Abstract
With the rapid advancement of artificial intelligence, intelligent farming has become a key trend in modern agriculture. In particular, the application of intelligent systems in broiler farming is essential for enhancing production efficiency and optimizing management practices. Broiler farming is a complex process involving multiple interrelated components. However, existing knowledge graphs primarily focus on disease and prevention, making it difficult to capture the intricate interdependencies within the farming process. This limits the effectiveness of knowledge-based support in decision-making. To develop a high-quality broiler farming knowledge system, this study adopts large language modeling technology to integrate a Chinese corpus and construct a comprehensive knowledge graph dataset covering four core dimensions: broiler breeds, farming environment, feeding management, and disease prevention. The construction of the dataset involved three key stages. First, text scanning was used to extract information from farming-related literature, while web crawlers collected data from authoritative online sources. The data were then cleaned and manually validated to ensure accuracy and consistency. Second, the DeepKE knowledge extraction framework is used to automatically extract triples related to broiler farming from the text. These are then used as prompts to guide large-scale pre-trained language models (LLMs) to complete and optimize the knowledge, ultimately constructing a relatively complete knowledge graph of broiler farming. Finally, the structured knowledge was stored in a Neo4j graph database to support efficient querying and reasoning. The dataset not only provides researchers and farms with multidimensional knowledge of the broiler farming domain, but also supports visual management and analysis, enables data-driven inference through large models, and offers new approaches to optimize farming strategies and enhance production efficiency.