IP Library › Granted Patent US 10,521,420
Granted Patent B2
US 10,521,420 · App. 14/814,634 · Granted Dec 31, 2019

Analyzing search queries to determine a user affinity and filter search results

Inventors: Hernan A. Cunico (Holly Springs, NC); Asima Silva (Holden, MA)
Assignee: International Business Machines Corporation
G06F16/24522G06F16/248G06F16/9535
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,521,420
App. No.
14/814,634
Granted
Dec 31, 2019
Kind
B2
Abstract

According to embodiments of the present invention, machines, systems, computer-implemented methods and computer program products for retrieving information pertaining to an affinity of a user are provided. In some embodiments, a search query is received from a user. The search query is analyzed to determine a bias of the user. The social media activity of the user is evaluated to determine affinity indicators for the user. Prior searches and selection of search results by the user is evaluated to detect patterns of the user. An affinity of the user is determined based on the bias, affinity indicators, and patterns. Initial search results are generated that satisfy the search query, and the initial search results are filtered based on the determined affinity of the user to produce search results in accordance with the determined affinity of the user.

Claims (23)

1. A system for processing a search query comprising:

at least one processor configured to:

receive the search query from a user;

analyze query terms of the search query to determine a bias of the user based on content, and meaning and tone of any phrases and words included in the query terms;

store the query terms in a query history included in a database;

generate an affinity score of the user based on the determined bias, affinity indicators based on social media activity of the user included in the database, and patterns of the user based on prior searches of the user and search result selections by the user, the prior searches and the search result selections having been stored in the query history included in the database, the affinity score providing an indication of one of a positive affinity, a negative affinity and a neutral affinity, and a degree of scale of the affinity;

generate initial search results satisfying the search query;

generate an affinity score for each item in the initial search results; and

produce a final search result based on the generated affinity score for the each item in the initial search results, the final search result being in accordance with the affinity score of the user, wherein:

the final search result is customized for the user based on the bias of the user, the affinity indicators associated with the user, and the patterns of the user, and

as the system collects, analyzes, and stores information pertaining to user affinity, accuracy of a relevancy of the final search result increases.

2. The system of claim 1 , wherein the social media activity includes one or more from a group of visited web sites, comments, likes, channel subscriptions, others followed by the user on social media, and others following the user on social media.

3. A computer program product for processing a search query, the computer program product comprising a computer readable storage medium having computer readable program instructions embodied therewith, the computer readable program instructions executable by a processor to cause the processor to:

receive the search query from a user;

analyze query terms of the search query to determine a bias of the user based on content, and meaning and tone of any phrases and words included in the query terms;

store the query terms in a query history included in a database;

generate an affinity score of the user based on the determined bias, affinity indicators based on social media activity of the user included in the database, and patterns of the user based on prior searches of the user and search result selections by the user, the prior searches and the search result selections having been stored in the query history included in the database, the affinity score providing an indication of one of a positive affinity, a negative affinity and a neutral affinity, and a degree of scale of the affinity;

generate initial search results satisfying the search query;

generate an affinity score for each item in the initial search results; and

produce a final search result based on the generated affinity score for the each item in the initial search results, the final search result being in accordance with the affinity score of the user, wherein:

the final search result is customized for the user based on the bias of the user, the affinity indicators associated with the user, and the patterns of the user, and

as information pertaining to user affinity is collected, analyzed, and stored, accuracy of a relevancy of the final search result increases.

4. The computer program product of claim 3 , wherein the social media activity includes one or more from a group of visited web sites, comments, likes, channel subscriptions, others followed by the user on social media, and others following the user on social media.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 31, 2015
From: CUNICO, HERNAN A.; SILVA, ASIMA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 036224/0410 →
Continuity (1)
Related Publication 20170031978A1 · Feb 2, 2017
Cited By (1)
US 12,229,202