中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.019 seconds)

    SEQUENTIAL DECISION ANALYSIS TECHNIQUES FOR E-SPORTS
    1.
    发明公开
    SEQUENTIAL DECISION ANALYSIS TECHNIQUES FOR E-SPORTS 审中-公开

    公开(公告)号：US20230169368A1

    公开(公告)日：2023-06-01

    申请号：US18154122

    申请日：2023-01-13

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Subhabrata Majumdar ,  Rajat Malik

    IPC: G06N5/04 ,  A63F13/46 ,  G06N20/00

    CPC classification number: G06N5/04 ,  A63F13/46 ,  G06N20/00

    Abstract: Aspects of the subject disclosure may include, for example, training a decision scoring model for an e-sport based on historical data for the e-sport. In various embodiments, the decision scoring model may be trained based on the historical data and on metadata associated with the e-sport. Some embodiments can include identifying a plurality of candidate in-game decision sequences based on decision parameters for a gameplay decision of an ongoing gaming session and a gaming session history for the ongoing gaming session. Various embodiments can include applying the decision scoring model to rank the plurality of candidate in-game decision sequences. Other embodiments are disclosed.

    INCREASING INCLUSIVITY IN MACHINE LEARNING OUTPUTS
    2.
    发明申请
    INCREASING INCLUSIVITY IN MACHINE LEARNING OUTPUTS 有权

    公开(公告)号：US20220327419A1

    公开(公告)日：2022-10-13

    申请号：US17227311

    申请日：2021-04-10

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Cheryl Brooks ,  Balachander Krishnamurthy ,  Subhabrata Majumdar

    IPC: G06N20/00 ,  G06F16/901

    Abstract: A method includes constructing an information graph based on a set of training data provided to a machine learning algorithm, identifying an area of the information graph in which to increase an inclusion of the information graph, wherein the inclusion comprises a consideration of a population that is underrepresented in the information graph, collecting, from an auxiliary data source, auxiliary data about the population for use in increasing the inclusion of the information graph, utilizing the auxiliary data to increase the inclusion of the information graph, to generate an updated information graph, using the updated information graph to generate a test output that incorporates information from the auxiliary data, generating, when the test output satisfies an inclusion criterion, a runtime output using the updated information graph, receiving user feedback regarding the runtime output, and determining, in response to the user feedback, whether to further increase inclusion of the runtime output.

    SEQUENTIAL DECISION ANALYSIS TECHNIQUES FOR E-SPORTS
    3.
    发明申请
    SEQUENTIAL DECISION ANALYSIS TECHNIQUES FOR E-SPORTS 有权

    公开(公告)号：US20210304030A1

    公开(公告)日：2021-09-30

    申请号：US16836189

    申请日：2020-03-31

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Subhabrata Majumdar ,  Rajat Malik

    IPC: G06N5/04 ,  G06N20/00 ,  A63F13/46

    Abstract: Aspects of the subject disclosure may include, for example, training a decision scoring model for an e-sport based on historical data for the e-sport. In various embodiments, the decision scoring model may be trained based on the historical data and on metadata associated with the e-sport. Some embodiments can include identifying a plurality of candidate in-game decision sequences based on decision parameters for a gameplay decision of an ongoing gaming session and a gaming session history for the ongoing gaming session. Various embodiments can include applying the decision scoring model to rank the plurality of candidate in-game decision sequences. Other embodiments are disclosed.

    TRAINING DATA FIDELITY FOR MACHINE LEARNING APPLICATIONS THROUGH INTELLIGENT MERGER OF CURATED AUXILIARY DATA
    6.
    发明申请
    TRAINING DATA FIDELITY FOR MACHINE LEARNING APPLICATIONS THROUGH INTELLIGENT MERGER OF CURATED AUXILIARY DATA 有权

    公开(公告)号：US20230057792A1

    公开(公告)日：2023-02-23

    申请号：US17408384

    申请日：2021-08-21

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Balachander Krishnamurthy ,  Subhabrata Majumdar

    IPC: G06N20/00 ,  G06F16/215

    Abstract: In one example, a method includes identifying a target performance metric of a machine learning algorithm, wherein the target performance metric is to be improved, obtaining a set of auxiliary data from a plurality of auxiliary data sources, wherein the plurality of auxiliary data sources is separate from a training data set used to train the machine learning algorithm, selecting a candidate attribute type from the set of auxiliary data, identifying a quality metric for the candidate attribute type, calculating a change in the target performance metric when data values associated with the candidate attribute type are included in the training data set, determining that a tradeoff between the target performance metric and the quality metric of the candidate attribute type is satisfied by inclusion of the data values in the training data set, and training the machine learning algorithm using the training data set augmented with the data value.

