专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明申请

US20140129492A1 CONCEPT NOISE REDUCTION IN DEEP QUESTION ANSWERING SYSTEMS 有权
标题翻译：在深度问题解答系统中概念减少噪声
公开(公告)号：US20140129492A1
公开(公告)日：2014-05-08
申请号：US13671810
申请日：2012-11-08
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： John A. Petri , Richard J. Stevens
IPC分类号： G06N99/00
CPC分类号： G06N99/005 , G09B19/0053
摘要： Method, computer program product, and system to perform an operation for a deep question answering system. The operation begins by computing a concept score for a first concept in a first case received by the deep question answering system, the concept score being based on a machine learning concept model for the first concept. The operation then excludes the first concept from consideration when analyzing a candidate answer and an item of supporting evidence to generate a response to the first case upon determining that the concept score does not exceed a predefined concept minimum weight threshold. The operation then increases a weight applied to the first concept when analyzing the candidate answer and the item of supporting evidence to generate the response to the first case when the concept score exceeds a predefined maximum weight threshold.
摘要翻译：方法，计算机程序产品和系统对深层问答系统进行操作。操作开始于在深问题应答系统接收的第一种情况下计算第一概念的概念分数，概念分数基于第一概念的机器学习概念模型。然后，当分析候选答案和支持证据的项目时，在确定概念得分不超过预定义的概念最小权重阈值时，该操作将第一概念排除在考虑之外，以产生对第一种情况的响应。当分析候选答案和支持证据的项目以在概念得分超过预定义的最大权重阈值时产生对第一种情况的响应时，该操作增加了应用于第一概念的权重。

42. 发明授权

US08713036B2 Processing abstract derived entities defined in a data abstraction model 失效
标题翻译：处理在数据抽象模型中定义的抽象派生实体
公开(公告)号：US08713036B2
公开(公告)日：2014-04-29
申请号：US13841529
申请日：2013-03-15
申请人： International Business Machines Corporation
发明人： Richard D. Dettinger , Richard J. Stevens , Jeffery W. Tenner
IPC分类号： G06F17/30 , G06F15/16
CPC分类号： G06F17/30554 , G06F17/30398
摘要： Techniques involving an abstract derived entity. The abstract derived entity is a data object present in an abstract data model that may be referenced by other entities in the abstract data model as though it were a relational table present in a physical data source. The abstract data model provides data access independent of the manner in which the data is physically represented in a set of physical data sources. The abstract derived entity may be used to provide aggregate data joined with other non-aggregate data. The abstract derived entity may describe a relational table comprising a set of aggregate data used to form a column of the relational table joined to other columns formed from the sets of input data specified by the abstract derived entity. The resulting abstract derived table may be queried as though it were an actual relational table stored in a physical data source.
摘要翻译：涉及抽象衍生实体的技术。抽象派生实体是呈现在抽象数据模型中的数据对象，其可以由抽象数据模型中的其他实体引用，就像它是物理数据源中存在的关系表一样。抽象数据模型提供数据访问，独立于在一组物理数据源中物理表示数据的方式。抽象派生实体可用于提供与其他非汇总数据连接的汇总数据。抽象派生实体可以描述关系表，其包括用于形成与由抽象派生实体指定的输入数据组形成的其他列连接的关系表的列的聚合数据集合。所得到的抽象派生表可以被查询，就像它是存储在物理数据源中的实际关系表一样。

