公开(公告)号：US11789940B2

公开(公告)日：2023-10-17

申请号：US16588155

申请日：2019-09-30

申请人： American Express Travel Related Services Company, Inc.

发明人： Yue Jiao ,  Salil Joshi ,  Shourya Roy ,  Dawn Thomas ,  Bharath Venkatesh

IPC分类号： G06F16/242 ,  G06N20/00 ,  G06F16/2455

CPC分类号： G06F16/243 ,  G06F16/24565 ,  G06N20/00

摘要： Disclosed are various approaches for providing a natural language interface for searching databases. A natural language query is parsed to identify a plurality of tokens. At least one operator is identified with a machine-learning model based at least in part on the plurality of tokens. Next, at least one attribute and at least one respective attribute value are identified with a machine-learning model based at least in part on the plurality of tokens. Then, at least one constraint is identified with a machine-learning model based at least in part on the plurality of tokens. Finally, a machine language query is generated based at least in part on the at least one operator, the constraint(s), the attribute(s), and the respective attribute value(s).

公开(公告)号：US20210049158A1

公开(公告)日：2021-02-18

申请号：US16588155

申请日：2019-09-30

申请人： American Express Travel Related Services Company, Inc.

发明人： Yue Jiao ,  Salil Joshi ,  Shourya Roy ,  Dawn Thomas ,  Bharath Venkatesh

IPC分类号： G06F16/242 ,  G06F16/2455 ,  G06N20/00

摘要： Disclosed are various approaches for providing a natural language interface for searching databases. A natural language query is parsed to identify a plurality of tokens. At least one operator is identified with a machine-learning model based at least in part on the plurality of tokens. Next, at least one attribute and at least one respective attribute value are identified with a machine-learning model based at least in part on the plurality of tokens. Then, at least one constraint is identified with a machine-learning model based at least in part on the plurality of tokens. Finally, a machine language query is generated based at least in part on the at least one operator, the constraint(s), the attribute(s), and the respective attribute value(s).