# US 2025/0086033 A1 · Data analytics for digital catalogs

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

- Number: US 2025/0086033 A1
- Document ID: US20250086033A1
- Status: Published application
- Kind: A1
- Application number: 18/925,777
- Filed: 2024-10-24
- Published: 2025-03-13
- Earliest claimed: 2023-09-12
- Assignees: Prodx, LLC
- Applicants: Prodx, LLC
- Inventors: Brodrick David Yastrum; Robert Lawrence Bertsch; Meaghan Carroll Jones; Matthew James Vezzani
- Web page: https://patentgrep.com/patent/US20250086033A1

## CPC

- G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications}
- G06Q 30/0603: {Catalogue creation or management}
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0475: Generative networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Techniques for standardizing a catalog of data and for using the standardized data to implement various APIs are disclosed. Non-standardized data is received. This data includes information describing items, customer information, and unstructured review data. The non-standardized data is converted to a standardized format, resulting in the generation of standardized data. The standardized data includes a hierarchy of defined categories. Each category is associated with a set of attribute types. The standardized data also includes anonymized profiles. The unstructured review data is also provided structure. A data model is generated based on the standardized data. Various APIs can then use the data model to perform operations.

## Claims

### Claim 1

A method comprising:
receiving non-standardized data comprising: information describing a plurality of items, said information being obtained from a first domain, and customer information that is also obtained from the first domain;
generating standardized data by converting a format of the non-standardized data into a standardized format, wherein:
the standardized data includes a hierarchy of multiple defined categories into which various portions of the standardized data are categorized, and
each of the multiple defined categories is associated with a corresponding set of attribute types that describe attributes for said each of the multiple defined categories;
including the standardized data within a data model, wherein the standardized data is made accessible to one or more application programming interfaces (APIs), including a variations API;
receiving, via the variations API, a user query targeting an item included in one of the multiple defined categories;
causing the variations API to use the standardized data to identify the item;
causing the variations API to use the standardized data to identify a variation of the item, wherein identifying the variation includes:
determining a first value for a first item attribute for the item and a second value for a second item attribute for the item;
identifying the variation by using the first value for a first variation attribute for the variation, wherein the first variation attribute corresponds to the first item attribute; and
further identifying the variation by using a third value, which is different from the second value, for a second variation attribute for the variation, wherein the second variation attribute corresponds to the second item attribute such that the variation is within a threshold level of similarity to the item and such that the variation is different than the item;
simultaneously displaying the first value with the third value on a user interface;
causing the first value to be selectable within the user interface; and
causing the third value to be selectable within the user interface.

### Claim 2 (depends on 1)

The method of claim 1, wherein the variation is a multi-dimensional variation.

### Claim 3 (depends on 1)

The method of claim 1, wherein the variation is a single dimensional variation.

### Claim 4 (depends on 1)

The method of claim 1, wherein the variation is also included in the one of the multiple defined categories.

### Claim 5 (depends on 1)

The method of claim 1, wherein the user interface further displays a fourth value for a third variation attribute.

### Claim 6 (depends on 1)

The method of claim 1, wherein the user interface further displays a fourth value for a third item attribute.

### Claim 7 (depends on 1)

The method of claim 1, wherein the standardized data includes metadata for each data item included in the standardized data.

### Claim 8 (depends on 1)

The method of claim 1, wherein the multiple defined categories include a first category that commonly describes multiple different items included in the plurality of items, and wherein a number of attribute types that are associated with the first category exceeds 20 attribute types.

### Claim 9 (depends on 1)

The method of claim 1, wherein the non-standardized data includes catalog data.

### Claim 10 (depends on 1)

The method of claim 1, wherein the non-standardized data further includes label data for an item included among the plurality of items, and wherein the label data is obtained from a second domain.

### Claim 11

A computer system comprising:
a processor system; and
a storage system that stores instructions that are executable by the processor system to cause the computer system to:
receive data comprising a first type of data and a second type of data, the first and second types of data being obtained from a common domain;
generate standardized data by converting a format of the received data into a standardized format, wherein:
the standardized data includes a hierarchy of categories into which various portions of the standardized data are categorized, and
each of the categories is associated with a corresponding set of attribute types that describe attributes for said each category;
include the standardized data within a data model, wherein the standardized data is made accessible to an application programming interface (API), including a variations API;
receive, via the variations API, a user query targeting an item included in one of the multiple defined categories;
cause the variations API to use the standardized data to identify the item;
cause the variations API to use the standardized data to identify a variation of the item, wherein identifying the variation includes:
determining a first value for a first item attribute for the item and a second value for a second item attribute for the item;
identifying the variation by using the first value for a first variation attribute for the variation, wherein the first variation attribute corresponds to the first item attribute; and
further identifying the variation by using a third value, which is different from the second value, for a second variation attribute for the variation, wherein the second variation attribute corresponds to the second item attribute such that the variation is within a threshold level of similarity to the item and such that the variation is different than the item;
simultaneously displaying the first value with the third value on a user interface;
causing the first value to be selectable within the user interface; and
causing the third value to be selectable within the user interface.

### Claim 12 (depends on 11)

The computer system of claim 11, wherein the received data further includes review data.

### Claim 13 (depends on 11)

The computer system of claim 11, wherein the first type of data describes a plurality of items, and wherein the standardized data includes a category identification (ID) linked to a group of the items that share one or more common characteristics.

### Claim 14 (depends on 11)

The computer system of claim 11, wherein the standardized data is made accessible to the API via an identification (ID) key.

### Claim 15 (depends on 14)

The computer system of claim 14, wherein the ID key is one of an ID key for a single item or an ID key for a particular category of multiple items.

### Claim 16 (depends on 11)

The computer system of claim 11, wherein the first type of data describes a plurality of items that are included in a catalog.

### Claim 17

A method comprising:
receiving data comprising information describing a plurality of items and customer information, wherein the received data is obtained from a first domain;
generating standardized data by converting a format of the received data into a standardized format, wherein:
the standardized data is organized into a hierarchy of multiple categories, and
each of the multiple categories is associated with a corresponding set of attribute types that describe attributes for said each category;
including the standardized data within a data model, wherein the standardized data is made accessible to an application programming interface (API), including a variations API;
receiving, via the variations API, a user query targeting an item included in one of the multiple defined categories;
causing the variations API to use the standardized data to identify the item;
causing the variations API to use the standardized data to identify a variation of the item, wherein identifying the variation includes:
determining a first value for a first item attribute for the item and a second value for a second item attribute for the item;
identifying the variation by using the first value for a first variation attribute for the variation, wherein the first variation attribute corresponds to the first item attribute; and
further identifying the variation by using a third value, which is different from the second value, for a second variation attribute for the variation, wherein the second variation attribute corresponds to the second item attribute such that the variation is within a threshold level of similarity to the item and such that the variation is different than the item;
simultaneously displaying the first value with the third value on a user interface;
causing the first value to be selectable within the user interface; and
causing the third value to be selectable within the user interface.

### Claim 18 (depends on 17)

The method of claim 17, wherein the method is performed by a service that includes at least one of a machine learning (ML) algorithm or a generative pre-trained transformer (GPT).

### Claim 19 (depends on 18)

The method of claim 18, wherein the service is a cloud service.

### Claim 20 (depends on 17)

The method of claim 17, wherein the plurality of items are items included in a catalog items.
