中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.016 seconds)

    Reconstructing message flows based on hash values
    2.
    发明授权
    Reconstructing message flows based on hash values 有权

    公开(公告)号：US10425335B2

    公开(公告)日：2019-09-24

    申请号：US15708172

    申请日：2017-09-19

    Applicant: SAP SE

    Inventor： Joy Bhattacharjee ,  Anantharaman Ravi ,  Mohsin Soudagar ,  Lokesh Chouhan ,  Raghav Sampath

    IPC: H04L12/743 ,  H04L12/721 ,  H04L12/26 ,  H04L9/06 ,  H04L9/32

    Abstract: A hash value is determined based on a payload of a message associated with a first system, the hash value related to a message flow instance that includes the message, wherein the payload associates the message with the message flow instance. Upon sending the message to a second system, generating a first event corresponding to the message, wherein the first event includes the hash value. The first event is sent to a monitoring system. The monitoring system receives a second event including the hash value, wherein the hash value included in the second event is determined in association with the second system. Based on the hash value, a relation is determined to associate the first event and the second event with the message flow instance. The message flow instance is reconstructed based on the determined relation.

    RECONSTRUCTING MESSAGE FLOWS BASED ON HASH VALUES
    3.
    发明申请
    RECONSTRUCTING MESSAGE FLOWS BASED ON HASH VALUES 审中-公开

    公开(公告)号：US20190089633A1

    公开(公告)日：2019-03-21

    申请号：US15708172

    申请日：2017-09-19

    Applicant: SAP SE

    Inventor： Joy Bhattacharjee ,  Anantharaman Ravi ,  Mohsin Soudagar ,  Lokesh Chouhan ,  Raghav Sampath

    IPC: H04L12/743 ,  H04L9/06 ,  H04L12/26 ,  H04L12/721

    CPC classification number: H04L45/7453 ,  H04L9/0643 ,  H04L9/3239 ,  H04L43/026 ,  H04L43/08 ,  H04L45/38

    Abstract: A hash value is determined based on a payload of a message associated with a first system, the hash value related to a message flow instance that includes the message, wherein the payload associates the message with the message flow instance. Upon sending the message to a second system, generating a first event corresponding to the message, wherein the first event includes the hash value. The first event is sent to a monitoring system. The monitoring system receives a second event including the hash value, wherein the hash value included in the second event is determined in association with the second system. Based on the hash value, a relation is determined to associate the first event and the second event with the message flow instance. The message flow instance is reconstructed based on the determined relation.

    LARGE LANGUAGE MODELS FOR EXTRACTING CONVERSATIONAL-STYLE EXPLANATIONS FOR ENTITY MATCHES
    4.
    发明申请
    LARGE LANGUAGE MODELS FOR EXTRACTING CONVERSATIONAL-STYLE EXPLANATIONS FOR ENTITY MATCHES 有权

    公开(公告)号：US20250077773A1

    公开(公告)日：2025-03-06

    申请号：US18358225

    申请日：2023-07-25

    Applicant: SAP SE

    Inventor： Rajesh Vellore Arumugam ,  Anantharaman Ravi ,  Matthias Frank ,  Sundeep Gullapudi ,  Yi Quan Zhou

    IPC: G06F40/284 ,  G06F16/248 ,  G06F40/40

    Abstract: Methods, systems, and computer-readable storage media for receiving, by an entity matching ML model, a query and target pair including a query entity and a target entity, providing, by the entity matching ML model, a query-target prediction by processing the query entity and the target entity, the query-target prediction indicating a match type between the query entity and the target entity, generating a prompt by populating a prompt template with at least a portion of the query-target prediction, inputting the prompt into a large language model (LLM), and receiving, from the LLM, an explanation that is responsive to the prompt and that describes one or more reasons for the query-target prediction output by the entity matching ML model.

    ADAPTIVE TRAINING COMPLETION TIME AND STATUS FOR MACHINE LEARNING MODELS
    5.
    发明公开
    ADAPTIVE TRAINING COMPLETION TIME AND STATUS FOR MACHINE LEARNING MODELS 审中-公开

    公开(公告)号：US20230229961A1

    公开(公告)日：2023-07-20

    申请号：US17646889

    申请日：2022-01-04

    Applicant: SAP SE

    Inventor： Sundeep Gullapudi ,  Anantharaman Ravi ,  Denny Jee King Gee ,  Yi Qing Isaac New

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: Methods, systems, and computer-readable storage media for providing a set of heuristics representative of training data that is to be used to process a ML model through a training pipeline, the training pipeline including multiple phases, determining a set of time estimates by providing the set of heuristics as input to a training heuristics model that provides the set of time estimates as output, each time estimate in the set of time estimates indicating an estimated duration of a respective phase of the training pipeline, receiving, during processing of the ML model through the training pipeline, progress data representative of a progress of processing of the ML model, determining a set of status estimates including a status estimate for each phase of the training pipeline based on the progress data, and transmitting the set of time estimates and the set of status estimates for display.

