System for generation of automated response follow-up

    公开(公告)号:US10970324B2

    公开(公告)日:2021-04-06

    申请号:US16125831

    申请日:2018-09-10

    Abstract: Aspects include generation of automated response follow-up. A response to a question from a user is received at a response follow-up system. The response follow-up system analyzes the response using natural language processing to identify one or more response terms. The response follow-up system generates one or more follow-up questions based on the one or more response terms. Based on the response, one or more follow-up responses to the one or more follow-up questions are pre-fetched from one or more content provider systems including one or more content servers, where a question answering system including the response follow-up system is communicatively coupled to the one or more content provider systems through a network. The response follow-up system modifies an aspect of a user interface displayed to the user based on the one or more follow-up questions and the one or more follow-up responses.

    Collaborative creation of annotation training data

    公开(公告)号:US09860308B2

    公开(公告)日:2018-01-02

    申请号:US14553028

    申请日:2014-11-25

    CPC classification number: H04L67/10 G06F17/241 G06Q10/101 H04L67/1095

    Abstract: Collaborative annotation of a document. A GUI is generated by a host computer that displays a document to annotate. The GUI is transmitted by the host computer to a plurality of client computers. Real time communication modes are established by the host computer between the client computers, each including communication channels between all the client computers. The host computer receives annotations entered into the GUIs at the client computers, each annotation identifying a span of words in the document to annotate and including an associated annotation type. The host computer updates the GUI to include for display the received annotations and inter-rater agreement statistics indicating the level of agreement between annotations received from each client computer and annotations received from the other client computers. The updated GUI is then transmitted by the host computer to the plurality of client computers.

    DETERMINING ANSWERS TO QUESTIONS USING A HIERARCHY OF QUESTION AND ANSWER PAIRS
    6.
    发明申请
    DETERMINING ANSWERS TO QUESTIONS USING A HIERARCHY OF QUESTION AND ANSWER PAIRS 审中-公开
    使用问题分析和回答对方法确定问题的答案

    公开(公告)号:US20160283581A1

    公开(公告)日:2016-09-29

    申请号:US14671300

    申请日:2015-03-27

    CPC classification number: G06F16/3329 G06F16/3331 G06F16/3344 G06F16/338

    Abstract: Software that answers questions asked of question answering systems, by performing the following steps: (i) identifying a hierarchy of question and answer pairs, where a first answer paired to a first question in the hierarchy of question and answer pairs includes at least a second answer paired to a second question in the hierarchy of question and answer pairs; (ii) receiving, by a question answering system, an input question from a first user; (iii) identifying first user contextual information pertaining to the first user; and (iv) answering the input question, by the question answering system, based, at least in part, on the hierarchy of question and answer pairs and the first user contextual information.

    Abstract translation: 通过执行以下步骤来回答问答系统问题的软件:(i)识别问答对的层次结构,其中第一个答案与问答对象层级中的第一个问题配对包括至少第二个 答案与问答对层次中的第二个问题配对; (ii)由问答系统接收来自第一用户的输入问题; (iii)识别与第一用户有关的第一用户上下文信息; 以及(iv)至少部分地基于问答系统回答输入问题,至少部分地基于问答对的层次结构和第一用户上下文信息。

    Displaying Quality of Question Being Asked a Question Answering System
    7.
    发明申请
    Displaying Quality of Question Being Asked a Question Answering System 有权
    显示问题质量问题回答系统

    公开(公告)号:US20150371137A1

    公开(公告)日:2015-12-24

    申请号:US14309637

    申请日:2014-06-19

    Abstract: A mechanism is provided in a data processing system for automatically generating question and answer pairs for training a question answering system for a given domain. The mechanism receives user input of question text for a question to be submitted to a question answering system in a user interface. The mechanism determines a question strength score for the question text. The question strength score represents a likelihood the question text will result in a correct answer with high confidence. The mechanism presents a graphical representation of the question strength score in the user interface.

    Abstract translation: 在数据处理系统中提供一种机制,用于自动生成用于训练给定域的问答系统的问答对。 该机制接收用户输入的问题文本,以便在用户界面中提交给问答系统的问题。 该机制确定问题文本的问题强度得分。 问题力量分数表示问题文本将导致高度置信的正确答案的可能性。 该机制呈现用户界面中问题强度得分的图形表示。

    Protecting Contents in a Content Management System by Automatically Determining the Content Security Level
    8.
    发明申请
    Protecting Contents in a Content Management System by Automatically Determining the Content Security Level 审中-公开
    通过自动确定内容安全级别来保护内容管理系统中的内容

    公开(公告)号:US20140149322A1

    公开(公告)日:2014-05-29

    申请号:US13686111

    申请日:2012-11-27

    CPC classification number: G06N5/02 G06Q10/10

    Abstract: An approach is provided to automatically classify and handle data. The approach is implemented by an information handling system. In the approach, data is received, from a sender, at a content management system. When the data is received, the system automatically utilizes an artificial intelligence (AI) engine (e.g., IBM Watson, etc.) to perform an unstructured information analysis using a pre-existing knowledge base. The result of using the AI engine is an identification of a confidentiality level of the data. The approach further performs an action based on the identified confidentiality level of the data.

    Abstract translation: 提供了一种自动分类和处理数据的方法。 该方法由信息处理系统实现。 在该方法中,从内容管理系统接收来自发送者的数据。 当接收到数据时,系统自动利用人工智能(AI)引擎(例如,IBM沃森等)使用预先存在的知识库来执行非结构化信息分析。 使用AI引擎的结果是识别数据的机密级别。 该方法进一步基于所识别的数据的机密级别执行动作。

    Ranking answers in ground truth of a question-answering system

    公开(公告)号:US10169423B2

    公开(公告)日:2019-01-01

    申请号:US14988780

    申请日:2016-01-06

    Abstract: A computer-implemented method for ranking answers of question-answer pairs in ground truth. The computer-implemented method includes annotating, via an annotation tool, the domain dictionary, including, at least one or more of lexicons, glossaries, knowledge base query for ranking the question-answer pairs. The computer-implemented method further includes defining search patterns of the annotated domain dictionary. The computer-implemented method further includes searching a documents corpus or knowledge based query of the domain dictionary for candidate answers of the question-answer pairs, based on the defined search patterns, the candidate are returned based on the search. The computer-implemented method for evaluating the candidate answers with the annotation tool to verify correctness or acceptability of the returned candidate answers based on the search.

Patent Agency Ranking