KEEN: Knowledge Graph-Enabled Governance System for Biological Assets

Zhengkang Fang, Keke Gai, Jing Yu, Yihang Wei, Zhentao Wei, Weilin Chan

Abstract: With the development of the biological industry and the need for improved productivity in agriculture and animal husbandry, there are higher demands for the governance of biological assets in the biological assets governance system. In order to harness existing knowledge and enhance the effectiveness and scalability of biological asset supervision, this research proposes a Knowledge graph-Enabled gov Er Nance system for biological assets (KEEN). The system leverages textual data and employs techniques such as entity recognition, relation extraction, and knowledge graph embedding to automatically generate a knowledge graph. This knowledge graph establishes relationships between biological behaviors and target identification, thereby expanding the capabilities of behavior recognition models to perform a wider range of biological asset supervision tasks. By enhancing the scalability of biological asset identification models, better decision-making and management can be achieved. Our evaluations demonstrate that the proposed method exhibits superior performance in terms of accuracy, scalability, and maintenance in the supervision of biological assets.