Machine Learning Models for Product Attribute Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for predicting attributes of products, such as ingredients, colors, and text on packaging, are often time-consuming and complex.
Innovation Solution
A system and method using machine learning models to determine attributes of products by inputting financial characteristics and properties of sample products, allowing for the production of products with desired attributes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to predict product attributes, then measurement precision can be achieved, but time consumption and complexity increase significantly
Solution Approach 1:
The patent replaces conventional mechanical/manual methods of attribute prediction with a machine learning-based computational system. The machine learning model automatically processes product data and predicts attributes without requiring manual analysis, thereby reducing time consumption while maintaining prediction accuracy.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between product data and attribute prediction results. This intermediary system automatically processes input data and generates predictions, eliminating the need for direct human analysis and significantly reducing the time required while preserving measurement precision.
2Measurement precision
If conventional methods are used to predict product attributes, then measurement precision can be achieved, but device complexity increases
Solution Approach 1:
The patent replaces complex conventional prediction systems with a streamlined machine learning-based system. The machine learning model consolidates multiple prediction functions into a single computational framework, reducing overall system complexity while maintaining or improving attribute prediction accuracy.
3Productivity
If machine learning models are used to determine product attributes, then productivity increases, but device complexity increases
Solution Approach 1:
The patent replaces manual product development processes with an automated machine learning system. This substitution dramatically increases productivity by automatically determining product attributes from input data, while the modular architecture of the machine learning model keeps system complexity manageable through standardized computational components.
Data Source
AI summary
In one embodiment, the present disclosure is directed to a method for producing a product. For each sample chemical composition of sample chemical compositions, the method inputs into a first model chemoinformatic properties of ingredients of the sample chemical composition, and a value of a property of the sample chemical composition. A new chemical composition is determined via the first model based thereon. The method inputs into a second model, for each sample product of sample products, a value for one or more visual properties of a packaging of the sample product, and one or more characteristics of the new chemical composition. A value is determined for each of the visual properties via the second model. A new product is produced comprising the new chemical composition and packaging comprising the values.