基于隐马尔可夫模型的公交乘客出行链识别方法

Recognition Method of Public Passenger Trip Chain Based on Hidden Markov Model

以公交IC卡数据为基础,结合公交站点周边土地类型及乘客时空转移序列构建隐马尔可夫模型对乘客的出行目的进行识别,继而实现完整乘客公交出行链的提取。采用石家庄某一工作日的公交IC卡数据来实现模型,并与同日期的公交乘客出行调查数据对比,结果表明模型与实际调查结果较为吻合,工作日公交乘客出行链以通勤类出行链为主,总占比达81.87%,通勤活动具有很强的时效性。本文模型为公交IC卡数据的深度研究提供了一定的基础。

Based on the bus IC card data, a Hidden Markov model was constructed to identify the traveling purpose of the passenger. By combining the land types around the bus station and the passenger space-time transfer sequence, the model extracted a complete bus traveling chain for passengers. The model was implemented by using Shijiazhuang’s bus IC card data for a working day and compared it with the bus passenger travel survey data of the same date. The results show that the model is consistent with the actual survey results. The bus passenger traveling chain is dominated by commuting travel chains, with a total proportion of 81.87%, and commuting activities have a strong timeliness. The proposed model provides a certain basis for in-depth research on public transit IC card data.