IP Library Granted Patent US 11,392,631
Granted Patent B2
US 11,392,631 · App. 17/103,109 · Granted Jul 19, 2022

System and method for programmatic generation of attribute descriptors

Inventors: Gaston L'Huillier (San Francisco, CA); Jonathan Esterhazy (San Francisco, CA); Dor Levi (San Francisco, CA); Amit Koren (Chicago, IL); Daniel Langdon (Las Condes, CL); Bhupesh Bansal (Sunnyvale, CA); Feras Karablieh (Issaquah, WA); Hernan Enrique Arroyo Garcia (Mountain View, CA); Srinivasa Raghavan Vedanarayanan (Sunnyvale, CA); Shawn Ryan Jeffrey (Burlingame, CA); Francisco Jose Larrain (Palo Alto, CA)
Assignee: Groupon, Inc.
G06F16/35G06F40/232G06F40/40
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 11,392,631
App. No.
17/103,109
Granted
Jul 19, 2022
Kind
B2
Abstract

Embodiments provide a computer-executable method, computer system and non-transitory computer-readable medium for programmatically processing text information to generate attribute descriptors contained therein. The method includes programmatically accessing, via a network device, a textual unit, the textual unit associated with a commercial entity or a commercial object. The method also includes executing a text processing engine to programmatically generate an attribute descriptor from the textual unit. The method further includes storing, on a non-transitory computer-readable storage device, the attribute descriptor in association with identification of the commercial entity or the commercial object.

Claims (55)

1. A system, comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to:

perform text processing to determine a set of pre-processed attribute descriptors associated with textual information;

perform an attribute descriptor cleaning process with respect to the set of pre-processed attribute descriptors to generate a set of attribute descriptors, wherein the attribute descriptor cleaning process is associated with spell checking that is trained based on context and a set of terms related to a commercial entity or a commercial object associated with the textual information;

compare each attribute descriptor of the set of attribute descriptors to an attribute descriptor record to identify a common attribute descriptor sub-set shared by the set of attribute descriptors and the attribute descriptor record;

generate a validated list of attribute descriptors by removing the common attribute descriptor sub-set from the set of attribute descriptors; and

transmit one or more computer-executable instructions to a computing device, the one or more computer-executable instructions programmed to cause the computing device to visually display one or more attribute descriptors from the validated set of attribute descriptors in association with the commercial entity or the commercial object.

2. The system of claim 1 , wherein the attribute descriptor cleaning process is further trained based on a set of previously determined misspelled attribute descriptors associated with the commercial entity or the commercial object.

3. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:

retrieve the textual information from a textual unit associated with the commercial entity or the commercial object.

4. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:

perform natural language processing to determine the set of pre-processed attribute descriptors associated with the textual information.

5. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:

generate at least a portion of the attribute descriptor record via a crowd-sourcing technique.

6. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:

determine one or more blacklisted attribute descriptors associated with the attribute descriptor record; and

generate the validated list of attribute descriptors based on the one or more blacklisted attribute descriptors.

7. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:

store, on a non-transitory computer-readable storage device, the validated list of attribute descriptors in association with identification of the commercial entity or the commercial object.

8. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:

analyze purchase data for a consumer identifier associated with the computing device to generate an attribute descriptor of interest for the consumer identifier;

match the attribute descriptor of interest to an attribute descriptor from the validated list of attribute descriptors; and

based on the match, transmit the one or more computer-executable instructions to the computing device to cause the computing device to visually display the attribute descriptor from the validated set of attribute descriptors in association with the consumer identifier.

9. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:

analyze profile data for a consumer identifier associated with the computing device to generate an attribute descriptor of interest for the consumer identifier;

match the attribute descriptor of interest to an attribute descriptor from the validated list of attribute descriptors; and

based on the match, transmit the one or more computer-executable instructions to the computing device to cause the computing device to visually display the attribute descriptor from the validated set of attribute descriptors in association with the consumer identifier.

10. A computer-implemented method, comprising:

performing, by a device comprising a processor, text processing to determine a set of pre-processed attribute descriptors associated with textual information;

performing, by the device, an attribute descriptor cleaning process with respect to the set of pre-processed attribute descriptors to generate a set of attribute descriptors, wherein the attribute descriptor cleaning process is associated with spell checking that is trained based on context and a set of terms related to a commercial entity or a commercial object associated with the textual information;

comparing, by the device, each attribute descriptor of the set of attribute descriptors to an attribute descriptor record to identify a common attribute descriptor sub-set shared by the set of attribute descriptors and the attribute descriptor record;

generating, by the device, a validated list of attribute descriptors by removing the common attribute descriptor sub-set from the set of attribute descriptors; and

transmitting, by the device, one or more computer-executable instructions to a computing device, the one or more computer-executable instructions programmed to cause the computing device to visually display one or more attribute descriptors from the validated set of attribute descriptors in association with the commercial entity or the commercial object.

