Requirements-Driven ML Models for Technical Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a knowledge gap between domain experts who understand data requirements and those who can implement technical configurations for data models, leading to difficulties in selecting suitable product configurations, such as industrial trucks or pumps, due to the complexity of available options and the need for specialized knowledge.
Innovation Solution
The use of machine learning models trained with requirements and configuration data to recommend suitable configurations for configurable objects, allowing users to input their needs and receive tailored recommendations for product categories and specific solutions, including configuration options.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If domain experts attempt to implement technical configurations for data models, then they can satisfy data requirements, but they lack the necessary technical expertise to produce physical or virtual data models
Solution Approach 1:
The patent introduces an automated data modeling system that acts as an intermediary between domain experts and technical implementation. The system includes a data model generator that receives semantic data models from domain experts and automatically produces physical data models and virtual data models, eliminating the need for domain experts to directly perform complex technical modeling tasks.
Solution Approach 2:
The patent replaces the manual mechanical process of technical configuration with an automated computational system. The data model generator uses algorithms and processing rules to automatically transform semantic data models into implementable physical and virtual data models, substituting human technical expertise with automated intelligence.
2Measurement precision
If users work with agents or consultants to determine suitable product configurations, then they can obtain expert recommendations, but the coordination process becomes difficult and time consuming
Solution Approach 1:
The patent enables users to independently determine suitable product configurations through an automated recommendation system. Users input their requirements, and the system automatically processes this information through requirement analysis components and configuration determination algorithms to generate recommendations without requiring external agents or consultants.
Solution Approach 2:
The patent performs preliminary analysis of requirements and pre-determines suitable configurations before the user needs to make a decision. The system includes components that proactively analyze requirements, identify suitable product categories, and determine optimal configurations in advance, eliminating the need for iterative consultation processes.
3Adaptability or versatility
If multiple users are trained to recommend solutions in different product categories, then comprehensive product knowledge is available, but the system complexity and coordination requirements increase
Solution Approach 1:
The patent creates a universal recommendation system that can handle multiple product categories through a single automated platform. The system includes a product category identifier and configuration determination component that can process various types of products and requirements, replacing the need for multiple specialized human users with one multi-functional automated system.
Data Source
AI summary
Techniques and solutions are provided for obtaining a suggested configuration for a configurable object. Typically, a particular object and object configuration are recommended based on technical characteristics of the object. However, a user or process wishing to obtain a recommendation may be more familiar with their operational requirements. Disclosed techniques can include an overall solutions category containing solutions of different solutions category subtypes. Sets of requirements attributes and configuration (technical) attributes can be defined for the solutions category. In some cases, a first machine learning model is trained using input values for the requirements attributes and the configuration attributes, and is used to recommend a particular solution in response to a set of input requirement attribute values. Different machine learning models can be trained for the various solutions, including using the configuration attributes for a particular solution, and can be used to recommend a configuration of a selected/recommend solution.