利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

1840 条记录 (耗时 0.022 秒)

    ANALYZING LANGUAGE UNITS FOR OPINIONS
    2.
    发明申请
    ANALYZING LANGUAGE UNITS FOR OPINIONS 审中-公开

    公开(公告)号：US20190205381A1

    公开(公告)日：2019-07-04

    申请号：US15858616

    申请日：2017-12-29

    申请人： Facebook, Inc.

    发明人： Antoine Raux ,  Martin Plouy

    IPC分类号： G06F17/27 ,  H04L12/58

    CPC分类号： G06F17/2785 ,  H04L51/02

    摘要： This application addresses techniques for personalizing natural language generation by conversational agents. These solutions allow for human-like, large scale opinion expression using a consistent style or personality. Training sentences may be retrieved and a vocabulary may be built based on an analysis of the training sentences. The sentences may be analyzed to determine: (1) whether they express an opinion; (2) whether the opinion is positive or negative; (3) whether the sentence fits in the context of the currently communication; and (4) whether the sentence came from a person with first-hand experience of the topic. Further classifications may be made based on characteristics such as the age or gender of the person expressing the opinion. These opinions may be entered into a repository and used for opinion expression, for example by using the statements directly in a conversation or by training a language generation model with the opinions.

    RELAY CHATBOT LINKED TO MULTIPLE CHATBOTS
    3.
    发明申请
    RELAY CHATBOT LINKED TO MULTIPLE CHATBOTS 审中-公开

    公开(公告)号：US20190199658A1

    公开(公告)日：2019-06-27

    申请号：US16220111

    申请日：2018-12-14

    申请人： KAKAO CORP.

    发明人： Yu Mi Kim ,  No Suk Myung ,  Ji Soo Hwang

    IPC分类号： H04L12/58 ,  G10L15/32 ,  G06F16/9032 ,  G06N20/00

    CPC分类号： H04L51/02 ,  G06F16/90332 ,  G06N20/00 ,  G10L15/32 ,  H04L51/046 ,  H04L51/14

    摘要： A chatbot server that provides an instant messaging service using a relay chatbot linked to multiple chatbots includes a receiving unit that receives, from a messenger server, a question message relevant to a service selected from multiple services and service account information corresponding to the selected service; a derivation unit that derives an answer to the question message using the relay chatbot corresponding to the service account information; and a transmission unit that transmits the answer to the messenger server, wherein the relay chatbot relays a user device to the multiple chatbots linked to the relay chatbot to derive the answer through at least one of the multiple chatbots.

    GENERATION AND RETRIEVAL OF REPORT INFORMATION
    5.
    发明申请
    GENERATION AND RETRIEVAL OF REPORT INFORMATION 审中-公开

    公开(公告)号：US20190158435A1

    公开(公告)日：2019-05-23

    申请号：US16253370

    申请日：2019-01-22

    申请人： Clover Leaf Environmental Solutions, Inc.

    发明人： John P. Killoran, JR. ,  Gina Katharine Von Damm ,  Dennis William Peek ,  Angela Kirkman

    IPC分类号： H04L12/58 ,  G06F16/955 ,  G06F16/24 ,  G06Q10/06

    CPC分类号： H04L51/02 ,  G06F16/24 ,  G06F16/955 ,  G06Q10/063112 ,  H04L51/30 ,  H04L51/34

    摘要： An information management system may store information related to tasks to be performed by workers in an organization. Workers in the organization may communicate with the information management system using email messages. The information management system may not require a login or authentication procedure, and workers may interact with the information management system without the need to log in to the information management system. The information management system may receive an email message from a worker that indicates a request for a report. The information management system may determine whether to transmit the report to the worker based on whether the worker is appropriately registered with the information management system, and/or whether the worker has administrative privileges. The information management system, in response to a positive determination, may transmit the report to the email address from which the requesting email message was sent.

    AUTHENTICATION OF SERVICE REQUESTS USING A COMMUNICATIONS INITIATION FEATURE
    6.
    发明申请
    AUTHENTICATION OF SERVICE REQUESTS USING A COMMUNICATIONS INITIATION FEATURE 审中-公开

    公开(公告)号：US20190132300A1

    公开(公告)日：2019-05-02

    申请号：US16026603

    申请日：2018-07-03

    申请人： LIVEPERSON, INC.

    发明人： Matan Barak ,  Todd Lewis ,  Justin Robert Mulhearn

    IPC分类号： H04L29/06 ,  H04L29/08 ,  H04L12/58 ,  H04L12/24

    CPC分类号： H04L63/08 ,  H04L41/00 ,  H04L51/02 ,  H04L51/046 ,  H04L51/18 ,  H04L51/32 ,  H04L67/02 ,  H04L67/141 ,  H04L67/306

    摘要： Described are computer-based methods and apparatuses, including computer program products, for facilitating communications initiated through a social networking account. A detected message communicated using a social networking account can be determined to satisfy a response criteria. Code for displaying a communications initiation feature on a customer communications apparatus associated with the social networking account can be transmitted. Selection information representing a selection of the communications initiation feature can be received and can include a parameter associated with the selection and origin information. The selection information can be validated by determining that the selection is associated with the social networking account and by comparing the parameter with a stored credential associated with the communications initiation feature. When the selection is validated, the communications can be facilitated.

    TURN-BASED REINFORCEMENT LEARNING FOR DIALOG MANAGEMENT
    7.
    发明申请
    TURN-BASED REINFORCEMENT LEARNING FOR DIALOG MANAGEMENT 审中-公开

    公开(公告)号：US20190115027A1

    公开(公告)日：2019-04-18

    申请号：US15782333

    申请日：2017-10-12

    申请人： Google LLC

    发明人： Pararth Shah ,  Larry Paul Heck ,  Dilek Hakkani-Tur

    IPC分类号： G10L15/30 ,  G06F17/30 ,  G10L15/16 ,  H04L12/58 ,  G10L17/22 ,  G10L15/00

    CPC分类号： G10L15/30 ,  G06F16/90332 ,  G06F17/27 ,  G10L15/005 ,  G10L15/16 ,  G10L15/22 ,  G10L17/22 ,  H04L51/02

    摘要： Techniques are described related to turn-based reinforcement learning for dialog management. In various implementations, dialog states and corresponding responsive actions generated during a multi-turn human-to-computer dialog session may be obtained. A plurality of turn-level training instances may be generated, each including: a given dialog state of the plurality of dialog states at an outset of a given turn of the human-to-computer dialog session; and a given responsive action that was selected based on the given dialog state. One or more of the turn-level training instances may further include a turn-level feedback value that reflects on the given responsive action selected during the given turn. A reward value may be generated based on an outcome of the human-to-computer dialog session. The dialog management policy model may be trained based on turn-level feedback values of the turn-level training instance(s) and the reward value.