中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

35 records (took 0.02 seconds)

    Sentiment analysis of data logs
    1.
    发明授权
    Sentiment analysis of data logs 有权
    数据日志的情绪分析

    公开(公告)号：US09536200B2

    公开(公告)日：2017-01-03

    申请号：US14011901

    申请日：2013-08-28

    Applicant: International Business Machines Corporation

    Inventor： Corville O. Allen ,  Kevin B. Haverlock ,  Michael D. Whitley

    IPC: G06F17/30 ,  G06N5/04 ,  G06F17/27

    CPC classification number: G06N5/041 ,  G06F17/2785

    Abstract: An approach is provided to use natural language processing (NLP) to analyze data logs. In the approach, a data log is analyzed with the data log including a number of entries. The analysis performed includes performance of a sentiment analysis of the entries using natural language processing. The result of the sentiment analysis results is a sentiment score. Entries from the data log are then visually highlighted based on their corresponding sentiment scores.

    Abstract translation: 提供了一种使用自然语言处理（NLP）来分析数据日志的方法。 在该方法中，使用包括多个条目的数据日志分析数据日志。 所进行的分析包括使用自然语言处理对条目进行情感分析。 情绪分析结果的结果是情绪评分。 然后从数据记录中的条目根据其相应的情绪评分进行视觉突出显示。

    Learning model for dynamic component utilization in a question answering system
    2.
    发明授权
    Learning model for dynamic component utilization in a question answering system 有权
    问答系统中动态组件利用的学习模型

    公开(公告)号：US09171478B2

    公开(公告)日：2015-10-27

    申请号：US13843103

    申请日：2013-03-15

    Applicant: International Business Machines Corporation

    Inventor： Corville O. Allen ,  Kyle L. Croutwater ,  Kevin B. Haverlock ,  Michael D. Whitley

    IPC: G09B7/02

    CPC classification number: G09B7/00 ,  G09B7/02

    Abstract: Mechanisms are provided in a data processing system for utilizing algorithms based on categories in a question answering system. The mechanisms capture a history of performance and correctness metrics for identifying efficiency of respective algorithms for finding answers to questions in respective question categories in a question answering system. The mechanisms determine sets of algorithms to use for respective question categories according to efficiency and correctness analysis. The mechanisms determine a question category of a given input question and execute a set of algorithms corresponding to the question category of the given input question that meet an efficiency threshold to contribute to finding a correct answer for the given input question.

    Abstract translation: 在用于利用问答系统中的类别的算法的数据处理系统中提供机制。 这些机制捕获了性能和正确性度量的历史，用于识别各种算法的效率，以在问答系统中的各个问题类别中找到问题的答案。 这些机制根据效率和正确性分析确定用于各个问题类别的算法集合。 这些机制确定给定输入问题的问题类别，并执行一组对应于给定输入问题的问题类别的算法，这些算法满足效率阈值，有助于为给定的输入问题找到正确答案。

    LEARNING MODEL FOR DYNAMIC COMPONENT UTILIZATION IN A QUESTION ANSWERING SYSTEM
    3.
    发明申请
    LEARNING MODEL FOR DYNAMIC COMPONENT UTILIZATION IN A QUESTION ANSWERING SYSTEM 有权
    在问题回答系统中动态组件利用的学习模型

    公开(公告)号：US20140272885A1

    公开(公告)日：2014-09-18

    申请号：US13843103

    申请日：2013-03-15

    Applicant: International Business Machines Corporation

    Inventor： Corville O. Allen ,  Kyle L. Croutwater ,  Kevin B. Haverlock ,  Michael D. Whitley

    IPC: G09B7/02

    CPC classification number: G09B7/00 ,  G09B7/02

    Abstract: Mechanisms are provided in a data processing system for utilizing algorithms based on categories in a question answering system. The mechanisms capture a history of performance and correctness metrics for identifying efficiency of respective algorithms for finding answers to questions in respective question categories in a question answering system. The mechanisms determine sets of algorithms to use for respective question categories according to efficiency and correctness analysis. The mechanisms determine a question category of a given input question and execute a set of algorithms corresponding to the question category of the given input question that meet an efficiency threshold to contribute to finding a correct answer for the given input question.