43. 发明申请

US20130226901A1 PROCESSING ABSTRACT DERIVED ENTITIES DEFINED IN A DATA ABSTRACTION MODEL 失效
标题翻译：处理摘要在数据抽象模型中定义的衍生实体
公开(公告)号：US20130226901A1
公开(公告)日：2013-08-29
申请号：US13841529
申请日：2013-03-15
申请人： International Business Machines Corporation
发明人： Richard D. Dettinger , Richard J. Stevens , Jeffery W. Tenner
IPC分类号： G06F17/30
CPC分类号： G06F17/30554 , G06F17/30398
摘要： A method, apparatus and article of manufacture for utilizing an abstract derived entity are disclosed. An abstract derived entity is a data object present in an abstract data model that may be referenced by other entities in the abstract data model as though it were a relational table present in a physical data source. In one embodiment, an abstract data model provides data access independent of the manner in which the data is physically represented in a set of physical data sources. In addition, an abstract derived entity may be used to provide aggregate data joined with other non-aggregate data. Aggregate data values are calculated from the column of a relational table, or other sets of input data. In one embodiment, an abstract derived entity may describe a describe relational table comprising a set of aggregate data used to form a column of the relational table joined to other columns formed from the sets of input data specified by the abstract derived entity. The resulting abstract derived table may be queried as though it were an actual relational table stored in a physical data source.
摘要翻译：公开了一种利用抽象派生实体的方法，装置和制品。抽象派生实体是呈现在抽象数据模型中的数据对象，其可以被抽象数据模型中的其他实体引用，就像它是物理数据源中存在的关系表一样。在一个实施例中，抽象数据模型提供独立于在一组物理数据源中物理表示数据的方式的数据访问。此外，抽象派生实体可用于提供与其他非汇总数据连接的汇总数据。汇总数据值根据关系表列或其他输入数据集计算。在一个实施例中，抽象派生实体可以描述描述关系表，其包括用于形成连接到由抽象派生实体指定的输入数据组形成的其他列的关系表的列的聚合数据集合。所得到的抽象派生表可以被查询，就像它是存储在物理数据源中的实际关系表一样。

44. 发明授权

US11424011B2 Analyzing knowledge graphs with unbounded insight generation 有权
公开(公告)号：US11424011B2
公开(公告)日：2022-08-23
申请号：US16215280
申请日：2018-12-10
申请人： International Business Machines Corporation
发明人： Richard J. Stevens , Fernando Jose Suarez Saiz , Eric W. Will , Adam Clark
IPC分类号： G16H50/70 , G16H10/60 , G16H20/00 , G06F16/28 , G06F16/2457 , G16H10/20 , G06F16/901
摘要： Techniques for unbounded therapy evaluation are provided. A request to suggest a potential therapy based on a patient profile is received. A plurality of accepted therapies is determined based on the patient profile, where the plurality of accepted therapies is based on stored definitions obtained from one or more subject matter experts. Next, a plurality of therapy components is identified based on the plurality of accepted therapies. A plurality of potential therapies is then identified based on the plurality of therapy components, where none of the plurality of potential therapies are included in the plurality of accepted therapies. A score is generated for a potential therapy of the plurality of potential therapies based on analyzing a knowledge graph, where the score indicates a suitability of the potential therapy for a patient associated with the patient profile. Finally, the potential therapy is provided, along with an indication of the score.

45. 发明授权

US11126645B2 Gathering information on user interactions with natural language processor (NLP) items to order presentation of NLP items in documents 有权
公开(公告)号：US11126645B2
公开(公告)日：2021-09-21
申请号：US15811260
申请日：2017-11-13
申请人： International Business Machines Corporation
发明人： Eric L. Erpenbach , Andrew J. Lavery , Richard J. Stevens , Fernando J. Suarez Saiz
IPC分类号： G06F16/335 , G16H50/70 , G16H10/60 , G06F16/23 , G06F16/93 , G06F16/332
摘要： Provided are a computer program product, system, and method for providing information on detected user interactions with natural language processor (NLP) items to a server to use to determine an order in which to render NLP items in a user interface. Interactions with natural language processing (NLP) items in documents are detected. For each interaction with an NLP item of the NLP items in the documents, determination is made of a context attribute value for a context attribute related to the interaction with the NLP item. Then interaction information is generated indicating the NLP item and the determined context attribute value. The interaction information is sent to the server to include in user interaction information in a database.

46. 发明授权

US11120061B2 Gathering information on user interactions with natural language processor (NLP) items to determine an order in which to present NLP items 有权
公开(公告)号：US11120061B2
公开(公告)日：2021-09-14
申请号：US16406915
申请日：2019-05-08
申请人： International Business Machines Corporation
发明人： Eric L. Erpenbach , Andrew J. Lavery , Richard J. Stevens , Fernando J. Suarez Saiz
IPC分类号： G06F16/335 , G16H50/70 , G16H10/60 , G06F16/23 , G06F16/93 , G06F16/332
摘要： Provided are a computer program product, system, and method for providing information on detected user interactions with natural language processor (NLP) items to a server to use to determine an order in which to render NLP items in a user interface. Interactions with natural language processing (NLP) items in documents are detected. For each interaction with an NLP item of the NLP items in the documents, determination is made of a context attribute value for a context attribute related to the interaction with the NLP item. Then interaction information is generated indicating the NLP item and the determined context attribute value. The interaction information is sent to the server to include in user interaction information in a database.

