IP Library › Granted Patent US 12,282,516
Granted Patent B2
US 12,282,516 · App. 17/738,332 · Granted Apr 22, 2025

Faceted navigation

Inventors: Venkata Goutham Simhadri (Atlanta, GA); Janani Balaji (Cumming, GA); Jeyaprakash Singarayar (Smyrna, GA); Olga Stolpovskaia (Marietta, GA); Suhail Shaikh (Atlanta, GA)
Assignee: Home Depot Product Authority, LLC
G06F16/9532G06F16/9574G06F40/40
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 12,282,516
App. No.
17/738,332
Granted
Apr 22, 2025
Kind
B2
Abstract

A method includes extracting a set of candidate keywords from clickstream data and natural language processing of product text for a plurality of search queries. The set of candidate keywords are filtered based on the clickstream data. The set of candidate keywords as filtered are ranked based on the clickstream data. The set of candidate keywords as ranked are clustered to remove near duplicates. The set of candidate keywords as ranked for a respective search query is output.

Claims (51)

1. A method, comprising:

extracting a first set of candidate keywords from a query log,

wherein the first set of candidate keywords includes a keyword to product relevance and a query to product relevance;

extracting a second set of candidate keywords from product text,

wherein extracting the second set includes natural language processing of the product text to identify product defined keywords;

filtering the first set of candidate keywords and the second set of candidate keywords based on clickstream data associated with the query logs to define a third set of candidate keywords;

ranking the third set of candidate keywords as filtered based on the clickstream data to define a fourth set of candidate keywords;

clustering the fourth set of candidate keywords as ranked,

wherein the clustering removes near duplicates from the fourth set of candidate keywords; and

storing the fourth set of candidate keywords as ranked for respective search queries in the query logs.

2. The method of claim 1 , wherein filtering the first set of candidate keywords and the second set of candidate keywords further comprises removing unigrams and product attributes.

3. The method of claim 2 , wherein filtering the first set of candidate keywords and the second set of candidate keywords further comprises removing keywords that are present in less than a threshold number of products.

4. The method of claim 1 , wherein extracting the second set of candidate keywords includes natural language processing (NLP) including clustering nouns and adjectives into topics.

5. The method of claim 1 , further comprising, in response to a user search, retrieving one or more keywords from the fourth set of candidate keywords based on the user search to define a fifth set of candidate keywords.

6. The method of claim 5 , further comprising outputting the fifth set of candidate keywords for display on a display of a user device.

7. The method of claim 6 , wherein the fifth set of candidate keywords is limited to a threshold number of keywords.

8. The method of claim 7 , wherein the fifth set of candidate keywords is displayed for faceted navigation and are selectable to modify search results visible on the display of the user device.

9. A non-transitory, computer-readable memory storing instructions that, when executed by a processor, cause the processor to perform a method, comprising:

extracting a first set of candidate keywords from a query log,

wherein the first set of candidate keywords includes a keyword to product relevance and a query to product relevance;

extracting a second set of candidate keywords from product text,

wherein the extracting includes natural language processing of the product text to identify product defined keywords;

filtering the first set of candidate keywords and the second set of candidate keywords based on clickstream data associated with the query logs to define a third set of candidate keywords;

ranking the third set of candidate keywords as filtered based on the clickstream data to define a fourth set of candidate keywords;

clustering the fourth set of candidate keywords as ranked,

wherein the clustering removes near duplicates from the fourth set of candidate keywords; and

storing the fourth set of candidate keywords as ranked for respective search queries in the query logs.

10. The non-transitory, computer-readable memory of claim 9 , wherein filtering the first set of candidate keywords and the second set of candidate keywords further comprises removing unigrams and product attributes.

11. The non-transitory, computer-readable memory of claim 10 , wherein filtering the first set of candidate keywords and the second set of candidate keywords further comprises removing keywords that are present in less than a threshold number of products.

12. The non-transitory, computer-readable memory of claim 9 , wherein extracting the second set of candidate keywords includes natural language processing (NLP) including clustering nouns and adjectives into topics.

13. The non-transitory, computer-readable memory of claim 9 , further comprising, in response to a user search, retrieving one or more keywords from the fourth set of candidate keywords based on the user search to define a fifth set of candidate keywords.

14. The non-transitory, computer-readable memory of claim 13 , further comprising, outputting the fifth set of candidate keywords for display on a display of a user device.

15. The non-transitory, computer-readable memory of claim 14 , wherein the fifth set of candidate keywords is limited to a threshold number of keywords.

16. The non-transitory, computer-readable memory of claim 15 , wherein the fifth set of candidate keywords are displayed for faceted navigation and are selectable to modify search results visible on the display of the user device.

17. A method, comprising:

receiving a search query;

retrieving one or more keywords from a database based on the search query as received,

wherein the one or more keywords are determined by:

extracting a first set of candidate keywords from a query log,

wherein the first set of candidate keywords includes a keyword to product relevance and a query to product relevance;

extracting a second set of candidate keywords from product text,

wherein extracting the second set includes natural language processing of the product text to identify product defined keywords;

filtering the first set of candidate keywords and the second set of candidate keywords based on clickstream data associated with the query logs to define a third set of candidate keywords;

ranking the third set of candidate keywords as filtered based on the clickstream data to define a fourth set of candidate keywords;

clustering the fourth set of candidate keywords as ranked,

wherein the clustering removes near duplicates from the fourth set of candidate keywords; and

selecting the one or more keywords from the fourth set of candidate keywords;

outputting the one or more keywords as retrieved to a user device for display via a user interface.

