Dynamically augmenting query to search for content not previously known to the user

Patent metadata

Field	Value
Publication number	US-11176209-B2
Application number	US-201916533275-A
Country	US
Kind code	B2
Filing date	Aug 6, 2019
Priority date	Aug 6, 2019
Publication date	Nov 16, 2021
Grant date	Nov 16, 2021

Abstract

A computer-implemented method, system and computer program product for improving query searches. After receiving a query from a user to conduct a content search, the query is analyzed for its semantic meaning and a categorized group of query tags and content tags in the central repository that is most semantically similar in meaning to the meaning of the query is identified. Furthermore, the content tags and query tags in the user's repository are analyzed to determine the interests of the user. The query may then be augmented to include one or more other terms of interest from the identified categorized group of query tags and content tags in the central repository that match the determined interests of the user within a threshold degree of relatedness, where these other terms of interest correspond to the content tags and query tags of the identified categorized group based on their assigned weight.

First claim

The invention claimed is:

1. A computer-implemented method for improving query searches, the method comprising:
monitoring and identifying queries issued as well as content searched and published on a network by users of computing devices;
analyzing said content to generate content tags, wherein said content tags are keywords or terms used to describe said analyzed content;
analyzing said queries to generate query tags, wherein said query tags are keywords or terms used to describe said analyzed queries;
storing said query tags and content tags in a central repository;
receiving a query to conduct a content search;
analyzing said query for semantic meaning;
identifying a group of query tags and content tags in said central repository that is most semantically similar in meaning to said semantic meaning of said query;
analyzing content tags and query tags in a user repository to determine interests of a user, wherein said user repository stores query tags and content tags based on analyzing queries issued and content of inventories searched and published on said network by said user; and
augmenting said query to include additional one or more other terms of interest that match said determined interests of said user within a threshold degree of relatedness, wherein said one or more other terms of interest comprise query tags and/or content tags from said identified group of query tags and content tags based on their assigned weight.

2. The method as recited in claim 1 further comprising:
recommending said augmented query to said user to be used by said user to conduct said content search;
receiving a response from said user regarding said recommendation; and
adjusting a weight assigned to said one or more other terms of interest in response to said user response.

3. The method as recited in claim 1 further comprising:
identifying content searched and published on said network by said user; analyzing said content for semantic meaning;
identifying a group of query tags and content tags in said central repository that is most semantically similar in meaning to said semantic meaning of said content; tagging said analyzed content with a first term of interest that matches said determined interests of said user within said threshold degree of relatedness, wherein said first term of interest corresponds to a tag within said identified group of query tags and content tags in said central repository;
recommending to said user to tag said analyzed content with said first term of interest;
receiving a response from said user regarding said recommendation; and
adjusting a weight assigned to said first term of interest in response to said user response.

4. The method as recited in claim 1 , wherein said one or more other terms of interest comprise one or more content tags and query tags with a weighting that exceeds a threshold value.

5. The method as recited in claim 1 further comprising:
generating keys to identify storage locations of said analyzed content;
storing said generated keys in said central repository; and
obtaining content requested in said query using one or more keys associated with content tags in said identified group of query tags and content tags in said central repository.

6. The method as recited in claim 1 , wherein said queries comprise text queries, video queries and natural language queries.

7. The method as recited in claim 1 , wherein said content comprises images, photographs, videos and web content.

8. A computer program product for improving query searches, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code comprising programming instructions for:
monitoring and identifying queries issued as well as content searched and published on a network by users of computing devices;
analyzing said content to generate content tags, wherein said content tags are keywords or terms used to describe said analyzed content;
analyzing said queries to generate query tags, wherein said query tags are keywords or terms used to describe said analyzed queries;
storing said query tags and content tags in a central repository;
receiving a query to conduct a content search;
analyzing said query for semantic meaning;
identifying a group of query tags and content tags in said central repository that is most semantically similar in meaning to said semantic meaning of said query;
analyzing content tags and query tags in a user repository to determine interests of a user, wherein said user repository stores query tags and content tags based on analyzing queries issued and content of inventories searched and published on said network by said user; and
augmenting said query to include additional one or more other terms of interest that match said determined interests of said user within a threshold degree of relatedness, wherein said one or more other terms of interest comprise query tags and/or content tags from said identified group of query tags and content tags based on their assigned weight.

9. The computer program product as recited in claim 8 , wherein the program code further comprises the programming instructions for:
recommending said augmented query to said user to be used by said user to conduct said content search;
receiving a response from said user regarding said recommendation; and
adjusting a weight assigned to said one or more other terms of interest in response to said user response.

10. The computer program product as recited in claim 8 , wherein the program code further comprises the programming instructions for:
identifying content searched and published on said network by said user; analyzing said content for semantic meaning;
identifying a group of query tags and content tags in said central repository that is most semantically similar in meaning to said semantic meaning of said content;
tagging said analyzed content with a first term of interest that matches said determined interests of said user within said threshold degree of relatedness, wherein said first term of interest corresponds to a tag within said identified group of query tags and content tags in said central repository;
recommending to said user to tag said analyzed content with said first term of interest;
receiving a response from said user regarding said recommendation; and
adjusting a weight assigned to said first term of interest in response to said user response.

11. The computer program product as recited in claim 8 , wherein said one or more other terms of interest comprise one or more content tags and query tags with a weighting that exceeds a threshold value.

12. The computer program product as recited in claim 8 , wherein the program code further comprises the programming instructions for:
generating keys to identify storage locations of said analyzed content;
storing said generated keys in said central repository; and
obtaining content requested in said query using one or more keys associated with content tags in said identified group of query tags and content tags in said central repository.

13. The computer program product as recited in claim 8 , wherein said queries comprise text queries, video queries and natural language queries.

14. The computer program product as recited in claim 8 , wherein said content comprises images, photographs, videos and web content.

15. A system, comprising:
a memory for storing a computer program for improving query searches; and
a processor connected to said memory, wherein said processor is configured to execute the program instructions of the computer prog

Assignees

• IBM

Inventors

• Davis Michael C
• Milligan Robert S
• Greenlee Gordan G
• Lascola Jason
• Molloy Christopher L
• Waite Steven A

Classifications

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F16/9532 Primary

  Query formulation · CPC title