Implementing user input and derived image and text from engineering drawings to map manufacturing requirements to a subset of manufacturers via natural language agent programs
Techniques for computer science, data science, data analytics, computer software, algorithmic analysis, and networked technologies for sourcing, procurement, manufacturing, and supply chain management in small-to-medium manufacturing (“SMM”) industries that involve processes whereby implementing user input and extracted image and text from engineering drawings may be used to map manufacturing requirements to a subset of manufacturers via natural language agent programs. More specifically, natural language agent programs may be implemented to apply input and extracted image and text from engineering drawings to a large language model (“LLM”). An example method may include receiving a user input including data representing requirements to manufacture a physical structure, concatenating an engineering drawing summary data, a shoptype description, and estimated part size instruction data to combine the at least two of the engineering drawing summary data, the shoptype description, and the estimated part size instruction data to generate a subset (e.g., a list) of qualified manufacturers (e.g., SMMs).
1. A method comprising:
receiving either a first user input or a second user input, or both, as an input including data representing requirements to manufacture a physical structure via an electronic network at a computing platform including one or more processors and one or more data stores;
concatenating at least two of engineering drawing summary data, a shoptype description, and estimated part size instruction data to combine the at least two of the engineering drawing summary data, the shoptype description, and the estimated part size instruction data;
generating an automated text query based on a combination of the at least two of the engineering drawing summary data, the shoptype description, and the estimated part size instruction data;
implementing a retrieval-augmented generation (“RAG”) algorithmic process to configure a manufacturing-specific prompt based on either the first user input or the second user input to access a proprietary database;
transmitting the first user input and the automated text query to a large language model as a function of the manufacturing-specific prompt; and
generating an output of the large language model including data representing a list of entities enabled to manufacture the physical structure in accordance with the requirements.
2. The method of claim 1 further receiving the first user input comprises:
receiving the data representing the requirements to manufacture the physical structure in a natural language including strings of one or more of text including alpha-numeric characters, wherein the strings comprise one or more of sentences, paragraphs, and electronic documents.
3. The method of claim 1 wherein either the first user input or the second user input, or both, comprises:
derived text data and derived image data of a digitized copy of a physical 2D engineering drawing.
4. The method of claim 1 further comprises:
receiving a second user input associated with the data representing the requirements to manufacture the physical structure, wherein the second user input is a digitized copy of a physical 2D engineering drawing depicting the physical structure.
5. The method of claim 4 further comprises:
analyzing the digitized copy of a physical 2D engineering drawing; and
deriving text including alpha-numeric characters to form derived text and derived image-based profile attributes to form derived image-based profile attributes.
6. The method of claim 1 wherein at least a portion of the second input is applied to the large language model, wherein the large language model includes a vision language model (“VLM”).
7. The method of claim 1 further comprises:
analyzing selection data to generate a shoptype description and a shoptype,
wherein the selection data is based on derived text from a digitized copy of a physical 2D engineering drawing.
8. The method of claim 1 further comprises:
estimate a size of the physical structure based on derived text and derived image-based profile attributes from a digitized copy of a physical 2D engineering drawing to form the estimated part size instruction data.
9. The method of claim 1 further comprises:
applying manufacturing rule data to a shoptype based on an estimated size of the physical structure; and
generating estimated part size instruction data as a natural language including strings of one or more of text including alpha-numeric characters.
10. The method of claim 9 wherein the manufacturing rule data comprise criteria to generate the list of entities enabled to manufacture the physical structure, the manufacturing rule data being expressed in a natural language.
11. The method of claim 1 further comprises:
applying manufacturing rule data to a shoptype based on an estimated size of the physical structure; and
generating the estimated part size instruction data as a natural language.
12. The method of claim 1 wherein the list of entities includes manufacturers.
13. The method of claim 12 wherein the list of entities includes a ranked subset of the manufacturers, which are ranked at least as a function of a shoptype and the requirements.
14. The method of claim 1 further comprising:
applying the input data and the automated text query to an agent program configured to interoperate with the large language model.
15. A system comprising:
a data store configured to store executable instructions; and
a processor configured to implement the executable instructions configured to:
receive a user input including data representing requirements to manufacture a physical structure via an electronic network at a computing platform including one or more processors and one or more data stores;
concatenate at least two of engineering drawing summary data, a shoptype description, and estimated part size instruction data to combine the at least two of the engineering drawing summary data, the shoptype description, and the estimated part size instruction data;
generate an automated text query based on a combination of the at least two of the engineering drawing summary data, the shoptype description, and the estimated part size instruction data;
implement a retrieval-augmented generation (“RAG”) algorithmic process to configure a manufacturing-specific prompt based on either the first user input or the second user input to access a proprietary database;
transmit the user input and the automated text query to a large language model as a function of the manufacturing-specific prompt; and
generate an output of the large language model including data representing a list of entities enabled to manufacture the physical structure in accordance with the requirements.
16. The system of claim 15 wherein the processor is further configured to:
receive the user input including derived text data and derived image data of a digitized copy of a physical 2D engineering drawing depicting the physical structure.
17. The system of claim 16 wherein the processor configured is further configured to:
receive another user input associated with the data representing the requirements to manufacture the physical structure, wherein the another user input is a digitized copy of a physical 2D engineering drawing depicting the physical structure;
analyze the digitized copy of a physical 2D engineering drawing; and
derive text including alpha-numeric characters to form derived text and derived image-based profile attributes to form derived image-based profile attributes.
18. The system of claim 15 wherein the processor is further configured to:
apply the input data and the automated text query as natural language to an agent program configured to interoperate with the large language model, wherein the agent program is a manufacturing-specific chatbot configured to accept natural language inputs to interoperate with the large language model.
19. A non-transitory computer readable medium having one or more computer program instructions configured to perform a method, the method comprising:
receiving a user input including data representing requirements to manufacture a physical structure via an electronic network at a computing platform including one or more processors and one or more data stores;
concatenating at least two of engineering drawing summary data, a shoptype description, and estimated part size instruction data to combine the at least two of the engineering drawing summary data, the shoptype description, and the estimated part size instruction data;
generating an automated text query based on a combination of the at least two of the engineering drawing summary data, the shoptype description, and the estimated part size instruction data;
implementing a retrieval-augmented generation (“RAG”) algorithmic process to configure a manufacturing-specific prompt based on either the first user input or the second user input to access a proprietary database;
transmitting the user input and the automated text query to a large language model as a function of the manufacturing-specific prompt; and
generating an output of the large language model including data representing a list of entities enabled to manufacture the physical structure in accordance with the requirements.
20. The method of claim 19 further comprises:
receiving the user input as derived text data and derived image data of a digitized copy of a physical 2D engineering drawing, or
receiving another user input associated with the data representing the requirements to manufacture the physical structure, wherein the another user input is a digitized copy of a physical 2D engineering drawing depicting the physical structure.