AI-Generated BOM and BOP from Product Specifications
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 for complex products lacking initial documentation, hindering efficient cost and sustainability value estimation during product development.
Innovation Solution
A semi-interactive AI-driven approach using natural language processing, user interaction, and reinforcement learning to generate and curate BOM and BOP, leveraging latent representations and directed acyclic graphs to automate the process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to generate bill of materials and bill of processes, then detailed accuracy can be achieved, but the process becomes extremely time-consuming and requires deep manufacturing knowledge
Solution Approach 1:
The patent introduces an AI model as an intermediary between the product specification and the BOM/BOP generation process. The AI model automatically generates bills of materials and bills of processes from product specifications, eliminating the need for manual creation while maintaining reasonable accuracy. This intermediary system handles the complex task of translating product requirements into detailed manufacturing breakdowns, significantly reducing time requirements.
Solution Approach 2:
The system enables self-service by allowing the AI model to autonomously generate BOM and BOP structures without requiring deep manufacturing expertise from users. The automated system performs the knowledge-intensive tasks of identifying materials, components, and manufacturing processes, making the tool accessible to users regardless of their manufacturing knowledge level while still producing detailed and accurate results.
2Measurement precision
If manual creation of BOM from scratch is performed for purchasing negotiations, then complete control over cost estimation is achieved, but the process requires creating all parts individually which is extremely labor-intensive
Solution Approach 1:
The AI model performs preliminary action by pre-generating bills of materials and bills of processes based on product specifications before purchasing negotiations begin. This pre-computation provides purchasing users with ready-to-use cost and sustainability value estimates, eliminating the need to create all parts individually during negotiations and significantly improving productivity while maintaining control over cost estimation.
3Measurement precision
If detailed knowledge of manufacturing techniques is required to set up BOP manually, then process accuracy is improved, but the barrier to entry increases and requires specialized expertise
Solution Approach 1:
The AI model performs self-service by automatically generating bills of processes from product specifications without requiring users to have deep manufacturing knowledge. The system independently identifies appropriate manufacturing processes, operations, and parameters, making the tool easy to operate for users regardless of their expertise level while still producing accurate process definitions.
Solution Approach 2:
The patent replaces the mechanical system of manual knowledge-based process definition with an AI-based intelligent system. Instead of requiring users to manually specify manufacturing processes based on their expertise, the AI model automatically determines appropriate processes through pattern recognition and learning from training data, substituting human expertise with automated intelligence.
4Measurement precision
If existing AI solutions are used that require 3D CAD or JT files, then manufacturing-specific accuracy is improved, but the applicability to early design phases with only natural language specifications is lost
Solution Approach 1:
The patent implements universality by creating an AI model that can handle multiple types of input formats including natural language specifications, 3D CAD files, and JT files. This multi-functional capability allows the system to be applied across different product development phases, from early conceptual design with text descriptions to later detailed design with 3D models, maintaining accuracy while significantly expanding adaptability.
Data Source
AI summary
For generating a bill of materials and a corresponding bill of processes for a product, a natural language processing module maps at least one document specifying a product into a latent representation, which is an embedding in latent space. A bill of materials generator receives the latent representation as input and generates a bill of materials for the product. A user interface detects user interactions with the generated bill of materials and creates a curated bill of materials depending on the user interactions. A bill of processes generator receives the latent representation and the curated bill of materials as input and constructs a bill of processes for the product. The method and system, or at least some of their embodiments, provide semi-automatic 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.