Apparatus and method for socially intelligent virtual entity

• US 20060282493A1
• Filed: 06/14/2005
• Published: 12/14/2006
• Est. Priority Date: 06/14/2005
• Status: Active Grant

• Current Assignee: Omron Corporation, Stanford University
• Original Assignee: Omron Corporation and Stanford University
• Inventors: Nakajima, Hiroshi, Yamada, Ryota, Nass, Clifford, Nishide, Ritsuko, Iwamura, Kimihiko, Brave, Scott Brenner
• Granted Patent: US 7,944,448 B2
• Time in Patent Office: Days
• US Class Current: 709/200
• CPC Class Codes: G06Q 90/00 Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing

Abstract

An agent that receives an input event and outputs Emotion_Response messages based on personality trait indices and emotional state indices is disclosed. The agent has a social response generator that receives an input event, an output from an emotional state register and an output from a predefined personality trait register, and updates at least one of a current state of the emotional state register or a Social_Response message stored an event buffer. The agent has an emotion generator that outputs an Emotion_Response message based on at least one of the Social_Response message stored in the event buffer, one or more outputs of the predefined personality trait register, or one or more outputs of the emotional state register. The agent operates within an environment server that provides contextual environment that facilitates interaction amongst a group of agents, which receive input events from the contextual environment and outputs emotional response messages thereto.

Claims

1. An agent comprising:

an interpreter that receives an input event and outputs a social event based on the interpretation of the input event;

a social response generator that receives the social event, an output from an emotional state register and an output from a predefined personality trait register, and updates at least one of a current state of the emotional state register and a social response message stored an event buffer;

an emotion generator that outputs an emotion response message based on at least one of the social response message stored in the event buffer, one or more outputs of the predefined personality trait register, or one or more outputs of the emotional state register;

a manifester that receives the emotion response message output from the emotion generator and converts the emotion response message into a behavior message; and

a role database comprising social characteristics used by the interpreter to create social events and data used by the manifester to convert the emotion response message into the behavior message.

2. The agent according to claim 1, wherein the emotional state register comprises a current emotion index, wherein predefined thresholds associated with the current emotion index represent at least one of the emotions of neutrality, happiness, sadness or anger.

3. The agent according to claim 1, wherein the emotional state register comprises a current confidence index, wherein the confidence level of the agent is represented as numerical value.

4. The agent according to claim 1, wherein the emotional state register comprises at least one or more of an agent interrelationship index, wherein the agent interrelationship index is indicative of relationships with other agents that receive input events, other agents that output behavior messages or other agents that observe an input event or a behavior message.

5. The agent according to claim 1, wherein the social response generator updates a current state of the emotional state register based on at least the social event or the output from the predefined personality trait register.

6. The agent according to claim 1, wherein the event buffer comprises a first buffer and a second buffer.

7. The agent according to claim 6, wherein the social response generator generates an unexpected response index that is stored in the first buffer.

8. The agent according to claim 6, wherein the social response generator generates a sensory input index that is stored in the second buffer.

9. The agent according to claim 6, wherein the social response generator generates a danger response index that is stored in the second buffer.

10. The agent according to claim 6, wherein a social response message stored in the first buffer is maintained for a predetermined first period of time, and a social response message stored in the second buffer is maintained for a predetermined second period of time, wherein the first period of time is shorter than the second period of time.

11. The agent according to claim 10, wherein the social response generator clears the social response message stored in the second buffer.

12. The agent according to claim 1, wherein the predefined personality trait register comprises at least one of an intelligence index, a conscientiousness index, an extraversion index, an agreeableness index or an emotional stability index.

13. The agent according to claim 12, wherein the predefined personality trait register further comprises at least one or more of an agent social status index, wherein the agent social status index is indicative of the social status of other agents that receive input events, other agents that output behavior messages or other agents that observe an input event or a behavior message.

