Portable inferred interest and expertise profiles

• US 8,650,149 B2
• Filed: 10/07/2011
• Issued: 02/11/2014
• Est. Priority Date: 03/29/2011
• Status: Active Grant

• Current Assignee: Manyworlds Incorporated
• Original Assignee: Manyworlds Incorporated
• Inventors: Flinn, Steven Dennis, Moneypenny, Naomi Felina
• Primary Examiner(s): CHEN, ALAN S
• Application Number:
  US13/268,035
• Publication Number:
  US 20120254096A1
• Time in Patent Office: 858 Days
• Field of Search: None
• US Class Current: 706/52
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06K 7/10366 the interrogation device being adapted for miscellaneous applications
• CPC Class Codes: G06K 7/10475 arrangements to facilitate interaction with further interrogation devices, e.g. such that at least two interrogation devices may function and cooperate in a network of such devices
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/02 using fuzzy logic computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A computer-implemented portable inferred interests and expertise profiling system generates an inferred user profile embodied as an inference vector, which is generated based on inferences from behavioral information and in accordance with standardized tags that are associated with topical areas in a first system. The inferences may be of, for example, interests or levels of expertise. Recommendations are then generated based on the inference vector and a different set of topics. Multiple inference vectors may be combined into a composite inference vector, which can serve as a basis for recommendations generated with respect to different sets of topics than those that informed the generation of the composite inference vector.

Claims

1. A computer-implemented method, comprising:

contributing a plurality of non-tagging usage behaviors associated with a first system to an inferencing function executed on a processor-based computing device, wherein the inferencing function generates a vector of inferred values based, at least in part, on an inference from the plurality of usage behaviors, wherein each of the inferred values corresponds to one of a plurality of standardized tags, wherein each of the plurality of standardized tags corresponds to one or more topics of a first plurality of topics that are within the first system; and

receiving a recommendation of an object associated with a second system from a computer-implemented recommender, wherein the recommender generates the recommendation based, at least in part, on the vector of inferred values and in accordance with the plurality of standardized tags, wherein each of the standardized tags are associated with one or more topics of a second plurality of topics that are within the second system.

2. The method of claim 1, further comprising:

contributing the plurality of non-tagging usage behaviors associated with the first system to the inferencing function, wherein the inferencing function generates the vector of inferred values based, at least in part, on the inference from the plurality of usage behaviors, wherein each of the inferred values corresponds to one of the plurality of standardized tags, wherein the standardized tags are automatically generated.

3. The method of claim 1, further comprising:

receiving the recommendation, wherein the vector of inferred values is based on inferences of interests.

4. The method of claim 1, further comprising:

receiving the recommendation, wherein the vector of inferred values is based on inferences of expertise.

5. The method of claim 1, further comprising:

receiving the recommendation, wherein the recommended object comprises a representation of a person, wherein the person is a user of the second system.

6. The method of claim 1, further comprising:

receiving the recommendation, wherein the recommendation is generated in accordance with a specified topical neighborhood.

7. The method of claim 1, further comprising:

receiving an explanation as to why the object was recommended.

8. A computer-implemented system, comprising:

an inferencing function executed on a processor-based computing device, wherein the inferencing function generates a vector of inferred values associated with a user based, at least in part, on an inference from a plurality of usage behaviors associated with a plurality of usage behavior categories and that are associated with the user'"'"'s use of a first system, wherein each of the inferred values corresponds to one of a plurality of standardized tags, wherein each tag of the plurality of standardized tags corresponds to one or more topics of a first plurality of topics that are within the first system; and

a computer-implemented recommender, wherein the recommender generates a recommendation for delivery to the user based, at least in part, on the vector of inferred values and in accordance with the plurality of standardized tags, wherein each tag of the plurality of standardized tags are associated with one or more topics of a second plurality of topics that are within a second system.

9. The system of claim 8, further comprising:

a standardized tag-generating function that automatically generates the plurality of standardized tags.

10. The system of claim 9, further comprising:

the standardized tag-generating function, wherein the standardized tags are generated based, at least in part, on a plurality of behaviors associated with a plurality of users.

11. The system of claim 9, further comprising:

the standardized tag-generating function, wherein the standardized tags are generated based, at least in part, on the comparison of the contents of a plurality of objects.

12. The system of claim 8, further comprising:

the inferencing function, wherein the inferencing function generates the vector of inferred values, and wherein the inferred values are based on inferences of interests.

13. The system of claim 8, further comprising:

the inferencing function, wherein the inferencing function generates the vector of inferred values, and wherein the inferred values are based on inferences of expertise.

14. The system of claim 8, further comprising:

the computer-implemented recommender, wherein the recommender generates the recommendation, wherein the recommendation comprises a representation of a user of the second system.

15. The system of claim 8, further comprising:

the computer-implemented recommender, wherein the recommender generates the recommendation that is in accordance with a specified topical neighborhood.

16. The system of claim 8, further comprising:

a computer-implemented explanatory function that generates an explanation as to why the recommendation was generated for delivery to the user, wherein the explanation comprises a reference to expertise.

17. An article comprising a non-transitory computer-readable medium storing instructions for enabling a processor-based system to:

generate a vector of inferred values associated with a user based, at least in part, on an inference from a plurality of non-tagging usage behaviors associated with the user'"'"'s use of a first system, wherein each of the inferred values corresponds to one of a plurality of standardized tags, wherein each tag of the plurality of standardized tags corresponds to one or more topics within the first system; and

generate a recommendation for delivery to the user based, at least in part, on the vector of inferred values and in accordance with the plurality of standardized tags, wherein each tag of the plurality of standardized tags are associated with one or more topics of a second plurality of topics that are within a second system.

18. The article of claim 17, further comprising the non-transitory computer-readable medium storing instructions for enabling the processor-based system to:

generate the vector of inferred values, wherein the inferred values are based on inferences of interests.

19. The article of claim 17, further comprising the non-transitory computer-readable medium storing instructions for enabling the processor-based system to:

generate the vector of inferred values, wherein the inferred values are based on inferences of expertise.

20. The article of claim 17, further comprising the non-transitory computer-readable medium storing instructions for enabling the processor-based system to:

generate an explanation for delivery to the user as to why the recommendation was delivered to the user.