中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.018 seconds)

    CLARIFICATION RECOMMENDATIONS FOR A LARGE LANGUAGE MODEL ANSWER WITH VARIOUS UNDERSTANDINGS OR MULTIPLE SUBTOPICS
    2.
    发明申请
    CLARIFICATION RECOMMENDATIONS FOR A LARGE LANGUAGE MODEL ANSWER WITH VARIOUS UNDERSTANDINGS OR MULTIPLE SUBTOPICS 有权

    公开(公告)号：US20250156651A1

    公开(公告)日：2025-05-15

    申请号：US18507620

    申请日：2023-11-13

    Applicant: International Business Machines Corporation

    Inventor： Ling Zhuo ,  Xiao Dong Wang ,  He Sheng Yang ,  Yi Shan Jiang ,  Yun Wang

    IPC: G06F40/40 ,  G06F16/9532 ,  G06F16/954

    Abstract: An embodiment detects by a Clustering Component of a Recommendation System, a candidate content based on a user query, responsive to the detected candidate content, executes a clustering algorithm on the detected candidate content to output a cluster and a cluster result. The embodiment decides, by a Recommendation Clarification Component of the Recommendation System, to recommend a clarification based on the cluster result, comprising computing a distance between a cluster and a response of a large language model to the user query where an option list is updated with the clarification where the clarification is based on the cluster and the distance. The embodiment also detects by the Recommendation System a selection in the option list, responsive to the detected selection, generates a prompt based on the selection where the prompt is inputted into the Recommendation System and the large language model.

    INTELLIGENT EXPANSION OF REVIEWER FEEDBACK ON TRAINING DATA
    4.
    发明公开
    INTELLIGENT EXPANSION OF REVIEWER FEEDBACK ON TRAINING DATA 审中-公开

    公开(公告)号：US20230214454A1

    公开(公告)日：2023-07-06

    申请号：US17568305

    申请日：2022-01-04

    Applicant: International Business Machines Corporation

    Inventor： Ke Wei Wei ,  Jun Wang ,  Shuang YS Yu ,  Guang Ming Zhang ,  Yuan Feng ,  Yi Dai ,  Ling Zhuo ,  Jing Xu

    IPC: G06K9/62 ,  G06N20/20

    CPC classification number: G06K9/6257 ,  G06K9/6263 ,  G06K9/6219 ,  G06N20/20

    Abstract: An embodiment generates an initial set of training data from monitoring data. The initial set of training data is generated by combining outputs from a plurality of pretrained classifiers. The embodiment trains a new classification model using the initial set of training data to identify anomalies in monitoring data. The embodiment performs a multiple-level clustering of the data samples resulting in a plurality of clusters of sub-clusters of data samples, and generates a review list of data samples by selecting a representative data sample from each of the clusters. The embodiment receives an updated data sample from the expert review that includes a revised target classification for at least one of the data samples of the expert review list. The embodiment then trains another replacement classification model using a revised set of training data that includes the updated data sample and associated revised target classification.

    Measure GUI response time
    5.
    发明授权
    Measure GUI response time 有权

    公开(公告)号：US11762939B2

    公开(公告)日：2023-09-19

    申请号：US17411297

    申请日：2021-08-25

    Applicant: International Business Machines Corporation

    Inventor： Ling Zhuo ,  Pei Pei Liang ,  Lin Yan Wu ,  Li Zhou ,  Yue Yang ,  Yun Bo Zhang ,  Tao Wen

    IPC: G06F40/14 ,  G06F16/957 ,  G06N5/04 ,  G06F18/21 ,  G06F18/22 ,  G06V30/18

    CPC classification number: G06F16/9574 ,  G06F18/21 ,  G06F18/22 ,  G06F40/14 ,  G06N5/04 ,  G06V30/18105

    Abstract: An approach is disclosed that determines an amount of time before a webpage is ready to use by a user by performing various actions. The approach captures a recording of the webpage from an invocation of the webpage for a period of time sufficient to load completely load the webpage with the capturing resulting in sequenced image frames. An AI system provides a loading point in the sequenced image frames based on an analysis of the frames input to the trained AI system. Image diversity and saturation measurements are calculated on consecutive image frames from the sequenced image frames resulting in an image change analysis. Native webpage events and times are detected from webpage characteristics gathered from the captured digital recording. The amount of time is then calculated based on the loading point from the AI system, the image change analysis; and the webpage events and their corresponding times.

    Recommending join operations of relational data among tables based on optimization model
    8.
    发明授权
    Recommending join operations of relational data among tables based on optimization model 有权

    公开(公告)号：US12093263B1

    公开(公告)日：2024-09-17

    申请号：US18123473

    申请日：2023-03-20

    Applicant: International Business Machines Corporation

    Inventor： Yuan Feng ,  Ling Zhuo ,  Qi Min ,  Pei Pei Liang ,  Yue Yang ,  Jun Wang

    IPC: G06F16/2455 ,  G06F11/34 ,  G06F16/242 ,  G06F16/2453

    CPC classification number: G06F16/2456 ,  G06F11/3409 ,  G06F16/2423 ,  G06F16/2453

    Abstract: A computer-implemented method, system and computer program product for recommending join operations of relational data among different tables. Relationships between one or more pairs of columns of relational data for one or more pairs of tables are identified by determining the semantic similarity between each pair of columns of relational data. The data content join converge for each of the identified relationships in connection with joining the tables involved in such identified relationships is determined. Furthermore, a join strength (indication of the degree that the relational data in the paired columns match) is calculated for each of the identified relationships based on the semantic similarity and the data content join coverage for such identified relationships. Based on the calculated join strength as well as other factors, a combination optimization algorithm identifies the best join combinations of relational data of the tables among a set of tables.

    TRAINING AND SCORING FOR LARGE NUMBER OF PERFORMANCE MODELS
    10.
    发明申请
    TRAINING AND SCORING FOR LARGE NUMBER OF PERFORMANCE MODELS 有权

    公开(公告)号：US20220318666A1

    公开(公告)日：2022-10-06

    申请号：US17218035

    申请日：2021-03-30

    Applicant: International Business Machines Corporation

    Inventor： Tong Luo ,  Yi Dai ,  Guang Ming Zhang ,  Bing Jiang Sun ,  Shun Xin Cao ,  Yan Chen ,  Ling Zhuo

    IPC: G06N20/00 ,  G05B23/02

    Abstract: A method is presented to facilitate the training of a very large number of machine-learning performance models used to detect anomalies in computing operations. The models are grouped together according to model type, and are allocated to different pods of a computing environment that is used to carry out the operations being monitored. Initial training of models in a group is carried out while monitoring resource usage, and a particular pod is selected for further training based on the resource usage. The pod selected for training preferably has a minimum change in resource usage before and after the initial training. A different pod can be selected for scoring the trained models. The pod selected for scoring preferably has a maximum resource usage during an initial scoring among all pods.

Patent Agency Ranking