Abstract:

[Significance] This paper addresses the issues of inconsistent acquisition standards, incomplete data collection, and unclear governance mechanisms in China's agricultural production data. It explores the existing governance models for agricultural production big data, clarifying the technical path for the value realization of data elements through the integration and innovative application of key big data governance technologies and tools in scenarios. This provides a reference for achieving high-quality agricultural production driven by data. [Progress] From the perspective of agricultural production big data governance, it explores 17 types of big data governance technologies and tools in 6 major processes: data acquisition and processing, data storage and exchange, data management, data analysis, large model, and data security guarantee. It deeply studies the application methods of big data governance technologies in agricultural production. The remote sensing, unmanned aerial vehicle, Internet of Things, and terminal data acquisition and processing systems are basically mature, the data storage and exchange system is developing rapidly, the data management technology is in the initial stage, the data analysis technology is widely applied, the large model technology system is initially formed, and the data security guarantee system is gradually applied. The above technologies are well applied in scenarios through tools and middleware such as data matching, computing power matching, network adaptation, model matching, scenario matching, and business configuration. It analyzes the data governance throughout the entire chain of agricultural production, including pre-production, production, and post-production, as well as service cases for different types of agricultural parks, research institutes and universities, production entities, and farmers. It shows that good data governance can provide sufficient planning and input analysis before production, helping planting entities to plan reasonably; in production, it can provide data-based guidance for key scenarios such as agricultural machinery operations and agricultural technical services to fully assist the decision-making process of the production process; and based on massive data, it can achieve good results in yield assessment and production benefit evaluation. It introduces the governance experience in national-level industrial parks, provincial-level agricultural science and technology parks, and some single-product entities, and investigates the technologies, practices, and tools of agricultural production big data governance at home and abroad, indicating that it is necessary to break through the business chain and service model of agricultural production across regions, themes, and scenarios. [Conclusions and Prospects] This paper puts forward insights on the future development direction of agricultural production big data governance, including promoting the formulation and implementation of standards for agricultural production big data governance, building a general resource pool for agricultural production big data governance, expanding diversified application scenarios for agricultural production big data governance, adapting to the new paradigm of agricultural production big data governance driven by large models and massive data, and strengthening the security and privacy protection of agricultural production big data.

Key words: agricultural production big data governance, agricultural production data acquisition and processing, agricultural production metadata, agricultural production data security, large model of agricultural production