Integrated search and adaptive discovery system and method

• US 8,843,433 B2
• Filed: 07/23/2012
• Issued: 09/23/2014
• 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): Holmes, Michael B
• Application Number:
  US13/555,941
• Publication Number:
  US 20120290518A1
• Time in Patent Office: 792 Days
• Field of Search: 706/52
• US Class Current: 706/52
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads

Abstract

An integrated search and adaptive discovery system and method integrates contents-based indexing and behavioral-based indexing of collections of computer-implemented objects to generate contextualized and/or personalized recommendations. The degree to which contextualization and/or personalization criteria are applied in generating recommendations can be tuned by the recommendation recipient. Personalization functions are applied that are informed by inferred interests and/or expertise, and personalization vectors can be transformed into a format executable by a search engine. Explanations may be provided to recommendation recipients as to why they received recommendations.

Claims

1. A computer-implemented method, comprising:

identifying a computer-implemented content object to serve as a contextual reference;

accessing a first plurality of values, wherein each of the first plurality of values is based on an inference of a first user'"'"'s interest level with respect to a topic, wherein each of the interest level inferences is derived from a plurality of behaviors;

accessing a second plurality of values, wherein each of the second plurality of values is based on an inferred degree of relevance to a topic of one or more phrases that are contained in the content object; and

generating a recommendation comprising one or more objects for delivery to the first user, wherein the recommendation is generated by a recommendation function executed on a processor-based device in accordance with the first plurality of values and the second plurality of values.

2. The method of claim 1, further comprising:

identifying the content object, wherein the content object is identified basis a selection of an object by the first user from a plurality of objects delivered in response to a search request invoked by the first user.

3. The method of claim 1, further comprising:

generating the recommendation, wherein the recommendation is generated in accordance with an inference of an expertise level of the first user, wherein the expertise level is derived from a plurality of behaviors.

4. The method of claim 1, further comprising:

generating the recommendation, wherein the recommendation is generated in accordance with an expertise tuning level set by the first user.

5. The method of claim 1, further comprising:

generating the recommendation, wherein the recommendation is generated in accordance with a contextual neighborhood associated with the content object, wherein the contextual neighborhood is generated by a behavioral indexing process.

6. The method of claim 1, further comprising:

generating the recommendation, wherein the recommendation is generated in accordance with a contextual affinity tuning level set by the first user.

7. The method of claim 1, further comprising:

generating an explanation for delivery to the first user as to why the recommendation was delivered to the first user, wherein the explanation comprises one or more phrases that associate a theme derived from the second plurality of values with a topic inferred to be of interest to the first user.

8. A computer-implemented system comprising one or more processors configured to:

identify a computer-implemented content object to serve as a contextual reference;

access a first plurality of values, wherein each of the first plurality of values is based on an inference of a first user'"'"'s interest level with respect to a topic, wherein each of the interest level inferences is derived from a plurality of behaviors;

access a second plurality of values, wherein each of the second plurality of values is based on an inferred degree of relevance to a topic of one or more phrases that are contained in the content object; and

generate a recommendation comprising one or more objects for delivery to the first user, wherein the recommendation is generated in accordance with the first plurality of values and the second plurality of values.

9. The system of claim 8, further comprising a processor configured to:

identify the content object, wherein the content object is identified basis the first user'"'"'s selection of an object from a plurality of objects delivered in response to a search request invoked by the first user.

10. The system of claim 8, further comprising a processor configured to:

generate the recommendation, wherein the recommendation is generated in accordance with an inference of an expertise level of the first user, wherein the expertise level is derived from a plurality of behaviors.

11. The system of claim 8, further comprising a processor configured to:

generate the recommendation, wherein the recommendation is generated in accordance with an expertise tuning level set by the first user.

12. The system of claim 8, further comprising a processor configured to:

generate the recommendation, wherein the recommendation is generated in accordance with a contextual neighborhood associated with the content object, wherein the contextual neighborhood is generated by a behavioral indexing process.

13. The system of claim 8, further comprising a processor configured to:

generate the recommendation, wherein the recommendation is generated in accordance with a contextual affinity tuning level set by the first user.

14. The system of claim 8, further comprising a processor configured to:

generate an explanation for delivery to the first user as to why the recommendation was delivered to the first user, wherein the explanation comprises one or more phrases that associate a theme derived from the second plurality of values with a topic inferred to be of interest to the first user.

15. The system of claim 8, further comprising a processor configured to:

generate an explanation for delivery to the first user as to why the recommendation was delivered to the first user, wherein the explanation comprises one or more phrases that reference a recommendation tuning control level set by the first user.

16. The system of claim 8, further comprising a processor configured to:

generate the recommendation, wherein the recommendation is generated in accordance with a serendipity tuning level set by the first user.

17. A computer-implemented system comprising one or more processors configured to:

access a plurality of usage behaviors associated with a first user of a first computer-implemented system that has been behaviorally indexed, wherein the behavioral indexing generates a plurality of topics;

generate a plurality of affinities between the first user of the first computer-implemented system and the plurality of topics, wherein each of the plurality of affinities is indicative of an inferred interest level of the first user for a topic of the plurality of topics, wherein each of the inferred interest levels is derived from one or more behaviors of the plurality of usage behaviors;

transform the plurality of affinities and topics into an object contents vector executable by a search function;

execute a search request from the first user, wherein the search request is executed in accordance with the object contents vector, and wherein the search request is executed against a plurality of objects residing in a second computer-implemented system; and

deliver the results of the search request to the first user.

18. The system of claim 17, further comprising a processor configured to:

transform the plurality of affinities, wherein the plurality of affinities are further in accordance with an inferred expertise level of the first user derived from one or more behaviors of the plurality of usage behaviors.

19. The system of claim 17, further comprising a processor configured to:

provide a control that selectively executes the search request against objects that have not been behaviorally indexed.

20. The system of claim 17, further comprising a processor configured to:

generate an explanation for delivery to the first user as to why a recommended object resulting from the search request was delivered to the first user, wherein the explanation comprises one or more phrases that associate a theme derived from the contents of the recommended object with a topic inferred to be of interest to the first user.