专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US09965548B2 Analyzing natural language questions to determine missing information in order to improve accuracy of answers 有权
公开(公告)号：US09965548B2
公开(公告)日：2018-05-08
申请号：US14097655
申请日：2013-12-05
申请人： International Business Machines Corporation
发明人： Peter F. Haggar , Dane A. Johnson , Mark G. Megerian , John E. Petri , Stephan J. Roorda , Leah R. Smutzer , Richard J. Stevens , Richard L. Stillwell
IPC分类号： G06F7/00 , G06F17/30 , G09B5/02 , G06Q10/10
CPC分类号： G06F17/30654 , G06Q10/10 , G09B5/02
摘要： A mechanism is provided in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for improving answers to an input question. An input question is received and parsed for a known set of critical information required to answer the input question. Responsive to one or more pieces of critical information failing to be identifiable in the input question, a user who submitted the input question is prompted for the one or more pieces of critical information via a graphical user interface (GUI).

32. 发明申请

US20180075194A1 Medical Condition Independent Engine for Medical Treatment Recommendation System 审中-公开
公开(公告)号：US20180075194A1
公开(公告)日：2018-03-15
申请号：US15262311
申请日：2016-09-12
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Thomas J. Eggebraaten , Mark G. Megerian , Richard J. Stevens
IPC分类号： G06F19/00
CPC分类号： G16H10/60 , G16H20/00 , G16H50/20 , G16H50/30 , G16H70/20 , G16H70/60
摘要： Mechanisms are provided which configure a medical treatment recommendation system to implement a medical condition independent treatment recommendation model. The medical condition independent treatment recommendation model operates on medical condition independent scoring features that are independent of any specific medical condition. The mechanisms configure the medical treatment recommendation system to receive a medical condition cartridge providing at least one medical condition specific evaluation feature that is specific to a medical condition, and process patient information based on a combination of an application of the at least one medical condition specific evaluation feature, and an execution of the medical condition independent treatment recommendation model of the medical treatment recommendation system, to generate a treatment recommendation for a patient medical condition associated with the patient. The mechanisms then output the treatment recommendation for the patient.

33. 发明授权

US09842296B2 Using cohorts in a question answering system 有权
公开(公告)号：US09842296B2
公开(公告)日：2017-12-12
申请号：US14492661
申请日：2014-09-22
申请人： International Business Machines Corporation
发明人： Adam T. Clark , Jeffrey K. Huebert , Aspen L. Payton , John E. Petri , Richard J. Stevens , Kathryn L. Whaley
IPC分类号： G06N5/04 , G06N5/02 , G06F17/30
CPC分类号： G06N5/022 , G06F17/3053 , G06N5/041 , G06N5/043 , G06N5/046 , G06N99/005
摘要： A cohort analysis mechanism analyzes cohorts with similar attributes to extrapolate additional knowledge and answer a question in a question answering system. The cohort analysis mechanism identifies cohorts for an entity of the question and extracts relevant data concerning the cohorts. The cohort analysis mechanism aggregates the relevant information for evidence scoring and answer scoring to answer a question posed to the question answering system. The aggregating of the data includes combining and ranking answers from the cohorts, gathering evidence and then answering the question with the gathered evidence.

34. 发明申请

US20160247071A1 USING COHORTS TO INFER ATTRIBUTES FOR AN INPUT CASE IN A QUESTION ANSWERING SYSTEM 有权
标题翻译：在问题解答系统中使用对象输入输入的属性
公开(公告)号：US20160247071A1
公开(公告)日：2016-08-25
申请号：US14626052
申请日：2015-02-19
申请人： International Business Machines Corporation
发明人： Adam T. Clark , Jeffrey K. Huebert , Aspen L. Payton , John E. Petri , Richard J. Stevens , Kathryn L. Whaley
IPC分类号： G06N5/04
CPC分类号： G06N5/04 , G06F17/3043
摘要： A cohort analysis mechanism analyzes cohorts to infer one or more additional attributes for an input case to provide a refined input case to answer a question in a question answering system. The refined input case is then used to answer a question in the question answering system. The refined input case can be used in a traditional question answering flow or in a flow that again uses cohort analysis to extract relevant data to answer the question. The cohort analysis mechanism analyzes cohorts to find common attributes in the cohorts and then determines whether to infer the common attributes into the refined input case. The cohort analysis mechanism may determine to dialog with a user to confirm an inferred attribute.
摘要翻译：队列分析机制分析队列以推断输入案例的一个或多个附加属性，以提供精简的输入案例来回答问题回答系统中的问题。然后，精确的输入案例用于回答问答系统中的问题。精简的输入案例可以用于传统问题回答流程或流程中，再次使用队列分析来提取相关数据来回答问题。队列分析机制分析队列，找出队列中的共同属性，然后确定是否将共同属性推断为精细输入案例。队列分析机制可以确定与用户对话以确认推断的属性。

35. 发明申请

US20160196504A1 Augmenting Answer Keys with Key Characteristics for Training Question and Answer Systems 审中-公开
标题翻译：增强应答键，具有培训问题和答案系统的关键特性
公开(公告)号：US20160196504A1
公开(公告)日：2016-07-07
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 , G06N7/00
CPC分类号： G06N99/005 , G06F19/00 , 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.
摘要翻译：提供了实施培训逻辑的机制，用于培训问答系统。与回答关键字相关的训练问题由质量检查系统接收和处理，以产生基于信息语料库的最终答案的培训问题的最终答案和支持最终答案的证据。分析支持证据以识别一个或多个证据属性，并且搜索应答密钥中的多个正确答案条目以识别与最终答案匹配的匹配正确答案条目。应答密钥中的匹配的正确答案条目被增加以包括增强应答密钥中的一个或多个证据属性，并且基于增强的应答密钥训练QA系统。

