-
公开(公告)号:US20210294829A1
公开(公告)日:2021-09-23
申请号:US17210318
申请日:2021-03-23
申请人: Sorcero, Inc.
摘要: Provided is a method including obtaining parameters and a document, determining a domain based on the parameters, where the domain maps to a first ontology, and where ontologies map n-grams onto a set of concepts. The method includes scoring a first set of n-grams of the document using a scoring model based on relations between members of the first set of n-grams, selecting sections of the text based on n-gram scores provided by the scoring model, and determining an initial n-gram set, where each respective n-gram of the initial n-gram set maps to a respective concept of the set of concepts, and where each respective n-gram is identified by an ontology other than the first ontology. The method includes determining related n-grams mapped to the set of concepts associated with the domain and generating a text summary for the document based on the sections and the related n-grams.
-
公开(公告)号:US11790889B2
公开(公告)日:2023-10-17
申请号:US17210320
申请日:2021-03-23
申请人: Sorcero, Inc.
IPC分类号: G10L15/06 , G10L15/197 , G06F40/20 , G10L15/16 , G06F16/332 , G06F9/451 , G06F16/33 , G06F16/36 , G06N20/00 , G06F16/34 , G06F40/40 , G06F16/22 , G06F16/9032 , G06F16/248 , G06F9/54 , G06F16/31 , G06F40/289 , G06N3/04 , G06F40/30 , G16H40/20 , G16H10/60 , G16H70/20
CPC分类号: G10L15/063 , G06F9/451 , G06F9/547 , G06F16/2237 , G06F16/248 , G06F16/328 , G06F16/3323 , G06F16/3329 , G06F16/3338 , G06F16/3344 , G06F16/3347 , G06F16/345 , G06F16/367 , G06F16/90332 , G06F40/20 , G06F40/289 , G06F40/30 , G06F40/40 , G06N3/04 , G06N20/00 , G10L15/16 , G10L15/197 , G16H10/60 , G16H40/20 , G16H70/20
摘要: Provided is a computer-implemented process including obtaining a corpus of natural-language text documents, automatically generating questions about information in corresponding portions of the documents, and associating the questions with the corresponding portions of the documents. The process further includes storing the questions and the associations with the corresponding portions of the documents in memory to form an index of automatically-generated questions to corresponding portions of documents that answer the questions.
-
公开(公告)号:US20210294781A1
公开(公告)日:2021-09-23
申请号:US17210320
申请日:2021-03-23
申请人: Sorcero, Inc.
IPC分类号: G06F16/22 , G06F16/248 , G06F16/9032 , G06F9/54
摘要: Provided is a computer-implemented process including obtaining a corpus of natural-language text documents, automatically generating questions about information in corresponding portions of the documents, and associating the questions with the corresponding portions of the documents. The process further includes storing the questions and the associations with the corresponding portions of the documents in memory to form an index of automatically-generated questions to corresponding portions of documents that answer the questions.
-
公开(公告)号:US20240079000A1
公开(公告)日:2024-03-07
申请号:US18465895
申请日:2023-09-12
申请人: Sorcero, Inc.
IPC分类号: G10L15/06 , G06F9/451 , G06F9/54 , G06F16/22 , G06F16/248 , G06F16/31 , G06F16/33 , G06F16/332 , G06F16/34 , G06F16/36 , G06F16/9032 , G06F40/20 , G06F40/289 , G06F40/30 , G06F40/40 , G06N3/04 , G06N20/00 , G10L15/16 , G10L15/197
CPC分类号: G10L15/063 , G06F9/451 , G06F9/547 , G06F16/2237 , G06F16/248 , G06F16/328 , G06F16/3323 , G06F16/3329 , G06F16/3338 , G06F16/3344 , G06F16/3347 , G06F16/345 , G06F16/367 , G06F16/90332 , G06F40/20 , G06F40/289 , G06F40/30 , G06F40/40 , G06N3/04 , G06N20/00 , G10L15/16 , G10L15/197 , G16H40/20
摘要: Provided is a computer-implemented process including obtaining a corpus of natural-language text documents, automatically generating questions about information in corresponding portions of the documents, and associating the questions with the corresponding portions of the documents. The process further includes storing the questions and the associations with the corresponding portions of the documents in memory to form an index of automatically-generated questions to corresponding portions of documents that answer the questions.
-
公开(公告)号:US11699432B2
公开(公告)日:2023-07-11
申请号:US17476324
申请日:2021-09-15
申请人: Sorcero, Inc
IPC分类号: G10L15/06 , G10L15/197 , G06F40/20 , G06F16/332 , G06F9/451 , G06F16/33 , G06F16/36 , G10L15/16 , G06N20/00 , G06F16/34 , G06F40/40 , G06F16/22 , G06F16/9032 , G06F16/248 , G06F9/54 , G06F16/31 , G06F40/289 , G06N3/04 , G06F40/30 , G16H40/20 , G16H10/60 , G16H70/20
CPC分类号: G10L15/063 , G06F9/451 , G06F9/547 , G06F16/2237 , G06F16/248 , G06F16/328 , G06F16/3323 , G06F16/3329 , G06F16/3338 , G06F16/3344 , G06F16/3347 , G06F16/345 , G06F16/367 , G06F16/90332 , G06F40/20 , G06F40/289 , G06F40/30 , G06F40/40 , G06N3/04 , G06N20/00 , G10L15/16 , G10L15/197 , G16H10/60 , G16H40/20 , G16H70/20
摘要: Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.
-
公开(公告)号:US11557276B2
公开(公告)日:2023-01-17
申请号:US17210318
申请日:2021-03-23
申请人: Sorcero, Inc.
IPC分类号: G06F16/33 , G06F16/36 , G06F16/34 , G06F40/40 , G10L15/06 , G10L15/197 , G06F40/20 , G10L15/16 , G06F16/332 , G06F9/451 , G06N20/00 , G06F16/22 , G06F16/9032 , G06F16/248 , G06F9/54 , G06F16/31 , G06F40/289 , G06N3/04 , G06F40/30 , G16H40/20 , G16H10/60 , G16H70/20
摘要: A method includes obtaining parameters and a document, determining a domain based on the parameters, where the domain maps to a first ontology, and where ontologies map n-grams onto a set of concepts. The method includes scoring a first set of n-grams of the document using a scoring model based on relations between members of the first set of n-grams, selecting sections of the text based on n-gram scores provided by the scoring model, and determining an initial n-gram set, where each respective n-gram of the initial n-gram set maps to a respective concept of the set of concepts, and where each respective n-gram is identified by an ontology other than the first ontology. The method includes determining related n-grams mapped to the set of concepts associated with the domain and generating a text summary for the document based on the sections and the related n-grams.
-
公开(公告)号:US20220005463A1
公开(公告)日:2022-01-06
申请号:US17476324
申请日:2021-09-15
申请人: Sorcero, Inc
IPC分类号: G10L15/06 , G10L15/197 , G06F40/20 , G10L15/16 , G06F16/332 , G06F9/451 , G06F16/33 , G06F16/36 , G06N20/00 , G06F16/34 , G06F40/40 , G06F16/22 , G06F16/9032 , G06F16/248 , G06F9/54 , G06F16/31 , G06F40/289 , G06N3/04 , G06F40/30
摘要: Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.
-
-
-
-
-
-