中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

181 records (took 0.022 seconds)

    SYSTEM AND METHOD FOR LEARNING PREFERENCES IN DIALOGUE PERSONALIZATION
    1.
    发明申请
    SYSTEM AND METHOD FOR LEARNING PREFERENCES IN DIALOGUE PERSONALIZATION 审中-公开

    公开(公告)号：WO2019133706A1

    公开(公告)日：2019-07-04

    申请号：PCT/US2018/067666

    申请日：2018-12-27

    Applicant: DMAI, INC.

    Inventor： FANG, Rui ,  LIU, Changsong

    IPC: G06F3/0484

    CPC classification number: G06F17/2785 ,  G06F16/90332 ,  G06F16/9035 ,  G06F17/279 ,  G06F17/2881 ,  G06N5/043 ,  G06N20/00

    Abstract: The present teaching relates to method, system, medium, and implementations for user machine dialogue. Historic dialogue data related to past dialogues are accessed and used to learn, via machine learning, expected utilities. During a dialogue involving a user and a machine agent, a representation of a shared mindset between the user and the agent is obtained to characterize the current state of the dialogue, which is then used to update the expected utilities. Continuous expected utility functions are then generated based on the updated expected utilities, wherein the continuous expected utility functions are to be used in determining how to conduct a dialogue with a user.

    METHODS AND SYSTEMS FOR RESPONDING TO INQUIRIES BASED ON SOCIAL GRAPH INFORMATION
    2.
    发明申请
    METHODS AND SYSTEMS FOR RESPONDING TO INQUIRIES BASED ON SOCIAL GRAPH INFORMATION 审中-公开

    公开(公告)号：WO2019125503A1

    公开(公告)日：2019-06-27

    申请号：PCT/US2017/068442

    申请日：2017-12-26

    Applicant: FACEBOOK, INC.

    Inventor： LIU, Xiaohu ,  DUMOULIN, Benoit F. ,  LIU, Baiyang

    IPC: G06F17/30 ,  G06Q50/00 ,  G06Q10/10 ,  G06Q50/12

    CPC classification number: G10L15/265 ,  G06F17/2785 ,  G06F17/279 ,  G06F17/2881 ,  G06Q50/01 ,  G10L13/043 ,  G10L15/22 ,  G10L15/30

    Abstract: Exemplary embodiments relate to improvements in digital assistants incorporating personalization based on social network data. Various aspects of the agent, such as the agent's voice, language style, and avatar may be personalized. Personalization may be applied to components of an agent's architecture (e.g., the virtual agent's language model, natural language generator, voice generation component, etc.). Moreover, by interfacing with the social network's social graph, the agent may be provided with information useful to performing certain tasks (e.g., a calendar for scheduling, food preferences for ordering tasks, etc.). An agent may be provided (and personalized) for a single user, or a group of users (e.g., a family). The agent can be personalized to anyone, which may allow (e.g.) for the agent to represent a celebrity or a person who is not currently available in interactions with others. Different agents can talk to each other, e.g. for purposes of scheduling meetings.

    SYSTEMS AND METHODS FOR BUILDING STATE SPECIFIC MULTI-TURN CONTEXTUAL LANGUAGE UNDERSTANDING SYSTEMS
    7.
    发明申请
    SYSTEMS AND METHODS FOR BUILDING STATE SPECIFIC MULTI-TURN CONTEXTUAL LANGUAGE UNDERSTANDING SYSTEMS 审中-公开
    用于构建状态特定的多转向语境语义理解系统的系统和方法

    公开(公告)号：WO2017218370A1

    公开(公告)日：2017-12-21

    申请号：PCT/US2017/036926

    申请日：2017-06-12

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： SARIKAYA, Ruhi ,  KIM, Young-Bum ,  ROCHETTE, Alexandre

    IPC: G06F17/27

    CPC classification number: G06F17/279 ,  G06F17/2775 ,  G06F17/28 ,  G06F17/2881 ,  G10L15/063 ,  G10L15/1815 ,  G10L15/1822 ,  G10L15/22

    Abstract: Systems and methods for building a dialog-state specific multi-turn contextual language understanding system are provided. More specifically, the systems and methods infer or are configured to infer a state-specific schema and/or state-specific rules from a formed single-shot language understanding model and/or a single-shot rule set. As such, the systems and methods only require the information necessary to form a single-shot language understanding model and/or a single-shot rule set from a builder to form or build the dialog-state specific multi-turn contextual language understanding system. Accordingly, the systems and methods for building a dialog-state specific multi-turn contextual language understanding system reduce the expertise, time, and resources necessary to build a dialog-state specific multi-turn contextual language understanding system for an application when compared to systems and methods that require further input from the builder than necessary to build a single-shot language understanding system.

    Abstract translation:

    提供了用于构建对话状态特定的多回转语境语言理解系统的系统和方法。 更具体地说，所述系统和方法推断或被配置为从形成的单发语言理解模型和/或单发规则集推断出状态特定模式和/或状态特定规则。 因此，系统和方法仅需要形成构建器的单镜头语言理解模型和/或单镜头规则集所需的信息，以形成或构建对话状态特定的多轮上下文语言理解系统。 因此，与系统相比，用于构建对话状态特定多回转语境语言理解系统的系统和方法减少了为应用程序构建对话状态特定多回转语境语言理解系统所需的专业知识，时间和资源 以及需要构建者进一步输入才能构建单镜头语言理解系统的方法。

    METHODS AND SYSTEMS FOR APPENDING A GRAPHIC TO A DIGITAL MESSAGE
    8.
    发明申请
    METHODS AND SYSTEMS FOR APPENDING A GRAPHIC TO A DIGITAL MESSAGE 审中-公开
    用于将图形附加到数字消息的方法和系统