14. The agent according to claim 1, wherein the emotion generator outputs the emotion response message in emotion categories having differing validity time periods based on at least one of the social response message stored in the event buffer, one or more outputs from the predefined personality trait register, or one or more outputs from the emotional state register.

15. The agent according to claim 14, wherein the emotion categories comprise at least a lasting emotion category, a short-lived emotion category and a momentary emotion category.

16. The agent according to claim 15, wherein the validity time period of the momentary emotion category is determined by an unexpected response index generated by the social response generator.

17. The agent according to claim 15, wherein the validity time period of the short-lived emotion category is determined by a danger response index or a sensory input response index generated by the social response generator.

18. The agent according to claim 15, wherein the emotion response message generated for the lasting emotion category comprises one of a neutrality value, a happiness value, a sadness value or an anger value.

19. The agent according to claim 15, wherein the emotion response message generated for the short-lived emotion category comprises at least one of a disgust value or a fear value.

20. The agent according to claim 15, wherein the emotion response message generated for the momentary emotion category comprises at least a surprise value.

21. The agent according to claim 1, wherein the interpreter determines if an input event requires processing using information from at least one of the role database, the emotional state register and the predefined personality trait register, and, if the determination is positive, creates the social event based on data input from at least one of the role database, the emotional state register and the predefined personality trait register and outputs the social event to the social response generator.

22. The agent according to claim 1, wherein the interpreter determines if an input event requires processing using information from at least one of the role database, the emotional state register and the predefined personality trait register, and, if the determination is negative, converts the input event into a social event and outputs the social event to the social response generator.

23. The agent according to claim 1, wherein the social response generator signals the interpreter after the social response generator has processed the social event and updated at least one of the emotional state register and the event buffer.

24. The agent according to claim 23, wherein the interpreter triggers the manifester to cause the emotion generator to output the emotion response message.

25. The agent according to claim 24, wherein the manifester processes the emotion response message using data from the role database and outputs the behavior message.

26. An article of manufacture, which comprises a computer readable medium having stored therein a computer program for an agent, the computer program comprising:

a first code portion which, when executed on a computer, receives an input event and outputs a social event based on an interpretation of the input event;

a second code portion which, when executed on a computer, receives the social event, an output from an emotional state register and an output from a predefined personality trait register, and updates at least one of a current state of the emotional state register and a social response message stored an event buffer;

a third code portion which, when executed on a computer, outputs an emotion response message based on at least one of the social response message stored in the event buffer, one or more outputs of the predefined personality trait register, or one or more outputs of the emotional state register;

a fourth code portion which, when executed on a computer, receives the emotion response message output from the emotion generator and converts the emotion response message into a behavior message; and

a fifth code portion which, when executed on a computer, comprises social characteristics used by the first code portion to create social events and data used by the fourth code portion to convert the emotion response message into the behavior message.

27. A software agent embodied in computer executable code for execution on a computer, the software agent comprising:

an interpreter that receives an input event and outputs a social event based on the interpretation of the input event;

a social response generator that receives the social event, an output from an emotional state register and an output from a predefined personality trait register, and updates at least one of a current state of the emotional state register and a social response message stored an event buffer;

an emotion generator that outputs an emotion response message based on at least one of the social response message stored in the event buffer, one or more outputs of the predefined personality trait register, or one or more outputs of the emotional state register;

a manifester that receives the emotion response message output from the emotion generator and converts the emotion response message into a behavior message; and

a role database comprising social characteristics used by the interpreter to create social events and data used by the manifester to convert the emotion response message into the behavior message.

28. A virtual environment comprising:

a plurality of software agents according to claim 27;

and

a scenario environment that receives user inputs and outputs input events, wherein the scenario environment receives a behavior message from a software agent and converts the behavior message into graphical representations of the software agent'"'"'s emotional response to an input event.

29. The virtual environment according to claim 28, further comprising a scenario database, coupled to the scenario environment, for providing a cyberspace context that allows the plurality of agents to interact with each other.

