With the continuous influx of application software onto the application software market, achieving accurate software recommendations for users in the huge software application market is urgent. To address this issue, each application software market currently provides its own classification tags. However, several problems still exist, such as the lack of objectivity, hierarchy, and standardization in these classifications, which in turn affects the accuracy of precise software recommendations. Accordingly, a customized BERTopic model is proposed to cluster the software description texts of the application software and the automatic tagging and updating of the application software tags are realized according to the clusters obtained by topic clustering and the extracted subject words. At the same time, a data enhancement method based on the c-TF-IDF algorithm is proposed to solve the problem of imbalance of datasets, and then the classification model based on the BERT-BiLSTM model is trained on the labeled datasets to classify the software in the dimension of the application function, so as to realize the accurate software recommendation for users. Based on the experimental verification of two datasets, 21 categories in the SourceForge dataset and 19 categories in the Chinese App Store dataset are subclassed by the clustering results of the customized BERTopic model, and the tags of 138 subclasses and 262 subclasses are formed, respectively. In addition, a complete tagged software description text dataset is constructed and the software tags are updated automatically. In the first stage of the classification experiment, the weighted average accuracy, recall rate, and F1 value can reach 0.92, 0.91, and 0.92, respectively. In the second stage, the weighted average accuracy, recall rate, and F1 value can all reach 0.96. After data enhancement, the weighted average F1 value of the classification model can be increased by up to two percentage points.

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.