# US 11,907,999 B2 · System, method, and computer readable medium for automatic item rankings

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,907,999 B2
- Document ID: US11907999B2
- Status: Granted
- Kind: B2
- Application number: 18/101,269
- Filed: 2023-01-25
- Published: 2023-05-25
- Granted: 2024-02-20
- Earliest claimed: 2021-01-13
- Assignees: Walmart Apollo, LLC
- Applicants: Walmart Apollo, LLC
- Inventors: Rahul Iyer; Shashank Kedia; Anirudha Sundaresan; Shubham Gupta; Praveenkumar Kanumala; Stephen Dean Guo; Kannan Achan
- Web page: https://patentgrep.com/patent/US11907999B2

## CPC

- G06Q 30/0631: {Recommending goods or services}
- G06F 16/2457: with adaptation to user needs
- G06F 16/24578: {using ranking}
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## 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.

## Claims

### Claim 1

A system comprising:
a computing device configured to:
receive a search query submitted by a user accessing a web site;
determine a requested item feature based on the search query;
perform text normalization on the requested item feature;
obtain, for each of a plurality of recommended items, a plurality of recommended item features;
perform text normalization on the plurality of recommended item features;
compare the text normalized requested item feature to a corresponding text normalized recommended item feature of the plurality of recommended item features to generate a comparison;
generate a ranked list of recommended items based on the comparison, the ranked list including a ranking of the plurality of recommended items; and
transmit the ranked list of recommended items to be displayed to the user in response to the search query.

### Claim 2 (depends on 1)

The system of claim 1, wherein the computing device is further configured to:
generate a plurality of relevancy values based on the comparison, the relevancy values based on a determined similarity value associated with the comparison;
transmit the plurality of relevancy values to a web server; and
determine 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.

### Claim 3 (depends on 2)

The system of claim 2, wherein the computing device is configured to:
determine, for each of the plurality of recommended items, a final relevancy value based on a corresponding plurality of relevancy values; and
store the final relevancy values in a data repository.

### Claim 4 (depends on 2)

The system of claim 2, 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.

### Claim 5 (depends on 2)

The system of claim 2, 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.

### Claim 6 (depends on 5)

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.

### Claim 7 (depends on 6)

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.

### Claim 8 (depends on 5)

The system of claim 5, wherein determining the 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.

### Claim 9 (depends on 8)

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 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.

### Claim 10 (depends on 5)

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.

### Claim 11

A method comprising:
receiving a search query submitted by a user accessing a website;
determining a requested item feature based on the search query;
performing text normalization on the 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;
comparing the text normalized one requested item feature to the text normalized recommended item feature of the plurality of recommended item features to generate a comparison;
generate a ranked list of recommended items based on the comparison, the ranked list including a ranking of the plurality of recommended items; and
transmitting the ranked list of recommended items to be displayed to the user in response to the search query.

### Claim 12 (depends on 11)

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

### Claim 13 (depends on 12)

The method of claim 12, 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.

### Claim 14 (depends on 12)

The method of claim 12, 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.

### Claim 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 a search query submitted by a user accessing a website;
determining a requested item feature based on the search query;
performing text normalization on the 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;
comparing the text normalized requested item feature to the text normalized recommended item feature of the plurality of recommended item features to generate a comparison;
generate a ranked list of recommended items based on the comparison, the ranked list including a ranking of the plurality of recommended items; and
transmitting the ranked list of recommended items to be displayed to the user in response to the search query.

### Claim 16 (depends on 15)

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:
generating a plurality of relevancy values based on the comparison; and
transmitting the plurality of relevancy values to a 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.

### Claim 17 (depends on 15)

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:
generating a plurality of relevancy values based on the comparison, the relevancy values based on a determined similarity value associated with the comparison;
determining, for each of the plurality of recommended items, a final relevancy value based on a corresponding plurality of relevancy values; and
storing the final relevancy values in a data repository.

### Claim 18 (depends on 17)

The non-transitory computer readable medium of claim 17, further comprising instructions stored thereon that, when executed by at least one processor, further cause the device to perform operations comprising:
generating an item relevance value, a brand relevance value, a count relevance value, and a size relevance value; and
applying a weight to each of the similarity values.

### Claim 19 (depends on 17)

The non-transitory computer readable medium of claim 17, further comprising instructions stored thereon that, when executed by at least one processor, further cause the device to perform operations comprising generating an item relevance value, a brand relevance value, a count relevance value, and a size relevance value.

### Claim 20 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein the instructions, when executed by the at least one processor, cause the device to further perform operations comprising:
determining a requested item based on the search query;
determining if the requested item is in stock; and
if the requested item is not in stock:
determining at least one substitute item,
generating, for each of the at least one substitute item, a final relevance value based on at least one of an item relevance, brand relevance, count relevance, or size relevance, and
substituting one of the at least one substitute item for the requested item based on the final relevance value.