专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明申请

US20120078890A1 LEXICAL ANSWER TYPE CONFIDENCE ESTIMATION AND APPLICATION 有权
标题翻译：综合答案型信心估计与应用
公开(公告)号：US20120078890A1
公开(公告)日：2012-03-29
申请号：US13242290
申请日：2011-09-23
申请人： James J. Fan , David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , James W. Murdock , Wlodek W. Zadrozny
发明人： James J. Fan , David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , James W. Murdock , Wlodek W. Zadrozny
IPC分类号： G06F17/30
CPC分类号： G09B7/00
摘要： A system, method and computer program product for automatically estimating the confidence of a detected LAT to provide a more accurate overall score for an obtained candidate answer. A confidence “score” or value of each detected LAT is obtained, and the system and method performs combining the confidence score with a degree of match between a LAT and an AnswerType of the candidate answer to provide improved overall score for the candidate answer.
摘要翻译：一种用于自动估计检测到的LAT的置信度以为所获得的候选答案提供更准确的总分的系统，方法和计算机程序产品。获得每个检测到的LAT的置信度“分数”或值，并且系统和方法执行将置信度分数与候选答案的LAT和答题类型之间的匹配度组合，以提供候选答案的改进的总分。

62. 发明申请

US20120078888A1 PROVIDING ANSWERS TO QUESTIONS USING LOGICAL SYNTHESIS OF CANDIDATE ANSWERS 有权
标题翻译：使用逻辑综合的候选答复提供问题的答案
公开(公告)号：US20120078888A1
公开(公告)日：2012-03-29
申请号：US13240108
申请日：2011-09-22
申请人： Eric W. Brown , Jennifer Chu-Carroll , David A. Ferrucci , Adam P. Lally , James W. Murdock, IV , John M. Prager
发明人： Eric W. Brown , Jennifer Chu-Carroll , David A. Ferrucci , Adam P. Lally , James W. Murdock, IV , John M. Prager
IPC分类号： G06F17/30
CPC分类号： G06F17/30654 , G06F17/3053 , G06F17/30595 , G06F17/30684
摘要： A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query, decomposing the input query into a plurality of different subqueries, and conducting a search in one or more data sources to identify at least one candidate answer to each of the subqueries. A ranking function is applied to each of the candidate answers to determine a ranking for each of these candidate answers; and for each of the subqueries, one of the candidate answers to the subquery is selected based on this ranking. A logical synthesis component is applied to synthesize a candidate answer for the input query from the selected the candidate answers to the subqueries. In one embodiment, the procedure applied by the logical synthesis component to synthesize the candidate answer for the input query is determined from the input query.
摘要翻译：一种用于产生问题答案的方法，系统和计算机程序产品。在一个实施例中，该方法包括接收输入查询，将输入查询分解为多个不同的子查询，以及在一个或多个数据源中进行搜索以识别每个子查询的至少一个候选答案。对每个候选答案应用排名函数，以确定每个候选答案的排名; 并且对于每个子查询，基于该排名来选择子查询的候选答案之一。应用逻辑综合分量来从选择的候选答案中对子查询合成输入查询的候选答案。在一个实施例中，由输入查询确定逻辑合成组件应用于合成输入查询的候选答案的过程。

63. 发明申请

US20120078873A1 USING ONTOLOGICAL INFORMATION IN OPEN DOMAIN TYPE COERCION 有权
公开(公告)号：US20120078873A1
公开(公告)日：2012-03-29
申请号：US13244348
申请日：2011-09-24
申请人： David A. Ferrucci , Aditya A. Kalyanpur , James W. Murdock, IV , Christopher A. Welty , Wlodek W. Zadrozny
发明人： David A. Ferrucci , Aditya A. Kalyanpur , James W. Murdock, IV , Christopher A. Welty , Wlodek W. Zadrozny
IPC分类号： G06F17/30
CPC分类号： G06N5/02 , G06F17/30654
摘要： A computer-implemented system, method and program product generates answers to questions in an input query text string. The method includes determining, by a programmed processor unit, a lexical answer type (LAT) string associated with an input query; automatically obtaining a candidate answer string to the input query from a data corpus; mapping the query LAT string to a first type string in a structured resource; mapping the candidate answer string to a second type string in the structured resource; and determining if the first type string and the second type string are disjointed; and scoring the candidate answer string based on the determination of the types being disjointed wherein the structured resource includes a semantic database providing ontological content.

