IP Library › Granted Patent US 12,730,788
Granted Patent B2
US 12,730,788 · App. 18/629,674 · Granted Sep 8, 2026

Systems and methods for interleaving search results

Inventors: Onur Gungor (Sunnyvale, CA); Tri Cao (San Bruno, CA); Vineet Abhishek (Mountain View, CA)
Assignee: Walmart Apollo, LLC
G06F16/217G06F11/3409G06F16/24578G06F16/9538
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 12,730,788
App. No.
18/629,674
Granted
Sep 8, 2026
Kind
B2
Abstract

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations: generating, using at least two different search algorithms, combined search results based on a search query, each search result of the combined search results having a respective rank based on at least one of the at least two different searching algorithms; determining a set of search results from the combined search results, wherein each result within the set of search results was respectively interacted with by at least one user; and determining a traffic impact for each result rank in the set of search results. Other embodiments are described herein.

Claims (68)

1 . A system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising:

generating, using at least two different search algorithms, combined search results based on a search query from an electronic device of a user, each search result of the combined search results having a respective rank based on at least one of the at least two different search algorithms;

storing interactions by at least one user with the search results of the combined search results, wherein an interaction with a respective search result of the combined search results indicates which of the at least two different search algorithms returned the respective search result;

determining a set of search results from the combined search results based on the stored interactions, wherein each result within the set of search results was respectively interacted with by the at least one user;

determining a traffic impact for at least one of the at least two different search algorithms based on the set of search results, wherein the traffic impact is based on:

a number of search results, in the set of search results, that were interacted with by the at least one user and were returned by both a first search algorithm and a second search algorithm of the at least two different search algorithms,

a number of search results, in the set of search results, that were interacted with by the at least one user and were returned by the first search algorithm but not the second search algorithm, and

a number of search results, in the set of search results, that were interacted with by the at least one user and were returned by the second search algorithm but not the first algorithm; and

implementing the first search algorithm or the second search algorithm on a website based on the determined traffic impact.

2 . The system of claim 1 , wherein generating the combined search results comprises:

interleaving search results of the second search algorithm and search results of the first search algorithm.

3 . The system of claim 1 , wherein generating the combined search results comprises:

including a copy of a search result returned by both the first search algorithm and the second search algorithm.

4 . The system of claim 1 , wherein the respective interaction with each result within the set of search results comprises at least one of:

a click through of the result;

an item view of the result;

an add to cart of the result; or

a purchase of the result.

5 . The system of claim 1 , wherein the operations further comprise:

hashing a user ID of the user; and

determining that the user is eligible for a search algorithm test based upon the user ID, as hashed.

6 . The system of claim 1 , wherein each search result within the set of search results has an identical rank in both search results of the first search algorithm and search results of the second search algorithm.

7 . The system of claim 1 , wherein the operations further comprise:

generating a report comprising the traffic impact, wherein generating the report is based at least in part on the respective interaction with each result within the set of search results, and is further based at least in part on at least one of:

determining a latency of the first search algorithm;

determining a latency of the second search algorithm;

adding the latency of the first search algorithm and the latency of the second search algorithm to the report;

determining a recall size of the first search algorithm;

determining a recall size of the second search algorithm; or

adding the recall size of the first search algorithm and the recall size of the second search algorithm to the report.

8 . The system of claim 7 , wherein generating the report further comprises:

plotting a graph comprising:

an axis for a lift of the second search algorithm over the first search algorithm for each respective rank in the combined search results; and

an axis for the traffic impact for each result rank in the set of search results; and

adding the graph to the report.

9 . A method being implemented via execution of computing instructions configured to run at one or more processors and configured to be stored at one or more non-transitory computer-readable media, the method comprising:

generating, using at least two different search algorithms, combined search results based on a search query from an electronic device of a user, each search result of the combined search results having a respective rank based on at least one of the at least two different search algorithms;

storing interactions by at least one user with the search results of the combined search results, wherein an interaction with a respective search result of the combined search results indicates which of the at least two different search algorithms returned the respective search result;

determining a set of search results from the combined search results based on the stored interactions, wherein each result within the set of search results was respectively interacted with by the at least one user;

determining a traffic impact for at least one of the at least two different search algorithms based on the set of search results, wherein the traffic impact is based on:

a number of search results, in the set of search results, that were interacted with by the at least one user and were returned by both a first search algorithm and a second search algorithm of the at least two different search algorithms,

a number of search results, in the set of search results, that were interacted with by the at least one user and were returned by the first search algorithm but not the second search algorithm, and

a number of search results, in the set of search results, that were interacted with by the at least one user and were returned by the second search algorithm but not the first search algorithm; and

implementing the first search algorithm or the second search algorithm on a website based on the determined traffic impact.

10 . The method of claim 9 , wherein generating the combined search results comprises:

interleaving search results of the second search algorithm and search results of the first search algorithm.

11 . The method of claim 9 , wherein generating the combined search results comprises:

including a copy of a search result returned by both the first search algorithm and the second search algorithm.

