisdictions for the organization, collects data sources/data using custom rules from a plurality of data sources of the list of data sources, determine criticality score for each of the plurality of data sources, calculates data source coverage and asset collection coverage, determines use case coverage, and determines security maturity score using a maturity score model. The maturity score model is a logistic equation which is a function of the data source coverage, the asset collection coverage, the criticality score associated with each of the plurality of data sources, the use case coverage, asset coverage by each the plurality of data sources.Type: GrantFiled: November 8, 2021Date of Patent: April 18, 2023Assignee: deepwatch, Inc.Inventors: Patrick Orzechowski, Steven Van Wasshenova, Corey Bodzin, Greg Genung, Erik Horton
-
Patent number: 11631043Abstract: Methods and system for securing delivery of a parcel when an intended recipient is unavailable, comprising at least one storage receptacle having an electronically controlled locking mechanism, the storage receptacle comprising an interface for receiving an access code for facilitating unlocking of the storage receptacle, a wireless communication radio, and a processor. The system further comprises a remote service manager comprising an access code generator and a wireless communication radio for transmitting an access code to a mobile computing device operated by a delivery carrier.Type: GrantFiled: October 26, 2016Date of Patent: April 18, 2023Assignee: Sargent Manufacturing CompanyInventors: Mark A. Caterino, Kevin Kraus, Garrett Lovejoy, Jason Williams, Martin Huddart
-
Patent number: 11631044Abstract: The present invention is a method and a device for tracking the unloading and loading of containers from and onto carrying platforms of tracks, using unloading and loading motion activity time course patterns characteristic of a specific container in combination with a specific carrying platform of a truck. In the invention the device is connected to a specific container and records the tilting angle of the container in the time course of unloading and/or loading from and onto a specific platform of the truck. A digital data processor produces from the data a motion activity time course pattern curve which is compared and matched for fitness to a predetermined standard motion activity time course pattern curve for the specific container and specific carrying platform of a truck and sends the degree of fitness to a data receiving terminal system.Type: GrantFiled: March 26, 2018Date of Patent: April 18, 2023Assignee: CYBERGREEN LTD.Inventors: Thabit Takrouri, Yossi Israeli-Shalev
-
Patent number: 11631045Abstract: A computer device implements a method of scheduling production of packaged dairy products in a production plant by simulation. The method obtains a production target for dairy products to be produced and packaged in the production plant, recipes for production of the packaged dairy products, where each recipe defines ingredients and recipe activities, and production unit data that specifies existing production units and available fluid paths in the production plant and associates the existing production units with unit activities and production capacities. The method further performs the simulation by generating, as a function of the recipes and the production unit data, time schedules of recipe activities performed at least partly by one or more combinations of the existing production units to achieve the production target data, and evaluating the time schedules for selection of at least one time schedule for the production plant.Type: GrantFiled: May 29, 2019Date of Patent: April 18, 2023Assignee: Tetra Laval Holdings & Finance S.A.Inventor: Ruben Garay
-
Delivery product assembly in collaboration with intelligent autonomous vehicle transportation system
Patent number: 11631046Abstract: Aspects of the present invention disclose a method for coordinating assembly of a final product in transit via an autonomous vehicle. The method includes one or more processors identifying a delivery request from a user for a product. The method further includes identifying suppliers of component parts of the product. The method further includes determining common delivery routes of the component parts of the product, wherein the common delivery routes includes respective routes from locations of the one or more suppliers to a delivery destination of the delivery request. The method further includes determining a delivery path to the delivery destination of the product based at least in part on the common delivery routes. The method further includes generating a final delivery plan corresponding to the product for one or more autonomous vehicles based at least in part on the delivery path and the suppliers of the component parts.Type: GrantFiled: July 8, 2020Date of Patent: April 18, 2023Assignee: International Business Machines CorporationInventors: Sarbajit K. Rakshit, Mukundan Sundararajan -
