利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

45 条记录 (耗时 0.022 秒)

    Travel itinerary recommendation engine using inferred interests and sentiments
    1.
    发明授权
    Travel itinerary recommendation engine using inferred interests and sentiments 有权

    公开(公告)号：US11100557B2

    公开(公告)日：2021-08-24

    申请号：US14532796

    申请日：2014-11-04

    申请人： International Business Machines Corporation

    发明人： Donna K. Byron ,  Ashok Kumar ,  Alexander Pikovsky ,  Mary D. Swift

    IPC分类号： G06Q30/06 ,  G06Q10/02 ,  G06F40/30 ,  G06Q50/14

    摘要： Travel itineraries are automatically prepared based upon user interests and sentiments inferred by deep semantic analysis of user-commented and user-preferred digital works of literature by receiving interests and associated sentiment levels for at least one user according to a deep semantic analysis of a plurality of works of literature, wherein the works of literature have been rated, commented, or both rated and commented by the user; searching repositories of travel items to find one or more matching travel items to the received more interests and associated sentiment levels; and preparing at least one travel itinerary including at least one found matching travel item. Travel itineraries may be prepared responsive to a user-initiated trip planning session, responsive to notification of a new travel item's availability, periodically, or a combination thereof.

    Cloud-driven hybrid data flow and collection
    2.
    发明授权
    Cloud-driven hybrid data flow and collection 有权

    公开(公告)号：US10834017B2

    公开(公告)日：2020-11-10

    申请号：US16186556

    申请日：2018-11-11

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Yuk L. Chan ,  Charles Kichler ,  Subbarao Seethamsetty ,  Mary D. Swift

    IPC分类号： H04L12/923 ,  H04L29/08 ,  G06F16/958

    摘要： Described herein are systems, devices, methods, computer-readable media, techniques, and methodologies for cloud-to-edge data flow migration. More specifically, example embodiments relate to migrating at least a portion of cloud-based data processing functionality from a cloud environment to network edge environment. The functionality can be migrated to anywhere along the network edge. Input data received or generated at a network edge device may be classified according to one or more classification criteria. At least a portion of cloud-based data processing functionality may then be selected for migration to the network edge based at least in part on the classified input data and/or one or more network characteristics. After migration, at least a portion of the input data may be processed by the migrated functionality. The input data processed at the network edge may then be sent to the cloud environment for additional processing by cloud-based data processing functionality.

    UTILIZING A DIALECTICAL MODEL IN A QUESTION ANSWERING SYSTEM
    3.
    发明申请
    UTILIZING A DIALECTICAL MODEL IN A QUESTION ANSWERING SYSTEM 有权
    在问题解答系统中应用对数模型

    公开(公告)号：US20160350279A1

    公开(公告)日：2016-12-01

    申请号：US14722862

    申请日：2015-05-27

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Donna K. Byron ,  Ashok Kumar ,  Mary D. Swift

    IPC分类号： G06F17/27 ,  G09B7/00

    CPC分类号： G06F17/2705 ,  G06F17/2785 ,  G06F17/30654 ,  G09B5/00 ,  G09B7/00

    摘要： A method, system or computer usable program product for utilizing a dialectical model for providing an answer to a user query including receiving a query from a user; applying NLP to the query to generate a first set of NLP structures; generating a contrary set of NLP structures contrary to the user query; evaluating the first set of NLP structures to identify a first set of evidence; evaluating the contrary set of NLP structures to identify a second set of evidence; evaluating a first set of hypotheses from the first set of NLP structures based by the first and second set of evidence, and a contrary set of hypotheses from the contrary set of NLP structures based by the first and second set of evidence, to determine a set of answers to the user query; and providing the set of answers to the user.

    摘要翻译： 一种用于利用辩证模型提供用户查询的答案的方法，系统或计算机可用程序产品，包括从用户接收查询; 将NLP应用于查询以生成第一组NLP结构; 产生与用户查询相反的相反的一组NLP结构; 评估第一组NLP结构以确定第一组证据; 评估相反的一组NLP结构，以确定第二组证据; 基于第一组和第二组证据，从第一组NLP结构评估第一组假设，以及基于第一和第二组证据的相反NLP结构集合的相反的一组假设，以确定一组 的用户查询的答案; 并向用户提供一组答案。

    USER INTERFACE FOR A QUERY ANSWERING SYSTEM
    6.
    发明申请
    USER INTERFACE FOR A QUERY ANSWERING SYSTEM 审中-公开

    公开(公告)号：US20180341699A1

    公开(公告)日：2018-11-29

    申请号：US16038153

    申请日：2018-07-17

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Donna K. Byron ,  Scott H. Isensee ,  Ashok Kumar ,  Mark Marrara ,  Mary D. Swift ,  Cale R. Vardy

    IPC分类号： G06F17/30 ,  G06F17/27

    摘要： A method, system or computer usable program product for utilizing a dialectical model for providing an answer to a user query including applying NLP to the query to generate a first set of NLP structures; generating a contrary set of NLP structures contrary to the user query; evaluating the first set of NLP structures to identify a first set of evidence; evaluating the contrary set of NLP structures to identify a second set of evidence; evaluating a first set of hypotheses from the first set of NLP structures and a contrary set of hypotheses from the contrary set of NLP structures to determine a set of answers to the user query; summarizing the set of answers including indicating derivation thereof; and providing the summarized set of answers to the user.

    SYSTEM AND METHOD FOR DEFINING AND USING DIFFERENT LEVELS OF GROUND TRUTH
    9.
    发明申请
    SYSTEM AND METHOD FOR DEFINING AND USING DIFFERENT LEVELS OF GROUND TRUTH 审中-公开
    用于定义和使用地面真相的不同水平的系统和方法

    公开(公告)号：US20170046624A1

    公开(公告)日：2017-02-16

    申请号：US14861254

    申请日：2015-09-22

    申请人： International Business Machines Corporation

    发明人： James W. Murdock, IV ,  Stephan J. Roorda ,  Mary D. Swift

    IPC分类号： G06N99/00

    CPC分类号： G06N99/005 ,  G09B7/00 ,  G09B7/02 ,  G09B19/06

    摘要： A method, computer program product, and computer system, for receiving a first set of ground truth instances from a first source. A second set of ground truth instances may be received from a second source. The first and second sets of ground truth instances may be weighed differently based on a level of trust associated with each of the first and second sources. The weighted first and second sets of ground truth instances may be applied in a machine learning task executed by a computer.

    摘要翻译： 一种用于从第一源接收第一组地面真值实例的方法，计算机程序产品和计算机系统。 可以从第二来源接收第二组地面真值实例。 可以基于与第一和第二源中的每一个相关联的信任级别来不同地对第一和第二组地面真实实例进行加权。 加权的第一和第二组地面真值实例可以应用于由计算机执行的机器学习任务中。