摘要
针对作物推荐施肥系统中知识与数据紧密结合、模块固化的缺点,提出基于知识库思想的施肥决策系统实现方法,通过采用知识库作为区域实体事实数据与程序代码的接口,依托推理机实现施肥知识与系统的有机集成,解决施肥决策系统常面临的可扩展、可自定义等需求。该文对施肥知识库与数据实体的相互关系、施肥知识分类、表达、存储以及应用设计等进行了详细讨论。应用该思想设计开发施肥系统,能够较好地模拟现实中的施肥决策过程,目前在实践中已得到较好的应用。
Crop fertilization recommendation system involves using models to calculate the needed amount of variety of nutrients during the crop growth, choosing suitable fertilizers, and arranging fertilization time. Whether it can be used widely or not, the key point is that the models or parameters in system can be customized easily with local agricultural production practices. To help address these issues, a software infrastructure is proposed. It adopts concepts form knowledge base with the aim of providing an overall logical framework for fertilization recommendation, in which the knowledge base as the interface between local entities and program code, and the professional fertilization mechanism as the inference engine. This paper discusses the fertilization knowledge’s classification, representation, storage and the relations with data entities, and presents the design of knowledge base and its application. Based on this method, a practical software system for cultivated land quality and fertilization management has been developed by integrating with GIS, and the scalability and localizability has been demonstrated by more than thirty counties’ cases.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2011年第12期126-131,共6页
Transactions of the Chinese Society of Agricultural Engineering
基金
浙江省自然科学基金资助项目(Y5080259)
浙江省耕地地力评价与测土配方施肥信息系统研究开发(2007R20A60D03)
关键词
肥料
决策
专家系统
知识库
推荐施肥
fertilizers
decision-making
expert system
knowledge base
fertilization recommendation
