Answers are grounded in this paper and cite their sources.
Intelligent knowledge management systems face significant challenges in accurately modeling dynamic user knowledge state evolution and planning optimal acquisition paths. Existing approaches rely on static inventories, ignore knowledge forgetting, and use myopic greedy strategies, causing poor user experience and high cognitive load. From a cognitive knowledge management (cognitive KM) perspective, the authors propose a framework that integrates dynamic state evolution with global path optimization. Using multisource interaction logs, they extract latent knowledge potential and build a dynamic tracing model incorporating a forgetting mechanism. Interventions are modeled as a Markov decision process (MDP), and a reward function with a cognitive gap penalty optimizes long-term knowledge acquisition paths. Experimental results show that the framework reduces prediction errors and generates personalized sequences with balanced cognitive load, offering a feasible reference for intelligent knowledge service systems.
No takes yet. Share an insight, caveat, or question.
Yonggang Yang (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: