System, method, and computer readable medium for automatic item rankings

Patent metadata

Field	Value
Publication number	US-11610249-B2
Application number	US-202117147895-A
Country	US
Kind code	B2
Filing date	Jan 13, 2021
Priority date	Jan 13, 2021
Publication date	Mar 21, 2023
Grant date	Mar 21, 2023

Abstract

This application relates to apparatus and methods for automatically determining item relevancy based on textual information. In some examples, a computing device receives a search query, and a plurality of items corresponding to the search query. The computing device may identify one or more features of the search query. The computing device may generate relevancy values for each of the items based on the features of the search query, and features of each of the plurality of items. For example, the computing device may generate, for each of the items, a plurality of relevance values, each relevance value generated based on a feature of the search query and corresponding features of the item. The computing device may transmit the generated relevancy values for the plurality of items. In some examples, the computing device may rank the plurality of items based on the generated relevancy values.

First claim

What is claimed is:

1. A system comprising:
a computing device configured to:
receive, from a web server, a search query submitted by a user accessing a website hosted by the web server;
determine at least one requested item feature based on the search query;
perform text normalization on the at least one requested item feature;
obtain, for each of a plurality of recommended items, a plurality of recommended item features from the web server;
perform text normalization on the plurality of recommended item features;
determine, for each of the plurality of recommended items, a plurality of relevancy values, each of the plurality of relevancy values generated based on a similarity value between the text normalized at least one requested item feature and a corresponding text normalized recommended item feature of the plurality of recommended item features;
rank the plurality of recommended items based on the plurality of relevancy values to generate a ranked list of recommended items; and
transmit, to the web server, the ranked list of recommended items to be displayed to the user in response to the search query.

2. The system of claim 1 , wherein:
the computing device is further configured to transmit the plurality of relevancy values to the web server; and
the web server determines an item advertisement for at least one item of the plurality of recommended items based on the plurality of relevancy values and displays the item advertisement to the user.

3. The system of claim 1 , wherein the computing device is configured to:
determine, for each of the plurality of recommended items, a final relevancy value based on the corresponding plurality of relevancy values; and
store the final relevancy values in a data repository.

4. The system of claim 1 , wherein determining, for each of the plurality of recommended items, the plurality of relevancy values further comprises:
applying a weight to each of the similarity values.

5. The system of claim 1 , wherein determining, for each of the plurality of recommended items, the plurality of relevancy values further comprises generating an item relevance value, a brand relevance value, a count relevance value, and a size relevance value.

6. The system of claim 5 , wherein the computing device is configured to generate the brand relevance value based on a hierarchical graph stored in a data repository.

7. The system of claim 6 , wherein the hierarchal graph contains a plurality of nodes and at least one edge connecting the plurality of nodes and the brand relevancy value between is further determined based on an edge connecting two nodes.

8. The system of claim 5 , wherein determining the at least one requested item feature based on the search query comprises determining a requested title feature, wherein the plurality of recommended item features comprise an item title feature, and wherein generating the item relevance value comprises determining a first similarity value based on the requested title feature and the item title feature corresponding to the recommended item.

9. The system of claim 8 , wherein generating the item relevance value comprises:
determining a second similarity value between each of the plurality of recommended item features and the at least one requested item feature;
applying a weight to each of the second similarity values; and
determining a third similarity value based on the weighted second similarity values.

10. The system of claim 5 , wherein generating at least one of the count relevance value and the size relevance value comprises determining a neighborhood relevance between the corresponding item feature and the at least one item feature.

11. A method comprising:
receiving, from a web server, a search query submitted by a user accessing a web site hosted by the web server;
determining at least one requested item feature based on the search query;
performing text normalization on the at least one requested item feature;
obtaining, for each of a plurality of recommended items, a plurality of recommended item features;
performing text normalization on the plurality of recommended item features;
determining, for each of the plurality of recommended items, a plurality of relevancy values, each of the plurality of relevancy values generated based on a determined similarity value between the text normalized at least one requested item feature and the text normalized recommended item feature of the plurality of recommended item features;
ranking the plurality of recommended items based on the plurality of relevancy values to generate a ranked list of recommended items; and
transmitting, to the web server, the ranked list of recommended items to be displayed to the user in response to the search query.

12. The method of claim 11 comprising:
determining, for each of the plurality of recommended items, a final relevancy value based on the corresponding plurality of relevancy values; and
storing the final relevancy values in a data repository.

13. The method of claim 11 wherein determining, for each of the plurality of recommended items, the plurality of relevancy values further comprises:
applying a weight to each of the similarity values.

14. The method of claim 11 wherein determining, for each of the plurality of recommended items, the plurality of relevancy values further comprises generating an item relevance value, a brand relevance value, a count relevance value, and a size relevance value.

15. A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause a device to perform operations comprising:
receiving, from a web server, a search query submitted by a user accessing a web site hosted by the web server;
determining at least one requested item feature based on the search query;
performing text normalization on the at least one requested item feature;
obtaining, for each of a plurality of recommended items, a plurality of recommended item features;
performing text normalization on the plurality of recommended item features;
determining, for each of the plurality of recommended items, a plurality of relevancy values, each of the plurality of relevancy values generated based on a determined similarity value between the text normalized at least one requested item feature and the text normalized recommended item feature of the plurality of recommended item features;
ranking the plurality of recommended items based on the plurality of relevancy values to generate a ranked list of recommended items; and
transmitting, to the web server, the ranked list of recommended items to be displayed to the user in response to the search query.

16. The non-transitory computer readable medium of claim 15 , further comprising instructions stored thereon that, when executed by at least one processor, further cause the device to perform operations comprising transmitting the plurality of relevancy values to the web server, wherein the web server determines an item advertisement for at least one item of the plurality of recommended items based on the plurality of relevancy values and displays the item advertisement to the user.

17. The non-transitory computer readable medium of claim 15 , further comprising instructions stored thereon that, when executed by at least one processor, further cause the device to perform operations comprising:
determining, for each of the plurality of recommended items, a final relevancy value based on the corresponding plurality of relevancy values; and
storing t

Assignees

• Walmart Apollo Llc

Inventors

• Iyer Rahul
• Kedia Shashank
• Sundaresan Anirudha
• Gupta Shubham
• Kanumala Praveenkumar
• Guo Stephen Dean
• Achan Kannan

Classifications

• G06F16/24578

  using ranking · CPC title

• G06Q10/087

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06F16/2457

  with adaptation to user needs · CPC title