AUGMENTING SEARCH QUERIES BASED ON PERSONALIZED ASSOCIATION PATTERNS

• US 20160283589A1
• Filed: 03/24/2015
• Published: 09/29/2016
• Est. Priority Date: 03/24/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bostick, James E., Ganci, John M. Jr., Rakshit, Sarbajit K., Trim, Craig M.
• Granted Patent: US 11,442,977 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method of augmenting a user'"'"'s search query based on analysis of content contributions of the user. One or more processors gather content contributions made to a media source by a user. Topic entities are identified from content contributed by the user. Semantic and syntactic analysis are performed on the content, and attributes of topic entities are determined based on the analysis. The topic entities are grouped based on similar and/or related attributes of the topic entities. The one or more processors determine relationships between the topic entities based on the grouping and the semantic analysis of the content contributed by the user of the media source. An ontology model is generated, based on the topic entities and their interrelationships, and responsive to determining the user initiates a search query, the one or more processors present additional topic entities as selection choices for augmenting the search query.

Claims

1. A method for augmenting a search query of a user, based on analysis of content contributions of the user, the method comprising:

one or more computer processors gathering content contributions made to a media source by a user of the media source;

the one or more computer processors identifying topic entities from content contributed by the user of the media source;

the one or more computer processors performing semantic analysis and syntactic analysis on the content contributed by the user of the media source;

the one or more computer processors determining, based on the semantic analysis and the syntactic analysis, attributes of the identified topic entities;

the one or more computer processors grouping the identified topic entities based on one or both of similar and related attributes of the identified topic entities;

the one or more computer processors determining relationships between the identified topic entities, based on one or more groups of the identified topic entities and the semantic analysis of the content contributed by the user of the media source;

the one or more computer processors generating an ontology model, based on the identified topic entities, and the relationships between the identified topic entities; and

the one or more computer processors responsive to determining that a search query has been initiated by the user, presenting to the user, additional topic entities as selection choices for augmenting the search query, based on the ontology model.

2. The method of claim 1, wherein the content contributions include one, or a combination of:

posted text, posted comments, likes, tags, chat content, users followed, topics followed, posted image metadata, and transcripts of posted video.

3. The method of claim 1, wherein the media source is one or more network based social media sites.

4. The method of claim 1, wherein the ontology model is represented graphically having topic entities as nodes of a graph and relationships as edges of the graph.

5. The method of claim 1, wherein the ontology model includes a set of interrelated triples that include a topic entity as a subject, a second topic entity as an object, and a relationship between the subject and object as a predicate.

6. The method of claim 1, wherein the ontology model is updated in response to analysis of an additional content contribution by the user.

7. The method of claim 1, wherein a relationship between topic nodes is positively reinforced by use of augmented search query topics from the ontology model, and the relationship between topic nodes is negatively reinforced by a lack of use of the augmented search query topics from the ontology model.

8. The method of claim 1, wherein presenting to the user, additional topic entities as selection choices for augmenting the search query, includes presenting indicators of magnitude of the relationships between topic entities.

9. A computer program product for augmenting a search query of a user, based on analysis of content contributions of the user, the computer program product comprising:

a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by one or more processors, the program instructions comprising;

program instructions to gather content contributions made to a media source by a user of a the media source;

program instructions to identify topic entities from content contributed by the user of the media source;

program instructions to perform semantic analysis and syntactic analysis on the content contributed by the user of the media source;

program instructions to determine, based on the semantic analysis and the syntactic analysis, attributes of the identified topic entities;

program instructions to group the identified topic entities based on one or both of similar and related attributes of the identified topic entities;

program instructions to determine relationships between the identified topic entities, based on one or more groups of the identified topic entities and the semantic analysis of the content contributed by the user of the media source;

program instructions to generate an ontology model, based on the identified topic entities, and the relationships between the identified topic entities; and

responsive to determining that a search query has been initiated by the user, program instructions to present to the user, additional topic entities as selection choices for augmenting the search query, based on the ontology model.

10. The computer program product of claim 9, wherein the content contributions includes one or more of:

posted text, posted comments, likes, tags, chat content, users followed, topics followed, posted images and transcripts of posted video.

11. The computer program product of claim 9, wherein the media source is one or more network based social media sites.

12. The computer program product of claim 9, wherein the ontology model is represented graphically having topic entities as nodes of a graph and relationships as edges of the graph.

13. The computer program product of claim 9, wherein the ontology model includes a set of interrelated triples that include a topic entity as a subject, a second topic entity as an object, and a relationship between the subject and object as a predicate.

14. The computer program product of claim 9, wherein a relationship between topic nodes is positively reinforced by use of augmented search query topics from the ontology model, and the relationship between topic nodes is negatively reinforced by a lack of use of the augmented search query topics from the ontology model.

15. The computer program product of claim 9, wherein presenting to the user, additional topic entities as selection choices for augmenting the search query, includes presenting indicators of magnitude of the relationships between topic entities.

16. A computer system for augmenting a search query of a user, based on analysis of content contributions of the user, the computer system comprising:

one or more computer processors;

one or more computer readable storage media; and

program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to gather content contributions made to a media source by a user of a the media source;

program instructions to identify topic entities from content contributed by the user of the media source;

program instructions to perform semantic analysis and syntactic analysis on the content contributed by the user of the media source;

program instructions to determine, based on the semantic analysis and the syntactic analysis, attributes of the identified topic entities;

program instructions to group the identified topic entities based on one or both of similar and related attributes of the identified topic entities;

program instructions to determine relationships between the identified topic entities, based on one or more groups of the identified topic entities and the semantic analysis of the content contributed by the user of the media source;

program instructions to generate an ontology model, based on the identified topic entities, and the relationships between the identified topic entities; and

responsive to determining that a search query has been initiated by the user, program instructions to present to the user, additional topic entities as selection choices for augmenting the search query, based on the ontology model.

17. The computer system of claim 16, wherein the ontology model is represented graphically having topic entities as nodes of a graph and relationships as edges of the graph.

18. The computer system of claim 16, wherein the ontology model includes a set of interrelated triples that include a topic entity as a subject, a second topic entity as an object, and a relationship between the subject and object as a predicate.

19. The computer system of claim 16, wherein a relationship between topic nodes is positively reinforced by use of augmented search query topics from the ontology model, and the relationship between topic nodes is negatively reinforced by a lack of use of the augmented search query topics from the ontology model.

20. The computer system of claim 16, wherein presenting to the user, additional topic entities as selection choices for augmenting the search query, includes presenting indicators of magnitude of the relationships between topic entities.