基于决策树的中毒诊断专家系统实现

Implementation of poisoning diagnosis expert system based on decision tree

为了使中毒诊断专家系统能快速确诊,在分析传统决策推理机制的基础上,提出一种改进的推理机制,应用到系统中,并给出了具体实现方法。该系统根据初始中毒症状,充分考虑中毒症状对确诊的贡献及诊断代价,动态构建决策树,然后通过启发式推理,最终得到确诊结果。系统测试结果显示基本达到预期目的。

In order to judge the poisoning quickly through poisoning diagnosis expert system, after analyzing the failure of previous model of inference, a novel model of inference was put forward with which the expert system applies, and the particular method of implementation was introduced. This system firstly set up a decision tree according to the symptoms , and then found the result（ the cause of poisoning） through repeatedly heuristic deduction. System test shows that it achieves the desired result.