# US 2025/0148310 A1 · Method for generating prediction model for supply lead time of parts

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

- Number: US 2025/0148310 A1
- Document ID: US20250148310A1
- Status: Published application
- Kind: A1
- Application number: 18/934,752
- Filed: 2024-11-01
- Published: 2025-05-08
- Earliest claimed: 2023-11-08
- Assignees: VMS Solutions Co. Ltd.
- Applicants: VMS Solutions Co. Ltd.
- Inventors: Seock Kyu YOO; Cherl Hong PARK; SungBum JUN; Chan Gyu LEE
- Web page: https://patentgrep.com/patent/US20250148310A1

## CPC

- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 30/0206: {Price or cost determination based on market factors}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

Provided is a method for generating a lead time prediction model including: receiving input data for a final part from a user, wherein the final part is composed of one or more component parts; obtaining a first data for each of the one or more component parts, wherein the first data includes at least price data and historical lead time data; performing preprocessing on the first data to generate second data; and generating a model for generating a predicted lead time for at least one of the final part and the one or more component parts by performing learning using the second data as a training dataset.

## Claims

### Claim 1

A method for generating a lead time prediction model, comprising:
receiving input data for a final part from a user, wherein the final part is composed of one or more component parts;
obtaining a first data for each of the one or more component parts, wherein the first data comprises at least price data and historical lead time data;
performing preprocessing on the first data to generate second data; and
generating a model for generating a predicted lead time for at least one of the final part and the one or more component parts by performing learning using the second data as a training dataset.

### Claim 2 (depends on 1)

The method of claim 1, wherein the performing preprocessing on the first data to generate second data, comprises:
generating the second data by combining the first data and arithmetic operators for each of the one or more component parts.

### Claim 3 (depends on 2)

The method of claim 2, wherein the generating the second data by combining the first data and arithmetic operators for each of the one or more component parts comprises:
removing combinations where operational units do not match from multiple combinations generated by combining the first data and arithmetic operators for each of the one or more component parts.

### Claim 4 (depends on 3)

The method of claim 3, wherein the removing combinations where the operational units do not match from the multiple combinations generated by combining the first data and arithmetic operators for each of the one or more component parts comprises:
removing, from combinations comprising addition or subtraction among the multiple combinations, combinations where the units of the data involved in addition or subtraction do not match.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
determining a Mean Square Error (MSE) improvement of the model for generating the predicted lead time; and
determining whether to retain the second data based on the MSE improvement.

### Claim 6 (depends on 5)

The method of claim 5, wherein the determining whether to retain the second data based on the MSE improvement comprises:
retaining the second data if the MSE improvement exceeds a reference value; and
removing the second data if the MSE improvement is less than or equal to the reference value.

### Claim 7 (depends on 6)

The method of claim 6, wherein the removing the second data if the MSE improvement is less than or equal to the reference value comprises:
removing the second data if the MSE improvement is less than or equal to the reference value, and generating third data using mutation and/or crossover operations; and
wherein the method further comprises performing learning using the third data as a training dataset.

### Claim 8 (depends on 1)

The method of claim 1, wherein the price data in the first data comprises at least one of current price and historical prices of the one or more component parts.

### Claim 9 (depends on 1)

The method of claim 1, wherein the obtaining the first data comprises:
obtaining the first data from a parts knowledge database (KDB).

### Claim 10

A non-transitory computer-readable recording medium, wherein the non-transitory computer-readable recording medium comprises computer-executable instructions, and
the instructions, when executed by a processor, perform operations comprising: receiving input data for a final part from a user, wherein the final part is composed of one or more component parts;
obtaining a first data for each of the one or more component parts, wherein the first data comprises at least historical price data and historical lead time data;
performing preprocessing on the first data to generate second data; and
generating a model for generating a predicted lead time for at least one of the final part and the one or more component parts by performing learning using the second data as a training dataset.
