-
1.发明申请公开(公告)号：US20210150133A1
公开(公告)日：2021-05-20
申请号：US17134964
申请日：2020-12-28
Applicant: Open Text SA ULC
IPC: G06F40/174 , G06K9/00 , G06N20/00 , G06F16/93 , G06F16/22 , G06F16/25 , G06K9/62 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
2.发明授权公开(公告)号：US12080091B2
公开(公告)日：2024-09-03
申请号：US18331990
申请日：2023-06-09
Applicant: Open Text SA ULC
IPC: G06F17/00 , G06F16/22 , G06F16/25 , G06F16/93 , G06F18/21 , G06F40/174 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274 , G06N20/00 , G06V30/19 , G06V30/412 , G06V30/414 , G06V30/416
CPC classification number: G06V30/416 , G06F16/2282 , G06F16/258 , G06F16/93 , G06F18/217 , G06F40/174 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274 , G06N20/00 , G06V30/1916 , G06V30/412 , G06V30/414
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as one negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
3.发明授权公开(公告)号：US11710334B2
公开(公告)日：2023-07-25
申请号：US17888933
申请日：2022-08-16
Applicant: Open Text SA ULC
IPC: G06F17/00 , G06V30/416 , G06N20/00 , G06F16/93 , G06F16/22 , G06F16/25 , G06F40/174 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274 , G06V30/412 , G06V30/414 , G06F18/21 , G06V30/19
CPC classification number: G06V30/416 , G06F16/2282 , G06F16/258 , G06F16/93 , G06F18/217 , G06F40/174 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274 , G06N20/00 , G06V30/1916 , G06V30/412 , G06V30/414
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
Patent Agency Ranking
4.发明授权公开(公告)号：US10241992B1
公开(公告)日：2019-03-26
申请号：US15964654
申请日：2018-04-27
Applicant: Open Text SA ULC
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
5.发明公开公开(公告)号：US20230334888A1
公开(公告)日：2023-10-19
申请号：US18331990
申请日：2023-06-09
Applicant: Open Text SA ULC
IPC: G06V30/416 , G06N20/00 , G06F16/93 , G06F16/22 , G06F16/25 , G06F40/174 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274 , G06V30/412 , G06V30/414 , G06F18/21 , G06V30/19
CPC classification number: G06V30/416 , G06N20/00 , G06F16/93 , G06F16/2282 , G06F16/258 , G06F40/174 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274 , G06V30/412 , G06V30/414 , G06F18/217 , G06V30/1916
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as one negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
6.发明授权公开(公告)号：US11455462B2
公开(公告)日：2022-09-27
申请号：US17134964
申请日：2020-12-28
Applicant: Open Text SA ULC
IPC: G06F17/00 , G06F40/174 , G06N20/00 , G06F16/93 , G06F16/22 , G06F16/25 , G06K9/62 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274 , G06V30/412 , G06V30/414 , G06V30/416
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
7.发明授权公开(公告)号：US10909311B2
公开(公告)日：2021-02-02
申请号：US16272692
申请日：2019-02-11
Applicant: OPEN TEXT SA ULC
IPC: G06F17/00 , G06F40/174 , G06K9/00 , G06N20/00 , G06F16/93 , G06F16/22 , G06F16/25 , G06K9/62 , G06F40/177 , G06F40/186 , G06F40/216 , G06F40/274
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
8.发明申请公开(公告)号：US20190332662A1
公开(公告)日：2019-10-31
申请号：US16272692
申请日：2019-02-11
Applicant: OPEN TEXT SA ULC
Abstract: A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.019 seconds)