    Abstract translation: 在用于利用问答系统中的类别的算法的数据处理系统中提供机制。 这些机制捕获了性能和正确性度量的历史，用于识别各种算法的效率，以在问答系统中的各个问题类别中找到问题的答案。 这些机制根据效率和正确性分析确定用于各个问题类别的算法集合。 这些机制确定给定输入问题的问题类别，并执行一组对应于给定输入问题的问题类别的算法，这些算法满足效率阈值，有助于为给定的输入问题找到正确答案。

    COLLECTING DIGITAL ASSETS TO FORM A SEARCHABLE REPOSITORY
    4.
    发明申请
    COLLECTING DIGITAL ASSETS TO FORM A SEARCHABLE REPOSITORY 审中-公开
    收集数字资产，形成可搜索的报告

    公开(公告)号：US20140195532A1

    公开(公告)日：2014-07-10

    申请号：US13737977

    申请日：2013-01-10

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Vijay Dheap ,  Michael D. Whitley

    IPC: G06F17/30

    CPC classification number: G06F16/901

    Abstract: A digital asset is identified, and a copy of the digital asset to store in a repository. Program code tokenizes plaintext into a grammar, wherein the plaintext is associated with the digital asset. If the digital asset is an image the program code is instructed to identify colors and shapes within the image, and also relationships between the image and other digital assets stored in the repository. Contextual information corresponding to the digital asset is generated by utilizing the plaintext that is tokenized into the grammar, wherein the contextual information includes parameter values representing the colors, shapes, and relationships identified. The repository is queried to retrieve one or more copies of other digital assets having contextual information that matches with the contextual information corresponding to the digital asset that is identified. The computer annotates the copy of the digital asset within the repository to form searchable metadata.

    Abstract translation: 识别数字资产，以及存储在存储库中的数字资产的副本。 程序代码将明文标记为语法，其中明文与数字资产相关联。 如果数字资产是图像，则指示程序代码识别图像内的颜色和形状，以及图像和存储在存储库中的其他数字资产之间的关系。 通过利用被标记为语法的明文生成对应于数字资产的上下文信息，其中上下文信息包括表示所识别的颜色，形状和关系的参数值。 查询存储库以检索具有与所识别的数字资产相对应的上下文信息匹配的上下文信息的其他数字资产的一个或多个副本。 计算机在存储库中注释数字资产的副本以形成可搜索的元数据。

    Learning model for dynamic component utilization in a question answering system
    5.
    发明授权
    Learning model for dynamic component utilization in a question answering system 有权

    公开(公告)号：US11189186B2

    公开(公告)日：2021-11-30

    申请号：US16179513

    申请日：2018-11-02

    Applicant: International Business Machines Corporation

    Inventor： Corville O. Allen ,  Kyle L. Croutwater ,  Kevin B. Haverlock ,  Michael D. Whitley

    IPC: G09B7/00 ,  G09B7/02

    Abstract: Mechanisms are provided in a data processing system for utilizing algorithms based on categories in a question answering system. The mechanisms capture a history of performance and correctness metrics for identifying efficiency of respective algorithms for finding answers to questions in respective question categories in a question answering system. The mechanisms determine sets of algorithms to use for respective question categories according to efficiency and correctness analysis. The mechanisms determine a question category of a given input question and execute a set of algorithms corresponding to the question category of the given input question that meet an efficiency threshold to contribute to finding a correct answer for the given input question.

    Learning model for dynamic component utilization in a question answering system
    7.
    发明授权
    Learning model for dynamic component utilization in a question answering system 有权

    公开(公告)号：US10121386B2

    公开(公告)日：2018-11-06

    申请号：US14872307

    申请日：2015-10-01

    Applicant: International Business Machines Corporation

    Inventor： Corville O. Allen ,  Kyle L. Croutwater ,  Kevin B. Haverlock ,  Michael D. Whitley

    IPC: G09B7/00 ,  G09B7/02

    Abstract: Mechanisms are provided in a data processing system for utilizing algorithms based on categories in a question answering system. The mechanisms capture a history of performance and correctness metrics for identifying efficiency of respective algorithms for finding answers to questions in respective question categories in a question answering system. The mechanisms determine sets of algorithms to use for respective question categories according to efficiency and correctness analysis. The mechanisms determine a question category of a given input question and execute a set of algorithms corresponding to the question category of the given input question that meet an efficiency threshold to contribute to finding a correct answer for the given input question.

