Ontology based recommendation systems and methods

• US 9,015,185 B2
• Filed: 12/05/2013
• Issued: 04/21/2015
• Est. Priority Date: 05/25/2007
• Status: Active Grant

• Current Assignee: PRJ Holding Company LLC
• Original Assignee: Piksel Incorporated
• Inventors: Kanigsberg, Issar Amit, Veidlinger, Daniel Marc, Mozersky, Myer Joshua
• Primary Examiner(s): Fleurantin, Jean B
• Application Number:
  US14/098,433
• Publication Number:
  US 20140180868A1
• Time in Patent Office: 502 Days
• Field of Search: 707/706, 707/707, 707/765, 707/769, 707/770, 707/776, 707/796
• US Class Current: 707/765
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A search technology generates recommendations with minimal user data and participation, and provides better interpretation of user data, such as popularity, thus obtaining breadth and quality in recommendations. It is sensitive to the semantic content of natural language terms and lets users briefly describe the intended recipient (i.e., interests, eccentricities, previously successful gifts). Based on that input, the recommendation software system and method determines the meaning of the entered terms and creatively discover connections to gift recommendations from the vast array of possibilities. The user may then make a selection from these recommendations. The search/recommendation engine allows the user to find gifts through connections that are not limited to previously available information on the Internet. Thus, interests can be connected to buying behavior by relating terms to respective items.

Claims

1. A computer-implemented method of recommending products and services, the method comprising:

one or more processors;

receiving an initial set of keywords from a profile associated with a user;

identifying at least one concept among the initial set of keywords, the at least one concept including at least a subset of the initial set of keywords;

comparing the at least one concept against a concept-specific ontology (CSO) database, the CSO database storing a plurality of concepts and respective property values indicating descriptive attributes of the plurality on concepts;

determining a set of related keywords for the initial set of keywords, the set of related keywords identified in the CSO database based on the property values; and

determining an item, which is at least one service, for recommendation to the user based on an association between the item and an expanded keyword set including the initial set of keywords and the set of related keywords,

wherein determining the item for recommendation includes selecting the item from a plurality of items based on a comparison between the expanded keyword set and a set of item keywords.

2. The method of claim 1, wherein determining the item for recommendation includes comparing the expanded keyword set against the set of item keywords, the item keywords including at least one keyword associated with the item.

3. The method of claim 2, wherein the set of item keywords includes initial item keywords and related item keywords, the related item keywords being determined from the CSO database based on the initial item keywords and the property values.

4. The method of claim 2, wherein the set of item keywords includes initial item keywords and related item keywords, and further comprising:

comparing the initial item keywords against the CSO database; and

determining the related item keywords, the related item keywords identified in the CSO database based on the property values and the initial item keywords.

5. The method of claim 1, wherein determining the item for recommendation is based further on an association between the item and a search string entered by the user.

6. The method of claim 1, wherein each of the set of related keywords is associated with one or more related concepts stored at the CSO database.

7. The method of claim 6, wherein determining the set of related keywords includes selecting the one or more related concepts based on an occurrence of property values common with the at least one concept associated with the initial set of keywords.

8. The method of claim 7, wherein each of the property values is assigned a relative weight, and wherein selecting the one or more related concepts is based on the relative weight.

9. The method of claim 1, wherein the CSO database further includes a plurality of classes, each of the plurality of concepts being associated with at least one of the plurality of classes.

10. The method of claim 9, wherein the respective property values are defined by the at least one of the plurality of classes.

11. The method of claim 9, wherein comparing the at least one concept against the CSO database includes excluding concepts unassociated with the at least one of the plurality of classes.

12. The method of claim 1, wherein the item includes video content.

13. A computer system for recommending products and services, the system comprising:

a concept-specific ontology (CSO) database configured to store a plurality of concepts and respective property values indicating descriptive attributes of the plurality on concepts; and

a recommendation engine implemented by one or more processors executing computer readable program instructions, the recommendation engine configured to;

identify at least one concept among an initial set of keywords and compare the at least one concept against the CSO database, the initial set of keywords being associated with a profile associated with a user, the at least one concept including at least a subset of the initial set of keywords;

determine a set of related keywords for the initial set of keywords, the set of related keywords identified in the CSO database based on the property values; and

determine an item, wherein the item is at least a service, for recommendation to the user based on an association between the item and an expanded keyword set including the initial set of keywords and the set of related keywords,

wherein determining the item for recommendation includes selecting the item from a plurality of items based on a comparison between the expanded keyword set and a set of item keywords.

14. The system of claim 13, wherein the recommendation engine is further configured to compare the expanded keyword set against the set of item keywords, the item keywords including at least one keyword associated with the item.

15. The system of claim 14, wherein the set of item keywords includes initial item keywords and related item keywords, the related item keywords being determined from the CSO database based on the initial item keywords and the property values.

16. The system of claim 14, wherein the set of item keywords includes initial item keywords and related item keywords, and wherein the recommendation engine is further configured to:

compare the initial item keywords against the CSO database; and

determine the related item keywords, the related item keywords identified in the CSO database based on the property values and the initial item keywords.

17. The system of claim 13, wherein the recommendation engine is further configured to determine the item for recommendation based on an association between the item and a search string entered by the user.

18. The system of claim 13, wherein each of the set of related keywords is associated with one or more related concepts stored at the CSO database.

19. The system of claim 18, wherein the recommendation engine is further configured to select the one or more related concepts based on an occurrence of property values common with the at least one concept associated with the initial set of keywords.

20. The system of claim 19, wherein each of the property values is assigned a relative weight, and wherein the recommendation engine is further configured to select the one or more related concepts is based on the relative weight.

21. The system of claim 13, wherein the CSO database further includes a plurality of classes, each of the plurality of concepts being associated with at least one of the plurality of classes.

22. The system of claim 21, wherein the respective property values are defined by the at least one of the plurality of classes.

23. The system of claim 21, wherein the recommendation engine is further configured to exclude concepts unassociated with the at least one of the plurality of classes.

24. The system of claim 13, wherein the item includes video content.

25. A computer program product stored on a non-transitory computer readable medium, the computer program product including computer readable instructions configured to recommend products and services by:

receiving an initial set of keywords from a profile associated with a user;

identifying at least one concept associated with the initial set of keywords;

comparing the at least one concept against a concept-specific ontology (CSO) database, the CSO database storing a plurality of concepts and respective property values indicating descriptive attributes of the plurality on concepts;

determining a set of related keywords for the initial set of keywords, the set of related keywords identified in the database based on the property values; and

determining an item, wherein the item is at least a service, for recommendation to the user based on an association between the item and an expanded keyword set including the initial set of keywords and the set of related keywords,

wherein determining the item for recommendation includes selecting the item from a plurality of items based on a comparison between the expanded keyword set and a set of item keywords.