专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US10474747B2 Adjusting time dependent terminology in a question and answer system 有权
公开(公告)号：US10474747B2
公开(公告)日：2019-11-12
申请号：US14107313
申请日：2013-12-16
申请人： International Business Machines Corporation
发明人： Daniel M. Jamrog , Jason D. LaVoie , Nicholas W. Orrick , Kristin A. Witherspoon
IPC分类号： G06F17/27
摘要： An approach is provided to adjust time dependent terminology in a question and answering (QA) system. The approach ingests a set of documents to produce a corpus utilized by the QA system. A base time is established and the approach acquires a temporally accurate lexicon of terms that correspond to the base time. A corpus of the QA system is updated according to the lexicon. The QA system answers a question according to the updated corpus.

2. 发明授权

US09519688B2 Collection and storage of a personalized, searchable, unstructured corpora 有权
公开(公告)号：US09519688B2
公开(公告)日：2016-12-13
申请号：US14517811
申请日：2014-10-18
申请人： International Business Machines Corporation
发明人： Daniel M. Jamrog , Jason D. LaVoie , Nicholas W. Orrick , Kristin A. Witherspoon
IPC分类号： G06F17/30 , G06F21/62 , G06F21/31 , H04L29/06
CPC分类号： G06F17/3053 , G06F17/30528 , G06F17/30554 , G06F17/30675 , G06F17/30696 , G06F17/30702 , G06F17/30867 , G06F21/31 , G06F21/62 , G06F21/6227 , H04L63/08 , H04L63/10
摘要： An approach is provided for utilizing unstructured corpora in a Question and Answer (QA) system. A question is received at the QA system. A private corpora is generated with the private corpora being associated with the user. The private corpora is generated from private data stores associated with the user as well as private data stores associated with other users. Access to the other user's private data sources is provided to the user by the other users. The system retrieves data responsive to the question from the private corpora. The responsive data is ranked based on its relevance to the question. Likely answers are identified based on the ranked responsive data and the likely answers are provided back to the user.

3. 发明申请

US20160110459A1 Realtime Ingestion via Multi-Corpus Knowledge Base with Weighting 有权
标题翻译：通过加权的多语料库知识库实时摄入
公开(公告)号：US20160110459A1
公开(公告)日：2016-04-21
申请号：US14517813
申请日：2014-10-18
申请人： International Business Machines Corporation
发明人： Daniel M. Jamrog , Jason D. LaVoie , Nicholas W. Orrick , Kristin A. Witherspoon
IPC分类号： G06F17/30
CPC分类号： G06F17/30867 , G06F17/30654
摘要： An approach is provided for updating corpora in a Question and Answer (QA) system. Ingestion of a first set of sources into a first corpus and a second set of sources into a second corpus with the second set of sources including updates to the first set of sources. A question is received. The system identifies candidate answers to the question using the sources included in the corpuses. Each candidate answer has a weighting. The system determines whether the first and second corpuses have an overlapping source from which two candidate answers were identified. If an overlapping source is found, the candidate answer from the overlapping source in the first corpus is assigned a lower weighting than the candidate answer from the second corpus. Likely answers are selected from the candidate answers based on the weighting and returned to the requestor.
摘要翻译：提供了一种在问答系统中更新语料库的方法。将第一组资源从第一组语料库和第二组资源中提取到具有第二组资源的第二语料库中，包括对第一组资源的更新。收到一个问题。系统使用语料库中包含的来源来识别问题的候选答案。每个候选答案都有加权。该系统确定第一和第二语料库是否具有从其中识别出两个候选答案的重叠源。如果找到重叠的源，则从第一语料库中的重叠源的候选答案被赋予比来自第二语料库的候选答案更低的权重。基于加权从候选答案中选择可能的答案并返回给请求者。

4. 发明申请

US20160110361A1 Collection and Storage of a Personalized, Searchable, Unstructured Corpora 有权
公开(公告)号：US20160110361A1
公开(公告)日：2016-04-21
申请号：US14517811
申请日：2014-10-18
申请人： International Business Machines Corporation
发明人： Daniel M. Jamrog , Jason D. LaVoie , Nicholas W. Orrick , Kristin A. Witherspoon
IPC分类号： G06F17/30 , G06F21/31 , G06F21/62
CPC分类号： G06F17/3053 , G06F17/30528 , G06F17/30554 , G06F17/30675 , G06F17/30696 , G06F17/30702 , G06F17/30867 , G06F21/31 , G06F21/62 , G06F21/6227 , H04L63/08 , H04L63/10
摘要： An approach is provided for utilizing unstructured corpora in a Question and Answer (QA) system. A question is received at the QA system. A private corpora is generated with the private corpora being associated with the user. The private corpora is generated from private data stores associated with the user as well as private data stores associated with other users. Access to the other user's private data sources is provided to the user by the other users. The system retrieves data responsive to the question from the private corpora. The responsive data is ranked based on its relevance to the question. Likely answers are identified based on the ranked responsive data and the likely answers are provided back to the user.

5. 发明申请

US20180083975A1 METHOD TO ALLOW FOR QUESTION AND ANSWER SYSTEM TO DYNAMICALLY RETURN DIFFERENT RESPONSES BASED ON ROLES 审中-公开
公开(公告)号：US20180083975A1
公开(公告)日：2018-03-22
申请号：US15273152
申请日：2016-09-22
申请人： International Business Machines Corporation
发明人： Donna K. Byron , Elie Feirouz , Daniel M. Jamrog , Kristin A. Witherspoon
IPC分类号： H04L29/06
摘要： Embodiments are directed to a question and answer (QA) pipeline system that adjusts answers to input questions based on a user criteria, thus implementing a content-based determination of access permissions. The QA system allows for information to be retrieved based on permission granted to a user. Documents are ingested and assigned an access level based on a defined information access policy. The QA system is implemented with the defined information access policy, the ingested documents, and the inferred access levels. For the QA system implementation, a user enters a question; primary search and answer extraction stages are performed; candidate answer extraction is performed using only content the user is allowed to access; the candidate answers are scored, ranked, and merged; ranked answers based on user permissions are filtered; and answers are provided to the user.

