Research on dynamic user profile and personalized resource recommendation mechanism of libraries based on crowd sensing

With the development of new generation of artificial intelligence (AI), the advancement of crowd sensing technology has been strongly promoted. However, this technology has not yet been applied to library knowledge services. For the first time, this paper introduces the concept of crowd sensing into a library knowledge service platform, and designs and develops a crowd sensing system oriented toward smart learning environments. This system takes mobile devices owned by large numbers of ordinary users as sensing units, senses and distributes tasks via the mobile Internet, acquires and analyzes multi-source data, and integrates and models user data through machine learning algorithms. On this basis, a dynamic user profile based on crowd sensing is constructed and implemented, and further, a mechanism and method for personalized resource recommendation are established. This enables the personalized recommendation of library learning resources, which has been practically applied in the AI-based smart knowledge service platform. Finally, the System Usability Scale (SUS) is adopted to evaluate the usability of the crowd sensing-based personalized resource recommendation system. The research results show that the system has good usability. It also designs an optimized model for knowledge services, and further analyzes the research implications and prospects from three perspectives: users, builders, and managers. This study pioneers the innovative application of crowd sensing technology in library knowledge services, provides new methods, models, and perspectives for research on knowledge acquisition and knowledge services of knowledge service platforms, and expands the theoretical and application system of AI-driven innovation in smart libraries.