36. 发明授权

US09087304B2 Concept noise reduction in deep question answering systems 有权
标题翻译：深层问答系统中的概念降噪
公开(公告)号：US09087304B2
公开(公告)日：2015-07-21
申请号：US13705345
申请日：2012-12-05
申请人： International Business Machines Corporation
发明人： John E. Petri , Richard J. Stevens
IPC分类号： G06F15/18 , G06F17/00 , G06N5/04 , G06N99/00 , G09B19/00
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。

37. 发明申请

US20140172883A1 PARTIAL AND PARALLEL PIPELINE PROCESSING IN A DEEP QUESTION ANSWERING SYSTEM 有权
公开(公告)号：US20140172883A1
公开(公告)日：2014-06-19
申请号：US13793809
申请日：2013-03-11
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Adam T. Clark , Mark G. Megerian , John E. Petri , Richard J. Stevens
IPC分类号： G06F17/30
CPC分类号： G06F17/30038 , G06F17/30675 , G06N5/022 , G06N99/005
摘要： System, method, and computer program product to reduce an amount of processing required to generate a response to a first case by a deep question answering system, by, determining that a similarity score, of the first case relative to a second case, exceeds a similarity threshold, identifying a first feature of the second case having a first relevance score exceeding a relevance threshold, identifying a first candidate answer for the first case that does not have the first feature, and refraining from analyzing the first candidate answer in generating the response to the first case, thereby reducing the amount of processing of the deep question answering system.

38. 发明申请

US20140172882A1 PARTIAL AND PARALLEL PIPELINE PROCESSING IN A DEEP QUESTION ANSWERING SYSTEM 有权
标题翻译：深层问题回答系统中的部分和并行管道处理
公开(公告)号：US20140172882A1
公开(公告)日：2014-06-19
申请号：US13717105
申请日：2012-12-17
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Adam T. Clark , Mark G. Megerian , John E. Petri , Richard J. Stevens
IPC分类号： G06F17/30
CPC分类号： G06F17/30038 , G06F17/30675 , G06N5/022 , G06N99/005
摘要： System, method, and computer program product to reduce an amount of processing required to generate a response to a first case by a deep question answering system, by, determining that a similarity score, of the first case relative to a second case, exceeds a similarity threshold, identifying a first feature of the second case having a first relevance score exceeding a relevance threshold, identifying a first candidate answer for the first case that does not have the first feature, and refraining from analyzing the first candidate answer in generating the response to the first case, thereby reducing the amount of processing of the deep question answering system.
摘要翻译：系统，方法和计算机程序产品，以减少由深度问答系统产生对第一种情况的响应所需的处理量，通过确定第一种情况相对于第二种情况的相似度得分超过相似性阈值，识别具有第一相关性分数超过相关性阈值的第二种情况的第一特征，识别第一种不具有第一特征的第一候选答案，并且避免分析第一候选答案以产生响应在第一种情况下，从而减少深层问答系统的处理量。

39. 发明申请

US20140172879A1 MULTI-DIMENSIONAL FEATURE MERGING FOR SUPPORTING EVIDENCE IN A QUESTION AND ANSWERING SYSTEM 有权
标题翻译：在问题和答复系统中支持证据的多维特征协调
公开(公告)号：US20140172879A1
公开(公告)日：2014-06-19
申请号：US13793287
申请日：2013-03-11
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Joel C. Dubbels , Thomas J. Eggebraaten , Mark G. Megerian , William C. Rapp , Richard J. Stevens , Patrick M. Wildt , Eric C. Will
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30654
摘要： Method, system, and computer program product to analyze a plurality of candidate answers identified as responsive to a question presented to a deep question answering system, by computing a first feature score for a first feature of an item of evidence, of a plurality of items of evidence, the first feature score being based on at least one attribute of the first feature, the item of evidence relating to a first candidate answer, of the plurality of candidate answers, and computing a merged feature score for the first candidate answer by applying the first feature score to a second feature score for a second feature of the item of evidence.
摘要翻译：方法，系统和计算机程序产品，通过计算多个项目中的证据项目的第一特征的第一特征分数来分析被识别为对呈现给深层问答系统的问题作出响应的多个候选答案第一特征分数基于第一特征的至少一个属性，与第一候选答案有关的证据项，多个候选答案中的一个，以及通过应用第一候选答案来计算第一候选答案的合并特征得分第一个特征得分为证据项目的第二个特征的第二个特征得分。

40. 发明申请

US20140172755A1 MULTI-DIMENSIONAL FEATURE MERGING FOR SUPPORTING EVIDENCE IN A QUESTION AND ANSWERING SYSTEM 有权
公开(公告)号：US20140172755A1
公开(公告)日：2014-06-19
申请号：US13716579
申请日：2012-12-17
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Joel C. Dubbels , Thomas J. Eggebraaten , Mark G. Megerian , William C. Rapp , Richard J. Stevens , Patrick M. Wildt , Eric W. Will
IPC分类号： G06N99/00
CPC分类号： G06F17/3053 , G06F17/30654
摘要： Method, system, and computer program product to analyze a plurality of candidate answers identified as responsive to a question presented to a deep question answering system, by computing a first feature score for a first feature of an item of evidence, of a plurality of items of evidence, the first feature score being based on at least one attribute of the first feature, the item of evidence relating to a first candidate answer, of the plurality of candidate answers, and computing a merged feature score for the first candidate answer by applying the first feature score to a second feature score for a second feature of the item of evidence.

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