A news service recommendation model for enterprise employees integrating behavioural analysis and sequential patterns

In modern corporate environments, employees' news access behaviours exhibit significant sequential patterns, leading to the emergence of various news recommendation methods based on sequential patterns. These methods leverage artificial intelligence (AI) technologies to deliver personalised news recommendations, promoting knowledge updates and skill enhancement, thereby improving work efficiency and corporate competitiveness. However, previous research primarily focused on the overall browsing sequence patterns, neglecting the influencing of interactions between employees and content (e.g., comments, shares) on their interest in information and future access decisions. To solve this issue, we propose an AI-driven model called behavioural analysis and sequential patterns-based news service recommendation (BS-NSR). This model integrates news browsing sequences, a weighting model, n-order additive Markov chains and collaborative filtering, utilising AI to combine employees' news access sequences and interaction data for highly personalised news recommendations. Experimental results show that the BS-NSR model significantly improves the precision and relevance of news recommendations, supporting employees' knowledge growth and personal development, and enhancing corporate competitiveness and innovation. Through this AI-driven precision recommendation mechanism, companies can better meet employees' knowledge needs, optimise internal knowledge flow, strengthen team collaboration, and improve decision-making efficiency.