-
公开(公告)号:US20250006203A1
公开(公告)日:2025-01-02
申请号:US18883994
申请日:2024-09-12
Applicant: GOOGLE LLC
Inventor: David Kliger Elson , David P. Whipp , Shir Judith Yehoshua
IPC: G10L17/22 , G06F16/332
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing dialogs. In one aspect, a method includes receiving a request associated with a task from a user device; submitting the request to each of a plurality of distinct data providers; receiving a plurality of suggested dialog responses from two or more of the data providers; scoring the one or more suggested dialog responses based on one or more scoring factors; determining a particular dialog response to provide to the user based on the scoring; and providing the determined dialog response to the user device.
-
公开(公告)号:US12112760B2
公开(公告)日:2024-10-08
申请号:US18222325
申请日:2023-07-14
Applicant: GOOGLE LLC
Inventor: David Kliger Elson , David P. Whipp , Shir Judith Yehoshua
IPC: G10L15/08 , G06F16/332 , G10L15/22 , G10L17/22
CPC classification number: G10L17/22 , G06F16/3329
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing dialogs. In one aspect, a method includes receiving a request associated with a task from a user device; submitting the request to each of a plurality of distinct data providers; receiving a plurality of suggested dialog responses from two or more of the data providers; scoring the one or more suggested dialog responses based on one or more scoring factors; determining a particular dialog response to provide to the user based on the scoring; and providing the determined dialog response to the user device.
-
公开(公告)号:US20210103624A1
公开(公告)日:2021-04-08
申请号:US17122906
申请日:2020-12-15
Applicant: GOOGLE LLC
Inventor: David P. Whipp , David Kliger Elson , Shir Judith Yehoshua
IPC: G06F16/9535 , G06F16/242 , G06F3/16 , H04M3/493 , G10L15/18 , G06F16/332 , G06F16/953 , G06F16/9536 , G10L15/22
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using frames for performing tasks. One of the methods includes receiving a first request to perform a task, the first request comprising user speech identifying the task; generating a frame associated with the task, wherein the frame comprises one or more types of values necessary to perform the task, and wherein each type of value can be satisfied by a respective value; receiving a second request to provide information related to a question, the second request comprising user speech identifying the question; providing information identifying the question to a search engine, and receiving a response identifying one or more terms; determining that at least one term can satisfy a type of value necessary to perform the task; and storing the at least one term in the frame.
-
公开(公告)号:US10713005B2
公开(公告)日:2020-07-14
申请号:US14988494
申请日:2016-01-05
Applicant: Google LLC
Inventor: Shir Judith Yehoshua , David Kliger Elson , David P. Whipp
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing dialogs. In one aspect, a method includes receiving a request to perform a task from a user device; obtaining a dialog corresponding to the task; providing multiple protocol buffers to the user device; receiving a voice input and one or more annotated protocol buffers from the user device, the one or more annotated protocol buffers identifying corresponding non-verbal responses to content in the protocol buffers; and using the received protocol buffers to update a state of the dialog and to interpret the voice input.
-
公开(公告)号:US20190304471A1
公开(公告)日:2019-10-03
申请号:US16378546
申请日:2019-04-08
Applicant: Google LLC
Inventor: David Kliger Elson , David P. Whipp , Shir Judith Yehoshua
IPC: G10L17/22 , G06F16/332
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing dialogs. In one aspect, a method includes receiving a request associated with a task from a user device; submitting the request to each of a plurality of distinct data providers; receiving a plurality of suggested dialog responses from two or more of the data providers; scoring the one or more suggested dialog responses based on one or more scoring factors; determining a particular dialog response to provide to the user based on the scoring; and providing the determined dialog response to the user device.
-
-
-
-