12 . The method of claim 9 , wherein the respective interaction with each result within the set of search results comprises at least one of:

a click through of the result;

an item view of the result;

an add to cart of the result; or

a purchase of the result.

13 . The method of claim 9 further comprising:

hashing a user ID of the user; and

determining that the user is eligible for a search algorithm test based upon the user ID, as hashed.

14 . The method of claim 9 , wherein each search result within the set of search results has an identical rank in both search results of the first search algorithm and search results of the second search algorithm.

15 . The method of claim 9 further comprising:

generating a report comprising the traffic impact, wherein generating the report is based at least in part on the respective interaction with each result within the set of search results, and is further based at least in part on at least one of:

determining a latency of the first search algorithm;

determining a latency of the second search algorithm;

adding the latency of the first search algorithm and the latency of the second search algorithm to the report;

determining a recall size of the first search algorithm;

determining a recall size of the second search algorithm; or

adding the recall size of the first search algorithm and the recall size of the second search algorithm to the report.

16 . The method of claim 15 , wherein generating the report further comprises: plotting a graph comprising: an axis for a lift of the second search algorithm over the first search algorithm for each respective rank in the combined search results; and an axis for the traffic impact for each result rank in the set of search results; and adding the graph to the report.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 27, 2024
From: GUNGOR, ONUR; CAO, TRI; ABHISHEK, VINEET
To: WALMART APOLLO, LLC
Reel/Frame 067246/0213 →
Continuity (3)
Continuation 17700030 · Mar 21, 2022
Continuation 16460429 · Jul 2, 2019
Related Publication 20240256507A1 · Aug 1, 2024
References Cited (108)
US 6728704B2 · Mao · 2004 [cited by examiner]
US 6832218B1 · Emens · 2004 [cited by examiner]
US 7424469B2 · Ratnaparkhi · 2008 [cited by applicant]
US 7873633B2 · Smolyanskiy · 2011 [cited by examiner]
US 8086600B2 · Bailey · 2011 [cited by examiner]
US 8090703B1 · Agarwal et al. · 2012 [cited by applicant]
US 8209330B1 · Covell et al. · 2012 [cited by applicant]
US 8266141B2 · Radlinski · 2012 [cited by examiner]
US 8359309B1 · Provine et al. · 2013 [cited by applicant]
US 8392394B1 · Kumar · 2013 [cited by examiner]
US 8433512B1 · Lopatenko et al. · 2013 [cited by applicant]
US 8484202B2 · Radlinski et al. · 2013 [cited by applicant]
US 8498974B1 · Kim · 2013 [cited by examiner]
US 8661029B1 · Kim et al. · 2014 [cited by applicant]
US 8756210B1 · Guha · 2014 [cited by applicant]
US 8762373B1 · Zamir et al. · 2014 [cited by applicant]
US 8874555B1 · Kim et al. · 2014 [cited by applicant]
US 9063972B1 · Marra et al. · 2015 [cited by applicant]
US 9210056B1 · Choudhary et al. · 2015 [cited by applicant]
US 9558233B1 · Kim et al. · 2017 [cited by applicant]
US 9646055B2 · Kumar · 2017 [cited by examiner]
US 10007730B2 · Horvitz et al. · 2018 [cited by applicant]
US 10042888B2 · Chen et al. · 2018 [cited by applicant]
US 10489284B1 · Saraf · 2019 [cited by applicant]
US 10878006B2 · Guney · 2020 [cited by applicant]
US 11537624B2 · Zhang et al. · 2022 [cited by applicant]
US 20030041054A1 · Mao et al. · 2003 [cited by applicant]
US 20040103087A1 · Mukherjee et al. · 2004 [cited by applicant]
US 20040215607A1 · Travis, Jr. · 2004 [cited by examiner]
US 20040267774A1 · Lin et al. · 2004 [cited by applicant]
US 20050149504A1 · Ratnaparkhi · 2005 [cited by applicant]
US 20050165745A1 · Hagale et al. · 2005 [cited by applicant]
US 20060106764A1 · Girgensohn et al. · 2006 [cited by applicant]
US 20060287980A1 · Liu · 2006 [cited by examiner]
US 20080126303A1 · Park et al. · 2008 [cited by applicant]
US 20080140647A1 · Bailey et al. · 2008 [cited by applicant]
US 20080275882A1 · Kehl et al. · 2008 [cited by applicant]
US 20090019030A1 · Smolyanskiy · 2009 [cited by applicant]
US 20090083226A1 · Kawale et al. · 2009 [cited by applicant]
