AI-Generated BOM and Process Planning From Product Documents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating a bill of materials (BOM) and bill of processes (BOP) are manual, time-consuming, and require deep knowledge of manufacturing processes, especially in early product development stages where detailed information is lacking, hindering efficient cost and sustainability value calculations.
Innovation Solution
A system utilizing natural language processing and reinforcement learning to generate a BOM and BOP automatically, allowing for semi-automatic creation through a latent representation of product documents, user interaction for refinement, and optimization based on key performance indicators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual methods are used to create bill of materials and bill of processes, then accuracy and reliability can be maintained through expert knowledge, but time consumption and complexity increase significantly
Solution Approach 1:
The system performs preliminary actions by pre-processing product documents and specifications to extract relevant information before the actual BOM/BOP generation. This includes parsing product descriptions, identifying components, and preparing manufacturing process data in advance, which reduces the time required for manual creation while maintaining accuracy through structured data preparation.
Solution Approach 2:
The patent introduces an intermediary system that acts as a bridge between product documentation and the BOM/BOP generation process. This intermediary layer automatically extracts and structures information from various document formats, transforming unstructured or semi-structured data into organized BOM and BOP data, thereby reducing manual effort while preserving accuracy through systematic information processing.
2Reliability
If manual creation of BOM and BOP is performed, then specialized knowledge of manufacturing processes can be applied, but device complexity and ease of operation deteriorate
Solution Approach 1:
The system enables self-service by automatically generating BOM and BOP data from product documents without requiring manual intervention from experts. The automated extraction and structuring processes handle the complexity internally, allowing users to obtain high-quality manufacturing process definitions without needing deep specialized knowledge or navigating complex manual creation procedures.
Solution Approach 2:
The patent replaces the manual mechanical process of expert-driven BOM/BOP creation with an automated computational system. Instead of relying on human experts to manually define manufacturing processes, the system uses algorithmic processing to extract and structure manufacturing information, thereby reducing the perceived complexity for users while maintaining or improving data quality through consistent automated application of manufacturing knowledge.
3Loss of information
If detailed manual input is required for BOM creation, then completeness of product information can be ensured, but productivity and speed of calculation decrease
Solution Approach 1:
The system performs preliminary information extraction and validation from product documents before the main calculation process. By pre-processing documentation to identify and extract all relevant product data, components, and specifications in advance, the system ensures information completeness is achieved during the preparation phase, allowing the subsequent cost and sustainability calculations to proceed rapidly without requiring detailed manual input during the calculation itself.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
For generating a bill of materials and a corresponding bill of processes for a product, a natural language processing module (NLP-M) maps at least one document specifying a product into a latent representation (LR), which is an embedding in latent space. A bill of materials generator (BOM-G) receives the latent representation (LR) as input and generates a bill of materials (BOM-TR) for the product. A user interface (Ul) detects user interactions with the generated bill of materials (BOM-TR) and creates a curated bill of materials (BOM-C) depending on the user interactions. A bill of processes generator (BOP-G) receives the latent representation (LR) and the curated bill of materials (BOM-C) as input and constructs a bill of processes (BOP-DAG) for the product. The method and system, or at least some of their embodiments, provide semiautomatic generation of the bill of materials and bill of processes for a product, using an AI engine. Compared to manually setting up a bill of materials and/or bill of processes within a software-system, the approach of using AI for generating this information can significantly speed up the process of calculating costs and sustainability values of a product. In this way the time from request for quotation until submitting the actual offer can be lowered significantly.