公开(公告)号：US20130339021A1

公开(公告)日：2013-12-19

申请号：US13526637

申请日：2012-06-19

Applicant: Om D. Deshmukh ,  Sachindra Joshi ,  Saurabh Saket ,  Ashish Verma

Inventor： Om D. Deshmukh ,  Sachindra Joshi ,  Saurabh Saket ,  Ashish Verma

IPC: G10L15/18

CPC classification number: G10L25/48 ,  G10L15/02 ,  G10L15/18 ,  G10L15/1822 ,  G10L15/26 ,  G10L21/10

Abstract: Techniques, an apparatus and an article of manufacture identifying one or more utterances that are likely to carry the intent of a speaker, from a conversation between two or more parties. A method includes obtaining an input of a set of utterances in chronological order from a conversation between two or more parties, computing an intent confidence value of each utterance by summing intent confidence scores from each of the constituent words of the utterance, wherein intent confidence scores capture each word's influence on the subsequent utterances in the conversation based on (i) the uniqueness of the word in the conversation and (ii) the number of times the word subsequently occurs in the conversation, and generating a ranked order of the utterances from highest to lowest intent confidence value, wherein the highest intent value corresponds to the utterance which is most likely to carry intent of the speaker.

Abstract translation: 从两个或多个方之间的对话中识别出可能携带说话人意图的一个或多个话语的技术，装置和制品。 一种方法包括从两个或更多方之间的会话按时间顺序获得一组话语的输入，通过将来自每个话语的组成词的意图置信度得分相加来计算每个话语的意图置信度值，其中意图置信度得分 基于（i）会话中的单词的唯一性和（ii）单词随后在会话中发生的次数，并且从最高级别生成排序的话语顺序，从而捕获每个单词对对话中后续话语的影响 到最低意图置信度值，其中最高意图值对应于最有可能携带说话者意图的话语。

公开(公告)号：US08561126B2

公开(公告)日：2013-10-15

申请号：US11025307

申请日：2004-12-29

Applicant: Rema Ananthanarayanan ,  Mukesh K Mohania ,  Ajay Kumar Gupta ,  Calvin Stacy Powers ,  Sachindra Joshi ,  Manish Anand Bhide

Inventor： Rema Ananthanarayanan ,  Mukesh K Mohania ,  Ajay Kumar Gupta ,  Calvin Stacy Powers ,  Sachindra Joshi ,  Manish Anand Bhide

IPC: G06F17/00

CPC classification number: G06F21/6218

Abstract: Methods, systems and computer program products for automatically enforcing obligations in accordance with a data-handling policy are disclosed. Requests by users for accessing data stored in a data repository are intercepted. A determination is made whether any obligations apply to each data item requested in accordance with the data handling policy. The determination may relate to whether rules having associated obligations identified in the data-handling policy apply to data items requested by a user. The obligations are automatically executed at an appropriate time after access of the data. Association of a data item requested by the user with an obligation may be recorded and tracked to determine the appropriate time for executing the obligation.

Abstract translation: 公开了根据数据处理政策自动执行义务的方法，系统和计算机程序产品。 用户访问存储在数据存储库中的数据的请求被截获。 确定是否对根据数据处理政策请求的每个数据项适用任何义务。 该确定可以涉及在数据处理策略中识别的具有相关义务的规则是否适用于用户请求的数据项。 义务在数据访问后的适当时间自动执行。 可以记录和跟踪用户请求的具有义务的数据项的关联，以确定执行义务的适当时间。

公开(公告)号：US08271281B2

公开(公告)日：2012-09-18

申请号：US12147898

申请日：2008-06-27

Applicant: Jayadeva ,  Sachindra Joshi ,  Himanshu Pant ,  Ashish Verma

Inventor： Jayadeva ,  Sachindra Joshi ,  Himanshu Pant ,  Ashish Verma

IPC: G10L17/00 ,  G09B19/04

CPC classification number: G09B19/04 ,  G10L15/26

Abstract: Techniques for assessing pronunciation abilities of a user are provided. The techniques include recording a sentence spoken by a user, performing a classification of the spoken sentence, wherein the classification is performed with respect to at least one N-ordered class, and wherein the spoken sentence is represented by a set of at least one acoustic feature extracted from the spoken sentence, and determining a score based on the classification, wherein the score is used to determine an optimal set of at least one question to assess pronunciation ability of the user without human intervention.