Patent number: 11631047Abstract: Methods and systems are provided for geocoding. An example method encompasses receiving, from a delivery data corpus, a delivery data comprising one or more addresses. The method thereafter comprises identifying, one or more tokens from said one or more addresses. Further the method leads to calculating, for each of said one or more tokens, an end token score and a sub-sequence token score. The method thereafter encompasses chunking, said one or more addresses based on said end token score and said sub-sequence token score to generate one or more address chunks. Further the method comprises generating, one or more polygon regions for each generated address chunks based on said chunking. Thereafter the method comprises merging, one or more generated polygon regions for each of the generated address chunks.Type: GrantFiled: April 10, 2020Date of Patent: April 18, 2023Assignee: FLIPKART INTERNET PVT. LTD.Inventors: Vishal Srivastava, Priyam Tejaswin, Lucky Dhakad, Amar Kumar Dani, Mohit Kumar
-
Patent number: 11631048Abstract: Described are systems and techniques to present information to a user of a materials handling facility using a representative color. A representative color at an inventory location is determined based on one or more colors used at the inventory location. Once determined, the representative color may be used in the presentation of a user interface that includes item data and visual elements therein. The use of the representative color in the user interface facilitates the identification of items or an inventory location within the material handling facility.Type: GrantFiled: April 25, 2019Date of Patent: April 18, 2023Assignee: AMAZON TECHNOLOGIES, INC.Inventors: Alexander Michael McNamara, Korwin Jon Smith, Benjamin Ralph Hollis, Sridhar Boyapati, Jared Joseph Frank
-
Patent number: 11631049Abstract: An inventory, disposition, and order management system and method utilizes multiple data sources to obtain complementary and augmented product data to determine an enhanced set of product data that reflects product inventory and disposition history information in a supply chain. The system and method can utilize the complementary and augmented product data to formulate recommended orders to achieve product dealer sales goals. The system and method compare the product data obtained from the data sources and reconcile any discrepancies. In at least one embodiment, the product data includes product identification data, product inventory data, product configuration data, and product disposition history data. Obtaining data from multiple sources allows the system and method to develop more accurate and complete data through an audit and reconciliation process as opposed to data obtained from a single source.Type: GrantFiled: March 4, 2020Date of Patent: April 18, 2023Assignee: Versata Development Group, Inc.Inventors: Jon Loyens, David R. Middleton, Rahul Subramaniam, Aditya P. Kulkarni, Asif Ahmed Sheikh
-
Patent number: 11631050Abstract: Methods and systems for incorporating physical documents into a document review workflow involving electronic documents. One or more embodiments detect a presence of a physical document within a field of view of an AR device and map the physical document to an existing electronic document based on visual features of the physical document. Additionally, one or more embodiments determine at least one difference between the physical document and the electronic document and create, for the physical document and the electronic document a shared state mapping including the difference(s). One or more embodiments then apply the difference to the physical document or the electronic document by displaying the difference(s) in an AR layer within the field of view of the AR device or storing the difference(s) in the electronic document.Type: GrantFiled: April 7, 2020Date of Patent: April 18, 2023Assignee: Adobe Inc.Inventors: Vikas Marda, Roshni Sheikh, Kartik Sachan, Aman Singhal
-
Patent number: 11631051Abstract: A method for enterprise information management includes receiving first input information, from a first user, that corresponds to a first identifying a first feature of an organization. The method further includes generating, using the first input information, a first data object that represents the first feature of the organization. The method further includes generating a second data object based on second input information. The method further includes hierarchically associating the second data object with the first data object using the first input information and the second input information. The method further includes generating output information, in response to a second user accessing the first data object, based on the first data object, the second data object, and contact information associated with the second user. The method further includes displaying the output information on a display.Type: GrantFiled: August 28, 2020Date of Patent: April 18, 2023Assignee: iPaladin, LLCInventors: Jill Creager, Rafal Sniezynski, Gene Diveglia