11. The computer-implemented method of claim 10 , wherein the performing the attribute descriptor cleaning comprises training the attribute descriptor cleaning process based on a set of previously determined misspelled attribute descriptors associated with the commercial entity or the commercial object.

12. The computer-implemented method of claim 10 , further comprising:

generating, by the device, at least a portion of the attribute descriptor record via a crowd-sourcing technique.

13. The computer-implemented method of claim 10 , further comprising:

determining, by the device, one or more blacklisted attribute descriptors associated with the attribute descriptor record, wherein the generating the validated list of attribute descriptors comprises generating the validated list of attribute descriptors based on the one or more blacklisted attribute descriptors.

14. The computer-implemented method of claim 10 , further comprising:

storing, by the device and on a non-transitory computer-readable storage device, the validated list of attribute descriptors in association with identification of the commercial entity or the commercial object.

15. The computer-implemented method of claim 10 , further comprising:

analyzing, by the device, purchase data or profile data for a consumer identifier associated with the computing device to generate an attribute descriptor of interest for the consumer identifier; and

matching, by the device, the attribute descriptor of interest to an attribute descriptor from the validated list of attribute descriptors, wherein the transmitting comprises transmitting the one or more computer-executable instructions to the computing device to cause the computing device to visually display the attribute descriptor from the validated set of attribute descriptors in association with the consumer identifier.

16. A computer program product, stored on a computer readable medium, comprising instructions that when executed by one or more computers cause the one or more computers to:

perform text processing to determine a set of pre-processed attribute descriptors associated with textual information;

perform an attribute descriptor cleaning process with respect to the set of pre-processed attribute descriptors to generate a set of attribute descriptors, wherein the attribute descriptor cleaning process is associated with spell checking that is trained based on context and a set of terms related to a commercial entity or a commercial object associated with the textual information;

compare each attribute descriptor of the set of attribute descriptors to an attribute descriptor record to identify a common attribute descriptor sub-set shared by the set of attribute descriptors and the attribute descriptor record;

generate a validated list of attribute descriptors by removing the common attribute descriptor sub-set from the set of attribute descriptors; and

transmit one or more computer-executable instructions to a computing device, the one or more computer-executable instructions programmed to cause the computing device to visually display one or more attribute descriptors from the validated set of attribute descriptors in association with the commercial entity or the commercial object.

17. The computer program product of claim 16 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:

determine one or more blacklisted attribute descriptors associated with the attribute descriptor record; and

generate the validated list of attribute descriptors based on the one or more blacklisted attribute descriptors.

18. The computer program product of claim 16 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:

analyze purchase data or profile data for a consumer identifier associated with the computing device to generate an attribute descriptor of interest for the consumer identifier;

match the attribute descriptor of interest to an attribute descriptor from the validated list of attribute descriptors; and

based on the match, transmit the one or more computer-executable instructions to the computing device to cause the computing device to visually display the attribute descriptor from the validated set of attribute descriptors in association with the consumer identifier.

Assignments (3)
CORRECTIVE ASSIGNMENT TO CORRECT THE LLLL PREVIOUSLY RECORDED AT REEL: 1212 FRAME: 0001. ASSIGNOR(S) HEREBY CONFIRMS THE NEW ASSIGNMENT. Recorded Jul 18, 2024
From: GROUPON, INC.
To: BYTEDANCE INC.
Reel/Frame 069174/0637 →
CONFIRMATORY ASSIGNMENT Recorded May 18, 2023
From: JEFFERY, SHAWN RYAN
To: GROUPON, INC.
Reel/Frame 064104/0069 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 24, 2020
From: L'HUILLIER, GASTON; ESTERHAZY, JONATHAN; LEVI, DOR; KOREN, AMIT; LANGDON, DANIEL; BANSAL, BHUPESH; ARROYO GARCIA, HERNAN ENRIQUE; VEDANARAYANAN, SRINIVASA RAGHAVAN; LARRAIN, FRANCISCO JOSE; JEFFREY, SHAWN RYAN; KARABLIEH, FERAS
To: GROUPON, INC.
Reel/Frame 054513/0218 →
Continuity (4)
Continuation 14811521 · Jul 28, 2015
Provisional Application 62033090 · Aug 4, 2014
Provisional Application 62030549 · Jul 29, 2014
Related Publication 20210182327A1 · Jun 17, 2021