64. 发明申请

US20120078636A1 EVIDENCE DIFFUSION AMONG CANDIDATE ANSWERS DURING QUESTION ANSWERING 有权
标题翻译：问题答复中的候选答复中的证据扩散
公开(公告)号：US20120078636A1
公开(公告)日：2012-03-29
申请号：US13243805
申请日：2011-09-23
申请人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally
发明人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally
IPC分类号： G06F17/27
CPC分类号： G06F17/30654 , G06F17/30507
摘要： Diffusing evidence among candidate answers during question answering may identify a relationship between a first candidate answer and a second candidate answer, wherein the candidate answers are generated by a question-answering computer process, the candidate answers have associated supporting evidence, and the candidate answers have associated confidence scores. All or some of the evidence may be transferred from the first candidate answer to the second candidate answer based on the identified relationship. A new confidence score may be computed for the second candidate answer based on the transferred evidence.
摘要翻译：在问题回答期间候选答案之间的扩散证据可以识别第一候选答案和第二候选答案之间的关系，其中候选答案由问答电脑程序产生，候选答案具有相关的支持证据，候选答案具有相关的信心分数。基于所识别的关系，所有或一些证据可以从第一候选答案转移到第二候选答案。可以基于转移的证据为第二候选答案计算新的置信度。

65. 发明申请

US20110066587A1 EVIDENCE EVALUATION SYSTEM AND METHOD BASED ON QUESTION ANSWERING 有权
标题翻译：基于问题回答的证据评估系统和方法
公开(公告)号：US20110066587A1
公开(公告)日：2011-03-17
申请号：US12561802
申请日：2009-09-17
申请人： David A. Ferrucci , Wlodek W. Zadrozny
发明人： David A. Ferrucci , Wlodek W. Zadrozny
IPC分类号： G06N5/02
CPC分类号： G06N5/04
摘要： An evidence evaluation method and system based on question answering converts a report of analyzed information and/or a model of information into a collection of questions, determines answers for the collection of questions. A fact in the report is marked as being supported if one or more of the answers for the collection of questions support the fact. A fact in the report of analyzed facts is marked as being refuted if one or more of the answers for the collection of questions refute the fact. The method and system also may collect the answers as evidence and add the evidence to the model of information to create an updated model of information. The steps may be repeated using the updated report and updated model.
摘要翻译：基于问题回答的证据评估方法和系统将分析信息和/或信息模型的报告转换为问题集合，确定问题收集的答案。如果收集问题的一个或多个答案支持这一事实，报告中的一个事实被标记为支持。如果收集问题的一个或多个答案反驳了事实，分析事实的报告中的一个事实被标示为被驳斥。方法和系统也可以收集答案作为证据，并将证据添加到信息模型中，以创建更新的信息模型。可以使用更新的报告和更新的模型重复这些步骤。

66. 发明授权

US07757163B2 Method and system for characterizing unknown annotator and its type system with respect to reference annotation types and associated reference taxonomy nodes 失效
标题翻译：用于表征未知注释器及其类型系统相对于引用注释类型和相关联的引用分类结点的方法和系统
公开(公告)号：US07757163B2
公开(公告)日：2010-07-13
申请号：US11620189
申请日：2007-01-05
申请人： Yurdaer N. Doganata , Youssef Drissi , David A. Ferrucci , Tong-Haing Fin , Genady Grabarnik , Lev Kozakov
发明人： Yurdaer N. Doganata , Youssef Drissi , David A. Ferrucci , Tong-Haing Fin , Genady Grabarnik , Lev Kozakov
IPC分类号： G06F17/00
CPC分类号： G06F17/30613 , G06Q10/10
摘要： An unknown annotator and its annotation type system are compared against a reference annotation type system. The comparison is done by providing a plurality of documents, and annotating each document using the reference set of document annotators, producing instances of reference annotation types, to generate a pre-annotated reference document set, and using the subject annotator and its subject annotation type system to generate a pre-annotated evaluation document set. Documents in the pre-annotated evaluation document set are compared to documents in the pre-annotated reference document set, and matches in location, within the compared documents, of instances of the subject annotation types and the reference annotation types are identified. Based on the matching data, reference document annotation types are selected that sufficiently correlate with the subject annotation type system. Based on the type system matching, the subject annotator and its type system are associated with a plurality of reference industrial taxonomy nodes.
摘要翻译：未知注释器及其注释类型系统与参考注释类型系统进行比较。比较是通过提供多个文档，并使用文献注释器的引用集来注释每个文档，产生引用注释类型的实例，以生成预先注释的参考文档集合，并且使用主题注释器及其主题注释类型系统生成预注释的评估文件集。将预先注释的评估文档集中的文档与预注释的参考文档集中的文档进行比较，并且在比较的文档中的位置匹配主题注释类型的实例和参考注释类型。基于匹配数据，选择与对象注释类型系统充分相关的参考文档注释类型。基于类型系统匹配，主体注释器及其类型系统与多个参考工业分类结点相关联。