US 20090089267A1 · Chi et al. · 2009 [cited by applicant]
US 20090089311A1 · Chi et al. · 2009 [cited by applicant]
US 20090094224A1 · Ricket et al. · 2009 [cited by applicant]
US 20090106221A1 · Meyerzon et al. · 2009 [cited by applicant]
US 20090119254A1 · Cross et al. · 2009 [cited by applicant]
US 20090287655A1 · Bennett · 2009 [cited by applicant]
US 20090292685A1 · Liu et al. · 2009 [cited by applicant]
US 20100082510A1 · Gao et al. · 2010 [cited by applicant]
US 20100082604A1 · Gutt et al. · 2010 [cited by applicant]
US 20100088020A1 · Sano et al. · 2010 [cited by applicant]
US 20100161643A1 · Gionis et al. · 2010 [cited by applicant]
US 20100174736A1 · Goodall · 2010 [cited by examiner]
US 20100179948A1 · Xie et al. · 2010 [cited by applicant]
US 20100198813A1 · Chi et al. · 2010 [cited by applicant]
US 20100306191A1 · LeBeau · 2010 [cited by examiner]
US 20100306213A1 · Taylor et al. · 2010 [cited by applicant]
US 20110004592A1 · Shiraishi · 2011 [cited by applicant]
US 20110004608A1 · Solaro · 2011 [cited by examiner]
US 20110137902A1 · Wable · 2011 [cited by examiner]
US 20110137932A1 · Wable · 2011 [cited by applicant]
US 20110270828A1 · Varma et al. · 2011 [cited by applicant]
US 20120023104A1 · Johnson et al. · 2012 [cited by applicant]
US 20120150837A1 · Radlinski · 2012 [cited by examiner]
US 20120221560A1 · Chevalier et al. · 2012 [cited by applicant]
US 20120303830A1 · Tobioka · 2012 [cited by applicant]
US 20130124496A1 · Edgar · 2013 [cited by examiner]
US 20130159298A1 · Mason et al. · 2013 [cited by applicant]
US 20130173573A1 · Song · 2013 [cited by examiner]
US 20130173639A1 · Chandra et al. · 2013 [cited by applicant]
US 20130191329A1 · Dozier et al. · 2013 [cited by applicant]
US 20130262454A1 · Srikrishna · 2013 [cited by applicant]
US 20140358882A1 · Diab · 2014 [cited by applicant]
US 20140358916A1 · Anand et al. · 2014 [cited by applicant]
US 20150039606A1 · Salaka et al. · 2015 [cited by applicant]
US 20150161176A1 · Majkowska et al. · 2015 [cited by applicant]
US 20150161255A1 · Battle · 2015 [cited by examiner]
US 20160055252A1 · Makeev et al. · 2016 [cited by applicant]
US 20160300140A1 · Joseph et al. · 2016 [cited by applicant]
US 20160321694A1 · Vorozhtsov · 2016 [cited by applicant]
US 20170091192A1 · Kuralenok et al. · 2017 [cited by applicant]
US 20170124183A1 · Braham et al. · 2017 [cited by applicant]
US 20170140053A1 · Vorobev et al. · 2017 [cited by applicant]
US 20170154313A1 · Duerr et al. · 2017 [cited by applicant]
US 20170185599A1 · Glover et al. · 2017 [cited by applicant]
US 20170255653A1 · Zhu et al. · 2017 [cited by applicant]
US 20180011876A1 · Li et al. · 2018 [cited by applicant]
US 20180150466A1 · Paquet et al. · 2018 [cited by applicant]
US 20180165310A1 · Coll et al. · 2018 [cited by applicant]
US 20180190272A1 · Georges et al. · 2018 [cited by applicant]
US 20190205472A1 · Kulkarni · 2019 [cited by applicant]
US 20190236202A1 · Guney · 2019 [cited by applicant]
US 20190253251A1 · Kobayashi et al. · 2019 [cited by applicant]
US 20190286746A1 · Li · 2019 [cited by examiner]
US 20200097560A1 · Kulkarni · 2020 [cited by applicant]
US 20200192920A1 · Filonov et al. · 2020 [cited by applicant]
US 20200250197A1 · Yang et al. · 2020 [cited by applicant]
US 20200293591A1 · Prelovac · 2020 [cited by examiner]
US 20200320100A1 · Piecko et al. · 2020 [cited by applicant]
US 20200320153A1 · Luz Xavier Da Costa · 2020 [cited by examiner]
US 20200380582A1 · Nuta et al. · 2020 [cited by applicant]
US 20200387517A1 · Huang et al. · 2020 [cited by applicant]
CA 2758813 · 2010 [cited by applicant]
CA 3128459 · 2020 [cited by applicant]
CN 101764807A · 2012 [cited by applicant]
DE 112005003035B4 · 2011 [cited by applicant]
TW I540448B · 2016 [cited by examiner]
WO 2019041284 · 2019 [cited by applicant]
Lewandowski, D, “A Framework for Evaluating the Retrieval Effectiveness of Search Engines”, arXiv: 1511.05817 [cs.IR], https://doi.org/10.48550/arXiv.1511.05817, Publication date Nov. 18, 2015, pp. 1-19. (Year: 2015). [cited by examiner]
Chapelle, O., et al., Large-Scale Validation and Analysis of Interleaved Search Evaluation, ACM Trans. Inf. Syst. 30, 1, Article 6 (Feb. 2012), 41 pages Feb. 2012. [cited by applicant]