CN-122024939-A - System, apparatus and method for material sub-graph model

Abstract

Systems, apparatuses, and methods for material sub-graph models are disclosed. The method may generate sub-graph using an Artificial Intelligence (AI) based sub-graph model of a material including decomposition of molecular structures of the material, and implement sub-graph modeling to extend the AI based model for large and/or complex molecules and enhance material property predictions. Aspects may relate to utilizing enhanced material property predictions to enhance overall performance of display-related products. For example, by using a material property prediction with higher accuracy for sub-graph modeling, a display device may be manufactured using materials that are considered to be most appropriate and/or efficient. The method may include generating a subgraph comprising molecular substructures of the material, and applying an AI-based model to the subgraph to generate a material property prediction based on the molecular substructures of the material.

Inventors

• Qu Shuhui
• Pu Zheyou
• CHENG QISEN
• LI ZHANGHUAN

Assignees

• 三星显示有限公司

Dates

Publication Date

20260512

Application Date

20251112

Priority Date

20250417

Claims (20)

1. 1. A method for a material sub-graph model, comprising: generating, by a processor, sub-graphs, each of the sub-graphs comprising a molecular sub-structure of a material; Applying, by the processor, an artificial intelligence based model to the subgraph to generate a material property prediction based on the molecular substructure of the material; Determining, by the processor, a function related to the material for production of a target device based on the material property prediction, and A signal is sent by the processor to a component to control the component to perform the function related to the material for the production of the target device.
2. 2. The method of claim 1, further comprising decomposing a molecular structure of the material into the molecular substructures.
3. 3. The method of claim 2, wherein the decomposing comprises breaking chemical bond decomposition having retrospective synthetic significance.
4. 4. The method of claim 1, further comprising generating an embedding of the sub-graph based on the sub-graph.
5. 5. The method of claim 4, wherein generating the embedding of the subgraph comprises processing the subgraph through a graph neural network.
6. 6. The method of claim 4, further comprising generating a sub-graph based on the embedding of the sub-graph.
7. 7. The method of claim 6, wherein the sub-graph includes nodes and edges.
8. 8. The method of claim 7, wherein each of the nodes corresponds to one of the subgraphs, and a value for each of the nodes corresponds to one of the embeddings of the subgraphs.
9. 9. The method of claim 8, wherein each of the edges represents a relationship between the subgraphs.
10. 10. The method of claim 9, further comprising generating an updated node embedding based on the sub-graph.
11. 11. The method of claim 10, wherein generating the updated node embedding comprises processing the sub-graph through a graph neural network.
12. 12. The method of claim 9, wherein the artificial intelligence based model analyzes the subgraph and models the relationship between the subgraphs.
13. 13. The method of claim 12, wherein the target device comprises an organic light emitting diode display device.
14. 14. The method of any one of claims 1 to 13, wherein the material property prediction is based on one or more of a physical property of the material, a chemical property of the material, a mechanical property of the material, and an optical property of the material.
15. 15. An apparatus for a material sub-graph model, comprising: one or more of the processors of the present invention, the one or more processors are configured to perform: generating sub-graphs, each of the sub-graphs comprising a molecular substructure of a material; Applying an artificial intelligence based model to the subgraph to generate a material property prediction based on the molecular substructure of the material; determining a function related to the material for production of the target device based on the material property prediction, and A signal is sent to a component to control the component to perform the function related to the material for the production of the target device.
16. 16. The apparatus of claim 15, wherein the one or more processors are further configured to perform decomposing a molecular structure of the material into the molecular substructures.
17. 17. The apparatus of claim 16, wherein the one or more processors are further configured to perform generating an embedding of the sub-graph based on the sub-graph.
18. 18. The apparatus of claim 17, wherein the one or more processors are further configured to perform generating a sub-graph based on the embedding of the sub-graph.
19. 19. The apparatus of claim 18, wherein the one or more processors are further configured to perform analyzing the sub-graph using the artificial intelligence based model and modeling relationships between the sub-graphs.
20. 20. A system for a material sub-graph model, comprising: Processing circuit, and A memory storing instructions that, when executed by the processing circuitry, cause the processing circuitry to perform: generating sub-graphs, each of the sub-graphs comprising a molecular substructure of a material; Applying an artificial intelligence based model to the subgraph to generate a material property prediction based on the molecular substructure of the material; determining a function related to the material for production of the target device based on the material property prediction, and A signal is sent to a component to control the component to perform the function related to the material for the production of the target device.

