Accelerated urbanization, sustained rural labor migration, and increasing inefficiencies in land management have contributed to the widespread abandonment of cultivated land in China, thereby posing significant challenges to national food security, agricultural sustainability, and rural revitalization. Although intelligent supervision technologies have been increasingly introduced into agricultural governance systems, the heterogeneous requirements of multiple stakeholders have not been systematically incorporated into existing platform design frameworks. To address this gap, a Kano model–based requirements analysis framework was developed and applied to the governance of farmland abandonment in a major agricultural county in Jiangxi Province, China. A mixed-methods approach integrating literature analysis, semi-structured interviews, and questionnaire surveys was adopted to identify, classify, and prioritize the requirements for an intelligent supervision platform. The identified requirements were categorized into four dimensions: must-be requirements (e.g., policy subsidy information and data stability), one-dimensional requirements (e.g., historical data comparison and land transfer information), attractive requirements (e.g., high-precision monitoring and fallow warning), and indifferent requirements (e.g., user operation training and feedback channels). The findings demonstrated that must-be requirements should be prioritized to ensure the operational reliability of the platform, whereas one-dimensional requirements should be continuously strengthened to improve core capabilities. Attractive requirements were found to significantly enhance user experience and should therefore be gradually integrated. In contrast, indifferent requirements should be strategically managed to avoid unnecessary allocation of resources. Empirical evidence for the optimization of intelligent supervision platforms in farmland abandonment governance was provided by this study, while the applicability of the Kano model in public governance technology requirement analysis was further validated. The findings are expected to contribute to the advancement of intelligent, data-driven, and precision-oriented farmland governance systems in China and other developing agricultural regions.
Effective tourism planning, scenic-area evaluation, and regulatory supervision depend on the accurate interpretation of extensive collections of tourism-related laws, administrative regulations, technical standards, and local normative documents. However, these documents are characterized by heterogeneous structures, frequent revisions, and complex cross-document dependencies, which limit the effectiveness of conventional keyword-based retrieval approaches and increase the risk of unsupported or unverifiable outputs generated by large language models. To address these challenges, a retrieval-augmented generation framework, termed ReguTourRAG, was proposed for intelligent question answering and knowledge access within tourism regulatory and standards corpora. A two-stage retrieval architecture was adopted. In the first stage, broad hybrid recall was performed through the collaborative integration of Best Matching 25 (BM25) lexical retrieval, Elastic Learned Sparse EncodeR (ELSER)-based sparse semantic retrieval, and Hierarchical Navigable Small World (HNSW)-based dense vector retrieval. In the second stage, candidate documents were refined through a cross-encoder reranking model, whereby high-value evidence was prioritized before response generation. Through the explicit separation of coverage-oriented recall and precision-oriented reranking, the traceability, completeness, and reliability of generated responses were enhanced for regulation-driven tourism management tasks. The proposed framework was evaluated using a corpus comprising 970 tourism regulatory and standards documents. Experimental results demonstrated consistent improvements over representative single-strategy retrieval-augmented generation baselines across multiple retrieval and generation metrics, including mean reciprocal rank, normalized discounted cumulative gain, accuracy, Recall-Oriented Understudy for Gisting Evaluation-Longest Common Subsequence (ROUGE-L), and BERTScore. The observed gains indicate that the collaborative utilization of lexical, sparse semantic, and dense retrieval signals, together with cross-encoder evidence refinement, provides substantial advantages for regulation-intensive domains in which precise legal terminology, semantic paraphrasing, and cross-document reasoning must be simultaneously accommodated. These findings suggest that ReguTourRAG offers a robust and scalable foundation for regulatory decision support, policy interpretation, compliance assessment, and intelligent knowledge services in tourism governance environments.
Open Access
Journal Metrics
Journal Overview
Associated Journals