    SYSTEM AND METHOD FOR PROVIDING MORE APPROPRIATE QUESTION/ANSWER RESPONSES BASED UPON PROFILES
    8.
    发明申请
    SYSTEM AND METHOD FOR PROVIDING MORE APPROPRIATE QUESTION/ANSWER RESPONSES BASED UPON PROFILES 审中-公开
    提供更多相关问题的系统和方法/基于配置文件的回答

    公开(公告)号：US20160269472A1

    公开(公告)日：2016-09-15

    申请号：US14641954

    申请日：2015-03-09

    Applicant: International Business Machines Corporation

    Inventor： Donna K. Byron ,  Ashok Kumar ,  Mary D. Swift ,  Michael D. Whitley

    IPC: H04L29/08

    CPC classification number: H04L67/10 ,  G06F16/345 ,  G06Q10/101 ,  G06Q50/01 ,  H04L67/00 ,  H04L67/2838 ,  H04L67/306

    Abstract: A method, computer program product, and computer system for receiving, by a computing device, a question from a user. A first answer provided by a first subject matter expert is identified. A second answer provided by a second subject matter expert is identified. It is determined that a profile of the user matches a first profile of the first subject matter expert more than a second profile of the second subject matter expert. The first answer provided by the first subject matter expert is sent to the user with a preference over the second answer provided by the second subject matter expert based upon, at least in part, determining that the profile of the user matches the first profile of the first subject matter expert more than the second profile of the second subject matter expert.

    Abstract translation: 一种用于由计算设备接收来自用户的问题的方法，计算机程序产品和计算机系统。 确定由第一主题专家提供的第一个答案。 确定第二主题专家提供的第二个答案。 确定用户的简档与第二主题专家的第二简档匹配第一主题专家的第一简档。 第一主题专家提供的第一个答案是以至少部分地基于第一主题专家提供的第二个答案为基础的第二个主题提供的第二个答案发送给用户， 第一主题专家超过第二主题专家的第二轮廓。

    Determining answers in a question/answer system when answer is not contained in corpus
    9.
    发明授权
    Determining answers in a question/answer system when answer is not contained in corpus 有权
    在答案不包含在语料库中时，确定问题/答案系统中的答案

    公开(公告)号：US09336485B2

    公开(公告)日：2016-05-10

    申请号：US13914906

    申请日：2013-06-11

    Applicant: International Business Machines Corporation

    Inventor： Peter F. Haggar ,  Dane A. Johnson ,  Stephan J. Roorda ,  Richard L. Stillwell ,  Michael D. Whitley

    IPC: G06F17/30 ,  G06N5/02

    CPC classification number: G06N5/02 ,  G06F17/30684

    Abstract: Mechanisms are provided for generating an answer for an input question when the answer is not directly present in a corpus of information. An input question is received from a computing device and analyzed to determine whether the input question is requesting an answer that is calculable. In response to a determination that the input question is requesting an answer that is calculable, one or more constituent data values are retrieved, from a corpus of information, for calculating the requested answer to the input question. A value corresponding to the requested answer is calculated based on the one or more retrieved constituent data values and is then output as the requested answer to the input question.

    Abstract translation: 提供了当答案不直接出现在信息语料库中时，为输入问题产生答案的机制。 从计算设备接收输入问题并进行分析，以确定输入问题是否请求可计算的答案。 响应于输入问题要求可计算的答案的确定，从信息语料库检索一个或多个组成数据值，以计算对输入问题的请求答案。 基于一个或多个检索到的构成数据值计算与所请求的答案相对应的值，然后作为所请求的答案输出到输入的问题。

Patent Agency Ranking