Adaptive computer-based personalities

• US 8,566,263 B2
• Filed: 06/15/2008
• Issued: 10/22/2013
• Est. Priority Date: 11/28/2003
• Status: Active Grant

• Current Assignee: Gula Consulting Limited Liability Company (Intellectual Ventures LLC)
• Original Assignee: World Assets Consulting AG LLC (Intellectual Ventures LLC)
• Inventors: Flinn, Steven Dennis, Moneypenny, Naomi Felina
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Bharadwaj, Kalpana
• Application Number:
  US12/139,487
• Publication Number:
  US 20080249968A1
• Time in Patent Office: 1,955 Days
• Field of Search: 706/14
• US Class Current: 706/14
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/004 Artificial life, i.e. computing arrangements simulating life

Abstract

A method and system for adapting computer-based personalities, as manifested by textual or audio communications, is disclosed. The communications comprise one or more phrases that may be selected non-deterministically. The frequency distribution of the plurality of potential phrases is updated based on the behaviors of the communications recipients. Thus, the frequency of the selection of phrases included in communications, and hence the “personality,” of the computer-based system, is influenced by prior usage behaviors. The computer-based personality may also exhibit “self-awareness” by monitoring changes in phrase frequency distributions over time, as well as being capable of expressing awareness of, and inferences from, changes in the behavior patterns of users over time.

Claims

1. A method comprising:

generating a first communication from syntactically structured phrases for delivery to a user, wherein the first communication forms a first natural language sentence;

assessing a behavior of the user in response to the first communication;

modifying a phrase frequency distribution for the syntactically structured phrases based, at least in part, on the behavior of the user; and

generating a second communication from the syntactically structured phrases for delivery to the user based on the phrase frequency distribution, wherein the second communication forms a second natural language sentence.

2. The method of claim 1 wherein:

the first communication comprises a recommendation for an item of content;

said assessing a behavior of the user comprises monitoring access of the item of content by the user; and

said modifying a phrase frequency distribution comprises increasing a relative phrase frequency for at least some of the syntactically structured phrases in the first communication in response to the user accessing the item of content.

3. The method of claim 1 wherein at least some of the syntactically structured phrases comprise predetermined syntactically structured sentences derived independently of the behavior of the user.

4. The method of claim 1 wherein the second communication comprises an audio communication.

5. The method of claim 1 further comprising:

identifying demeanor categories for the syntactically structured phrases; and

generating the second communication based on the demeanor categories for the syntactically structured phrases.

6. A computer-based adaptive communication system comprising:

means to identify a syntactical structure for a first communication;

means to select from a plurality of phrases to form the first communication based on the syntactical structure;

means to assess a response of a user to the first communication;

means to modify a phrase frequency distribution of the plurality of phrases based, at least in part, on the response of the user; and

means to select from the plurality of phrases to form a second communication for delivery to the user based on the phrase frequency distribution.

7. The system of claim 6 wherein the first communication and the second communication each form natural language sentences.

8. The system of claim 6 wherein the first communication comprises a recommendation and the second communication comprises an explanation of why the recommendation was generated.

9. The system of claim 6 wherein the second communication comprises a written communication.

10. The system of claim 6 wherein the second communication comprises an audio communication.

11. The system of claim 6 further comprising

means to identify personality attributes for the plurality of phrases;

and

means to select from the plurality of phrases to form the second communication based on the personality attributes.

12. An apparatus, comprising:

logic circuitry configured to;

generate a vector comprising affinities between a user of a computer-based system and a plurality of computer-based objects wherein the affinities are based, at least in part, on a plurality of user behaviors associated with accessing the computer-based objects;

evaluate changes in the affinities of the vector;

select one or more syntactically structured phrases based, at least in part, on the changes in the affinities of the vector, wherein the one or more syntactically structured phrases form a natural language communication; and

present the natural language communication to the user.

13. The system of claim 12 wherein at least some of the computer-based objects comprise information associated with other users.

14. The system of claim 12 wherein at least some of the syntactically structured phrases express an awareness of the changes in the affinities.

15. The system of claim 12 wherein at least some of the syntactically structured phrases express inferences regarding the changes in the affinities of the vector.

16. The system of claim 12 wherein the natural language communication comprises an explanation corresponding to an adaptive recommendation.

17. The system of claim 12 wherein the logic circuitry is configured to probabilistically select the syntactically structured phrases based, at least in part, on the changes in the affinities of the vector over a period of time.

18. The system of claim 12 wherein the logic circuitry is configured:

assess additional user behaviors after the user receives the natural language communication; and

generate an additional natural language communication comprising additional syntactically structured phrases based, at least in part, on the additional user behaviors.

19. The system of claim 12 wherein the natural language communication comprises a written communication.

20. The system of claim 12 wherein the natural language communication comprises an audio communication.

21. An apparatus, comprising:

logic circuitry configured to;

form a first natural language communication from syntactically structured phrases;

present the first natural language communication to a user;

monitor data accessed by the user in response to the first natural language communication;

identify demeanor categories for the syntactically structured phrases; and

form a second natural language communication from the syntactically structured phrases based on the data accessed by the user and the demeanor categories.

22. The apparatus of claim 21 wherein the logic circuitry is further configured to:

identify a frequency distribution for the syntactically structured phrases based on the data accessed by the user; and

form the second natural language communication based on the frequency distribution.

23. The apparatus of claim 21 wherein the second natural language communication recommends additional data to the user and an explanation of why the additional data was recommended to the user.

24. The apparatus of claim 21 wherein the second natural language communication expresses an awareness of changes in the data accessed by the user.