Conversational system user experience
Examples of the present disclosure describe systems and methods relating to conversational system user experience. In an example, a conversational system may use one or more sensors of a user device to affect the topic or direction of a conversation or to identify a new conversation topic. The conversational system may also receive input from a user, wherein a GUI may enable the user to specify or alter semantic information used during the conversation. The GUI may comprise one or more skeuomorphic elements designed to provide a familiar or intuitive way for the user to interact with the conversational system. The GUI may also be used to disambiguate messages or convey emotion or sentiment to the user. In another example, haptic or audio feedback may be provided alongside a message to convey emotion to the user during the conversation.
1. A system comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, causes the system to perform a set of operations, the set of operations comprising:
receiving, from a user device of a conversational system, a response attribute indication, wherein the response attribute indication comprises at least one response attribute to affect the operation of the conversational system;
generating, based on the response attribute indication, a vector for use during a conversational session;
receiving, as part of the conversational session, a message from the user device;
generating, from a set of potential responses associated with the at least one response attribute, a response to the message based on the vector; and
providing the response to the user device.
2. The system of claim 1 , wherein the response attribute indication comprises a value, and generating the vector comprises using the value as a weight for a variable of a response attribute associated with the response attribute indication.
3. The system of claim 1 , wherein generating the response comprises:
determining context information associated with the conversational session, wherein the context information comprises information associated with one or more sensors of the user device; and
generating, based on the context information, the response to the message.
4. The system of claim 1 , wherein generating the response comprises determining an emotion for the generated response, and wherein providing the generated response comprises providing the determined emotion to the user device.
5. The system of claim 1 , wherein the set of operations further comprises:
changing, based on a change to a first response attribute indicated by the response attribute indication, a second response attribute, wherein the second response attribute is related to the first response attribute.
6. The system of claim 1 , wherein the response attribute indication is received as a result of a user interaction with a skeuomorphic graphical user interface element displayed by the user device.
7. The system of claim 1 , wherein the response attribute indication comprises an indication relating to a characteristic of a message to be generated by the conversational system.
8. A computer-implemented method, comprising:
receiving, from a user device, a first message associated with a conversational session;
generating, based on a first response attribute for the conversational session, a first response to the first message;
providing the first response to the user device;
receiving a response attribute indication from the user device, wherein the response attribute indication comprises a second response attribute to affect the operation of the conversational system;
generating, based on the second response attribute, a second response to a second message associated with the conversational session; and
providing the second response to the user device.
9. The computer-implemented method of claim 8 , wherein generating a response to a message from the user device comprises:
determining context information associated with the conversational session, wherein the context information comprises information associated with one or more sensors of the user device; and
generating, based on the context information, the response to the message.
10. The computer-implemented method of claim 8 , wherein generating a response to a message from the user device comprises:
determining an emotion for the response by evaluating one or more response attributes associated with the conversational session;
and providing the emotion as part of the response.
11. The computer-implemented method of claim 8 , wherein the method further comprises causing the user device to provide feedback associated with at least one of the first response and the second response, and wherein the provided feedback comprises updating a skeuomorphic graphical user interface element displayed by the user device.
12. The computer-implemented method of claim 8 , wherein the method further comprises causing the user device to provide feedback associated with at least one of the first response and the second response, and wherein the provided feedback comprises haptic feedback associated with the determined emotion.
13. The computer-implemented method of claim 8 , wherein the method further comprises causing the user device to provide feedback associated with at least one of the first response and the second response, and wherein the provided feedback comprises audio feedback associated with the determined emotion.
14. A computer-implemented method for adjusting a response attribute of a conversational system, comprising:
receiving, from a user device during a conversational session, a response attribute indication, wherein the response attribute indication comprises at least one response attribute to affect the operation of the conversational system;
generating, based on the response attribute indication, a vector for use during the conversational session;
receiving, as part of the conversational session, a message from the user device;
generating, from a set of potential responses associated with the at least one response attribute, a response to the message based on the vector; and
providing the generated response to the user device.
15. The method of claim 14 , wherein the response attribute indication comprises a value, and generating the vector comprises using the value as a weight for a variable of a response attribute associated with the response attribute indication.
16. The method of claim 14 , wherein generating the response comprises:
determining context information associated with the conversational session, wherein the context information comprises information associated with one or more sensors of the user device; and
generating, based on the context information, the response to the message.
17. The method of claim 14 , wherein generating the response comprises determining an emotion for the generated response, and wherein providing the generated response comprises providing the determined emotion to the user device.
18. The method of claim 14 , further comprising:
changing, based on a change to a first response attribute indicated by the response attribute indication, a second response attribute, wherein the second response attribute is related to the first response attribute.
19. The method of claim 14 , wherein the response attribute indication is received as a result of a user interaction with a skeuomorphic graphical user interface element displayed by the user device.
20. The method of claim 14 , wherein the response attribute indication comprises an indication relating to a characteristic of a message to be generated by the conversational system.