Intelligent social agent architecture

• US 20030187660A1
• Filed: 06/28/2002
• Published: 10/02/2003
• Est. Priority Date: 02/26/2002
• Status: Abandoned Application

• Current Assignee: SAP AG (SAP SE)
• Original Assignee: SAP AG (SAP SE)
• Inventors: Gong, Li
• Application Number:
  US10/184,113
• Publication Number:
  US 20030187660A1
• Time in Patent Office: Days
• US Class Current: 704/277
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

An intelligent social agent is an animated computer interface agent with social intelligence that has been developed for a given application or type of applications and a particular user population. The social intelligence of the agent comes from the ability of the agent to be appealing, affective, adaptive, and appropriate when interacting with the user.

Claims

1. An apparatus for implementing an intelligent social agent, the apparatus comprising:

an information extractor configured to;

access a user profile associated with the user,

receive an input associated with a user, and

extract context information from the received input;

an adaptation engine configured to;

receive the context information and the user profile from the information extractor, and process the context information and the user profile to produce an adaptive output; and

an output generator configured to;

receive the adaptive output from the adaptation engine, and represent the adaptive output in the intelligent social agent.

2. The apparatus of claim 1 wherein the input is physiological data associated with the user and the information extractor is configured to receive the physiological data.

3. The apparatus of claim 1 wherein the input is application program information associated with the user and the information extractor is configured to receive application program information associated with the user.

4. The apparatus of claim 1 wherein the information extractor is further configured to extract information about an affective state of the user from the received input.

5. The apparatus of claim 4 wherein the information extractor is configured to extract information about an affective state of the user based on physiological information associated with the user.

6. The apparatus of claim 4 wherein the information extractor configured to extract information about an affective state of the user is configured to extract information about an affective state of the user based on vocal analysis information associated with the user by extracting verbal content and analyzing speech characteristics of the user.

7. The apparatus of claim 4 wherein the information extractor configured to extract information about an affective state of the user is configured to extract information about an affective state of the user based on verbal information from the received input.

8. The apparatus of claim 1 wherein the information extractor configured to extract context information is configured to extract a geographical position of the user by using a global positioning system.

9. The apparatus of claim 8 wherein the information extractor configured to extract context information is configured to extract information based on the geographical position of the user.

10. The apparatus of claim 1 wherein the information extractor configured to extract context information is configured to extract information about the application content associated with the user.

11. The apparatus of claim 1 wherein the information extractor configured to extract context information is configured to extract information about a linguistic style of the user from the received input.

12. The apparatus of claim 1 wherein:

the output generator is a verbal generator;

the adaptation engine configured to produce an adaptive output is configured to produce a verbal expression; and

the verbal generator produces the verbal expression in the intelligent social agent.

13. The apparatus of claim 1 wherein:

the generator is an affect generator;

the adaptation engine configured to produce an adaptive output is configured to produce a facial expression; and

the affect generator represents the facial expression in the intelligent social agent.

14. The apparatus of claim 1 wherein the output generator is a multi-modal output generator that represents the adaptive output in the intelligent social agent using at least one of a first mode and a second mode.

15. The apparatus of claim 14 wherein:

the first mode is a verbal mode;

the second mode is an affect mode;

the adaptive engine configured to produce an adaptive output is configured to;

produce a facial expression, and

produce an verbal expression; and

the multi-modal output generator represents the facial expression and the verbal expression in the intelligent social agent.

16. The apparatus of claim 1 wherein:

the adaptation engine is further configured to produce an emotional expression to be represented by the intelligent social agent; and

the output generator is configured to represent the emotional expression in the intelligent social agent.

17. A mobile device for implementing an intelligent social agent that interacts with a user, the mobile device comprising:

a processor connected to a memory and one or more input/output devices;

a social intelligence engine configured to interact with the processor, the social intelligence engine including;

an information extractor configured to;

access a user profile associated with the user,

receive an input associated with a user, and

extract context information from the received input;

an adaptation engine configured to;

receive the context information and the user profile from the information extractor, and process the context information and the user profile to produce an adaptive output; and

an output generator configured to;

receive the adaptive output from the adaptation engine, and represent the adaptive output in the intelligent social agent.

18. The mobile device of claim 17 wherein the input is physiological data associated with the user and the information extractor is configured to receive the physiological data.

19. The mobile device of claim 17 wherein the input is application program information associated with the user and the information extractor is configured to receive the application program information.

20. The mobile device of claim 17 wherein the information extractor is further configured to extract information about an affective state of the user from the received input.

21. The mobile device of claim 20 wherein the information extractor is configured to extract information about an affective state of the user based on physiological information associated with the user.

22. The mobile device of claim 20 wherein the information extractor configured to extract information about an affective state of the user is configured to extract information about an affective state of the user based on vocal analysis information associated with the user by extracting verbal content and analyzing speech characteristics of the user from the received input.

23. The mobile device of claim 20 wherein the information extractor configured to extract information about an affective state of the user is configured to extract information about an affective state of the user based on verbal information from the received input.

24. The mobile device of claim 17 wherein the information extractor configured to extract context information is configured to extract a geographical position of the user by using a global positioning system.

25. The mobile device of claim 24 wherein the information extractor configured to extract context information is configured to extract information based on the geographical position of the user.

26. The mobile device of claim 17 wherein information extractor configured to extract context information is configured to extract information about the application content associated with the user.

27. The mobile device of claim 17 wherein information extractor configured to extract context information is configured to extract information about a linguistic style of the user from the received input.

28. The mobile device of claim 17 wherein:

the output generator is a verbal generator;

the adaptation engine configured to produce an adaptive output is configured to produce a verbal expression; and

the verbal generator produces the verbal expression in the intelligent social agent.

29. The mobile device of claim 17 wherein:

the generator is an affect generator;

the adaptation engine configured to produce an adaptive output is configured to produce a facial expression; and

the affect generator represents the facial expression in the intelligent social agent.

30. The mobile device of claim 17 wherein the output generator is a multi-modal output generator that represents the adaptive output in the intelligent social agent using at least one of a first mode and a second mode.

31. The mobile device of claim 30 wherein:

the first mode is a verbal mode;

the second mode is an affect mode;

the adaptive engine configured to produce an adaptive output is configured to;

produce a facial expression, and

produce an verbal expression; and

the multi-modal output generator represents the facial expression and the verbal expression in the intelligent social agent.

32. The mobile device of claim 17 wherein:

the adaptation engine is further configured to produce an emotional expression to be represented by the intelligent social agent; and

the output generator is configured to represent the emotional expression in the intelligent social agent.