Systems and methods for personalizing search engine recall and ranking using machine learning techniques

Patent metadata

Field	Value
Publication number	US-11704374-B2
Application number	US-202117163400-A
Country	US
Kind code	B2
Filing date	Jan 30, 2021
Priority date	Jan 30, 2021
Publication date	Jul 18, 2023
Grant date	Jul 18, 2023

Abstract

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of: providing a search engine that includes, or communicates with, a recall personalization model configured to generate personalized recall sets of search results for users; receiving, at the search engine, a search query submitted by a user; generating, using the recall personalization module, a feature vector for the user that includes contextual features associated with the user; generating, using the recall personalization model, a simulated narrowing query that includes the search query submitted by the user and the feature vector; generating, using the search engine, a recall set of search results based, at least in part, on the simulated narrowing query. Other embodiments are disclosed herein.

First claim

What is claimed is:

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, perform functions comprising:
providing a search engine comprising, or communicating with, a recall personalization model configured to generate personalized recall sets of search results for users;
receiving, at the search engine, a generic search query submitted by a user, wherein the generic search query comprises less than three attribute descriptors;
generating, using the recall personalization model, a feature vector for the user comprising contextual features associated with the user, wherein each contextual feature of the contextual features reflects a respective user preference of personalization preferences associated with the user;
generating, using the recall personalization model, a simulated narrowing query that supplements the generic search query submitted by the user with the feature vector for the user comprising the contextual features; and
generating, using the search engine, a recall set of the search results based, at least in part, on the simulated narrowing query, wherein the recall set of the search results accounts for the personalization preferences associated with the user.

2. The system of claim 1 , wherein:
the generic search query identifies an item type category without additional descriptors;
the search engine further supplements the generic search query with the contextual features; and
the contextual features enable the search engine to customize the recall set of the search results based, at least in part, on the personalization preferences associated with the user.

3. The system of claim 1 , wherein generating the feature vector for the user comprising the contextual features further comprises:
appending the feature vector with one or more attribute keys associated with a brand attribute.

4. The system of claim 3 , wherein generating the feature vector for the user comprising the contextual features further comprises:
appending the feature vector with one or more attribute keys associated with a flavor attribute; and
appending the feature vector with one or more attribute keys associated with a price band attribute.

5. The system of claim 1 , wherein the recall personalization model comprises:
an attribute selection component that is configured to determine a number of attribute keys to be incorporated into the feature vector comprising the contextual features associated with the user; and
a machine learning architecture configured to convert the generic search query into the simulated narrowing query to account for the personalization preferences associated with the user, wherein the contextual features are derived from historical data associated with the user.

6. The system of claim 5 , wherein the attribute selection component comprises a statistical model that is configured to determine the number of attribute keys to be incorporated into the feature vector for the user.

7. The system of claim 6 , wherein the statistical model selects the number of attribute keys based, at least in part, on a number of the personalization preferences for the user.

8. The system of claim 6 , wherein the statistical model selects the number of attribute keys based, at least in part, on preference scores associated with attribute values of the attribute keys.

9. The system of claim 1 , wherein:
a plurality of attribute keys are pre-computed for the user;
each of the plurality of attribute keys comprises a respective attribute value and a respective preference score;
the respective preference score indicates a respective affinity of the user for the respective attribute value; and
the plurality of attribute keys are incorporated into the feature vector for the user.

10. The system of claim 1 , wherein:
the search engine is configured to communicate with a personalized ranking model; and
the personalized ranking model is configured to sort the recall set of the search results based on the personalization preferences associated with the user.

11. A method implemented via execution of computing instructions configured to run at one or more processors and stored at non-transitory computer-readable media, the method comprising:
providing a search engine comprising, or communicating with, a recall personalization model configured to generate personalized recall sets of search results for users;
receiving, at the search engine, a generic search query submitted by a user, wherein the generic search query comprises less than three attribute descriptors;
generating, using the recall personalization model, a feature vector for the user comprising contextual features associated with the user, wherein each contextual feature of the contextual features reflects a respective user preference of personalization preferences associated with the user;
generating, using the recall personalization model, a simulated narrowing query that supplements the generic search query submitted by the user with the feature vector for the user comprising the contextual features; and
generating, using the search engine, a recall set of the search results based, at least in part, on the simulated narrowing query, wherein the recall set of the search results accounts for the personalization preferences associated with the user.

12. The method of claim 11 , wherein:
the generic search query identifies an item type category without additional descriptors;
the search engine further supplements the generic search query with the contextual features; and
the contextual features enable the search engine to customize the recall set of the search results based, at least in part, on the personalization preferences associated with the user.

13. The method of claim 11 , wherein generating the feature vector for the user comprising the contextual features further comprises:
appending the feature vector with one or more attribute keys associated with a brand attribute.

14. The method of claim 13 , wherein generating the feature vector for the user comprising the contextual features further comprises:
appending the feature vector with one or more attribute keys associated with a flavor attribute; and
appending the feature vector with one or more attribute keys associated with a price band attribute.

15. The method of claim 11 , wherein the recall personalization model comprises:
an attribute selection component that is configured to determine a number of attribute keys to be incorporated into the feature vector comprising the contextual features associated with the user; and
a machine learning architecture configured to convert the generic search query into the simulated narrowing query to account for the personalization preferences associated with the user, wherein the contextual features are derived from historical data associated with the user.

16. The method of claim 15 , wherein the attribute selection component comprises a statistical model that is configured to determine the number of attribute keys to be incorporated into the feature vector for the user.

17. The method of claim 16 , wherein the statistical model selects the number of attribute keys based, at least in part, on a number of the personalization preferences for the user.

18. The method of claim 16 , wherein the statistical model selects the number of attribute keys based, at least in part, on preference scores associated with attribute values of the attribute keys.

Assignees

• Walmart Apollo Llc

Inventors

• Cho Hyun Duk
• Kumar Sushant
• Achan Kannan
• Sinha Nimesh
• Inan Aysenur

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/9532

  Query formulation · CPC title

• G06N20/00

  Machine learning · CPC title