Abstract: Provided is a distributed machine learning device which can efficiently converge a plurality of parameters. The distributed machine learning device includes: block configuration determination unit that determines a plurality of configurations of blocks each being a subset of a plurality of parameters used for a prediction model, and acquires a change amount of each subset of parameters belonging to the block, based on a result of executing processing of optimizing the plurality of parameters, and changes an element of the subset of the parameters in the block, based on the acquired change amount.
Abstract: A method of monitoring network traffic of a connected vehicle. The method includes receiving network traffic information from a vehicle gateway, the network traffic information including malicious and/or benign information. The method also includes storing the network traffic information on a data server and periodically updating the network traffic information stored on the data server.
Abstract: An architecture for providing an on-demand dynamic cloudlet instantiation by leveraging a grouping of software defined network devices and their respective associated analytics modules. A method can comprise receiving quality of service data representing a 5G small cell device of a group of 5G small cell devices; generating a policy rule representing a predictive policy to facilitate an instantiation of a dynamic on-demand cloudlet node into a fog of dynamic on-demand cloudlet node instantiations; and facilitating the instantiation of the dynamic on-demand cloudlet node into the fog, by a hybrid fiber coaxial device, based on the policy rule and an indication received from the hybrid fiber coaxial that a traffic surge in communications with the 5G small cell device has occurred.
Abstract: A device may receive, from a network device in near-real time, a packet of data associated with network traffic of a network, wherein the packet includes privacy-related data and network-related data. The device may read the privacy-related data from the packet. The device may generate anonymous data based on the privacy-related data, wherein the anonymous data obscures the privacy-related data. The device may generate a mapping between the anonymous data and the privacy-related data. The device may combine the anonymous data and the network-related data to generate a masked packet. The device may provide the masked packet to a server device. The device may receive, from the server device, data identifying a recommendation that is generated by processing the masked packet with an artificial intelligence model. The device may perform one or more actions based on the recommendation.
Abstract: A device may receive a request for an operation that includes a plurality of processing steps may identify metadata information. The device may determine a first processing step, and select a first microservice to call and a first transport protocol to utilize to call the first microservice. The device may call the first microservice, and may receive, from the first microservice a first output. The device may determine a second processing step, and select a second microservice to call and a second transport protocol to utilize to call the second microservice, wherein the second transport protocol is different from the first transport protocol. The device may call the second microservice, and may receive, from the second microservice, a second output. The device may provide a response to the request based on the first output and the second output.
Type:
Grant
Filed:
October 14, 2021
Date of Patent:
November 15, 2022
Assignee:
Capital One Services, LLC
Inventors:
Tuhin Gupta, Prabhu Ranjith Kumar Koduri, Parameswaran V Vaidyanathan, Joji Thomas John, Ashwin Jacob, Siju Thomas, Kevin Gleaton, Amit Singh, Vivek Paul Chandrasekharan, Mithun Jose, Venkata Sudha Aluru, Manoj Pemmasani, Justin Reid, Michael P. Newell
Abstract: In a method for using a smart link to access a digital resource, a smart link access request is received from an electronic device interacting with a smart link, wherein a smart link provides access to at least one destination digital resource of a plurality of destination digital resources associated with the smart link. The at least one destination digital resource to access is determined based at least on the smart link access request. The electronic device is directed to the determined at least one destination digital resource.
Type:
Grant
Filed:
January 21, 2021
Date of Patent:
November 15, 2022
Assignee:
VMware, Inc.
Inventors:
Scott Tilney, Stephen Schmidt, Gary Grossi, Michelle Lee
Abstract: Resource utilization in edge-computing clusters and other computing clusters can be improved according to some aspects described herein. For example, an event handler can detect an event involving a state change to a data object. In response to detecting the event, the event handler can access an event registry storing relationships between a group of controllers and a group of events that are to be handled by the group of controllers. The event handler can determine, using the event registry, a controller that is configured to handle the event. The event handler can then transmit a command over a network to a computing cluster that includes a reconciler associated with the controller, where the command is for causing the reconciler to perform a reconciliation operation with respect to the data object. Separating the event-handling logic from the reconciliation logic in this way may improve resource utilization.
Type:
Grant
Filed:
May 21, 2021
Date of Patent:
November 15, 2022
Assignee:
RED HAT, INC.
Inventors:
Sebastien Han, Ricardo Noriega De Soto, Huamin Chen
Abstract: A coding and Incentive-based distributed computing management system includes: a parameter server that publishes a gradient descent computation task to update parameters of distributed computing, sends the published task to end devices, and groups end devices into clusters by receiving related information from the plurality of end devices, determines the number of stragglers in each cluster and sends the number of stragglers to the end devices, along with an encoding scheme for gradient descent computation, and distributes incentive to the end devices based on encoded results and the end devices that receive the published task from the parameter server, sends an intention to participate in the published task and related information to the parameter server, determines CPU-cycle frequencies by receiving information on the grouping of the end devices and related information from the parameter server, and performs encoding for gradient descent computation and send a computed gradient to the parameter server.
Type:
Grant
Filed:
September 17, 2021
Date of Patent:
November 8, 2022
Assignee:
KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
Inventors:
JunKyun Choi, Nakyoung Kim, Dae-Jin Kim, Hyunseo Park
Abstract: A method and device for machine learning wherein, in order to create favorable method conditions, an at least first machine learning model is trained via an at least first data set, a second machine learning model is trained via a second data set, an at least first prediction data set is formed via the trained at least first machine learning model, a second prediction data set is formed via the trained second machine learning model, a linking machine learning model is trained at least via the first prediction data set and the second prediction data set, a third prediction data set is formed via the linking machine learning model, and controlled variables for controlling a control apparatus are formed at least via the third prediction data set, such that the demand for computing power is reduced and the prediction accuracy and control accuracy are increased.
