Designing and Algorithm Implementing of the Expert System Platform for Assistant Identification of Agricultural Pests Based on a Dendriform Hierarchical Structure

摘要

Being numerous, the insect and disease pests were organized within classifications described as a dendriform hierarchical (tree-shape) structure. The data of the structure were managed by database management system (DBMS), tables were designed to store the information about the species/category and related characteristics. The characteristics were related to the species/category to construct a junction/x-ref table as the knowledge base of the expert system for insect and disease pest identification, including sets of identification characteristics for all species/category in the table. Relational calculus was employed to estimate the potential species/category of the insect and disease pests in relation to inclusion of the set of characters selected by users and the sets of identification characteristics in the knowledge base of the system. The system can be used as an open and flexible platform for professional users involved in plant protection to establish new expert application systems that provide pest identification services for common agricultural users.