公开(公告)号：US20220092403A1

公开(公告)日：2022-03-24

申请号：US17024788

申请日：2020-09-18

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Zhuoxuan Jiang ,  Lijun Mei ,  JIAN Wang ,  Zi Ming Huang

IPC: G06N3/08 ,  G06F40/40 ,  H04L12/58

Abstract: A method, system, and computer program product processes dialog data. The method includes obtaining dialog data including heterogeneous data items. The method includes generating a heterogeneous network based on the dialog data. The heterogeneous network includes two or more bipartite subnetworks representing the relationship of the data items in the dialog data. The nodes of the two or more bipartite subnetworks correspond to the data items in the dialog data. The method includes determining node representations for the nodes in the heterogeneous network through representation learning.

公开(公告)号：US20190132258A1

公开(公告)日：2019-05-02

申请号：US15802023

申请日：2017-11-02

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Yong Deng Hu ,  JING LI ,  Qiang Liu ,  Jing Quan ,  JIAN Wang ,  Xing Xing Di

IPC: H04L12/927

Abstract: A method, computer program product, and system are provided. A resource exhaustion is predicted based on the available resource and a consumption speed of the resource in a bare-metal server. Then it is determined whether the resource exhaustion will have an impact on the Service Level Agreement (SLA) and, responsive to the determination that the resource exhaustion will have an impact on the SLA, a control of the resource consumption speed is enacted to slow down the resource exhaustion and to maintain the SLA.

公开(公告)号：US20210081502A1

公开(公告)日：2021-03-18

申请号：US16569874

申请日：2019-09-13

Applicant: International Business Machines Corporation

Inventor： JIAN MIN JIANG ,  JIAN Wang ,  SONGFANG HUANG

IPC: G06F17/28 ,  G06F17/22

Abstract: Method and apparatus are presented for receiving a medical or medical condition related input term or phrase in a source language, and translating the term or phrase from the source language into at least one target language to obtain a set of translated terms of the input term. For each translated term in the set of translations, the method and apparatus further translate the set of translations back into the source language to obtain an output list of standard versions of the input term, scoring each entry of the output list as to probability of being the most standard version of the input term, and providing the entry of the output list that has the highest score to a user.