Scholarlink

The Main Parameter of Value (MPV) is a vital factor in TRIZ’ Trend of Engineering System Evolution (TESE), helping to understand what customers like in specific products. The Trend of S-Curve Evolution in TESE shows how the MPV changes over time, guiding decisions for innovating products. In the current industrial landscape, the surge in industrial revolution is reshaping consumer choices towards sustainable products. Manufacturers vie for market dominance, continually seeking insights into customers’ preferences regarding MPVs for design forecasts and sustainable innovations. However, existing MPV analyses are primarily manual, lacking a computational model for predicting future MPVs. This study addresses this gap by proposing an AI-driven computational model for identifying potential MPVs. Utilizing the Python programming, the methodology incorporates Natural Language Processing (NLP) for feature extraction and Machine Learning algorithms, including Naïve Bayes and Linear Regression Classifier to achieve accurate means of predicting and understanding MPVs. The anticipated outcome is an automated S-Curve analysis derived from AI-analyzed MPV data. This visual representation of evolving MPVs over time is expected to empower manufacturers with insights for strategic decision-making and innovation in sustainable product development, fostering a competitive edge in the market.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Analytical Model for Sustainable Product Ideation Based on Main Parameter Values and Social Network Data

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mostafa Ghane,
  • Denis Cavallucci

摘要

The Main Parameter of Value (MPV) is a vital factor in TRIZ’ Trend of Engineering System Evolution (TESE), helping to understand what customers like in specific products. The Trend of S-Curve Evolution in TESE shows how the MPV changes over time, guiding decisions for innovating products. In the current industrial landscape, the surge in industrial revolution is reshaping consumer choices towards sustainable products. Manufacturers vie for market dominance, continually seeking insights into customers’ preferences regarding MPVs for design forecasts and sustainable innovations. However, existing MPV analyses are primarily manual, lacking a computational model for predicting future MPVs. This study addresses this gap by proposing an AI-driven computational model for identifying potential MPVs. Utilizing the Python programming, the methodology incorporates Natural Language Processing (NLP) for feature extraction and Machine Learning algorithms, including Naïve Bayes and Linear Regression Classifier to achieve accurate means of predicting and understanding MPVs. The anticipated outcome is an automated S-Curve analysis derived from AI-analyzed MPV data. This visual representation of evolving MPVs over time is expected to empower manufacturers with insights for strategic decision-making and innovation in sustainable product development, fostering a competitive edge in the market.