Claims:We Claim:
1. A method of generating a three-dimensional (3D) training content, the method comprising:
classifying, by a 3D content generation system, a 3D model, based on a feature set associated with one or more objects associated with the 3D model by using a pre-trained Machine Learning (ML) model;
assigning, by the 3D content generation system, a class and at least one tag to the one or more objects based on the pre-trained ML model;
assigning, by the 3D content generation system, one or more functionalities to the one or more objects based on the at least one tag assigned to the one or more objects; and
creating, by the 3D content generation system, the 3D training content for the 3D model by using the one or more objects in the 3D model assigned with the at least one tag and the one or more functionalities.

2. The method as claimed in claim 1, wherein classifying the 3D model further comprises:
parsing the 3D model to determine the one or more objects in the 3D model;
extracting the feature set for the one or more objects in the 3D model; and
determining the class and the at least one tag for the one or more objects in the 3D model based on the feature set comparison for the one or more objects by the pre-trained ML model.

3. The method as claimed in claim 1, wherein the one or more objects in the 3D model comprises a parent object and one or more child objects in the 3D model.

4. The method as claimed in claim 1, further comprising training the pre-trained ML model by manually annotating the class and the at least one tag for the one or more objects in the 3D model.

5. The method as claimed in claim 1, wherein the pre-trained ML model comprises a deep neural network.

6. A 3D content generation system for generating a 3D training content, the 3D content generation system comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
classify a 3D model based on a feature set associated with one or more objects associated with the 3D model by using a pre-trained Machine Learning (ML) model;
assign a class and at least one tag to identify the one or more objects based on the pre-trained ML model;
assign one or more functionalities to the one or more objects based on the at least one tag assigned to the one or more objects; and
create the 3D training content for the 3D model by using the one or more objects in the 3D model assigned with the at least one tag and the one or more functionalities.

7. The system as claimed in claim 6, wherein the memory stores processor instructions, which, on execution, causes the processor to:
parse the 3D model to determine the one or more objects in the 3D model;
extract the feature set for the one or more objects in the 3D model; and
determine the class and the at least one tag for the one or more objects in the 3D model based on the feature set comparison for the one or more objects by the pre-trained ML model.

8. The system as claimed in claim 6, wherein the one or more objects in the 3D model comprises a parent object and one or more child objects in the 3D model.

9. The system as claimed in claim 6, wherein the processor is further configured to train the pre-trained ML model by manually annotating the class and the at least one tag for the one or more objects in the 3D model.

10. The system as claimed in claim 6, wherein the pre-trained ML model comprises a deep neural network.

Dated this 21st day of May, 2019

R Ramya Rao
Of K&S Partners
Agent for the Applicant
IN/PA-1607
, Description:Technical Field
[001] This disclosure relates generally to facilitate the generation of 3D training content, and more particularly to a system and a method of automated 3D training content generation.