都匀市公共交通客流量结构化分析数据集

数据采集从企业自有的“公交安全、调度数字一体化系统平台”采集都匀市20条公交线路的上下行月度客流量；从“都匀市公交IC卡管理系统”调取站点上车人数，实时采集后通过异常值过滤、缺失值补全保障质量；加工环节先拆分聚合为 “线路-方向-站点-时段-日均客流”五维结构化数据，再用使用高峰时段客流统计、“固定阈值分类法”划分站点客流等级、日平均时段计算客流占比，形成从源头采集到结构化加工的标准化流程。

Data collection: Data was obtained from the enterprise-owned "Integrated Digital Platform for Bus Safety and Dispatching" to collect monthly passenger flow data for both up and down directions of 20 bus routes in Duyun City. Boarding passenger volumes at each bus stop were retrieved from the "Duyun City Bus IC Card Management System", with real-time collection followed by outlier filtering and missing value imputation to ensure data quality. In the data processing stage, the raw data was first split and aggregated into five-dimensional structured data following the schema of "Route-Direction-Stop-Time Period-Daily Average Passenger Flow". Subsequently, passenger flow statistics for peak hours were conducted, the "fixed threshold classification method" was used to categorize passenger flow levels at each stop, and the proportion of passenger flow across each daily average time period was calculated, forming a standardized workflow from source data collection to structured data processing.

搜集汇总

背景与挑战

背景概述

该数据集是由都匀市公共交通总公司自行产生的结构化分析数据集，专注于都匀市20条公交线路的客流量数据，数据规模为610kb，每日更新。它通过采集公交安全调度系统和IC卡管理系统的实时数据，经过质量处理后加工成‘线路-方向-站点-时段-日均客流’五维结构，服务于公交企业运力优化、政府部门线路规划、乘客出行决策和应急响应等多场景应用，具有高时效性和精准分析特点。