# US 2021/0241342 A1 · Systems and methods for ingredient-to-product mapping

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

- Number: US 2021/0241342 A1
- Document ID: US20210241342A1
- Status: Published application
- Kind: A1
- Application number: 16/779,474
- Filed: 2020-01-31
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: Walmart Apollo, LLC
- Applicants: Walmart Apollo, LLC
- Inventors: Navin Naidu; Steven Pui Sum Cheng; Kartikeya Misra
- Web page: https://patentgrep.com/patent/US20210241342A1

## CPC

- G06Q 30/0627: {by specifying product or service characteristics, e.g. product dimensions}
- G06F 16/24522: {Translation of natural language queries to structured queries}
- G06F 40/295: Named entity recognition
- G06N 20/00: Machine learning
- G06Q 30/0603: {Catalogue creation or management}
- G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)}
- G09B 19/0092: {Nutrition}
- G06F 40/14: Tree-structured documents (parsing G06F40/205; validation G06F40/226)
- G06F 40/216: using statistical methods
- G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)

## Abstract

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform using a plugin system in a user interface to identify each ingredient in an ingredient list of a recipe published on a webpage shown on the user interface; identifying query strings from content on the webpage associated with one or more ingredients of the recipe; identifying one or more respective recipe products and a respective quantity for each of the one or more ingredients; locating a respective catalog product in an online catalog for each of the one or more respective recipe products; automatically generating a list of catalog products; automatically generating a link comprising the list of catalog products; automatically redirecting the user interface to an online retail website; and automatically adding the list of catalog products to an electronic shopping cart. Other embodiments are disclosed.

## Claims

### Claim 1

A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform:
using a plugin system in a user interface to identify each ingredient in an ingredient list of a recipe published on a webpage shown on the user interface by:
identifying query strings from content on the webpage associated with one or more ingredients of the recipe; and
identifying one or more respective recipe products and a respective quantity for each of the one or more respective recipe products for each of the one or more ingredients;
locating a respective catalog product in an online catalog for each of the one or more respective recipe products based on the respective quantity for each of the one or more respective recipe products;
automatically generating a list of catalog products based on the respective catalog products, as located;
automatically generating a link comprising the list of catalog products;
automatically redirecting the user interface, via the link and the plugin system, to an online retail website comprising the online catalog; and
automatically adding the list of catalog products to an electronic shopping cart.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the webpage displays a video; and
the content on the webpage comprises subtitles from a closed caption feature on the video.

### Claim 3 (depends on 1)

The system of claim 1, wherein:
the webpage displays a video; and
the content on the webpage comprises a transcript of the video.

### Claim 4 (depends on 3)

The system of claim 3, wherein the transcript comprises an extensible markup language (XML) document.

### Claim 5 (depends on 4)

The system of claim 4, wherein:
identifying the query strings from content on the webpage associated with one or more ingredients of the recipe comprises:
parsing one or more text phrases from the XML document; and
locating the respective catalog product in the online catalog for each of the one or more respective recipe products comprises:
using an n-gram learning model to match keywords parsed from the one or more text phrases from the XML document to the respective catalog products in the online catalog.

### Claim 6 (depends on 1)

The system of claim 1, wherein the computing instructions are further configured to run on the one or more processors and perform:
training a machine learning model to identify each of the one or more ingredients from the query string, wherein input data for the machine learning model comprises respective extracted partial text phrases from query strings matching (i) respective ingredients of the one or more ingredients and (ii) respective quantities for the respective ingredients.

### Claim 7 (depends on 6)

The system of claim 6, wherein identifying the one or more respective recipe products and a respective quantity for each of the one or more respective recipe products for each of the one or more ingredients comprises:
generating, using the machine learning model, as trained, output comprising predictive indications of (i) a respective recipe product of the one or more respective recipe products for each of the query strings, and (ii) a respective quantity of each respective recipe product.

### Claim 8 (depends on 6)

The system of claim 6, wherein the machine learning model comprises a core Named Entity Recognition (NER) machine learning model.

### Claim 9 (depends on 1)

The system of claim 1, wherein the computing instructions are further configured to run on the one or more processors and perform:
when the respective catalog product is not identified in the online catalog, refining an identification of the one or more respective recipe products by using an n-gram learning model by:
creating one or more n-grams from the query string; and
searching the online catalog using each respective n-gram as a search query to identify a respective catalog product in the online catalog.

### Claim 10 (depends on 1)

The system of claim 1, wherein the webpage comprises:
a retail webpage;
an affiliate webpage; or
a third-party webpage.

### Claim 11

A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:
using a plugin system in a user interface to identify each ingredient in an ingredient list of a recipe published on a webpage shown on the user interface by:
identifying query strings from content on the webpage associated with one or more ingredients of the recipe; and
identifying one or more respective recipe products and a respective quantity for each of the one or more respective recipe products for each of the one or more ingredients;
locating a respective catalog product in an online catalog for each of the one or more respective recipe products based on the respective quantity for each of the one or more respective recipe products;
automatically generating a list of catalog products based on the respective catalog products, as located;
automatically generating a link comprising the list of catalog products;
automatically redirecting the user interface, via the link and the plugin system, to an online retail website comprising the online catalog; and
automatically adding the list of catalog products to an electronic shopping cart.

### Claim 12 (depends on 11)

The method of claim 11, wherein:
the webpage displays a video; and
the content on the webpage comprises subtitles from a closed caption feature on the video.

### Claim 13 (depends on 11)

The method of claim 11, wherein:
the webpage displays a video; and
the content on the webpage comprises a transcript of the video.

### Claim 14 (depends on 13)

The method of claim 13, wherein the transcript comprises an extensible markup language (XML) document.

### Claim 15 (depends on 14)

The method of claim 14, wherein:
identifying the query strings from content on the webpage associated with one or more ingredients of the recipe comprises:
parsing one or more text phrases from the XML document; and
locating the respective catalog product in the online catalog for each of the one or more respective recipe products comprises:
using an n-gram learning model to match keywords parsed from the one or more text phrases from the XML document to the respective catalog products in the online catalog.

### Claim 16 (depends on 11)

The method of claim 11, further comprising:
training, a machine learning model, to identify each of the one or more ingredients from the query string, wherein input data for the machine learning model comprises respective extracted partial text phrases from query strings matching (i) respective ingredients of the one or more ingredients and (ii) respective quantities for the respective ingredients.

### Claim 17 (depends on 16)

The method of claim 16, wherein identifying the one or more respective recipe products and a respective quantity for each of the one or more respective recipe products for each of the one or more ingredients comprises:
generating, using the machine learning model, as trained, output comprising predictive indications of (i) a respective recipe product of the one or more respective recipe products for each of the query strings, and (ii) a respective quantity of each respective recipe product.

### Claim 18 (depends on 16)

The method of claim 16, wherein the machine learning model comprises a core Named Entity Recognition (NER) machine learning model.

### Claim 19 (depends on 11)

The method of claim 11, further comprising:
when the respective catalog product is not identified in the online catalog, refining an identification of the one or more respective recipe products by using an n-gram learning model by:
creating one or more n-grams from the query string; and
searching the online catalog using each respective n-gram as a search query to identify a respective catalog product in the online catalog.

### Claim 20 (depends on 11)

The method of claim 11, wherein the webpage comprises:
a retail webpage;
an affiliate webpage; or
a third-party webpage.