    DATA-DRIVEN ENRICHMENT OF DATABASE ELEMENTS
    7.
    发明申请
    DATA-DRIVEN ENRICHMENT OF DATABASE ELEMENTS 有权

    公开(公告)号：US20220350810A1

    公开(公告)日：2022-11-03

    申请号：US17306300

    申请日：2021-05-03

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Subhabrata Majumdar ,  Rajat Malik

    IPC: G06F16/2457 ,  G06N20/00 ,  G06N7/00

    Abstract: Techniques for determining, modifying, and correcting data elements of documents, tables, and databases are presented. A data management component (DMC) can determine and extract entities of a group of entities, and relationships between entities, in documents, tables, and databases based on analysis of the entities and information relating thereto. DMC can determine a trained model representative of the entities and their relationships based on the relationships. For a subsequently received entity, DMC can predict a relationship between the subsequent entity and an entity of the entity group based on the model. DMC can determine candidate data modifications associated with the subsequent entity based on the relationship between the subsequent entity and the entity. DMC can rank the candidate data modifications based on probabilities that the candidate data modifications are a correct data modification, wherein data modification information relating to the ranking can be presented as an output.

    TEMPORAL BEHAVIOR-DRIVEN CURATION OF SHORT-FORM MEDIA SEGMENTS
    8.
    发明申请
    TEMPORAL BEHAVIOR-DRIVEN CURATION OF SHORT-FORM MEDIA SEGMENTS 有权

    公开(公告)号：US20220141549A1

    公开(公告)日：2022-05-05

    申请号：US17089640

    申请日：2020-11-04

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Subhabrata Majumdar ,  Deirdre Paul ,  Eric Zavesky

    IPC: H04N21/845 ,  H04N21/234

    Abstract: An example method includes extracting a plurality of candidate content segments from a first item of media content, wherein the plurality of candidate content segments is extracted over a first window of time and a second window of time, determining, for a first candidate content segment of the plurality of candidate segments that is extracted during both the first window of time and the second window of time, that user interest in the first candidate content segment is increasing, and generating a single stream of content segments, where the single stream of content segments includes a subset of the plurality of candidate content segments including the first candidate content segment.

    AUTOMATED, USER-DRIVEN, AND PERSONALIZED CURATION OF SHORT-FORM MEDIA SEGMENTS
    10.
    发明公开
    AUTOMATED, USER-DRIVEN, AND PERSONALIZED CURATION OF SHORT-FORM MEDIA SEGMENTS 审中-公开

    公开(公告)号：US20230156261A1

    公开(公告)日：2023-05-18

    申请号：US18155055

    申请日：2023-01-16

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Subhabrata Majumdar ,  Deirdre Paul ,  Eric Zavesky

    IPC: H04N21/2668 ,  H04N21/2343 ,  H04N21/83 ,  H04N21/258

    CPC classification number: H04N21/2668 ,  H04N21/2343 ,  H04N21/83 ,  H04N21/25891

    Abstract: An example method includes obtaining a plurality of candidate media segments for possible inclusion in a single stream of media segments that is personalized for a first user, wherein at least one candidate media segment of the plurality of candidate media segments comprises an excerpt from a media asset, selecting, based on a known media consumption behavior of the first user, a subset of the plurality of candidate media segments, wherein the subset includes candidate media segments of the plurality of candidate media segments that are to be included in the single stream of media segments, modifying at least one candidate media segment in the subset based on the known media consumption behavior of the first user, and compiling the subset into the single stream of media segments, wherein the single stream of media segments includes the at least one candidate media segment in the subset that was modified.

Patent Agency Ranking