工程车辆安全画像分析数据
收藏资源简介：
通过对接入企业自建重点车辆智管平台的工程车辆的驾驶员超速、疲劳驾驶、抽烟、打电话等违规行为进行统计分析，并基于汇总结果进行画像构建，最后确定风险等级。应用场景适用于针对工程车辆和驾驶员的安全管理应用，对车辆和驾驶员进行安全画像评价，可用于工程车辆驾驶员的正向激励机制设计、管理模式落实、定向安全培训等场景。数据集可协助构建“工程车辆驾驶员安全画像智能分析系统”，实现风险分级、精准培训、动态激励的闭环管理。 平台可通过可视化界面直观展现每个工程车驾驶员的画像构建情况和详细的违规明细，从而对驾驶员的安全风险进行直接分级。安全画像构建，有助于对驾驶员进行针对性的培训和安全教育，规划和推广有助于驾驶员成长的正向激励机制，该数据集可应用于驾驶员安全管理领域，通过正向激励和管理机制来促进工程车领域的安全管理能力提升。1、数据采集：通过企业自建平台，对接入平台管理的车辆以及驾驶过程中的违规行为进行采集和分析。 2、数据处理：以车牌号码为唯一字段，对一季度的驾驶行为进行统计和分析，比较从而得出不同画像分值和风险等级。 3、算法规则： 画像分值=超速次数*0.3+疲劳驾驶次数*0.3+抽烟次数*0.2+打电话次数*0.2; 风险等级=IF(画像分值>200,"高",IF(画像分值>50,"中","低")); 其他说明: 风险等级划分： 风险级别计算：低风险（0-50分）：行为规范；中风险（50-200分）：需关注；高风险（>200分）：重点管控。
This dataset performs statistical analysis on violations such as speeding, fatigued driving, smoking, and phone calling committed by drivers of engineering vehicles connected to the self-built enterprise key vehicle intelligent management platform, constructs safety profiles for the drivers based on the aggregated results, and finally determines their risk levels. Its application scenarios are targeted at the safety management of engineering vehicles and their drivers, including safety profile evaluation for both vehicles and drivers, and can be applied to scenarios such as the design of positive incentive mechanisms for engineering vehicle drivers, implementation of management models, and targeted safety training. This dataset can assist in building the "Intelligent Analysis System for Safety Profiles of Engineering Vehicle Drivers", realizing closed-loop management of risk grading, precise training, and dynamic incentives. The platform can intuitively display the profile construction status and detailed violation records of each engineering vehicle driver through a visual interface, thereby directly grading the driver's safety risk. The construction of safety profiles helps to conduct targeted training and safety education for drivers, plan and promote positive incentive mechanisms conducive to driver growth. This dataset can be applied to the field of driver safety management, and improve the safety management capability in the engineering vehicle sector through positive incentives and management mechanisms. 1. Data Collection: Collect and analyze the vehicles managed by the connected platform and the violation behaviors during driving through the self-built enterprise platform. 2. Data Processing: Take the license plate number as the unique identifier, conduct statistical analysis on driving behaviors in the first quarter, and derive different profile scores and risk levels through comparison. 3. Algorithm Rules: Profile Score = Number of Speeding Violations * 0.3 + Number of Fatigued Driving Violations * 0.3 + Number of Smoking Violations * 0.2 + Number of Phone Calling Violations * 0.2; Risk Level = IF(Profile Score > 200, "High", IF(Profile Score > 50, "Medium", "Low")); Other Notes: Risk Level Classification: Risk Level Calculation: Low Risk (0-50 points): Compliant behaviors; Medium Risk (50-200 points): Requires attention; High Risk (>200 points): Key supervision and control.
