Granted Patent B2

US 12,265,764 · App. 18/907,937 · Granted Apr 1, 2025

Inventors: Maor Farid (Rosh HaAyin, IL); Mordechai Moravia (Rosh HaAyin, IL)

Assignee: SCINTIUM LTD

G06F30/27G06F40/20

Abstract

Claims (71)

1. A computerized method for generating a 3D Computer-Aided Design (CAD), the method comprising:

receiving an input comprising requirements for a new design;

processing the input to generate a CAD design using a trained Artificial Intelligence (AI) model, wherein the CAD design is an assembly of at least two separate components, wherein each of the components is selected from a sub-assembly and a part, comprising at least one known component, wherein processing the input further comprises:

generating an embedding vector corresponding to an ideal component to be included in the CAD design;

accessing a vector database (Vector DB) storing a plurality of vectors, wherein each vector represents a known component used in designs;

searching the Vector DB to identify a matching vector to the embedding vector;

retrieving a known component corresponding to the matching vectors; and

generating the CAD design using the retrieved known component; and

outputting the CAD design.

2. The method of claim 1 , wherein the input comprises at least an input modality of a CAD design and requirements pertaining to the CAD design.

3. The method of claim 1 , wherein the input comprises a plurality of input modalities and requirements pertaining to the input modalities, and wherein prior to processing the input modalities, the method further comprising:

fusing the input modalities to generate a fused input using Large Language Model (LLM); and

processing the fused input.

4. The method of claim 3 , wherein each of the input modalities is selected from a group comprising: a textual description, a sketch, a CAD design, a 2D illustration image, and a technical specification.

5. The method of claim 1 , further comprising enriching the input with targeted organization-specific data, and processing the enriched input to generate the CAD design.

6. The method of claim 5 , wherein the targeted organization-specific data comprises an organization's Product Lifecycle Management (PLM) system, including CAD data stored within the PLM system and an organization's documents.

7. The method of claim 1 , wherein at least one of the vectors stored in the Vector DB represents a known component obtained from targeted organization-specific data.

8. The method of claim 1 , wherein processing the input further comprises:

enriching the input based on at least responses to requests for additional information based on pre-trained engineering requirements or data based on responses to user-initiated questions; and

processing the enriched input to generate the CAD design.

9. The method of claim 1 , wherein the outputted CAD design is compliant with Design for Manufacturing and Automation (DFMA) standards.

10. The method of claim 1 , wherein the outputted CAD design includes technical specification of the CAD design.

11. The method of claim 1 , wherein the outputted CAD design includes technical specification of at least one subcomponent of the CAD design.

12. The method of claim 1 , further comprising:

repeatedly:

receiving at least one request for a change to the outputted CAD design;

processing the modification request to generate a revised CAD design; and

outputting the revised CAD design.

13. A computerized method for training an artificial intelligence (AI) model to generate a 3D Computer-Aided Design (CAD), the method comprising:

obtaining input data comprising at least requirements for a new design; and

training the AI model to interpret the input data and generate a corresponding CAD design, wherein the CAD design is an assembly of at least two separate components, wherein at least one of the components is a known component,

wherein training the AI model further comprises training the AI model to:

generate an embedding vector corresponding to an ideal component to be included in the CAD design;

access a vector database storing a plurality of vectors, wherein each vector represents a known component used in designs;

search the vector database to identify a matching vector to the embedding vector;

retrieve a known component corresponding to the matching vectors; and

generate the CAD design using the retrieved known component.

14. The method of claim 13 , wherein each of the components is selected from a sub-assembly and a part.

15. The method of claim 13 , wherein the input comprises a plurality of input modalities, wherein the method further comprises:

prior to training the AI model, preprocessing the plurality of input modalities, using at least a Large Language Model (LLM), by:

generating embedding vectors for each of the modalities using vector embedding techniques; and

fusing the embedding vectors in various combinations of the modalities to create linked representations of the input data modalities; and

training the AI model to interpret the input data and the generated combination.

16. The method of claim 15 , wherein each of the input modalities is selected from a group comprising: a CAD design and requirements pertaining to the CAD design, a textual description, a sketch, a 2D illustration image, and a technical specification.

17. The method of claim 13 , further comprising enriching the input data with targeted organization-specific data.

18. The method of claim 17 , wherein enriching the input comprises integrating data from the organization's Product Lifecycle Management (PLM) system, including CAD data stored within the PLM system and the organization's documents.

19. The method of claim 17 , wherein training the AI model to identify and model the engineering constraints comprises masking some of the components during training and teaching the AI model to predict an appropriate component to place in the masked position.

20. The method of claim 13 , wherein training the AI model further comprises training the AI model to identify and model the engineering constraints between the different components.

21. The method of claim 13 , further comprising training the AI model to:

enrich the input based on at least responses to requests for additional information based on pre-trained engineering requirements or data based on responses to user-initiated questions; and

process the enriched input to generate the CAD design.

22. The method of claim 13 , wherein the AI model is trained to generate a corresponding CAD design compliant with Design for Manufacturing and Automation (DFMA) standards.

23. The method of claim 13 , wherein the AI model is trained to output technical specification of the outputted CAD design.

24. A computer system for generating a 3D Computer-Aided Design (CAD), the system comprising a processing circuitry being configured to:

receive an input comprising requirements for a new design;

process the input to generate a CAD design using a trained Artificial Intelligence (AI) model, wherein the CAD design is an assembly of at least two separate components, wherein each of the components is selected from a sub-assembly and a part, comprising at least one known component, wherein the processing circuitry being configured to process the input by:

generate an embedding vector corresponding to an ideal component to be included in the CAD design;

access a vector database (Vector DB) storing a plurality of vectors, wherein each vector represents a known component used in designs;

search the Vector DB to identify a matching vector to the embedding vector;

retrieve a known component corresponding to the matching vectors; and

generate the CAD design using the retrieved known component; and

output the CAD design.

25. A non-transitory computer readable storage medium tangibly embodying a program of instructions that, when executed by a computer, cause the computer to perform a computerized method for generating a 3D Computer-Aided Design (CAD), the method comprising:

receiving an input comprising requirements for a new design;

processing the input to generate a CAD design using a trained Artificial Intelligence (AI) model, wherein the CAD design is an assembly of at least two separate components, wherein each of the components is selected from a sub-assembly and a part, comprising at least one known component, wherein processing the input further comprises:

generating an embedding vector corresponding to an ideal component to be included in the CAD design;

accessing a vector database (Vector DB) storing a plurality of vectors, wherein each vector represents a known component used in designs;

searching the Vector DB to identify a matching vector to the embedding vector;

retrieving a known component corresponding to the matching vectors; and

generating the CAD design using the retrieved known component; and

outputting the CAD design.

Assignments (2)

Continuity (4)

References Cited (34)