# US 2025/0166742 A1 · Virtual material design service framework for developing material for secondary battery based on microservice architecture and operating method thereof

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

- Number: US 2025/0166742 A1
- Document ID: US20250166742A1
- Status: Published application
- Kind: A1
- Application number: 18/656,960
- Filed: 2024-05-07
- Published: 2025-05-22
- Earliest claimed: 2023-11-16
- Assignees: Korea Electronics Technology Institute
- Applicants: Korea Electronics Technology Institute
- Inventors: Sang Yub LEE; Inpyo CHO; Jaekyu LEE
- Web page: https://patentgrep.com/patent/US20250166742A1

## CPC

- G16C 60/00: Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
- G06V 10/82: using neural networks
- G16C 20/30: Prediction of properties of chemical compounds, compositions or mixtures
- G16C 20/70: Machine learning, data mining or chemometrics
- G16C 20/90: Programming languages; Computing architectures; Database systems; Data warehousing
- G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Proposed is a virtual material design service framework system for developing a material for a secondary battery based on a microservice architecture. The system may include a user interface unit receiving information on a new material having at least one structure of a molecular structure, a microstructure, and a cell structure, an experiment database unit storing experiment data information corresponding to the information on the new material, and a simulation unit generating a simulation model by performing simulations on the received information on the new material. The system may also include a data modeling unit generating a data model based on the experiment data information, a combination modeling unit combining the simulation model and the data model according to a combination modeling scheme, and an artificial intelligence service unit converting the combination model into an image and deriving a candidate material based on a predetermined image recognition scheme.

## Claims

### Claim 1

A virtual material design service framework system for developing a material for a secondary battery based on a microservice architecture, the virtual material design service framework system comprising:
a user interface configured to receive information on a new material having at least one structure of a molecular structure, a microstructure, and a cell structure;
an experiment database configured to store experiment data information corresponding to the information on the new material;
a simulation processor configured to generate a simulation model by performing simulations on the received information on the new material;
a data modeling processor configured to generate a data model based on the experiment data information;
a combination modeling processor configured to combine the simulation model and the data model according to a combination modeling scheme; and
an artificial intelligence service processor configured to convert the combination model into an image and to derive a candidate material based on a predetermined image recognition scheme.

### Claim 2 (depends on 1)

The virtual material design service framework system of claim 1, wherein the user interface, the experiment database processor, the simulation processor, and the data modeling processor are configured to be managed through an application processor.

### Claim 3 (depends on 1)

The virtual material design service framework system of claim 1, wherein:
the artificial intelligence service processor is configured to train a predetermined artificial intelligence model for deriving the candidate material through the image recognition scheme, and
the artificial intelligence model is configured to be transmitted to an external cloud server through an infrastructure communication interface connected to the artificial intelligence service processor.

### Claim 4 (depends on 1)

The virtual material design service framework system of claim 1, wherein the simulation model, the data model, the combination model, the image, and the candidate material corresponding to each of the molecular structure, the microstructure, and the cell structure are configured to be checked in parallel.

### Claim 5 (depends on 1)

The virtual material design service framework system of claim 1, wherein the artificial intelligence service processor is configured to:
determine whether information on a candidate material corresponding to the molecular structure is suitable when a candidate material corresponding to the microstructure is generated, and
determine whether information on the candidate material corresponding to the microstructure is suitable when a candidate material corresponding to the cell structure is generated.

### Claim 6 (depends on 1)

The virtual material design service framework system of claim 1, wherein the artificial intelligence service processor comprises:
a first artificial intelligence model configured to predict a physical property based on an image of the molecular structure by the combination model,
a second artificial intelligence model configured to predict a structure based on an image of the microstructure by the combination model, and
a third artificial intelligence model configured to predict performance deterioration based on an image of the cell structure by the combination model.

### Claim 7

An operating method of a virtual material design service framework for developing a material for a secondary battery based on a microservice architecture, the operating method comprising:
receiving information on a new material having at least one structure of a molecular structure, a microstructure, and a cell structure;
generating a simulation model by performing simulations on the received information on the new material;
generating a data model based on experiment data information corresponding to the information on the new material;
generating a combination model by combining the simulation model and the data model according to a combination modeling scheme; and
converting the combination model into an image and deriving a candidate material through a pre-trained artificial intelligence model to which a predetermined image recognition scheme has been applied.

### Claim 8 (depends on 7)

The operating method of claim 7, wherein the simulation model, the data model, the combination model, the image, and the candidate material corresponding to each of the molecular structure, the microstructure, and the cell structure are checked in parallel.

### Claim 9 (depends on 7)

The operating method of claim 7, wherein deriving the candidate material through the pre-trained artificial intelligence model comprises:
determining whether information on a candidate material corresponding to the molecular structure is suitable when a candidate material corresponding to the microstructure is generated, and
determining whether information on the candidate material corresponding to the microstructure is suitable when a candidate material corresponding to the cell structure is generated.

### Claim 10 (depends on 7)

The operating method of claim 7, wherein deriving the candidate material through the pre-trained artificial intelligence model comprises deriving the candidate material based on a first artificial intelligence model for predicting a physical property based on an image of the molecular structure by the combination model, a second artificial intelligence model for predicting a structure based on an image of the microstructure by the combination model, and a third artificial intelligence model for predicting performance deterioration based on an image of the cell structure by the combination model.