6. 发明授权

US09836520B2 System and method for automatically validating classified data objects 有权
公开(公告)号：US09836520B2
公开(公告)日：2017-12-05
申请号：US14178497
申请日：2014-02-12
申请人： International Business Machines Corporation
发明人： Romina M. J. Jose , Jason D. LaVoie , Kavita Patil , Aleksandr E. Petrov , Jeffrey R. Pratt , Edward T. Winchester , Kristin A. Witherspoon
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30598
摘要： A method, system and computer-usable medium are disclosed for enhancing a classification system to include an automatic classification validation system. The automatic classification validation system takes the classification results and automatically validates them for correctness. More specifically, the automatic classification validation system analyzes the data objects in the categories and, if any outliers are identified, then determines a context of the data object from a plurality of records contained within a certain category to determine the context. The classification validation system then uses the context of the data object to validate the classification.

7. 发明授权

US09703840B2 Handling information source ingestion in a question answering system 有权
公开(公告)号：US09703840B2
公开(公告)日：2017-07-11
申请号：US14458435
申请日：2014-08-13
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Daniel M. Jamrog , Kristin A. Witherspoon
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/3043 , G06F17/30528 , G06F17/30554 , G06F17/30867 , G06F17/30873
摘要： A question-answering (QA) system first receives input questions. Each question is then assigned to a first question category of a plurality of question categories. The QA system then identifies a set of candidate answers to each question using a core information source. A set of confidence scores, including a confidence score for each candidate answer, is then calculated. The QA system then determines that the first set of confidence scores fails to satisfy confidence criteria. In response to this determination, an updated information source is ingested.

8. 发明授权

US09342561B2 Creating and using titles in untitled documents to answer questions 有权
标题翻译：在无标题文档中创建和使用标题来回答问题
公开(公告)号：US09342561B2
公开(公告)日：2016-05-17
申请号：US14150272
申请日：2014-01-08
申请人： International Business Machines Corporation
发明人： Daniel M. Jamrog , Jason D. LaVoie , Nicholas W. Orrick , Alexander Pikovsky , Kristin A. Witherspoon
IPC分类号： G06F17/30
CPC分类号： G06F17/3053
摘要： Mechanisms for ingesting a document from a corpus of documents for use by a Question and Answer (QA) system are provided. The mechanisms receive a document from a corpus of documents and generate one or more titles for the document based on an analysis of content of the document. The mechanisms generate score values for the titles based on a measure of a degree to which the titles represent the content of the document. The mechanisms store the score values in association with the titles as document metadata associated with the document and output the document and document metadata to the QA system. The QA system utilizes the document metadata and document to generate a candidate answer to an input question.
摘要翻译：提供了从一个文件语料库中提取一个文件以供问答（QA）系统使用的机制。这些机制从文档语料库接收文档，并根据对文档内容的分析，为文档生成一个或多个标题。这些机制基于标题表示文档内容的程度的度量来产生标题的得分值。该机制将与标题相关联的得分值存储为与文档相关联的文档元数据，并将文档和文档元数据输出到质量检查系统。 QA系统利用文档元数据和文档来生成输入问题的候选答案。

9. 发明授权

US09715531B2 Weighting search criteria based on similarities to an ingested corpus in a question and answer (QA) system 有权
公开(公告)号：US09715531B2
公开(公告)日：2017-07-25
申请号：US15042744
申请日：2016-02-12
申请人： International Business Machines Corporation
发明人： Daniel M. Jamrog , Jason D. LaVoie , Nicholas W. Orrick , Kristin A. Witherspoon
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30864
摘要： A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer (QA) system, for weighting search criteria based on similarities to an ingested corpus in the QA system. A set of question characteristics found in a received input question are compared to a set of data characteristics respectively describing data in each corpus of a corpora. For each question characteristic in the set of found question characteristics, a first weight is assigned to the corpus within which data associated with the data characteristic resides in response to the question characteristic being more related to a data characteristic; otherwise a second weight is assigned, where the first weight is greater than the second weight. A selective search is then performed for an answer to the received input question in one or more corpora with a higher weighting.

10. 发明申请

US20160259793A1 HANDLING INFORMATION SOURCE INGESTION IN A QUESTION ANSWERING SYSTEM 有权
标题翻译：在问题解答系统中处理信息源入侵
公开(公告)号：US20160259793A1
公开(公告)日：2016-09-08
申请号：US15157440
申请日：2016-05-18
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Daniel M. Jamrog , Kristin A. Witherspoon
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/3043 , G06F17/30528 , G06F17/30554 , G06F17/30867 , G06F17/30873
摘要： A question-answering (QA) system first receives input questions. Each question is then assigned to a first question category of a plurality of question categories. The QA system then identifies a set of candidate answers to each question using a core information source. A set of confidence scores, including a confidence score for each candidate answer, is then calculated. The QA system then determines that the first set of confidence scores fails to satisfy confidence criteria. In response to this determination, an updated information source is ingested.
摘要翻译：问答系统首先收到输入问题。然后将每个问题分配给多个问题类别的第一问题类别。然后，质量检查系统使用核心信息源识别每个问题的一组候选答案。然后计算一组置信度分数，包括每个候选答案的置信度分数。然后，QA系统确定第一组置信度分数不能满足置信度标准。响应于该确定，摄取更新的信息源。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式