18. The method of claim 17 , wherein outputting the one or more keywords comprises limiting a number of the keywords below a threshold.

19. The method of claim 17 , wherein the outputting causes display via the user interface in a faceted navigation menu.

20. The method of claim 19 , comprising filtering one or more search results based on a selection in the faceted navigation menu of the one or more keywords as retrieved.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 23, 2024
From: SIMHADRI, VENKATA GOUTHAM; BALAJI, JANANI; SINGARAYAR, JEYAPRAKASH; STOLPOVSKAIA, OLGA; SHAIKH, SUHAIL
To: HOME DEPOT PRODUCT AUTHORITY, LLC
Reel/Frame 067505/0751 →
Continuity (3)
Provisional Application 63193582 · May 26, 2021
Provisional Application 63185665 · May 7, 2021
Related Publication 20220358172A1 · Nov 10, 2022
References Cited (29)
US 8688673B2 · Sarkar · 2014 [cited by examiner]
US 9092802B1 · Akella · 2015 [cited by examiner]
US 10909075B2 · Sharp et al. · 2021 [cited by applicant]
US 20100114654A1 · Lukose · 2010 [cited by examiner]
US 20140081941A1 · Bai et al. · 2014 [cited by applicant]
US 20160300287A1 · Johnson · 2016 [cited by examiner]
US 20170017721A1 · Sauper · 2017 [cited by examiner]
US 20190179810A1 · Miller · 2019 [cited by examiner]
US 20210133271A1 · Williams · 2021 [cited by examiner]
US 20220284234A1 · Hoffman · 2022 [cited by examiner]
ISA/US, Int'l Search Report and Written Opinion issued in PCT/US22/28258, dated Sep. 12, 2022, 13 pgs. [cited by applicant]
Anchahua et al., “User experience maturity model for ecommerce websites,” in 2018 Congreso Internacional de Innovacion y Tendencias en Ingenieria (CONIITI), 2018, pp. 1-6. [cited by applicant]
Boudin, “pke: an open source python-based keyphrase extraction toolkit,” in Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations, Osaka, Japan, Dec. 2016, pp.… [cited by applicant]
Devlin et al., “BERT: pre-training of deep bidirectional transformers for language understanding,” CoRR, vol. abs/1810.04805, 2018. [cited by applicant]
Guo et al., “Debiasing grid-based product search in e-commerce,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery Data Mining, ser. KDD '20. New York, NY, USA: Association for Comput… [cited by applicant]
Karat et al., “Designing personalized user experiences for ecommerce: Theory, methods, and research,” in CHI '03 Extended Abstracts on Human Factors in Computing Systems, ser. CHI EA '03. New York, NY, USA: Association … [cited by applicant]
Koren et al., “Personalized interactive faceted search,” in Proceedings of the 17th International Conference on World Wide Web, ser. WWW '08. New York, NY, USA: Association for Computing Machinery, 2008, p. 477-486. [cited by applicant]
Liu et al., “Numerical facet range partition: Evaluation metric and methods,” in Proceedings of the 26th International Conference on World Wide Web Companion, ser. WWW '17 Companion. Republic and Canton of Geneva, CHE: … [cited by applicant]
Liu et al., “Unsupervised approaches for automatic keyword extraction using meeting transcripts,” in Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Associatio… [cited by applicant]
Mihalcea et al., “TextRank: Bringing order into text,” in Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. Barcelona, Spain: Association for Computational Linguistics, Jul. 2004, p… [cited by applicant]
Mikolov et al., “Efficient estimation of word representations in vector space,” 2013, 12 pp. [cited by applicant]
Qingyun et al., “Keyword extraction method for complex nodes based on textrank algorithm,” in 2020 International Conference on Computer Engineering and Application (ICCEA), 2020, pp. 359-363. [cited by applicant]
Sondhi et al., “A taxonomy of queries for e-commerce search,” in The 41st International ACM SIGIR Conference on Research Development in Information Retrieval, ser. SIGIR '18. New York, NY, USA: Association for Computing… [cited by applicant]
Vandic et al., “Dynamic facet ordering for faceted product search engines,” IEEE Trans. on Knowl. and Data Eng., vol. 29, No. 5, p. 1004-1016, May 2017. [cited by applicant]
Vandic et al., “Facet selection algorithms for web product search,” in Proceedings of the 22nd ACM International Conference on Information Knowledge Management, ser. CIKM '13. New York, NY, USA: Association for Computin… [cited by applicant]
Ying et al., “A graphbased approach of automatic keyphrase extraction,” Procedia Computer Science, vol. 107, pp. 248-255, 12 2017. [cited by applicant]
Zhang et al., “Keyphrase extraction using deep recurrent neural networks on Twitter,” in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas: Association for Computation… [cited by applicant]
Zhang et al., “Keywords extraction based on word2vec and textrank,” in Proceedings of the 2020 The 3rd International Conference on Big Data and Education, ser. ICBDE '20. New York, NY, USA: Association for Computing Mac… [cited by applicant]
Zhang et al., “Navigation configuration and placement influences the visual search efficiency and preference,” in Proceedings of the 26th International Conference on World Wide Web Companion, ser. WWW '17 Companion. Rep… [cited by applicant]