Abstract translation: 提供了用于评估用户发音能力的技术。 这些技术包括记录用户说出的句子，执行口语句子的分类，其中相对于至少一个N阶类执行分类，并且其中所述口语句子由一组至少一个声学 从所述口语句子中提取的特征，以及基于所述分类来确定得分，其中所述分数用于确定至少一个问题的最佳集合以评估用户的语音能力，而无需人为干预。

公开(公告)号：US20120197892A1

公开(公告)日：2012-08-02

申请号：US13434105

申请日：2012-03-29

Applicant: JEFFREY M. ACHTERMANN ,  INDRAJIT BHATTACHARYA ,  KEVIN W. ENGLISH, JR. ,  SHANTANU R. GODBOLE ,  SACHINDRA JOSHI ,  ASHWIN SRINIVASAN ,  ASHISH VERMA

Inventor： JEFFREY M. ACHTERMANN ,  INDRAJIT BHATTACHARYA ,  KEVIN W. ENGLISH, JR. ,  SHANTANU R. GODBOLE ,  SACHINDRA JOSHI ,  ASHWIN SRINIVASAN ,  ASHISH VERMA

IPC: G06F17/30

CPC classification number: G06F17/30598 ,  G06F17/3071 ,  G06F17/30864

Abstract: A computer system for evaluating cross-domain clusterability upon a target domain and a source domain. The cross-domain clusterability is calculated as a linear combination of a target clusterability and a source-target pair matchability, by use of a trade-off parameter that determines relative contribution of the target clusterability and the source-target pair matchability. The target clusterability quantifies how clusterable the target domain is. The source-target pair matchability is calculated as an average of a target-side matchability and a source-side matchability, which quantifies how well target centroids of the target domain are aligned with the source centroids and how well source centroids of the source domain are aligned with the target centroids, respectively.

Abstract translation: 用于评估目标域和源域的跨域可聚集性的计算机系统。 通过使用确定目标可聚集性和源 - 目标对匹配性的相对贡献的折衷参数，跨域可聚集性计算为目标可聚集性和源 - 目标对匹配性的线性组合。 目标可集群性量化目标域的可集群性。 源 - 目标对匹配性被计算为目标端匹配度和源端匹配度的平均值，其量化目标域的目标质心与源中心的匹配程度以及源域的源中心有多好 与目标质心分别对齐。

公开(公告)号：US20120150867A1

公开(公告)日：2012-06-14

申请号：US12966698

申请日：2010-12-13

Applicant: Danish Contractor ,  Thomas Hampp-Bahnmueller ,  Sachindra Joshi ,  Raghuram Krishnapuram ,  Kenney Ng

Inventor： Danish Contractor ,  Thomas Hampp-Bahnmueller ,  Sachindra Joshi ,  Raghuram Krishnapuram ,  Kenney Ng

IPC: G06F17/30

CPC classification number: G06F17/3071 ,  G06F17/30598 ,  G06F17/30622

Abstract: Provided are techniques for creating an inverted index for features of a set of data elements, wherein each of the data elements is represented by a vector of features, wherein the inverted index, when queried with a feature, outputs one or more data elements containing the feature. The features of the set of data elements are ranked. For each feature in the ranked list, the inverted index is queried for data elements having the feature and not having any previously selected feature and a cluster of the data elements is created based on results returned in response to the query.