30. The virtual environment according to claim 29, wherein the scenario database comprises a plurality of different cyberspace contexts.

31. The virtual environment according to claim 28, further comprising a scenario database, coupled to the scenario environment, for providing a cyberspace context that graphically depicts the interaction between the plurality of software agents based on behavior messages received from the plurality of software agents.

32. A method for generating emotional responses for a software agent, comprising:

receiving and interpreting an input event based on stored social characteristics and outputting a social event based on the interpretation of the input event;

receiving the social event, an output from an emotional state register and an output from a predefined personality trait register, and updating at least one of a current state of the emotional state register and a social response message stored an event buffer;

outputting an emotion response message based on at least one of the social response message stored in the event buffer, one or more outputs of the predefined personality trait register, or one or more outputs of the emotional state register;

receiving the emotion response message output from the emotion generator and converting the emotion response message into a behavior message based on stored social characteristics.

33. The method according to claim 32, wherein the emotional state register comprises a current emotion index, wherein predefined thresholds associated with the current emotion index represent at least one of the emotions of neutrality, happiness, sadness or anger.

34. The method according to claim 32, wherein the emotional state register comprises a current confidence index, wherein the confidence level of the software agent is represented as numerical value.

35. The method according to claim 32, wherein the emotional state register comprises at least one or more of an agent interrelationship index, wherein the agent interrelationship index is indicative of relationships with other software agents that receive input events, other software agents that output behavior messages or other software agents that observe an input event or a behavior message.

36. The method according to claim 32, wherein the updating of the current state of the emotional state register based on at least the social event or the output from the predefined personality trait register.

37. The method according to claim 32, wherein the event buffer comprises a first buffer and a second buffer.

38. The method according to claim 37, wherein the social response generator generates an unexpected response index that is stored in the first buffer.

39. The method according to claim 37, wherein the social response generator generates a sensory input index that is stored in the second buffer.

40. The method according to claim 37, wherein the social response generator generates a danger response index that is stored in the second buffer.

41. The method according to claim 32, wherein the predefined personality trait register comprises at least one of an intelligence index, a conscientiousness index, an extraversion index, an agreeableness index or an emotional stability index.

42. The method according to claim 41, wherein the predefined personality trait register further comprises at least one or more of an agent social status index, wherein the agent social status index is indicative of the social status of other software agents that receive input events, other software agents that output behavior messages or other software agents that observe an input event or a behavior message.

43. The method according to claim 32, wherein the emotion response message is output in emotion categories having differing validity time periods based on at least one of the social response message stored in the event buffer, one or more outputs from the predefined personality trait register, or one or more outputs from the emotional state register.

44. The method according to claim 42, wherein the emotion categories comprise at least a lasting emotion category, a short-lived emotion category and a momentary emotion category

45. The method according to claim 43, wherein the emotion response message generated for the lasting emotion category comprises one of a neutrality value, a happiness value, a sadness value or an anger value.

46. The method according to claim 43, wherein the emotion response message generated for the short-lived emotion category comprises at least one of a disgust value or a fear value.

47. The method according to claim 43, wherein the emotion response message generated for the momentary emotion category comprises at least a surprise value.

48. The method according to claim 32, further comprising a determination if an input event requires processing using information from at least one of the role database, the emotional state register and the predefined personality trait register, and, if the determination is positive, creating the social event based on data input from at least one of the role database, the emotional state register and the predefined personality trait register and outputing the social event to the social response generator.

49. The agent according to claim 32, further comprising a determination if an input event requires processing using information from at least one of the role database, the emotional state register and the predefined personality trait register, and, if the determination is negative, converting the input event into a social event and outputting the social event to the social response generator.

50. The agent according to claim 32, wherein the method further comprises generating the emotion response message after the social event has been processed, and outputting the behavior message based on social characteristics applied to the emotional response message.