Description

System, apparatus and method for material sub-graph model Cross Reference to Related Applications The present application claims the benefit of priority from U.S. provisional application No. 63/719,527, filed 11/12 at 2024, and U.S. patent application No. 19/182,427, filed 4/17 at 2025, the disclosures of which are incorporated herein by reference in their entireties as if fully set forth herein. Technical Field Aspects of some embodiments of the present disclosure generally relate to machine learning and/or artificial intelligence. More particularly, the subject matter disclosed herein relates to determining material properties for displaying related products based on artificial intelligence. Background Material property predictions may involve evaluating physical, chemical, mechanical, and/or optical properties that may be used to display materials in related products. Thus, it may be desirable to utilize computational models (e.g., artificial intelligence based models) to generate material property predictions, which may then be used to display various aspects of the design and/or manufacture of the relevant product, including material selection, performance optimization, and innovations in display technology. The above information disclosed in this background section is for enhancement of understanding of the background of the present disclosure and, therefore, it may contain information that does not form the prior art. Disclosure of Invention The present disclosure relates generally to electronic devices. More particularly, the subject matter disclosed herein relates to determining material properties for display of related electronic devices based on artificial intelligence. Aspects of some embodiments of the present disclosure relate to material property prediction and/or analysis. For example, aspects of some embodiments of the present disclosure relate to improving accuracy and efficiency of material property predictions by utilizing artificial intelligence and/or material sub-graph models. Material property predictions may involve evaluating physical, chemical, mechanical, and/or optical properties that may be used to display materials in related products. Thus, it may be desirable to utilize computational models (e.g., artificial intelligence based models) to generate material property predictions, which may then be used to display various aspects of the design and/or manufacture of the relevant product, including material selection, performance optimization, and innovations in display technology. However, there may be problems associated with applying Artificial Intelligence (AI) technology to material property predictions in a manner that maintains the robustness and/or efficiency of AI and can be extended to relatively large sizes and complexities of molecular structures of materials that may be used to display related products. Aspects of some embodiments of the present disclosure relate to systems and methods for AI-based material subgraph modeling, including decomposition of molecular structures of materials, generation of subgraph patterns, and implementation of subgraph modeling in a manner that can extend AI-based models to large and/or complex molecules and enhance their expressive capabilities. Accordingly, the disclosed embodiments may improve the overall performance of display-related products by utilizing materials that are deemed most appropriate and/or effective. In some embodiments, a method for a material subgraph model includes generating, by a processor, subgraphs, each subgraph including a molecular substructure of a material, applying, by the processor, an AI-based model to the subgraph to generate a material property prediction based on the molecular substructure of the material, determining, by the processor, a function related to the material for production of a target device based on the material property prediction, and sending, by the processor, a signal to a component to control the component to perform the function related to the material for production of the target device. In some embodiments, the method may further include decomposing the molecular structure of the material into molecular substructures. In some embodiments, the decomposition may include breaking chemical Bonds (BRIC) decomposition with retrospective synthetic significance. In some embodiments, the method may further include generating an embedding of the subgraph based on the subgraph. In some embodiments, generating the embedding of the subgraph may include processing the subgraph through a graph neural network. In some embodiments, the method may further include generating the sub-graph pattern based on the embedding of the sub-graph. In some embodiments, the sub-graph may include nodes and edges. In some embodiments, each of the nodes corresponds to one of the subgraphs, and the value for each of the nodes corresponds to one of the embeddings of the subgraphs. In some embodiments, each of the