基于HMM的多维数据下扶贫对象状态预测  

State Prediction of Poverty Alleviation Objects Based on HMM and Multidimensional Data

作　　者：何俊 洪孙焱 周义方 申时凯 邹目权 He Jun;Hong Sunyan;Zhou Yifang;Shen Shikai;Zou Muquan(College of Information Engineering,Kunming University,Kunming 650214,China;Information Center,Kunming University,Kunming 650214,China;Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan,Kunming 650214,China.)

机构地区：[1]昆明学院信息工程学院,云南昆明650214 [2]昆明学院信息中心,云南昆明650214 [3]云南省高校数据治理与智能决策重点实验室,云南昆明650214

出　　处：《系统仿真学报》2022年第5期1118-1126,共9页Journal of System Simulation

基　　金：国家自然科学基金(62066023);国家级新工科研究与实践项目(E-JSJRJ20201342);云南省地方本科高校基础研究联合专项(2017FH001-058);云南省教育厅科学研究基金(2018JS391)。

摘　　要：针对扶贫领域中贫困、脱贫和返贫状态预测不准确,影响状态变迁的关键因素难以识别的问题,从扶贫基础数据和多个行业数据中提取8个关键特征和22个观测状态,构建观察状态和隐含状态关联关系,建立扶贫对象状态预测隐马尔可夫模型(hidden markov model,HMM)。以某深度贫困县连续3年的数据为样本,进行参数训练、测试实验和结果验证,结果表明该方法对返贫、贫困和脱贫状态有较强的预测能力,误差率较低,且能准确识别出影响返贫的关键要素。该方法对指导精准扶贫工作具有非常重要的实际意义。In order to solve the problems of inaccurate prediction of poverty, poverty reduction and poverty returen, and the difficulty in identifying the key factors affecting the state transition, 8 key features and 22 observed states are extracted from the poverty reduction basic data and multi-industry data.The relationship between observed state and implied state is constructed, and the hidden markov model(HMM)of poverty alleviation is established. Data of a deep poverty county for three consecutive years are used as samples for parameter training, test experiment and result verification. The results show that the method has a strong prediction ability for back poverty, poverty and poverty alleviation with low error rate, and can accurately identify the key elements affecting poverty return. The method is of great practical significance for guiding the precise poverty alleviation work.

关 键 词：隐马尔可夫模型 精准扶贫 数据分析 预测方法 返贫 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论] TP391.9[自动化与计算机技术—计算机科学与技术]