知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

252 records (took 0.044 seconds)

    ITERATIVE ANSWER AND SUPPLEMENTAL INFORMATION EXTRACTION FOR MACHINE READING COMPREHENSION
    1.
    发明公开
    ITERATIVE ANSWER AND SUPPLEMENTAL INFORMATION EXTRACTION FOR MACHINE READING COMPREHENSION 审中-公开

    公开(公告)号：US20230267342A1

    公开(公告)日：2023-08-24

    申请号：US17678275

    申请日：2022-02-23

    Applicant: International Business Machines Corporation

    Inventor： Sahil Bansal ,  Raunak Sinha ,  Seema Nagar ,  Atul Kumar

    IPC: G06N5/04

    CPC classification number: G06N5/04

    Abstract: Methods, systems, and computer program products for iterative answer and supplemental information extraction for machine reading comprehension are provided herein. A computer-implemented method includes obtaining a user query and items of context information related to the user query; identifying at least one of the items of context information to be used in connection with generating supplemental information by processing the user query and at least a portion of the multiple items of context information; generating the answer using an artificial intelligence-based question answering system; generating a modified version of the user query based on keywords derived from the generated answer and keywords derived from the user query; generating items of supplemental information for the generated answer by processing the modified version of the user query and the at least one identified item of context information; and performing automated actions based on the items of supplemental information.

    AUTOMATICALLY CLASSIFYING HETEROGENOUS DOCUMENTS USING MACHINE LEARNING TECHNIQUES
    5.
    发明申请
    AUTOMATICALLY CLASSIFYING HETEROGENOUS DOCUMENTS USING MACHINE LEARNING TECHNIQUES 有权

    公开(公告)号：US20220309276A1

    公开(公告)日：2022-09-29

    申请号：US17215641

    申请日：2021-03-29

    Applicant: International Business Machines Corporation

    Inventor： Atul Kumar ,  Sahil Bansal ,  Ruchi Mahindru ,  Seema Nagar ,  Daniela Rosu

    IPC: G06K9/00 ,  G06N20/00 ,  G06K9/62

    Abstract: Methods, systems, and computer program products for automatically classifying heterogeneous documents using machine learning techniques are provided herein. A computer-implemented method includes extracting multiple features from one or more sets of heterogeneous documents; arranging at least a portion of the extracted features into multiple hierarchically-defined classes; selecting one or more of the documents associated with each of the multiple hierarchically-defined classes; training at least one machine learning model using at least a portion of the selected documents; and automatically classifying at least one input document into one or more of the multiple hierarchically-defined classes by processing one or more portions of the at least one input document using the at least one trained machine learning model.

    Automatic summarization with bias minimization
    6.
    发明授权
    Automatic summarization with bias minimization 有权

    公开(公告)号：US11227099B2

    公开(公告)日：2022-01-18

    申请号：US16421159

    申请日：2019-05-23

    Applicant: International Business Machines Corporation

    Inventor： Manish Anand Bhide ,  Kuntal Dey ,  Nishtha Madaan ,  Seema Nagar ,  Sameep Mehta

    IPC: G06F40/151 ,  G06F40/205 ,  G06F17/18 ,  G06F40/284

    Abstract: A processor may receive a record. The record may include one or more segments of text. The processor may automatically generate a first summary of the record. The processor may determine an overall bias of the first summary. The overall bias of the first summary may be identified from one or more instances of bias in the first summary. The processor may generate a second summary of the record. The second summary of the record may include an indicator of the overall bias of the first summary. The indicator may include a description of a type of overall bias of the first summary and a numerical value of the overall bias of the first summary. The processor may determine an overall bias of the second summary. The processor may display the second summary of the record to a user.

    MULTI-CHANNEL BASED JUST-IN-TIME FIREWALL CONTROL
    8.
    发明申请
    MULTI-CHANNEL BASED JUST-IN-TIME FIREWALL CONTROL 有权

    公开(公告)号：US20210344645A1

    公开(公告)日：2021-11-04

    申请号：US16863206

    申请日：2020-04-30

    Applicant: International Business Machines Corporation

    Inventor： Pramod Vadayadiyil Raveendran ,  Seema Nagar ,  Sougata Mukherjea ,  Kuntal Dey

    IPC: H04L29/06

    Abstract: A method for controlling the transfer of data through a firewall. The method includes one or more computer processors establishing a first communication channel between a first server and a second server. The method further includes transmitting, via the first communication channel, information related to a pending transmission of data from the first server to the second server. The method further includes receiving from the second server, via the first communication channel, a set of security information associated with accessing the second server via a second communication channel. The method further includes establishing the second communication channel between the first server and the second server based on the set of security information received from the second server. The method further includes transmitting the data from the first server to the second server utilizing the established second communication channel.

    Supervised environment controllable auto-generation of HTML
    10.
    发明授权
    Supervised environment controllable auto-generation of HTML 有权

    公开(公告)号：US11093217B2

    公开(公告)日：2021-08-17

    申请号：US16701463

    申请日：2019-12-03

    Applicant: International Business Machines Corporation

    Inventor： Abhijit Mishra ,  Enara C Vijil ,  Seema Nagar ,  Kuntal Dey

    IPC: G06F9/44 ,  G06F8/30 ,  G06F16/951 ,  G06N3/08 ,  G06F8/60 ,  G06N3/04 ,  G06F8/20

    Abstract: In an approach to generating HTML based on a plurality of content and design controls, one or more computer processors crawl one or more conforming websites. The one or more computer processors create a training set of crawled conforming webpages, wherein each crawled conforming webpage in the training set of crawled conforming webpages includes associated web code labeled a combination of respective one or more content controls and respective one or more design controls; encode the combination of the respective one or more design controls and the respective one or more content controls based on one or more user preferences utilizing a created design encoder and a created content encoder; create a decoder with the training set of crawled conforming webpages and associated encoded content and design vectors; generate web code based on the encoded design and content controls utilizing the created decoder; implement generated web code.

Patent Agency Ranking