Method and apparatus for multi-view conversational query production

    公开(公告)号:US11954136B2

    公开(公告)日:2024-04-09

    申请号:US17898867

    申请日:2022-08-30

    发明人: Linfeng Song

    IPC分类号: G06F16/00 G06F16/332 G06N5/02

    摘要: A method of training a model for query generation, the method performed by at least one processor and including receiving a training instance query corresponding to a dialogue history. The method further including generating a first static view of the model based on a number of common words between the training instance query and the dialogue history. The method further including generating a second static view of the model based on one or more tokens not covered by the dialogue history, the one or more tokens corresponding to one or more query words. The method further including generating a dynamic view of the model based on a score operation that compares a candidate query generated from the model with a target query. The method further including training the model based at least on the first static view, the second static view, and the dynamic view.

    POWER-EFFICIENT TRACKING USING MACHINE-LEARNED PATTERNS AND ROUTINES

    公开(公告)号:US20240114316A1

    公开(公告)日:2024-04-04

    申请号:US17957792

    申请日:2022-09-30

    申请人: Tile, Inc.

    摘要: A method comprises accessing historical signal and other information received from a tracking device configured to scan for signals transmitted by local devices and record other data as the tracking device moves within the geographic area during each of a plurality time intervals. A training dataset is generated based on the historical signal and other information and used to train a machine learning model configured to predict tracking device movement patterns. The machine learning model is applied to current signal and other information to detect a variance from one or more predefined routines associated with the tracking device. A notification is sent to a monitoring device associated with the tracking device in response to detecting the variance from the one or more predefined routines associated with the tracking device.

    System, Method, and Computer Program Product for Testing a Machine Learning Model Based on Simulations in an Offline Environment

    公开(公告)号:US20240112046A1

    公开(公告)日:2024-04-04

    申请号:US17959398

    申请日:2022-10-04

    IPC分类号: G06N5/02

    CPC分类号: G06N5/022

    摘要: Provided is a system for testing a machine learning (ML) model based on simulations in an offline environment that includes at least one processor programmed or configured to receive historical transaction data, generate online simulation data, wherein generating the online simulation data includes modifying the historical timestamp of each data record to provide online simulation data. The processor is further programmed or configured to determine a timeline for a plurality of data insertion actions and a plurality of data request actions based on the online simulation data, perform a simulation of online activities involving a stateful ML model using the timeline for the plurality of data insertion actions and the plurality of data request actions, and validate the stateful ML model based on the simulation of online activities. Methods and computer program products are also provided.

    USAGE DETECTION AND NOTIFICATION IN A HETEROGENEOUS COMPUTING PLATFORM

    公开(公告)号:US20240111610A1

    公开(公告)日:2024-04-04

    申请号:US17936864

    申请日:2022-09-30

    IPC分类号: G06F9/54 G06F9/48 G06N5/02

    摘要: Systems and methods for usage detection and notification in a heterogenous computing platform are described. In an illustrative, non-limiting embodiment, an Information Handling System (IHS) may include a heterogeneous computing platform comprising a plurality of devices and a memory coupled to the platform, where the memory comprises a plurality of sets of firmware instructions, where each of the sets of firmware instructions, upon execution by a respective device, enables the respective device to provide a corresponding firmware service, and where at least one of the plurality of devices operates as an orchestrator configured to: receive context or telemetry data from at least a subset of the plurality of devices and instruct one or more selected devices to execute one or more Artificial Intelligence (AI) models configured to characterize one or more workloads executed by the IHS based, at least in part, upon the context or telemetry data.

    Intelligent lock credential validation

    公开(公告)号:US11948412B2

    公开(公告)日:2024-04-02

    申请号:US17339194

    申请日:2021-06-04

    申请人: RemoteLock, Inc.

    摘要: A method for operating an access control device having a processor, a memory, and an internet connection comprises receiving a credential from a user; checking, by comparing the credential to matching credential information that would indicate the user is authorized to enter stored in the memory of the access control device, if no matching credential information that indicates the user is authorized is found in the memory of the access control device, then checking, at a remote cloud server, a list of buffered credential information for the matching credential information that indicates the user is authorized, and if the matching credential information that indicates the user is authorized is found, sending an unlock signal from the remote cloud server to the access control device.

    SYSTEMS AND METHODS FOR KNOWLEDGE GRAPH-ENABLED CROSS-DOMAIN ANALYTICS USING MACHINE LEARNING

    公开(公告)号:US20240104480A1

    公开(公告)日:2024-03-28

    申请号:US18057712

    申请日:2022-11-21

    IPC分类号: G06Q10/06 G06N5/02

    CPC分类号: G06Q10/06393 G06N5/02

    摘要: A method including collating data from a plurality of data sources into a first data repository; identifying, using a machine-learning model, class clusters and relationship clusters of the collated data in the first data repository; generating a domain-specific semantic model as a graph-structured data model based on the identified class clusters and relationship clusters; generating a data object model using the domain-specific semantic model and the collated data in the first data repository; creating a first domain-specific knowledge graph by associating the data object model with the domain-specific semantic model; creating a cross-domain analytics knowledge graph for deriving insights involving cross-domain analytics by merging the first domain-specific knowledge graph with a second domain-specific knowledge graph created from a second data repository; and deriving insights corresponding to performance of one or more of an asset or a process in a facility based on utilization of the cross-domain analytics knowledge graph.

    SYSTEMS AND METHODS TO ASSOCIATE AN EXCHANGE WITH ONE OF MULTIPLE CONTAINERS OF A CAPACITY PLAN

    公开(公告)号:US20240095088A1

    公开(公告)日:2024-03-21

    申请号:US17949459

    申请日:2022-09-21

    申请人: Simnang IP, LLC

    IPC分类号: G06F9/50 G06F9/445 G06N5/02

    摘要: Systems, methods, and computer-readable storage media to model exchanges of a capacity plan with configuration parameters and to provide a plurality of configuration parameters for individual exchanges included in a capacity plan. One system includes a communication network interface, a memory, and one or more processors. The memory to store a plurality of containers corresponding to the capacity plan, a ledger to broadcast exchanges associated with the capacity plan, and control structures to model exchanges with the configuration parameters of a given sub-ledger of the plurality of sub-ledgers. The one or more processors generate the plurality of containers and receive and broadcast exchanges.