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 method implemented by one or more processors of a user device, comprising:
receiving a spoken utterance from a user of the user device, the spoken utterance being directed to a first party computer-implemented agent that is executed at the user device;
determining whether the spoken utterance includes a request to interact with a third party computer-implemented agent, the third party computer-implemented agent being accessible by the user device over one or more networks; and
in response to determining that the spoken utterance includes the request to interact with the third party computer-implemented agent:
causing the third party computer-implemented agent to engage in a dialog with the user, wherein causing the third party computer-implemented agent to engage in the dialog with the user comprises:
causing the third party computer-implemented agent to generate third party computer-implement agent voice output based on a particular style of speech that is specified by third party computer-implemented agent data associated with the third party computer-implemented agent; and
causing the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
2. The method of claim 1 , further comprising:
in response to determining that the spoken utterance does not include the request to interact with the third party computer-implemented agent:
generating first party computer-implement agent voice output based on an additional particular style of speech that differs from the particular style of speech that is specified by the third party computer-implemented agent data associated with the third party computer-implemented agent; and
causing the first party computer-implement agent voice output to be provided for presentation to the user at the user device.
3. The method of claim 1 , wherein causing the third party computer-implemented agent to generate the third party computer-implement agent voice output is further based on a conversational flow that is also specified by the third party computer-implemented agent data associated with the third party computer-implemented agent.
4. The method of claim 1 , in response to determining that the spoken utterance includes the request to interact with the third party computer-implemented agent and prior to causing the third party computer-implemented agent to engage in the dialog with the user, further comprising:
establishing, over one or more of the networks, a communication between the user device and an additional device,
wherein the third party computer-implemented agent is executed at the additional device, and
wherein the communication between the user device and the additional device enables the third party computer-implemented agent to communicate with the first party computer-implemented agent.
5. The method of claim 4 , wherein the third party computer-implemented agent data associated with the third party computer-implemented agent is received at the user device prior to establishing the communication between the user device and the additional device.
6. The method of claim 1 , wherein causing the third party computer-implemented agent to engage in the dialog with the user further comprises:
providing, over one or more of the networks, a representation of the spoken utterance to the third party computer-implemented agent; and
receiving, over one or more of the networks, a representation of the third party computer-implement agent voice output based on a particular style of speech.
7. The method of claim 6 , wherein the representation of the spoken utterance comprises a speech encoding of the spoken utterance and/or a text representation of the spoken utterance.
8. The method of claim 6 , wherein the representation of the third party computer-implement agent voice output comprises the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
9. The method of claim 6 , wherein the representation of the third party computer-implement agent voice output comprises text corresponding to the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
10. The method of claim 9 , wherein causing the third party computer-implement agent voice output to be provided for presentation to the user at the user device comprises:
generating, based on the text corresponding to the third party computer-implement agent voice output and based on the third party computer-implemented agent data, the third party computer-implement agent voice output in the particular style of speech; and
causing the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
11. A user device comprising:
one or more processors; and
memory storing instructions that, when executed, cause the one or more processors to:
receive a spoken utterance from a user of the user device, the spoken utterance being directed to a first party computer-implemented agent that is executed at the user device;
determine whether the spoken utterance includes a request to interact with a third party computer-implemented agent, the third party computer-implemented agent being accessible by the user device over one or more networks; and
in response to determining that the spoken utterance includes the request to interact with the third party computer-implemented agent:
cause the third party computer-implemented agent to engage in a dialog with the user, wherein the instructions to cause the third party computer-implemented agent to engage in the dialog with the user comprise instructions to:
cause the third party computer-implemented agent to generate third party computer-implement agent voice output based on a particular style of speech that is specified by third party computer-implemented agent data associated with the third party computer-implemented agent; and
cause the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
12. The user device of claim 11 , wherein the instructions further cause the one or more processors to:
in response to determining that the spoken utterance does not include the request to interact with the third party computer-implemented agent:
generate first party computer-implement agent voice output based on an additional particular style of speech that differs from the particular style of speech that is specified by the third party computer-implemented agent data associated with the third party computer-implemented agent; and
cause the first party computer-implement agent voice output to be provided for presentation to the user at the user device.
13. The user device of claim 11 , wherein causing the third party computer-implemented agent to generate the third party computer-implement agent voice output is further based on a conversational flow that is also specified by the third party computer-implemented agent data associated with the third party computer-implemented agent.
14. The user device of claim 11 , in response to determining that the spoken utterance includes the request to interact with the third party computer-implemented agent and prior to causing the third party computer-implemented agent to engage in the dialog with the user, wherein the instructions further cause the one or more processors to:
establish, over one or more of the networks, a communication between the user device and an additional device,
wherein the third party computer-implemented agent is executed at the additional device, and
wherein the communication between the user device and the additional device enables the third party computer-implemented agent to communicate with the first party computer-implemented agent.
15. The user device of claim 11 , wherein the instructions to cause the third party computer-implemented agent to engage in the dialog with the user further comprise instructions to:
provide, over one or more of the networks, a representation of the spoken utterance to the third party computer-implemented agent; and
receive, over one or more of the networks, a representation of the third party computer-implement agent voice output based on a particular style of speech.
16. The user device of claim 15 , wherein the representation of the spoken utterance comprises a speech encoding of the spoken utterance and/or a text representation of the spoken utterance.
17. The user device of claim 15 , wherein the representation of the third party computer-implement agent voice output comprises the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
18. The user device of claim 15 , wherein the representation of the third party computer-implement agent voice output comprises text corresponding to the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
19. The user device of claim 18 , wherein the instructions to cause the third party computer-implement agent voice output to be provided for presentation to the user at the user device comprise instructions to:
generate, based on the text corresponding to the third party computer-implement agent voice output and based on the third party computer-implemented agent data, the third party computer-implement agent voice output in the particular style of speech; and
cause the third party computer-implement agent voice output to be provided for presentation to the user at the user device.
20. A non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:
receiving a spoken utterance from a user of the user device, the spoken utterance being directed to a first party computer-implemented agent that is executed at the user device;
determining whether the spoken utterance includes a request to interact with a third party computer-implemented agent, the third party computer-implemented agent being accessible by the user device over one or more networks; and
in response to determining that the spoken utterance includes the request to interact with the third party computer-implemented agent:
causing the third party computer-implemented agent to engage in a dialog with the user, wherein causing the third party computer-implemented agent to engage in the dialog with the user comprises:
causing the third party computer-implemented agent to generate third party computer-implement agent voice output based on a particular style of speech that is specified by third party computer-implemented agent data associated with the third party computer-implemented agent; and
causing the third party computer-implement agent voice output to be provided for presentation to the user at the user device.