公开(公告)号：US20250028571A1

公开(公告)日：2025-01-23

申请号：US18355018

申请日：2023-07-19

Applicant: International Business Machines Corporation

Inventor： Jin Wang ,  Lei Gao ,  A Peng Zhang ,  Xiang Zhen Gan ,  Xian Wu ,  Ke Du

IPC: G06F9/50

Abstract: A computer-implemented method, program product, and systems for managing distributed processes is provided. Embodiments of the present invention define additional system parameters to a kernel using a union structure. Embodiments of the present invention can then process information manager kernel using a cluster model using a formed distance between one node of the plurality and another node of the plurality. Embodiments of the present invention can then control an interval for information collection and sorting frequency for each node of the plurality of nodes in the system.

公开(公告)号：US12056622B2

公开(公告)日：2024-08-06

申请号：US17166793

申请日：2021-02-03

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jing James Xu ,  Lei Gao ,  A Peng Zhang ,  Rui Wang ,  Si Er Han ,  Xiao Ming Ma

IPC: G06N5/00 ,  G06N5/04

CPC classification number: G06N5/04

Abstract: A method for identifying influential effects that contribute most to a status change of a target index for goal seeking analysis. The method includes generating a candidate list of significant changed predictors between the normal and abnormal status time periods in collected data, and building a plurality of regression models from the collected data. The method determines a first value (trend value or Pearson correlation value) for each of the significant changed predictors based on whether at least one of the significant changed predictors have a significant change trend using the regression models. The method obtains a second predictor importance value for each of the significant changed predictors from a single model built on all the collected data. The method generates a final predictor value for each of the significant changed predictors by combining the first value with the second predictor importance value for each of the significant changed predictors.

公开(公告)号：US11971796B2

公开(公告)日：2024-04-30

申请号：US17323222

申请日：2021-05-18

Applicant: International Business Machines Corporation

Inventor： Xiao Ming Ma ,  Si Er Han ,  Lei Gao ,  A Peng Zhang ,  Chun Lei Xu ,  Rui Wang ,  Jing James Xu

IPC: G06F11/30 ,  G06N20/00

CPC classification number: G06F11/3055 ,  G06F11/3072 ,  G06N20/00

Abstract: An approach is provided in which the approach builds a combination model that includes a normal status model and an abnormal status model. The normal status model is built from a set of time-sequenced normal status records and the abnormal status model is built from a set of time-sequenced abnormal status records. The approach computes a set of time-sequenced coefficient combination values of the normal status model and the abnormal status model based on applying a set of fitting coefficient characteristics to the normal status model and the abnormal status model. The approach performs goal seek analysis on a system using the combination model and the set of time-sequenced coefficient combination values.

公开(公告)号：US11947449B2

公开(公告)日：2024-04-02

申请号：US17811198

申请日：2022-07-07

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Lei Gao ,  Jin Wang ,  A Peng Zhang ,  Kai Li ,  Jun Wang ,  Jing James Xu ,  Rui Wang ,  Xin Feng Zhu

IPC: G06F9/44 ,  G06F11/36

CPC classification number: G06F11/3692 ,  G06F11/3688

Abstract: Embodiments of the present disclosure relate to a method, system and computer program product for semantic search based on a graph database. In some embodiments, a method is disclosed. According to the method, the user jobs of a user are obtained from a first software product. Based on the user jobs, target test cases are selected from a plurality of test cases associated with the first software product and a second software product. The target test cases are applied to the first software product and the second software product, and in accordance with a determination that a result of applying the target test cases satisfies a predetermined criterion, an instruction is provided to indicate migrating from the first software product to the second software product. In other embodiments, a system and a computer program product are disclosed.

公开(公告)号：US20230306312A1

公开(公告)日：2023-09-28

申请号：US17699613

申请日：2022-03-21

Applicant: International Business Machines Corporation

Inventor： Xiao Ming Ma ,  Si Er Han ,  Xue Ying Zhang ,  Wen Pei Yu ,  Jing Xu ,  Jing James Xu ,  Lei Gao ,  A Peng Zhang

IPC: G06N20/10

CPC classification number: G06N20/10

Abstract: Examples described herein provide a computer-implemented method that includes determining a kernel width for the machine learning model. The method further includes building a local interpretable linear model using the kernel width. The method further includes computing a contribution and confidence for a feature of the local interpretable linear model. The method further includes updating the local interpretable linear model to generate a final model and computing an overall confidence for the final model.

公开(公告)号：US20220083519A1

公开(公告)日：2022-03-17

申请号：US17019383

申请日：2020-09-14

Applicant: International Business Machines Corporation

Inventor： Jing James Xu ,  Jing Xu ,  Xiao Ming Ma ,  Jian Jun Wang ,  Jun Wang ,  A Peng Zhang ,  Xing Wei

IPC: G06F16/215 ,  G06N5/04 ,  G06F16/21 ,  G06F16/2457 ,  G16H10/60

Abstract: Embodiments relate to a system, computer program product, and method for determining missing values in respective data records with an explanatory analysis to provide a context of the determined values. Such method includes receiving a dataset including incomplete data records that are missing predictors and complete data records. A model is trained with the complete data records and candidate predictors for the missing predictors are generated. A predictor importance value is generated for each candidate predictor and the candidate predictors that have a predictor importance value in excess of a first threshold value are promoted. Respective promoted candidate predictors are inserted into the respective incomplete data records, thereby creating tentative data records. The tentative data records are injected into the model, a fit value is determined for each of the tentative data records, and a tentative data record with a fit value exceeding a second threshold value is selected.

公开(公告)号：US11151309B1

公开(公告)日：2021-10-19

申请号：US16934175

申请日：2020-07-21

Applicant: International Business Machines Corporation

Inventor： Lei Gao ,  Xin Feng Zhu ,  Kai Li ,  A Peng Zhang ,  Jia Xing Tang ,  Jin Wang

IPC: G06F17/00 ,  G06F40/169 ,  G06K9/46 ,  G06T11/60 ,  G06K9/62

Abstract: Embodiments of the present disclosure relate to screenshot-based memos. In an embodiment, a computer-implemented method is disclosed. The method comprises a monitoring displaying screen on a computing device for determining whether the displaying screen reaches a preset trigger condition. The method further comprises capturing a snapshot of the displaying screen in response to the displaying screen reaching the preset trigger condition. The method further comprises matching one or more screenshots comprised in one or more screenshot-based memos and the captured snapshot for obtaining a similarity degree. The method further comprises deploying the one or more screenshot-based memos on the displaying screen in response to the similarity degree meeting a preset similarity threshold. In other embodiments, a system and a computer program product are disclosed.