融合混合知识与MCTS的针灸排序方案设定方法

Acupuncture Sequential Scheming Method With Hybrid Knowledge and MCTS

传统的序列决策方法旨在对决策过程与决策步骤进行建模,以求解得到最优的决策序列.然而,序列决策建模过程对目标函数的确定性要求高,且序列搜索的算法多以深度优先或广度优先等遍历搜索为主,鲜有考虑搜索过程的随机性.蒙特卡洛树搜索算法(Monte Carlo tree search,MCTS)虽然适合求解随机序列搜索问题,但目前仅应用于博弈型搜索过程,鲜有探讨需要专家参与的知识约束序列决策的搜索策略,另外,传统MCTS算法往往存在搜索范围过大、收敛不及时等问题.为此,提出一种融合群决策经验型知识和部分确定型决策序列片段的混合知识约束的MCTS序列决策方法,并给出了详细的求解流程.最后,将所提方法应用于一类中风后吞咽功能障碍针灸穴位排序方案制订问题,给出了融合混合知识与MCTS的针灸排序方案设定方法,并与其他方法进行对比,验证了所提方法的可行性和有效性,为年轻医师的针灸方案制订技能的标准化培训工作奠定了方法基础.

The traditional method of sequential decision-making aims to establish the decision-making processes model and decision-making steps to obtain the optimal decision-making sequence.However,the decision-making process of sequence decision-making is highly deterministic for objective function,the depth first or breadth first algorithms are always employed in the sequence searching,suffering the randomness of search process.Although Monte Carlo tree search algorithm(MCTS)is suitable for solving the random sequence search problem,it is only used to the game-type search process at present,and rarely applied in the sequence decision problem of knowledge constraint with expert participation,as well as,the traditional MCTS algorithms often have problems such as:too large search scope and poor convergence.In response,this paper proposes an MCTS sequence decision-making method based on hybrid knowledge constrained empirical knowledge of group decision-making and partially deterministic decision sequence segments,along with the detailed steps.Finally,the proposed method is employed in a kind of post-stroke dysphagia dysfunction acupuncture point sorting problem,then,we gave the acupuncture sequential scheming method with hybrid knowledge and MCTS.Comparing with other methods,the feasibility and effectiveness of the proposed method is verified,formulating the standardization training skills for the young doctor's acupuncture program,laying the foundation for the method.