Abstract translation: 提供了用于为一组数据元素的特征创建反向索引的技术，其中每个数据元素由特征向量表示，其中当用特征查询时，反向索引输出一个或多个包含 特征。 该组数据元素的特征被排序。 对于排序列表中的每个特征，对具有该特征并且没有任何先前选择的特征的数据元素查询反向索引，并且基于响应于该查询返回的结果来创建数据元素的集群。

公开(公告)号：US20110270808A1

公开(公告)日：2011-11-03

申请号：US12771543

申请日：2010-04-30

Applicant: Tanveer A. Faruquie ,  Sachindra Joshi ,  Hima P. Karanam ,  Marvin Mendelssohn ,  Mukesh K. Mohania ,  Angel Smith ,  L. V. Subramaniam ,  Girish Venkatachaliah

Inventor： Tanveer A. Faruquie ,  Sachindra Joshi ,  Hima P. Karanam ,  Marvin Mendelssohn ,  Mukesh K. Mohania ,  Angel Smith ,  L. V. Subramaniam ,  Girish Venkatachaliah

IPC: G06F17/30

CPC classification number: G06F17/2735 ,  G06F17/2795

Abstract: A clustering-based approach to data standardization is provided. Certain embodiments take as input a plurality of addresses, identify one or more features of the addresses, cluster the addresses based on the one or more features, utilize the cluster(s) to provide a data-based context useful in identifying one or more synonyms for elements contained in the address(es), and standardize the address(es) to an acceptable format, with one or more synonyms and/or other elements being added to or taken away from the input address(es) as part of the standardization process.

Abstract translation: 提供了基于聚类的数据标准化方法。 某些实施例将多个地址作为输入，识别地址的一个或多个特征，基于一个或多个特征聚集地址，利用群集提供用于识别一个或多个同义词的基于数据的上下文 对于包含在地址中的元素，并将地址标准化为可接受的格式，其中一个或多个同义词和/或其他元素作为标准化的一部分被添加到或从输入地址中取走 处理。

公开(公告)号：US07882099B2

公开(公告)日：2011-02-01

申请号：US12054482

申请日：2008-03-25

Applicant: Neeraj Agrawal ,  Sreeram Viswanath Balakrishnan ,  Sachindra Joshi

Inventor： Neeraj Agrawal ,  Sreeram Viswanath Balakrishnan ,  Sachindra Joshi

IPC: G06F17/30

CPC classification number: G06F17/30864 ,  Y10S707/99931 ,  Y10S707/99932 ,  Y10S707/99933 ,  Y10S707/99935

Abstract: A method (100) of crawling the Web (620) is disclosed. The method (100) crawls (120) Web pages on the Web starting from a given (110) set of seed Universal Resource Locators (URLs). Crawled Web pages are partitioned (140) into sets of relevant and irrelevant pages. A set of exclusion and/or inclusion patterns are discovered (150) from the sets of relevant and irrelevant pages, and subsequent crawling of the Web is restricted through the set of exclusion and/or inclusion patterns.

Abstract translation: 公开了一种爬行网（620）的方法（100）。 该方法（100）从给定的（110）种子通用资源定位符（URL）集合起，爬行（120）Web上的网页。 抓取的网页被分割（140）成相关和不相关的页面集合。 从相关和不相关页面的集合中发现一组排除和/或包含模式（150），并且通过一组排除和/或包含模式来限制Web的后续爬网。

公开(公告)号：US20100185648A1

公开(公告)日：2010-07-22

申请号：US12353669

申请日：2009-01-14

Applicant: Himanshu Chauhan ,  Om D. Deshmukh ,  Vijay Kumar Garg ,  Sachindra Joshi ,  Ashish Verma

Inventor： Himanshu Chauhan ,  Om D. Deshmukh ,  Vijay Kumar Garg ,  Sachindra Joshi ,  Ashish Verma

IPC: G06F7/06 ,  G06F17/30

CPC classification number: G06F3/167 ,  G06F16/9577 ,  G10L13/00 ,  G10L15/26

Abstract: Techniques for enabling voice access to information residing on the World Wide Web are provided. The techniques include receiving a query from a user, wherein the query comprises a voice-based request to access information residing on the World Wide Web, identifying one or more websites corresponding to the query, fetching the information from a website, wherein fetching the information comprises executing a hypertext transfer protocol (HTTP) request, organizing the information into a voice-based response and delivering the response to the user.

