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. 发明申请

WO2013005227A1 SYSTEM AND METHOD FOR INFORMATION FUSION 审中-公开
标题翻译：信息融合的系统和方法
公开(公告)号：WO2013005227A1
公开(公告)日：2013-01-10
申请号：PCT/IN2012/000117
申请日：2012-02-20
申请人： TATA CONSULTANCY SERVICES LIMITED , SHROFF, Gautam , AGARWAL, Puneet , SHARMA, Saurabh , BHAT, Shefali
发明人： SHROFF, Gautam , AGARWAL, Puneet , SHARMA, Saurabh , BHAT, Shefali
IPC分类号： G06N5/02
CPC分类号： G06N5/02
摘要： Methods and systems for information fusion are described herein. In one implementation, the method includes posting a fact on a layered memory structure (126) and indexing the posted fact to a group, such that facts with a similar property measure are indexed to same group. Further, one or more knowledge modules (122) are applied on the posted fact and one or more input facts indexed to the group. Based on the application of the one or more knowledge modules (122) an output fact is provided and it is determined whether the output fact is a deduced fact based on a probability estimate.
摘要翻译：本文描述了用于信息融合的方法和系统。在一个实现中，该方法包括在分层存储器结构（126）上发布事实并将发布的事实索引到组，使得具有相似属性度量的事实被索引到同一组。此外，将一个或多个知识模块（122）应用于已发布的事实以及索引到该组的一个或多个输入事实。基于一个或多个知识模块（122）的应用，提供输出事实，并且基于概率估计确定输出事实是否是推导的事实。

2. 发明申请

WO2011051970A3 METHOD AND SYSTEM FOR OBTAINING SEMANTICALLY VALID CHUNKS FOR NATURAL LANGUAGE APPLICATIONS 审中-公开
公开(公告)号：WO2011051970A3
公开(公告)日：2011-05-05
申请号：PCT/IN2010/000693
申请日：2010-10-27
申请人： TATA CONSULTANCY SERVICES LTD. , GOYAL, Shailly , BHAT, Shefali , GULATI, Shailja , ANANTARAM, Chandrasekhar
发明人： GOYAL, Shailly , BHAT, Shefali , GULATI, Shailja , ANANTARAM, Chandrasekhar
IPC分类号： G06F17/30
摘要： A method and system for obtaining semantically valid chunks for natural language applications are disclosed in the present invention. The method includes the following steps: identifying predicates, objects and comparison operators in a natural language query; binding the identified predicates and objects using the identified comparison operator; replacing all occurrences of string comparator operators in said natural language query with corresponding mathematical operators; binding predicates and objects of same data type; checking compatibility of bound predicates and objects using domain ontology; binding string objects to their compatible predicates using domain ontology; forming constraint predicate sets from the remaining predicates of the query in order to find semantically valid chunk sets from said natural language query; syntactically parsing natural language query for absolving ambiguities; determining the depth between any two predicates using domain ontology, thereby providing a syntactically and semantically valid chunk set adapted to be used as a query.

3. 发明申请

WO2011051970A2 METHOD AND SYSTEM FOR OBTAINING SEMANTICALLY VALID CHUNKS FOR NATURAL LANGUAGE APPLICATIONS 审中-公开
标题翻译：用于获取自然语言应用的语义有限域的方法和系统
公开(公告)号：WO2011051970A2
公开(公告)日：2011-05-05
申请号：PCT/IN2010000693
申请日：2010-10-27
申请人： TATA CONSULTANCY SERVICES LTD , GOYAL SHAILLY , BHAT SHEFALI , GULATI SHAILJA , ANANTARAM CHANDRASEKHAR
发明人： GOYAL SHAILLY , BHAT SHEFALI , GULATI SHAILJA , ANANTARAM CHANDRASEKHAR
IPC分类号： G06F17/27
CPC分类号： G06F17/2785 , G06F17/30684
摘要： A system for obtaining semantically valid chunks for natural language application queries, said system comprising: predicate identifying means for identifying predicates in a natural language query; object identifying means for identifying objects in said natural language query; - identification means for identifying comparison operators in said natural language query; first binding means adapted to bind said identified predicate with said identified objects using said identified comparison operator; mathematical operator dictionary means adapted to replace all occurrences of string comparator operators in said natural language query with corresponding mathematical operators; second binding means for binding predicates and objects of same data type; compatibility checking means for checking compatibility of bound predicates and objects using domain ontology; third binding means for binding string objects (not previously bound to any predicate) to their compatible predicates using domain ontology; - constraint predicate set forming means for forming constraint predicate sets from the remaining predicates of the query in order to find semantically valid chunk sets from said natural language query; syntactic parsing means adapted to syntactically parse natural language query for absolving ambiguities; and - depth determination means, using domain ontology, for determining depth between any two predicates, thereby providing a syntactically and semantically valid chunk set adapted to be used as a query.
摘要翻译：一种用于获取用于自然语言应用查询的语义有效块的系统，所述系统包括：谓词识别装置，用于识别自然语言查询中的谓词; 用于识别所述自然语言查询中的对象的对象识别装置; - 用于识别所述自然语言查询中的比较运算符的识别装置; 第一绑定装置，适于使用所述识别的比较运算符将所述识别的谓词与所述识别的对象绑定; 数学运算符字典意味着适用于用所述自然语言查询中的所有出现的字符串比较运算符替换相应的数学运算符; 用于绑定相同数据类型的谓词和对象的第二绑定手段; 兼容性检查手段用于使用域本体检查绑定谓词和对象的兼容性; 使用域本体将字符串对象（以前未绑定到任何谓词）绑定到其兼容谓词的第三个绑定方法; - 约束谓词集形成装置，用于从所述查询的剩余谓词形成约束谓词集合，以便从所述自然语言查询中发现语义有效的组块; 适用于语法解析自然语言查询以解决歧义的句法解析手段; 和 - 深度确定装置，使用域本体来确定任何两个谓词之间的深度，由此提供适于用作查询的语法上和语义上有效的块组。

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