    DEPLOYMENT OF MACHINE LEARNING MODELS USING LARGE LANGUAGE MODELS AND FEW-SHOT LEARNING
    6.
    发明申请
    DEPLOYMENT OF MACHINE LEARNING MODELS USING LARGE LANGUAGE MODELS AND FEW-SHOT LEARNING 有权

    公开(公告)号：US20250036974A1

    公开(公告)日：2025-01-30

    申请号：US18358245

    申请日：2023-07-25

    Applicant: SAP SE

    Inventor： Rajesh Vellore Arumugam ,  Anantharaman Ravi ,  Isaac New Yi Qing ,  Sundeep Gullapudi ,  Yi Quan Zhou

    IPC: G06N5/04 ,  G06N20/20

    Abstract: Methods, systems, and computer-readable storage media for providing, for a set of ML models, a set of training metrics determined using test data during a training phase, providing, for a production-use ML model, a set of inference metrics based on predictions generated by the production-use ML model, generating, by a prompt generator, a set of few-shot examples using the set of training metrics and the set of inference metrics, inputting, by the prompt generator, the set of few-shot examples to a LLM as prompts, transmitting, to the LLM a query, displaying, to a user, a recommendation that is received from the LLM and responsive to the query, receiving input from a user indicating a user-selected ML model responsive to the recommendation, and deploying a user-selected ML model to an inference runtime for production use.

    DYNAMIC CALIBRATION OF CONFIDENCE-ACCURACY MAPPINGS IN ENTITY MATCHING MODELS
    7.
    发明公开
    DYNAMIC CALIBRATION OF CONFIDENCE-ACCURACY MAPPINGS IN ENTITY MATCHING MODELS 审中-公开

    公开(公告)号：US20230214456A1

    公开(公告)日：2023-07-06

    申请号：US17646886

    申请日：2022-01-04

    Applicant: SAP SE

    Inventor： Sundeep Gullapudi ,  Rajesh Vellore Arumugam ,  Anantharaman Ravi ,  Prawira Putra Fadjar ,  Wei Xia

    IPC: G06K9/62

    CPC classification number: G06K9/6265

    Abstract: Methods, systems, and computer-readable storage media for receiving a first set of predictions generated by a ML model during execution of a training pipeline to train the ML model, each prediction in the first set of predictions being associated with a confidence, determining a set of confidence bins based on confidences of the first set of predictions, for each confidence bin in the set of confidence bins, providing an accuracy, processing the set of confidence bins and accuracies through a regression model to provide one or more regressions, each regression representing a confidence-to-accuracy relationship, defining a set of confidence thresholds based on at least one regression of the one or more regressions, and during an inference phase, applying the set of confidence thresholds to selectively filter predictions from a second set of predictions generated by the ML model.

    Reconstructing message flows based on hash values
    8.
    发明授权
    Reconstructing message flows based on hash values 有权

    公开(公告)号：US10986020B2

    公开(公告)日：2021-04-20

    申请号：US16535442

    申请日：2019-08-08

    Applicant: SAP SE

    Inventor： Joy Bhattacharjee ,  Anantharaman Ravi ,  Mohsin Soudagar ,  Lokesh Chouhan ,  Raghav Sampath

    IPC: H04L12/743 ,  H04L12/721 ,  H04L12/26 ,  H04L9/06 ,  H04L9/32

    Abstract: A hash value is determined based on a payload of a message associated with a first system, the hash value related to a message flow instance that includes the message, wherein the payload associates the message with the message flow instance. Upon sending the message to a second system, generating a first event corresponding to the message, wherein the first event includes the hash value. The first event is sent to a monitoring system. The monitoring system receives a second event including the hash value, wherein the hash value included in the second event is determined in association with the second system. Based on the hash value, a relation is determined to associate the first event and the second event with the message flow instance. The message flow instance is reconstructed based on the determined relation.

Patent Agency Ranking