# US 2024/0257199 A1 · Automatically cataloguing item compatibility features

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

- Number: US 2024/0257199 A1
- Document ID: US20240257199A1
- Status: Published application
- Kind: A1
- Application number: 18/162,945
- Filed: 2023-02-01
- Published: 2024-08-01
- Earliest claimed: 2023-02-01
- Assignees: Adobe Inc.
- Applicants: Adobe Inc.
- Inventors: Soumya Unnikrishnan; Michele Saad; Saina Lajevardi
- Web page: https://patentgrep.com/patent/US20240257199A1

## CPC

- G06Q 30/0621: {by configuring or customising goods or services}
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 30/0625: {by formulating product or service queries, e.g. using keywords or predefined options}
- G06Q 30/0631: {Recommending goods or services}
- 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

## Abstract

Systems and methods for inferring compatibility relationships are described. Embodiments of the present disclosure identify user interaction history including an interaction between a user and a first product, wherein the first product comprises an attribute that is compatible with a subset of available products; query a database that includes the available products to identify a second product from the subset of available products based on the attribute, wherein the second product is identified based on a knowledge graph that includes a first node representing the first product and a second node representing the second product; and provide a customized user experience for the user that indicates the second product and the attribute.

## Claims

### Claim 1

A method comprising:
identifying, through an item compatibility apparatus, user interaction history including an interaction between a user and a first product, wherein the first product comprises an attribute that is compatible with a subset of available products;
querying, using a prediction component, a database that includes the available products to identify a second product from the subset of available products based on the attribute, wherein the second product is identified based on a knowledge graph that includes a first node representing the first product and a second node representing the second product; and
providing, through a user interface, a customized user experience for the user that indicates the second product and the attribute.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
identifying an additional interaction between the user and a third product;
determining, using the prediction component, that the third product is not compatible with the first product based on the knowledge graph and the attribute; and
providing an alert to the user that the third product is not compatible with the first product based on the determination.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
receiving unstructured product data about the first product;
performing, using a natural language processing (NLP) component, natural language processing on the unstructured product data to identify the first product and the attribute; and
generating, using a knowledge graph component, the knowledge graph based on the natural language processing.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
generating, using the knowledge graph component the first node, the second node, and an edge between the first node and the second node based on the natural language processing, wherein the edge indicates compatibility of the first product and the second product.

### Claim 5 (depends on 3)

The method of claim 3, further comprising:
generating, using the knowledge graph component, the first node, a third node representing the attribute, and an edge between the first node and the third node based on the natural language processing, wherein the edge indicates the first product has the attribute.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
generating, using an embedding component, a first vector representation of the first product, wherein the first node corresponds to the first vector representation.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
generating, using the embedding component, a second vector representation of the second product, wherein the second node corresponds to the second vector representation; and
computing, using the prediction component, a similarity score between the first vector representation and the second vector representation, wherein the second product is identified based on the similarity score.

### Claim 8 (depends on 6)

The method of claim 6, further comprising:
updating, using the embedding component, the first vector representation using a graph neural network based on the knowledge graph.

### Claim 9

A method comprising:
receiving unstructured product data about a first product;
performing, using a natural language processing (NLP) component, natural language processing on the unstructured product data to identify the first product and an attribute that indicates compatibility of the first product with a subset of available products;
generating, using a knowledge graph component, a knowledge graph that represents the first product and the attribute; and
generating, using a generative model, listing content for the first product based on the knowledge graph, wherein the listing content indicates compatibility of the first product with the subset of available products based on the attribute.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
generating, using the knowledge graph component, a first node, a second node, and an edge between the first node and the second node based on the natural language processing, wherein the edge indicates compatibility of the first product and a second product, and wherein the knowledge graph includes the first node, the second node, and the edge.

### Claim 11 (depends on 9)

The method of claim 9, further comprising:
receiving ground-truth named entity recognition (NER) data, wherein the ground-truth NER data comprises unstructured text and ground-truth annotations;
performing, using the natural language processing component, natural language processing on the unstructured text to generate predicted annotations;
comparing, using a training component, the predicted annotations to the ground-truth annotations; and
updating, using the training component, parameters of the natural language processing component based on the comparison.

### Claim 12 (depends on 9)

The method of claim 9, further comprising:
receiving ground-truth embedding data, wherein the ground-truth embedding data comprises ground-truth vector representations;
generating, using an embedding component, predicted vector representations of the products and attributes;
comparing, using a training component, the predicted vector representations to the ground-truth vector representations; and
updating, using the training component, parameters of the embedding component based on the comparison.

### Claim 13 (depends on 9)

The method of claim 9, further comprising:
receiving structured product data about a first product, a compatibility attribute, and a plurality of compatible products;
comparing, using a training component, the identified subset of available products from the unstructured product data with the plurality of compatible products from the structured product data; and
updating, using the training component, parameters of a prediction component based on the comparison.

### Claim 14 (depends on 9)

The method of claim 9, further comprising:
receiving ground-truth listing data including a product, a plurality of compatibility attributes, and a ground-truth product description;
generating, using the generative model, a predicted product description for the product, wherein the generative model is seeded with inferred compatibility information about the product;
comparing, using a training component, the predicted product description to the ground-truth product description; and
updating, using the training component, parameters of the generative model based on the comparison.

### Claim 15 (depends on 9)

The method of claim 9, wherein:
the listing content includes a product bundle promotion, wherein the product bundle promotion comprises a plurality of products that are compatible with the first product.

### Claim 16

An apparatus comprising:
a processor;
a memory including instructions executable by the processor;
a natural language processing component configured to perform natural language processing on unstructured product data to identify a first product and an attribute that indicates compatibility of the first product with a subset of available products;
a knowledge graph component configured to generate a knowledge graph that represents the first product and the attribute; and
an embedding component configured to generate a first vector representation of the first product.

### Claim 17 (depends on 16)

The apparatus of claim 16, further comprising:
a prediction component configured to identify a second product that is compatible with the first product.

### Claim 18 (depends on 16)

The apparatus of claim 16, further comprising:
a generative model configured to generate a product description for the first product, wherein the product description includes inferred compatibility information.

### Claim 19 (depends on 16)

The apparatus of claim 16, wherein:
the natural language processing component comprises a named entity recognition model.

### Claim 20 (depends on 16)

The apparatus of claim 16, wherein:
the embedding component comprises a graph neural network.
