Forming chatbot output based on user state
Techniques are described herein for chatbots to achieve greater social grace by tracking users' states and providing corresponding dialog. In various implementations, input may be received from a user at a client device operating a chatbot, e.g., during a first session between the user and the chatbot. The input may be semantically processed to determine a state expressed by the user to the chatbot. An indication of the state expressed by the user may be stored in memory for future use by the chatbot. It may then be determined, e.g., by the chatbot based on various signals, that a second session between the user and the chatbot is underway. In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user.
1. A method implemented using one or more processors and comprising:
detecting, at a first client device that executes a first portion of a virtual assistant, by one or more input devices of the first client device, one or more physical actions of a user, wherein the one or more physical actions are detected during a first session between the user and the virtual assistant;
analyzing, by the virtual assistant, one or more attributes of the one or more physical actions of the user to determine a state of the user during the first session;
storing, by the virtual assistant in memory hosted on a cloud infrastructure that is accessible to at least the first client device, an indication of the state of the user determined during the first session for future use by the virtual assistant;
determining, by the virtual assistant based on one or more signals, that a second session between the user and the virtual assistant that is distinct from the first session is underway;
forming, by a second portion of the virtual assistant that executes on the cloud infrastructure, based on the stored indication of the state of the user, a natural language output, wherein the natural language output is associated with the state of the user determined during the first session; and
outputting, by the virtual assistant via one or more output devices of the first client device or a second client device, as part of the second session, the natural language output.
2. The method of claim 1 , wherein the state of the user comprises a physical condition of the user.
3. The method of claim 1 , wherein the state of the user is a negative sentiment, and the natural language output comprises an inquiry of whether the user has improved.
4. The method of claim 1 , wherein the one or more physical actions of the user comprise a facial expression.
5. The method of claim 1 , wherein the one or more physical actions of the user comprise a gesture made by the user.
6. The method of claim 1 , wherein the one or more signals further include detection of one or more intervening interactions between the user and the first client device other than dialog between the user and the virtual assistant.
7. The method of claim 1 , wherein the one or more signals further include passage of a predetermined time interval since a last interaction between the user and the virtual assistant.
8. The method of claim 1 , wherein the one or more signals further include detection of a change in a context of the user since a last interaction between the user and the virtual assistant.
9. A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to perform the following operations:
detecting, at a first client device that executes a first portion of a virtual assistant, by one or more input devices of the first client device, one or more physical actions of a user, wherein the one or more physical actions are detected during a first session between the user and the virtual assistant;
analyzing, by the virtual assistant, one or more attributes of the one or more physical actions of the user to determine a state of the user during the first session;
storing, by the virtual assistant in memory hosted on a cloud infrastructure that is accessible to at least the first client device, an indication of the state of the user determined during the first session for future use by the virtual assistant;
determining, by the virtual assistant based on one or more signals, that a second session between the user and the virtual assistant that is distinct from the first session is underway;
forming, by a second portion of the virtual assistant that executes on the cloud infrastructure, based on the stored indication of the state of the user, a natural language output, wherein the natural language output is associated with the state of the user determined during the first session; and
outputting, by the virtual assistant via one or more output devices of the first client device or a second client device, as part of the second session, the natural language output.
10. The system of claim 9 , wherein the state of the user comprises a physical condition of the user.
11. The system of claim 9 , wherein the state of the user is a negative sentiment, and the natural language output comprises an inquiry of whether the user has improved.
12. The system of claim 9 , wherein the one or more physical actions of the user comprise a facial expression.
13. The system of claim 9 , wherein the one or more physical actions of the user comprise a gesture made by the user.
14. The system of claim 9 , wherein the one or more signals further include detection of one or more intervening interactions between the user and the first client device other than dialog between the user and the virtual assistant.
15. The system of claim 9 , wherein the one or more signals further include passage of a predetermined time interval since a last interaction between the user and the virtual assistant.
16. The system of claim 9 , wherein the one or more signals further include detection of a change in a context of the user since a last interaction between the user and the virtual assistant.
17. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:
detecting, at a first client device that executes a first portion of a virtual assistant, by one or more input devices of the first client device, one or more physical actions of a user, wherein the one or more physical actions are detected during a first session between the user and the virtual assistant;
analyzing, by the virtual assistant, one or more attributes of the one or more physical actions of the user to determine a state of the user during the first session;
storing, by the virtual assistant in memory hosted on a cloud infrastructure that is accessible to at least the first client device, an indication of the state of the user determined during the first session for future use by the virtual assistant;
determining, by the virtual assistant based on one or more signals, that a second session between the user and the virtual assistant that is distinct from the first session is underway;
forming, by a second portion of the virtual assistant that executes on the cloud infrastructure, based on the stored indication of the state of the user, a natural language output, wherein the natural language output is associated with the state of the user determined during the first session; and
outputting, by the virtual assistant via one or more output devices of the first client device or a second client device, as part of the second session, the natural language output.
18. The at least one non-transitory computer-readable medium of claim 17 , wherein the state of the user comprises a physical condition of the user.
19. The at least one non-transitory computer-readable medium of claim 17 , wherein the one or more physical actions of the user comprise a facial expression.
20. The at least one non-transitory computer-readable medium of claim 17 , wherein the one or more physical actions of the user comprise a gesture made by the user.