Conversational agent response determined using a sentiment
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.
1. A computer-implemented method comprising:
receiving, by a computer-implemented agent that is specific to a user device of a user, and from a third party, third party agent data for a third party agent to be associated with the third party, the third party agent data including:
a conversational flow associated with a purpose of the third party, and
a particular style of speech, from among multiple disparate styles of speech, for the third part agent;
receiving, by the computer-implemented agent, a spoken utterance that specifies a requirement to establish communication with the third party agent; and
in response to receiving the spoken utterance:
causing the third party agent to engage in a dialog with the user of the user device, wherein causing the third party agent to engage in the dialog with the user comprises:
causing the third party agent to generate voice output using the particular style of speech and based on the conversational flow associated with the purpose of the third party; and
providing, for output at the user device, the generated voice output.
2. The method of claim 1 , further comprising:
receiving, by the computer-implemented agent that is specific to the user device of the user, and from the third party, additional third party agent data for an additional third party agent to be associated with the third party, the additional third party agent data including:
an additional conversational flow associated with an additional purpose of the third party, and
an additional particular style of speech, from among the multiple disparate styles of speech, for the additional third party agent;
during the dialog between the third party agent and the user:
receiving, by the computer-implemented agent, a further spoken utterance that specifies a further requirement to establish communication with the additional third party agent; and
in response to receiving the further spoken utterance:
causing the third party agent to engage in a further dialog with the user of the user device, wherein causing the additional third party agent to engage in the further dialog with the user comprises:
causing the additional third party agent to further generate voice output using the additional particular style of speech and based on the additional conversational flow associated with the additional purpose of the third party; and
providing, for output at the user device, the further generated voice output.
3. The method of claim 2 , wherein the third party agent is a restaurant information agent associated with a restaurant entity, and wherein the additional third party is a restaurant reservation agent associated with the restaurant entity.
4. The method of claim 3 , wherein the purpose of the third party included in the third party agent data is to obtain menu information for the restaurant entity, and wherein the additional purpose included in the additional third party data is to make a restaurant reservation at the restaurant entity.
5. The method of claim 2 , wherein the additional particular style of speech is a same style of speech as the particular style of speech.
6. The method of claim 2 , wherein the additional particular style of speech is a distinct style of speech from the particular style of speech.
7. The method of claim 2 , wherein causing the additional third party agent to engage in the further dialog with the user further comprises:
causing the third party agent to transfer the dialog to the additional third party agent to initiate the further dialog.
8. The method of claim 1 , wherein the conversational flow associated with the purpose is based on a default template selected from a plurality of disparate default templates.
9. The method of claim 8 , further comprising:
receiving, by the computer-implemented agent, and from the third party, user input that customizes the default template to generate a customized template for the conversational flow.
10. The method of claim 1 , wherein the spoken utterance that specifies the requirement to establish communication with the third party agent specifies the purpose of the third party included in the third party agent data.
11. A system comprising:
at least one processor; and
at least one memory storing instructions that, when executed, cause the at least one processor to:
receive, by a computer-implemented agent that is specific to a user device of a user, and from a third party, third party agent data for a third party agent to be associated with the third party, the third party agent data including:
a conversational flow associated with a purpose of the third party, and
a particular style of speech, from among multiple disparate styles of speech, for the third part agent;
receive, by the computer-implemented agent, a spoken utterance that specifies a requirement to establish communication with the third party agent; and
in response to receiving the spoken utterance:
cause the third party agent to engage in a dialog with the user of the user device, wherein the instructions to cause the third party agent to engage in the dialog with the user comprise instructions to:
cause the third party agent to generate voice output using the particular style of speech and based on the conversational flow associated with the purpose of the third party; and
provide, for output at the user device, the generated voice output.
12. The system of claim 11 , wherein the instructions further cause the at least one processor to:
receive, by the computer-implemented agent that is specific to the user device of the user, and from the third party, additional third party agent data for an additional third party agent to be associated with the third party, the additional third party agent data including:
an additional conversational flow associated with an additional purpose of the third party, and
an additional particular style of speech, from among the multiple disparate styles of speech, for the additional third party agent;
during the dialog between the third party agent and the user:
receive, by the computer-implemented agent, a further spoken utterance that specifies a further requirement to establish communication with the additional third party agent; and
in response to receiving the further spoken utterance:
cause the third party agent to engage in a further dialog with the user of the user device, wherein the instructions to cause the additional third party agent to engage in the further dialog with the user comprise the instructions to:
cause the additional third party agent to further generate voice output using the additional particular style of speech and based on the additional conversational flow associated with the additional purpose of the third party; and
provide, for output at the user device, the further generated voice output.
13. The system of claim 12 , wherein the third party agent is a restaurant information agent associated with a restaurant entity, and wherein the additional third party is a restaurant reservation agent associated with the restaurant entity.
14. The system of claim 13 , wherein the purpose of the third party included in the third party agent data is to obtain menu information for the restaurant entity, and wherein the additional purpose included in the additional third party data is to make a restaurant reservation at the restaurant entity.
15. The system of claim 12 , wherein the additional particular style of speech is a same style of speech as the particular style of speech.
16. The system of claim 12 , wherein the additional particular style of speech is a distinct style of speech from the particular style of speech.
17. The system of claim 12 , wherein the instructions to cause the additional third party agent to engage in the further dialog with the user further causes the instructions to:
cause the third party agent to transfer the dialog to the additional third party agent to initiate the further dialog.
18. A non-transitory computer-readable storage medium storing instructions that, when executed, cause one or more processors to:
receive, by a computer-implemented agent that is specific to a user device of a user, and from a third party, third party agent data for a third party agent to be associated with the third party, the third party agent data including:
a conversational flow associated with a purpose of the third party, and
a particular style of speech, from among multiple disparate styles of speech, for the third part agent;
receive, by the computer-implemented agent, a spoken utterance that specifies a requirement to establish communication with the third party agent; and
in response to receiving the spoken utterance:
cause the third party agent to engage in a dialog with the user of the user device, wherein the instructions to cause the third party agent to engage in the dialog with the user comprise instructions to:
cause the third party agent to generate voice output using the particular style of speech and based on the conversational flow associated with the purpose of the third party; and
provide, for output at the user device, the generated voice output.