IP Library › Granted Patent US 9,830,633
Granted Patent B2
US 9,830,633 · App. 14/816,930 · Granted Nov 28, 2017

Deriving dynamic consumer defined product attributes from input queries

Inventors: Madhu K. Chetuparambil (Raleigh, NC); George T. Jacob Sushil (Bangalore, IN); Kalapriya Kannan (Bangalore, IN)
Assignee: International Business Machines Corporation
G06Q30/0625G06F17/3053G06F17/30528G06F17/30864G06F17/30979G06Q30/0256G06Q30/0282
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 9,830,633
App. No.
14/816,930
Granted
Nov 28, 2017
Kind
B2
Abstract

Methods and systems of defining product attributes may involve receiving a search query and extracting a user expectation from the search query. In addition, an attribute may be defined for a product based on the user expectation. In one example, consumer generated content such as forum content, review content, blog content and social networking content, is used to define the attribute.

Claims (35)

1. A computer program product comprising:

a non-transitory computer readable storage medium; and

computer usable code stored on the non-transitory computer readable storage medium, where executed by a processor, the computer usable code causes a computer to:

receive a search query by a user that is to include a stated expectation with respect to a general product to be identified in the search query by a general product type;

parse the search query to identify an intensifier that is to indicate a quality of interest to the user for the product and to distinguish between the product and the stated expectation;

dynamically define an attribute for the product distinguished by the parse or a synonym thereof, wherein the defined attribute is to include the stated expectation distinguished by the parse or a synonym thereof;

filter consumer generated content using the defined attribute to obtain one or more specific products to be identified in the search results by a manufacturer of the one or more specific products;

rate the one or more specific products based on one or more opinions that are to mention the defined attribute to be expressed in the consumer generated content to identify in the search results closest matching specific products for the general product; and

present the search results to the user including the closest matching specific products identified by the manufacturer.

2. The computer program product of claim 1 , wherein executed by a processor, the computer usable code causes a computer to assign a rank specific to the defined attribute to the one or more specific products based on the one or more opinions expressed in the consumer generated content.

3. The computer program product of claim 1 , wherein the consumer generated content is to include at least one of forum content, review content, blog content and social networking content.

4. The computer program product of claim 1 , wherein executed by a processor, the computer usable code causes a computer to filter the consumer generated content based on contextual information to obtain the one or more specific products.

5. The computer program product of claim 4 , wherein executed by a processor, the computer usable code causes a computer to:

consult a sentiment rule to determine a relevance of the consumer generated content to the search query; and

disregard irrelevant consumer generated content based on the sentiment rule, wherein at least one irrelevant consumer generated content is to lack correct context information.

6. The computer program product of claim 1 , wherein executed by a processor, the computer usable code causes a computer to populate the defined attribute for another product in a same category as the product.

7. The computer program product of claim 1 , wherein executed by a processor, the computer usable code causes a computer rate the one or more products based on one or more opinions that are to mention a synonym of the defined attribute to be expressed in the consumer generated content.

8. A method comprising utilizing a processor to implement:

receiving a search query by a user that includes a stated expectation with respect to a general product to be identified in the search query by a general product type;

parsing the search query to identify an intensifier that is to indicate a quality of interest to the user for the product and to distinguish between the product and the stated expectation;

dynamically defining an attribute for the product distinguished by the parse or a synonym thereof, wherein the defined attribute is to include the stated expectation distinguished by the parse or a synonym thereof;

filtering consumer generated content using the defined attribute to obtain one or more specific products to be identified in the search results by a manufacturer of the one or more specific products;

rating the one or more specific products based on one or more opinions that mention the defined attribute expressed in the consumer generated content to identify in the search results closest matching specific products for the general product; and

presenting the search results to the user including the closest matching specific products identified by the manufacturer.

9. The method of claim 8 , further including assigning a rank specific to the defined attribute to the one or more specific products based on the one or more opinions expressed in the consumer generated content.

10. The method of claim 8 , wherein the consumer generated content includes at least one of forum content, review content, blog content and social networking content.

11. An apparatus comprising a processor to:

receive a search query by a user that is to include a stated expectation with respect to a general product to be identified in the search query by a general product type;

parse the search query to identify an intensifier that is to indicate a quality of interest to the user for the product and to distinguish between the product and the stated expectation;

dynamically define an attribute for the product distinguished by the parse or a synonym thereof, wherein the defined attribute is to include the stated expectation distinguished by the parse or a synonym thereof;

filter consumer generated content using the defined attribute to obtain one or more specific products to be identified in the search results by a manufacturer of the one or more specific products;

rate the one or more specific products based on one or more opinions that are to mention the defined attribute to be expressed in the consumer generated content to identify in the search results closest matching specific products for the general product; and

present the search results to the user including the closest matching specific products identified by the manufacturer.

12. The apparatus of claim 11 , wherein the processor is to assign a rank specific to the defined attribute to the one or more specific products based on the one or more opinions expressed in the consumer generated content.

13. The apparatus of claim 11 , wherein the consumer generated content is to include at least one of forum content, review content, blog content and social networking content.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 6, 2015
From: CHETUPARAMBIL, MADHU K.; JACOB SUSHIL, GEORGE T.; KANNAN, KALAPRIYA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 036268/0968 →
Continuity (3)
Continuation 13421143 · Mar 15, 2012
Continuation 13232543 · Sep 14, 2011
Related Publication 20150339752A1 · Nov 26, 2015