Interactive recommendations

• US 8,566,261 B2
• Filed: 12/17/2010
• Issued: 10/22/2013
• Est. Priority Date: 12/17/2010
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mital, Vijay, Thompson, R. Donald III, Povey, Robert, Katzenberger, Gary Shon
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US12/971,914
• Publication Number:
  US 20120158622A1
• Time in Patent Office: 1,040 Days
• Field of Search: 706/12
• US Class Current: 706/12
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

An interactive recommendation system generates one or more recommendations (e.g., recommended products, travel destinations, etc.) for a user based on a recommendation model. The recommendation model includes one or more criteria that are used to analyze a datastore of user characteristics (e.g., a user'"'"'s age, location, past online behavior, etc.) and generate one or more recommendations based thereon. The interactive recommendation system further presents a user interface that allows the user to interactively modify the criteria of the recommendation model and to apply the modified recommendation model to the datastore in order to generate one or more modified recommendations. In this manner, for example, the user can customize the recommendations he or she receives by interacting with the recommendation system to modify the recommendation model used to generate such recommendations.

Claims

1. A method comprising:

identifying one or more characteristics of a user to which a recommendation is to be provided;

selecting an initial recommendation model;

generating a recommendation for the user based on the initial recommendation model;

communicating the recommendation to the user;

presenting a modification interface to the user to allow the user to modify the initial recommendation model;

receiving from the user one or more criteria to modify the initial recommendation model;

modifying the one or more criteria to generate a modified recommendation model; and

generating a modified recommendation using the modified recommendation model.

2. The method of claim 1 further comprising adding a new criterion to the recommendation model to generate the modified recommendation model.

3. The method of claim 1 wherein the one or more criteria uses at least one or more user characteristics as a parameter.

4. The method of claim 3 wherein the one or more user characteristics includes past user behavior.

5. The method of claim 1 wherein generating the modified recommendation further comprises generating the modified recommendation based on mining social data using the modified recommendation model.

6. The method of claim 1 wherein generating the modified recommendation further comprises generating the modified recommendation based on mining online commercial data using the modified recommendation model.

7. The method of claim 1 wherein generating the modified recommendation further comprises generating the modified recommendation based on mining a resource description framework (RDF) datastore.

8. The method of claim 1 further comprising:

receiving from the user a recommendation model selection criterion;

generating a plurality of recommendation models that meet the recommendation model selection criterion;

receiving from the user a selection of one of the plurality of recommendation models; and

generating the modified recommendation by analyzing the datastore using the selected recommendation model.

9. The method of claim 1 further comprising:

generating a plurality of recommendation models, wherein the plurality of recommendation models is selected based on a ranking criteria;

receiving from the user a selection of one of the plurality of recommendation models; and

generating the modified recommendation by analyzing a datastore using a SPARQL query based on the selected recommendation model.

10. The method of claim 9, wherein the ranking criteria is based on rankings provided by a plurality of users.

11. One or more computer-readable storage media encoding computer-executable instructions for executing on a computer system a computer process, the computer process comprising:

presenting to a user a list of a plurality of recommendation models;

receiving a selection of one of the plurality of recommendation models from the user;

generating a recommendation for the user based on the selected recommendation model;

presenting a modification interface to the user to allow the user to modify the selected recommendation model;

receiving from the user one or more criteria to modify the selected recommendation model;

modifying the one or more criteria to generate a modified recommendation model; and

generating a modified recommendation using the modified recommendation model.

12. The one or more computer-readable storage media of claim 11 wherein the computer process further comprises:

adding a new criterion to the recommendation model to generate the modified recommendation model.

13. The one or more computer-readable storage media of claim 11 wherein generating the modified recommendation further comprises:

generating the modified recommendation based on mining at least one of (1) social data using the modified recommendation model and (2) commercial data using the modified recommendation model.

14. The one or more computer-readable storage media of claim 11 wherein the computer process further comprises receiving from the user a recommendation model selection criterion;

and generating the list of recommendation models to be presented to the user based on the received recommendation selection criterion.

15. The one or more computer-readable storage media of claim 11 wherein generating the modified recommendation comprises generating the modified recommendation by analyzing a resource description framework (RDF) datastore using a query generated from the selected recommendation model the computer process further comprises:

generating a plurality of recommendation models.

16. The one or more computer-readable storage media of claim 11 wherein the one or more criteria use at least one or more user characteristics as a parameter.

17. A system comprising:

an interactive recommendation manager generating a recommendation for a user based on a recommendation model, the recommendation model comprising one or more criteria, the recommendation model selected by the user;

a recommendation modification manager modifying the at least one of the one or more criteria based on an interactive modification input from the user to generate a modified recommendation model; and

a recommendation generation manager generating a modified recommendation using the modified recommendation model.

18. The system of claim 17 wherein the recommendation modification manager further comprising adding a new criterion to the recommendation model to generate the modified recommendation model.

19. The system of claim 17 wherein the one or more criteria uses past user behavior as a parameter.

20. The system of claim 17 wherein the recommendation generation manager generates the modified recommendation based on mining a resource description framework (RDF) datastore.