    公开(公告)号：WO2017096345A1

    公开(公告)日：2017-06-08

    申请号：PCT/US2016/064900

    申请日：2016-12-05

    Applicant: CODEQ LLC

    Inventor： FERNANDEZ, Paulo, Malvar ,  BAKER, Douglas, Dane ,  SMITH, Russ

    IPC: G06F13/00 ,  G06F15/16 ,  G06Q10/00 ,  H04L12/58

    CPC classification number: G06F3/04817 ,  G06F17/21 ,  G06F17/276 ,  G06F17/2785 ,  G06F17/279

    Abstract: Systems and methods for appending one or more graphics to a digital message are disclosed. In one embodiment, a method for appending one or more graphic to a digital message may include (1) receiving a digital message; (2) applying natural language processing to the digital image by at least one computer processor; (3) appending one or more graphic to the digital message based at least in part on the natural language processing; and (4) outputting the digital message with one or more appended graphic.

    Abstract translation: 公开了用于将一个或多个图形附加到数字消息的系统和方法。 在一个实施例中，用于将一个或多个图形附加到数字消息的方法可以包括（1）接收数字消息; （2）由至少一个计算机处理器对数字图像应用自然语言处理; （3）至少部分基于自然语言处理将一个或多个图形附加到数字消息; 和（4）用一个或多个附加图形输出数字消息。

    METHOD AND APPARATUS FOR FACILITATING CUSTOMER INTENT PREDICTION
    9.
    发明申请
    METHOD AND APPARATUS FOR FACILITATING CUSTOMER INTENT PREDICTION 审中-公开
    方法和设备，以方便客户的预测

    公开(公告)号：WO2017075081A1

    公开(公告)日：2017-05-04

    申请号：PCT/US2016/058908

    申请日：2016-10-26

    Applicant: 24/7 CUSTOMER, INC.

    Inventor： WALIA, Anmol

    IPC: G06F17/20

    CPC classification number: G06F17/279 ,  G06F17/2223 ,  G06F17/273 ,  G06F17/2735 ,  G06F17/278 ,  G06F17/30654 ,  H04M3/5166 ,  H04M3/527 ,  H04M7/0045

    Abstract: A computer-implemented method and an apparatus facilitate customer intent prediction. The method includes receiving natural language communication provided by a customer on at least one enterprise related interaction channel. Textual data corresponding to the natural language communication is generated by converting one or more non-textual portions in the natural language communication to a text form. One or more processing operations are performed on the textual data to generate normalized text. The normalized text is configured to facilitate interpretation of the natural language communication. At least one intention of the customer is predicted, at least in part, based on the normalized text and a reply is provisioned to the customer based on the predicted intention. The reply is provisioned to the customer on the at least one enterprise related interaction channel in response to the natural language communication.

    Abstract translation: 计算机实现的方法和装置便于客户意图预测。 该方法包括接收由客户在至少一个企业相关交互通道上提供的自然语言通信。 通过将自然语言通信中的一个或多个非文本部分转换为文本形式来生成与自然语言通信相对应的文本数据。 对文本数据执行一个或多个处理操作以生成标准化文本。 规范化文本被配置为便于对自然语言通信的解释。 至少部分基于标准化文本来预测客户的至少一个意图，并基于预测意图向客户提供答复。 响应于自然语言通信，将回答提供给至少一个企业相关交互通道上的客户。

    DETECTING ACTIONABLE ITEMS IN A CONVERSATION AMONG PARTICIPANTS
    10.
    发明申请
    DETECTING ACTIONABLE ITEMS IN A CONVERSATION AMONG PARTICIPANTS 审中-公开
    在参与者对话中检测可处理的项目

    公开(公告)号：WO2017053208A1

    公开(公告)日：2017-03-30

    申请号：PCT/US2016/052362

    申请日：2016-09-17

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： HAKKANI-TUR, Dilek Zeynep ,  HE, Xiaodong ,  CHEN, Yun-Nung

    IPC: G10L15/22 ,  G06F17/27 ,  G10L15/26

    CPC classification number: G10L15/16 ,  G06F17/2785 ,  G06F17/279 ,  G06N99/005 ,  G06Q10/10 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26

    Abstract: A computer-implemented technique is described herein for detecting actionable items in speech. In one manner of operation, the technique entails: receiving utterance information that expresses at least one utterance made by one participant of a conversation to at least one other participant of the conversation; converting the utterance information into recognized speech information; using a machine-trained model to recognize at least one actionable item associated with the recognized speech information; and performing at least one computer-implemented action associated the actionable item(s).The machine-trained model may correspond to a deep-structured convolutional neural network. In some implementations, the technique produces the machine-trained model using a source environment corpus that is not optimally suited for a target environment in which the model is intended to be applied. The technique further provides various adaptation techniques for adapting a source-environment model so that it better suits the target environment.

    Abstract translation: 本文描述了一种用于检测语音中的可操作项目的计算机实现的技术。 在一种操作方式中，技术包括：接收表达至少一个对话参与者的至少一个话语的话语信息给对话的至少一个其他参与者; 将话语信息转换成识别的语音信息; 使用机器训练的模型来识别与所识别的语音信息相关联的至少一个可操作项目; 并且执行与可操作项目相关联的至少一个计算机实现的动作。机器训练的模型可以对应于深层结构的卷积神经网络。 在一些实现中，该技术使用源环境语料库产生机器训练的模型，该源环境语料库不是最适合于其中应用模型的目标环境。 该技术进一步提供了各种适应技术，以适应源 - 环境模型，使其更适合于目标环境。

Patent Agency Ranking