Conversational agents

Patent metadata

Field	Value
Publication number	US-2016351193-A1
Application number	US-201615217157-A
Country	US
Kind code	A1
Filing date	Jul 22, 2016
Priority date	Jul 31, 2014
Publication date	Dec 1, 2016
Grant date	—

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for handing off a user conversation between computer-implemented agents. One of the methods includes receiving, by a computer-implemented agent specific to a user device, a digital representation of speech encoding an utterance, determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with another computer-implemented agent, and establishing, by the computer-implemented agent, a communication between the other computer-implemented agent and the user device.

First claim

What is claimed is:

1 . (canceled)

2 . A computer-implemented method comprising:
receiving, by a computer-implemented agent specific to a user device, a digital representation of speech encoding an utterance; determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with another computer-implemented agent represented by data, stored on the user device, that identifies a particular spoken style of speech for the other computer-implemented agent from among two or more different spoken styles of speech for a particular language; establishing, by the user device, a communication between the other computer-implemented agent and the user device; receiving, by the user device, identification of a response to the utterance from the other computer-implemented agent; determining, by the user device, the particular spoken style of speech for the other computer-implemented agent to use for presentation of the response; and presenting, by the user device, the response to the utterance received from the other computer-implemented agent according to the particular spoken style of speech.

3 . The method of claim 2 wherein the other computer-implemented agent is not specific to the user device.

4 . The method of claim 2 wherein establishing the communication with the other computer-implemented agent and the user device comprises establishing the communication with the user device and the other computer-implemented agent executing on another device.

5 . The method of claim 2 wherein establishing the communication with the other computer-implemented agent and the user device comprises establishing the communication with the other computer-implemented agent and the computer-implemented agent.

6 . The method of claim 2 wherein the computer-implemented agent is for a first application on the user device and the other computer-implemented agent is for a second, different application on the user device.

7 . The method of claim 2 comprising:
providing a representation of the utterance to the other computer-implemented agent.

8 . The method of claim 7 wherein the representation comprises the digital representation of speech.

9 . The method of claim 7 wherein the representation comprises a text representation of the utterance.

10 . The method of claim 9 wherein receiving identification of the response to the utterance from the other computer-implemented agent comprises:
receiving, by the user device from the other computer-implemented agent, another representation of a response to the utterance; and
generating, using the other representation, data to cause a presentation of the response to the utterance.

11 . The method of claim 7 wherein providing the representation of the utterance to the other computer-implemented agent comprises providing data for a user who spoke the utterance to the other computer-implemented agent.

12 . The method of claim 11 wherein providing data for the user who spoke the utterance to the other computer-implemented agent comprises:
determining privacy settings for the user that define types of data for the user that the computer-implemented agent may provide to the other computer-implemented agent;
determining data for the user who spoke the utterance that may be shared with the other computer-implemented agent based on the privacy settings for the user; and
providing the data for the user who spoke the utterance to the other computer-implemented agent according to the privacy settings.

13 . The method of claim 2 wherein the data, stored on the user device, that represents the other computer-implemented agent includes a definition of a data flow for the other computer-implemented agent that identifies a response for the other computer-implemented agent given a particular type of input.

14 . The method of claim 2 wherein the data, stored on the user device, that represents the other computer-implemented agent includes text-to-speech parameters for responses provided by the other computer-implemented agent.

15 . The method of claim 2 comprising:
receiving, by the user device, a description of an entity that created the other computer-implemented agent; and
providing, by the user device, a representation of the description of the entity that created the other computer-implemented agent for presentation.

16 . The method of claim 2 wherein the data, stored on the user device, that identifies the particular spoken style of speech comprises data that identifies a) particular idioms and b) a particular vocabulary for the other computer-implemented agent.

17 . The method of claim 2 wherein determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with the other computer-implemented agent comprises:
determining, by the computer-implemented agent using the utterance, that the utterance is not specific to a particular second computer-implemented agent;
determining, by the computer-implemented agent using the utterance, two or more second computer-implemented agents each of which can respond to the utterance;
providing a prompt that requests selection of one of the second computer-implemented agents;
receiving indication of a selected one of the second computer-implemented agents; and
determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with the selected one of the second computer-implemented agents.

18 . A system comprising more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving, by a computer-implemented agent specific to a user device, a digital representation of speech encoding an utterance; determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with another computer-implemented agent represented by data, stored on the user device, that identifies a particular spoken style of speech for the other computer-implemented agent from among two or more different spoken styles of speech for a particular language; establishing, by the user device, a communication between the other computer-implemented agent and the user device; receiving, by the user device, identification of a response to the utterance from the other computer-implemented agent; determining, by the user device, the particular spoken style of speech for the other computer-implemented agent to use for presentation of the response; and presenting, by the user device, the response to the utterance received from the other computer-implemented agent according to the particular spoken style of speech.

19 . The system of claim 18 wherein the other computer-implemented agent is not specific to the user device.

20 . The system of claim 18 wherein establishing the communication with the other computer-implemented agent and the user device comprises establishing the communication with the user device and the other computer-implemented agent executing on another device.

21 . A non-transitory computer readable storage medium storing instructions executable by a data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising:
receiving, by a computer-implemented agent specific to a user device, a digital repr

Assignees

• Google Inc

Inventors

• Chen Johnny
• Dean Thomas L
• Lau Qiangfeng Peter
• Gandhe Sudeep
• Schine Gabriel

Classifications

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G06F17/30654

  Physics · mapped topic

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L13/08

  Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title