-
公开(公告)号：US20210271718A1
公开(公告)日：2021-09-02
申请号：US16806438
申请日：2020-03-02
发明人： Arvind Agarwal , Vitobha Munigala , Mitesh H. Vasa , Shanmukha Guttula , Ankush Gupta , Nicholas Gomez Phan
IPC分类号： G06F16/93 , G06F16/28 , G06F16/2458 , G06N20/00 , G06F40/30
摘要： One embodiment provides a method, including: obtaining at least two documents, wherein one of the at least two documents comprises a revision different than another of the at least two documents; identifying, within each of the at least two documents, portions corresponding to groups of text containing a conceptual unit; assigning at least a subset of the identified portions to a category type corresponding to a topic of a given portion, wherein the assigning comprises (i) generating a semantic tag for the identified portions in the subset and (ii) tagging the identified portions in the subset with the semantic tag; and determining changes between the at least two documents, wherein the determining comprises (iii) aligning given portions across the at least two documents based upon a relationship between the given portions across the at least two documents, (iv) identifying semantic differences between the aligned portions, and (v) identifying any remaining unaligned portions.
-
公开(公告)号：US11720533B2
公开(公告)日：2023-08-08
申请号：US17536860
申请日：2021-11-29
发明人： Rajmohan Chandrahasan , Ankush Gupta , Venkata Nagaraju Pavuluri , Arvind Agarwal , Sameep Mehta
CPC分类号： G06F16/213 , G06F16/2282 , G06F16/2358 , G06F16/2462 , G06F18/2178 , G06N3/045
摘要： Techniques for automatically determining different data types found in databases are disclosed. In one example, a computer implemented method comprises receiving a portion of identifying information for one or more components of a database, and generating one or more descriptions for the one or more components based at least in part on the portion of the identifying information for the one or more components. The one or more descriptions are inputted to one or more machine learning models, and, using the one or more machine learning models, one or more data types associated with the one or more components are predicted. The prediction is based at least in part on the one or more descriptions.
-
公开(公告)号：US11500840B2
公开(公告)日：2022-11-15
申请号：US16804399
申请日：2020-02-28
IPC分类号： G06F16/22 , G06F16/383 , G06K9/62 , G06F16/26 , G06F16/2457
摘要： Methods, systems, and computer program products for contrasting document-embedded structured data and generating summaries thereof are provided herein. A computer-implemented method includes extracting two or more tables from two or more input documents, wherein each of the two or more input documents comprises structured data and unstructured data; normalizing the two or more extracted tables using one or more alignment techniques; determining at least one of (i) one or more differences and (ii) one or more similarities across the two or more extracted tables by performing a comparison of the two or more normalized tables; deriving one or more insights from the comparison by applying at least one analytical model to the at least one of the one or more determined differences and one or more determined similarities; and outputting at least a portion of the one or more insights to at least one user.
-
公开(公告)号：US20210271654A1
公开(公告)日：2021-09-02
申请号：US16804399
申请日：2020-02-28
IPC分类号： G06F16/22 , G06F16/383 , G06F16/26 , G06F16/2457 , G06K9/62
摘要： Methods, systems, and computer program products for contrasting document-embedded structured data and generating summaries thereof are provided herein. A computer-implemented method includes extracting two or more tables from two or more input documents, wherein each of the two or more input documents comprises structured data and unstructured data; normalizing the two or more extracted tables using one or more alignment techniques; determining at least one of (i) one or more differences and (ii) one or more similarities across the two or more extracted tables by performing a comparison of the two or more normalized tables; deriving one or more insights from the comparison by applying at least one analytical model to the at least one of the one or more determined differences and one or more determined similarities; and outputting at least a portion of the one or more insights to at least one user.
-
公开(公告)号：US10885019B2
公开(公告)日：2021-01-05
申请号：US16163289
申请日：2018-10-17
发明人： Nitin Gupta , Ankush Gupta , Vijay Ekambaram
IPC分类号： G06F17/00 , G06F16/23 , G06N20/00 , G06F16/35 , G06F16/332
摘要： One embodiment provides a method, including: receiving a plurality of review comments from each of a plurality of reviewers tasked with reviewing a document; categorizing each of the plurality of review comments into one of a plurality of review topics; identifying a conflict between a first review comment provided by one of the plurality of reviewers and a second review comment provided by another of the plurality of reviewers, wherein the identifying a conflict comprises (i) identifying a sentiment of the first review comment and a sentiment of the second review comment and (ii) determining that the sentiment of the first review comment and the sentiment of the second review comment are different; and generating a question set comprising a plurality of questions based upon a conflict identified for a review comment of the corresponding reviewer, wherein the corresponding reviewer answering the generated question resolves the conflict.
-
公开(公告)号：US20230169050A1
公开(公告)日：2023-06-01
申请号：US17536860
申请日：2021-11-29
发明人： Rajmohan Chandrahasan , Ankush Gupta , Venkata Nagaraju Pavuluri , Arvind Agarwal , Sameep Mehta
CPC分类号： G06F16/213 , G06F16/2282 , G06F16/2462 , G06F16/2358 , G06K9/6263 , G06N3/0454
摘要： Techniques for automatically determining different data types found in databases are disclosed. In one example, a computer implemented method comprises receiving a portion of identifying information for one or more components of a database, and generating one or more descriptions for the one or more components based at least in part on the portion of the identifying information for the one or more components. The one or more descriptions are inputted to one or more machine learning models, and, using the one or more machine learning models, one or more data types associated with the one or more components are predicted. The prediction is based at least in part on the one or more descriptions.
-
公开(公告)号：US11630869B2
公开(公告)日：2023-04-18
申请号：US16806438
申请日：2020-03-02
发明人： Arvind Agarwal , Vitobha Munigala , Mitesh H. Vasa , Shanmukha Guttula , Ankush Gupta , Nicholas Gomez Phan
IPC分类号： G06F16/93 , G06F16/28 , G06F40/30 , G06N20/00 , G06F16/2458
摘要： One embodiment provides a method, including: obtaining at least two documents, wherein one of the at least two documents comprises a revision different than another of the at least two documents; identifying, within each of the at least two documents, portions corresponding to groups of text containing a conceptual unit; assigning at least a subset of the identified portions to a category type corresponding to a topic of a given portion, wherein the assigning comprises (i) generating a semantic tag for the identified portions in the subset and (ii) tagging the identified portions in the subset with the semantic tag; and determining changes between the at least two documents, wherein the determining comprises (iii) aligning given portions across the at least two documents based upon a relationship between the given portions across the at least two documents, (iv) identifying semantic differences between the aligned portions, and (v) identifying any remaining unaligned portions.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.016 秒)