Abstract translation: 提供了能够对驻留在万维网上的信息进行语音访问的技术。 这些技术包括从用户接收查询，其中查询包括访问驻留在万维网上的信息的基于语音的请求，识别与查询相对应的一个或多个网站，从网站获取信息，其中获取信息 包括执行超文本传输​​协议（HTTP）请求，将信息组织成基于语音的响应并将响应传递给用户。

公开(公告)号：US07379932B2

公开(公告)日：2008-05-27

申请号：US11314432

申请日：2005-12-21

Applicant: Neeraj Agrawal ,  Sreeram Viswanath Balakrishnan ,  Sachindra Joshi

Inventor： Neeraj Agrawal ,  Sreeram Viswanath Balakrishnan ,  Sachindra Joshi

IPC: G06F17/30

CPC classification number: G06F17/30864 ,  Y10S707/99931 ,  Y10S707/99932 ,  Y10S707/99933 ,  Y10S707/99935

Abstract: A method (100) of crawling the Web (620) is disclosed. The method (100) crawls (120) Web pages on the Web starting from a given (110) set of seed Universal Resource Locators (URLs). Crawled Web pages are partitioned (140) into sets of relevant and irrelevant pages. A set of exclusion and/or inclusion patterns are discovered (150) from the sets of relevant and irrelevant pages, and subsequent crawling of the Web is restricted through the set of exclusion and/or inclusion patterns.

Abstract translation: 公开了一种爬行网（620）的方法（100）。 该方法（100）从给定的（110）种子通用资源定位符（URL）集合起，爬行（120）Web上的网页。 抓取的网页被分割（140）成相关和不相关的页面集合。 从相关和不相关页面的集合中发现一组排除和/或包含模式（150），并且通过一组排除和/或包含模式来限制Web的后续爬网。

公开(公告)号：US06754651B2

公开(公告)日：2004-06-22

申请号：US09836118

申请日：2001-04-17

Applicant: Amit Anil Nanavati ,  Krishna Prasad Chitrapura ,  Sachindra Joshi ,  Raghuram Krishnapuram

Inventor： Amit Anil Nanavati ,  Krishna Prasad Chitrapura ,  Sachindra Joshi ,  Raghuram Krishnapuram

IPC: G06F1730

CPC classification number: G06F17/30539 ,  G06F17/3061 ,  Y10S707/954 ,  Y10S707/961 ,  Y10S707/99932 ,  Y10S707/99933 ,  Y10S707/99943 ,  Y10S707/99945

Abstract: The present invention provides a system and a method for mining a new kind of association rules called disjunctive association rules, where the antecedent or the consequent of a rule may contain disjuncts of terms (XY or X⊕Y). Such rules are a natural generalisation to the kind of rules that have been mined hitherto. Furthermore, disjunctive association rules are generalised in the sense that the algorithm also mines rules which have disjunctions of conjuncts (C(AB)(DE)). Since the number of combinations of disjuncts is explosive, we use clustering to find a generalized subset. The said clustering is preferably performed using agglomerative clustering methods for finding the greedy subset.

Abstract translation: 本发明提供了一种用于挖掘称为分离关联规则的新型关联规则的系统和方法，其中规则的先决条件或结果可以包含术语的分离（X Y或X⊕Y）。 这样的规则是对迄今为止开采的那种规则的自然概括。 此外，分离关联规则在一般意义上是泛化的，即该算法还采用具有联结分离的规则（C （A B）（D E） 。 由于分离组合的数量是爆炸性的，我们使用聚类来找到广义子集。 所述聚类优选使用用于发现贪婪子集的聚集聚类方法进行。