Abstract: A server system includes a database for storing data, a memory device for storing data selected from the data in the database, and a processing device that selects data from the database, stores the selected data in the memory device, and transmits over a communication network an availability signal to a client, the availability signal including an identifier of the selected data and indicating that the selected data is stored in the memory device and is available to be accessed by the client.
Type:
Grant
Filed:
January 30, 2020
Date of Patent:
November 1, 2022
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventors:
David Clerc, Jacques Fontignie, Luis Garcés-Erice, John G. Rooney, Paolo Scotton
Abstract: A computer-implemented method comprises receiving a subscription request from at least one subscriber, the subscription request defining one or more subscription parameters; obtaining one or more events from at least one publisher; marshalling the one or more events according to the one or more subscription parameters; and delivering the one or more events to the subscriber based on the marshalling.
Type:
Grant
Filed:
December 30, 2020
Date of Patent:
October 25, 2022
Assignee:
BlackBerry Limited
Inventors:
Nicholas Ivan Landry, Ashkan Amiri, Geordon Thomas Ferguson, Biswaroop Mukherjee
Abstract: A mechanism for providing connection to a database is described. A connection to the database is intercepted. The connection is assigned to an instance of the database. A sidecar is configured to proxy the connection to the database. The sidecar is stateless and passes all communications for the connection to the instance of the database.
Type:
Grant
Filed:
March 12, 2020
Date of Patent:
October 18, 2022
Assignee:
Cyral Inc.
Inventors:
Manav Ratan Mital, Srinivas Nageswarrao Vadlamani, Pramod Chandraiah, Hugo Araújo de Sousa
Abstract: A source of bias identification (SoBI) tool is provided that identifies sources of bias in a dataset. A bias detection operation is performed on results of a computer model, based on an input dataset, to generate groupings of values for a protected attribute corresponding to a detected bias in the operation of the computer model. The SoBI tool generates a plurality of sub-groups for each grouping of values. Each sub-group comprises an individual value, or a sub-range, for the protected attribute. The SoBI tool analyzes each of the sub-groups in the plurality of sub-groups, based on at least one source of bias identification criterion, to identify one or more sources of bias in the input dataset. The SoBI tool outputs a bias notification to an authorized computing device specifying the one or more sources of bias in the input dataset.
Type:
Grant
Filed:
June 25, 2020
Date of Patent:
October 18, 2022
Assignee:
International Business Machines Corporation
Abstract: A method and system for performing at least one service are disclosed. The method and system include receiving a communication for a data source at a wrapper. The wrapper includes a dispatcher and at least one service. The dispatcher receives the communication and is data agnostic. The method and system also include providing the communication from the dispatcher to the data source and to the at least one service. The at least one service inspects the communication and may perform additional functions.
Abstract: A technique for intruder detection is described. Communications for a data source in an organization are intercepted and analyzed to identify an intruder detection signature. An intrusion is determined based on the intruder detection signature and an alarm generated based on the intrusion.
Type:
Grant
Filed:
June 12, 2020
Date of Patent:
October 18, 2022
Assignee:
Cyral Inc.
Inventors:
Manav Ratan Mital, Srinivas Nageswarrao Vadlamani, Pramod Chandraiah, Pedro Henrique Bragioni Las-Casas, Kaizen Navid Towfiq, Timothy Do Nguyen
Abstract: A POI valuation method, apparatus, device and computer storage medium are disclosed. The method comprises: obtaining information of first POIs with known values and information of second POIs with unknown values within a regional range; creating a valuation model which is configured to revaluate a first POI using values of surrounding POIs of the first POI, the surrounding POIs including other first POIs and second POIs within a predetermined range of distance from the first POI, and adjusting values of second POIs in the surrounding POIs using an error between a revaluated value of first POI and the known value of the first POI; training the valuation model until the error is minimized; obtaining the values of the second POIs from the valuation model. The solutions may reduce the requirement for manpower and improve the valuation efficiency as compared with manually valuation of POIs one by one.
Type:
Grant
Filed:
July 22, 2020
Date of Patent:
October 11, 2022
Assignee:
BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
Inventors:
Miao Fan, Jizhou Huang, An Zhuo, Ying Li, Ping Li, Haifeng Wang
Abstract: Mechanisms for predicting a multimedia session MOS are provided. The multimedia session has a video session and an audio session. The video quality and the audio quality are represented by vectors of per-time-unit scores of video quality and audio quality, respectively. The multimedia session is represented by a vector of the rebuffering start times of each rebuffering event, and a vector of the rebuffering durations of each rebuffering event. Audiovisual quality features are generated from the vectors of per-time-unit scores of video and audio quality. Buffering features are generated from the vector of rebuffering start times of each rebuffering event and the vector of rebuffering durations of each rebuffering event. A multimedia session MOS is then estimated based on the generated audiovisual quality features and the generated buffering features.
Type:
Grant
Filed:
June 22, 2020
Date of Patent:
October 4, 2022
Assignee:
TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
Inventors:
Tomas Lundberg, Jing Fu, Gunnar Heikkilä, David Lindero, Junaid Shaikh
Abstract: The present invention is directed to systems and methods for providing secure dynamic address resolution and communication. Accordingly, a node may include processor and memory having instructions thereon, that when executed, cause the node to pair with another node. The pairing may include creating a DNS record on the node including a current address associated with the second node, this current address may be dynamically updated. The instructions may further allow the node to transmit a message to the second node, based on a resolved address from the DNS record on the first node. Authentication, dynamic message encryption and the provision of a DNS cache may further be implemented on the node.