67. 发明授权

US09508038B2 Using ontological information in open domain type coercion 有权
标题翻译：使用开放域类型胁迫的本体信息
公开(公告)号：US09508038B2
公开(公告)日：2016-11-29
申请号：US13605339
申请日：2012-09-06
申请人： David A. Ferrucci , Aditya Kalyanpur , James W. Murdock, IV , Christopher A. Welty , Wlodek W. Zadrozny
发明人： David A. Ferrucci , Aditya Kalyanpur , James W. Murdock, IV , Christopher A. Welty , Wlodek W. Zadrozny
IPC分类号： G06F7/00 , G06N5/02
CPC分类号： G06N5/02 , G06F17/30654
摘要： A computer-implemented system, method and program product generates answers to questions in an input query text string. The method includes determining, by a programmed processor unit, a lexical answer type (LAT) string associated with an input query; automatically obtaining a candidate answer string to the input query from a data corpus; mapping the query LAT string to a first type string in a structured resource; mapping the candidate answer string to a second type string in the structured resource; and determining if the first type string and the second type string are disjointed; and scoring the candidate answer string based on the determination of the types being disjointed wherein the structured resource includes a semantic database providing ontological content.
摘要翻译：计算机实现的系统，方法和程序产品会在输入查询文本字符串中生成问题的答案。该方法包括由编程的处理器单元确定与输入查询相关联的词汇答案类型（LAT）字符串; 从数据语料库自动获得候选答案字符串到输入查询; 将查询LAT字符串映射到结构化资源中的第一个类型的字符串; 将候选答案字符串映射到结构化资源中的第二类型字符串; 以及确定所述第一类型字符串和所述第二类型字符串是否脱离; 以及基于所述不相交类型的确定对所述候选答案字符串进行评分，其中所述结构化资源包括提供本体内容的语义数据库。

68. 发明授权

US09323831B2 Providing answers to questions using hypothesis pruning 有权
标题翻译：使用假设修剪提供问题的答案
公开(公告)号：US09323831B2
公开(公告)日：2016-04-26
申请号：US13613999
申请日：2012-09-13
申请人： Jennifer Chu-Carroll , David A. Ferrucci , David C. Gondek , Adam P. Lally , James W. Murdock, IV
发明人： Jennifer Chu-Carroll , David A. Ferrucci , David C. Gondek , Adam P. Lally , James W. Murdock, IV
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/3053 , G06F17/30528 , G06F17/30554 , G06F17/30654 , G06F17/30867
摘要： A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving a query, conducting a search through one or more data sources to identify candidate answers to the query, and providing each of the candidate answers with a preliminary score. The method further comprises filtering out any of the candidate answers with a preliminary score that does not satisfy a defined condition. The candidate answers having preliminary scores that satisfy this condition form a subset of the candidate answers. Each of the candidate answers in this subset is processed to produce further scores. A ranking function is applied to these further scores to determine a ranking for each of the candidate answers in the subset; and after this ranking function is applied, one or more of the candidate answers are selected as one or more final answers to the query.
摘要翻译：一种用于产生问题答案的方法，系统和计算机程序产品。在一个实施例中，所述方法包括接收查询，通过一个或多个数据源进行搜索以识别对所述查询的候选答案，以及向每个候选答案提供初步分数。该方法还包括用不满足定义条件的初步分数来过滤任何候选答案。具有满足该条件的初步分数的候选人答案构成候选答案的子集。处理该子集中的每个候选答案以产生进一步的分数。排序函数被应用于这些进一步的分数以确定该子集中每个候选答案的排名; 并且在应用该排序功能之后，将一个或多个候选答案选择为查询的一个或多个最终答案。

69. 发明授权

US09146917B2 Validating that a user is human 有权
标题翻译：验证用户是否是人
公开(公告)号：US09146917B2
公开(公告)日：2015-09-29
申请号：US13547436
申请日：2012-07-12
申请人： Michael A. Barborak , David A. Ferrucci , James W. Murdock, IV , Wlodek W. Zadrozny
发明人： Michael A. Barborak , David A. Ferrucci , James W. Murdock, IV , Wlodek W. Zadrozny
IPC分类号： G06F21/31 , G06F17/27
CPC分类号： G06F17/27 , G06F21/31 , G06F2221/2103 , G06F2221/2133
摘要： A method of validating that a user is human. A user question is generated using a computerized device. The user question is output to a user. A user response to the user question is received from the user. The user response is validated as having been provided by a human.
摘要翻译：验证用户是人的方法。使用计算机化设备生成用户问题。用户问题输出给用户。从用户接收用户对用户问题的响应。用户响应被验证为已经由人提供。

70. 发明授权

US08959043B2 Fact checking using and aiding probabilistic question answering 有权
标题翻译：事实检查使用和辅助概率问题回答
公开(公告)号：US08959043B2
公开(公告)日：2015-02-17
申请号：US13600628
申请日：2012-08-31
申请人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , Siddharth Patwardhan
发明人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , Siddharth Patwardhan
IPC分类号： G06F17/00 , G06N5/02 , G06F9/44 , G06N7/02 , G06N7/06 , G06N7/00
CPC分类号： G06N7/005
摘要： A system and a computer program product for verifying a statement are provided. The system is configured to receive a statement. The system is configured to decompose the received statement into one or more sets of question and answer pairs. The system is configured to determine a confidence value of each answer in the one or more question and answer pair sets. The system is configured to combine the determined confidence values. The combined confidence values represent a probability that the received statement is evaluated as true.
摘要翻译：提供了一种用于验证语句的系统和计算机程序产品。系统配置为接收语句。该系统被配置为将接收到的语句分解成一组或多组问答对。该系统被配置为确定一个或多个问答对集合中每个答案的置信度值。该系统被配置为组合确定的置信度值。组合的置信度值表示接收到的语句被评估为真的概率。

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