Research on the Generation Method of Suspense Stories Based on New-Type Inference

With the rapid development of artificial intelligence technology, its application in the field of creative writing has gradually become a research hotspot, especially in the generation of suspense stories. How to enhance the dramatic tension of suspense story plots while maintaining narrative coherence is an important challenge currently faced by researchers. This paper proposes a method for generating suspense stories based on a novel type of inference, aiming to advance the development of automatic suspense story generation technology. First, a new semantic knowledge framework—situation graph—is constructed, which can not only capture the semantics of micro-scenes but also dynamically track the evolution of the story. Second, the Psycho-Computational Suspense Model (PCSM) is proposed, which transforms psychological suspense heuristic rules into inferential constraint indicators and integrates them into the inference search process as suspense factors. Finally, Suspense-Aware Monte Carlo Tree Search (SA-MCTS) is introduced, which drives large language models (LLMs) to generate suspense stories through a co-evolution mechanism of dual inference paths. Experiments demonstrate that the proposed method has achieved significant results in terms of plot complexity, character depth, and suspense creation, providing new ideas and approaches for the development of automatic suspense story generation technology.