47. 发明申请

US20210056302A1 DOCUMENT ANALYSIS TECHNIQUE FOR UNDERSTANDING INFORMATION 有权
公开(公告)号：US20210056302A1
公开(公告)日：2021-02-25
申请号：US16545891
申请日：2019-08-20
申请人： International Business Machines Corporation
发明人： Andrew J. Lavery , Fernando Jose Suarez Saiz , Richard J. Stevens , Eric L. Erpenbach
IPC分类号： G06K9/00 , G06F17/27 , G10L15/183
摘要： A computer-implemented method, system and computer program product for understanding information using a document analysis technique. An initial corpus of information is formed by identifying a document(s) that match a search criteria. The initial corpus of information is expanded with a set of documents containing statements with a semantic meaning within a threshold degree of similarity to a semantic meaning of statements contained within the document(s) used to form the initial corpus of information. Viewpoint(s) are then extracted from the expanded corpus of information using a natural language processing technique. A new set of documents is analyzed by identifying the subject, assertion and context statements. Assertions in the new set of documents that are within a threshold degree of agreement or disagreement with the extracted viewpoint are highlighted to assist the user in understanding how information aligns with a viewpoint.

48. 发明申请

US20190266181A1 GATHERING INFORMATION ON USER INTERACTIONS WITH NATURAL LANGUAGE PROCESSOR (NLP) ITEMS TO DETERMINE AN ORDER IN WHICH TO PRESENT NLP ITEMS 审中-公开
公开(公告)号：US20190266181A1
公开(公告)日：2019-08-29
申请号：US16406915
申请日：2019-05-08
申请人： International Business Machines Corporation
发明人： Eric L. Erpenbach , Andrew J. Lavery , Richard J. Stevens , Fernando J. Suarez Saiz
IPC分类号： G06F16/335 , G06F16/332 , G06F16/93 , G16H10/60 , G16H50/70 , G06F16/23
摘要： Provided are a computer program product, system, and method for providing information on detected user interactions with natural language processor (NLP) items to a server to use to determine an order in which to render NLP items in a user interface. Interactions with natural language processing (NLP) items in documents are detected. For each interaction with an NLP item of the NLP items in the documents, determination is made of a context attribute value for a context attribute related to the interaction with the NLP item. Then interaction information is generated indicating the NLP item and the determined context attribute value. The interaction information is sent to the server to include in user interaction information in a database.

49. 发明申请

US20190147102A1 GATHERING INFORMATION ON USER INTERACTIONS WITH NATURAL LANGUAGE PROCESSOR (NLP) ITEMS TO ORDER PRESENTATION OF NLP ITEMS IN DOCUMENTS 审中-公开
公开(公告)号：US20190147102A1
公开(公告)日：2019-05-16
申请号：US15811260
申请日：2017-11-13
申请人： International Business Machines Corporation
发明人： Eric L. Erpenbach , Andrew J. Lavery , Richard J. Stevens , Fernando J. Suarez Saiz
IPC分类号： G06F17/30 , G06F19/00
摘要： Provided are a computer program product, system, and method for providing information on detected user interactions with natural language processor (NLP) items to a server to use to determine an order in which to render NLP items in a user interface. Interactions with natural language processing (NLP) items in documents are detected. For each interaction with an NLP item of the NLP items in the documents, determination is made of a context attribute value for a context attribute related to the interaction with the NLP item. Then interaction information is generated indicating the NLP item and the determined context attribute value. The interaction information is sent to the server to include in user interaction information in a database.

50. 发明授权

US10147047B2 Augmenting answer keys with key characteristics for training question and answer systems 有权
公开(公告)号：US10147047B2
公开(公告)日：2018-12-04
申请号：US14591413
申请日：2015-01-07
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Christine A. Grev , Richard J. Stevens
IPC分类号： G06N99/00 , G06N5/04 , G16H10/20 , G16H50/20
摘要： Mechanisms are provided for implementing training logic for training a Question and Answer (QA) system. A training question, associated with an answer key, is received and processed by the QA system to generate a final answer to the training question and supporting evidence for the final answer based on a corpus of information. The supporting evidence is analyzed to identify one or more evidence attributes and a plurality of correct answer entries in the answer key are searched to identify a matching correct answer entry that matches the final answer. The matching correct answer entry in the answer key is augmented to include the one or more evidence attributes in an augmented answer key and the QA system is trained based on the augmented answer key.

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