Optimization of Human-Computer Interaction Collaborative Translation System for AI-Oriented Knowledge Management

With the continuous progress of artificial intelligence (AI) technology, the field of knowledge management is facing new opportunities and challenges. The purpose of this study is to improve the efficiency and user experience of collaborative translation system by optimizing the design of human-computer interaction interface and then promote knowledge sharing and transformation in a multilingual environment. This paper uses principal component analysis to extract features, uses genetic algorithm to select features, and then introduces enhanced scalar calculation algorithm (ESCA) to improve system performance. The experimental results show that compared with traditional methods, the ESCA method proposed in this study shows significant advantages in key indicators such as accuracy and calculation time; the accuracy is as high as 98%. In addition, this paper provided new tools and support for knowledge management. The research not only opens up a new way for HCI interface optimization, but also contributes to the development of AI-driven knowledge management system.