Enhancing Efficacy in Problem Solving and Data Protection through the Integration of Function-Oriented Search and ChatGPT

Abstract

As a Large Language Models, ChatGPT's ability to learn from big data and respond to diverse user queries makes it a powerful tool for R&D. Despite the potential benefits of using ChatGPT, there exist the vulnerabilities for users' protection. As a countermeasure of this issue, this study proposes to utilize Function-Oriented Search (FOS), a particular methodology based on TRIZ (Theory of Inventive Problem Solving). FOS projects an innovative approach to problem solving by abstracting the essence of a problem by defining it functionally and generating solutions from different areas where the function can best be performed. When using ChatGPT, thus, this study argues that FOS would ensure proper results while mitigating the exposure of sensitive information. Although it requires specialized training and sufficient hands-on experiences to implement FOS in order to select and conceptualize problem focus areas, this study suggests that ChatGPT can be an efficient tool for developers who adopt FOS. Not only for experts on FOS, but also for those who are not familiar with FOS, the use of ChatGPT enables to conduct efficient and comprehensive problem explorations and devise solutions. By demonstrating the application of FOS in practical cases, this study findings supported the potential benefits of ChatGPT as a dynamic collaborator in problem solving. The findings also showed that FOS can generate suitable solutions of using ChatGPT while maintaining the protection of personal or corporate information. This study would contribute to the emerging field of AI by confirming the possible synergy with TRIZ's FOS and ChatGPT, a Large Language Model.