青岛市长期不用气及户用安全风险告警数据

随着社会逐步进入老龄化社会，面临的独居老人生活问题越来越受到政府、爱心人士的关心。燃气公司通过户主年龄，户内用气量与平均用气量比较，推断用户是否为独居老人。结合日用气量的连续特征，判断燃气用户用气是否正常，并结合报警情况和报警时间，及时发现户内老人发生安全风险的情况并及时处理。1、获取要素字段数据：用气时间、日用气量、户号、地址区域、地址区域内用户数、平均每户正常用气量、近期缴费方式（柜台、线上缴费）、开户时间、通气时间
2、输入日用气量、用气时间，使用ARIMA模型训练，输出平均每户正常用气量，根据60岁以上人群，按每5年一组进行分组，统计组内平均每户正常用气量，根据60岁以上且用气量显著低于平均每户正常用气量，且缴费方式为柜台，判断为独居老人，将该名单记录。
3、结合时序分析和深度学习预测结果，建立综合的安全风险评估模型。采用K-means聚类算法，根据用户的地址区域、平均每户正常用气量的特征，识别异常用气行为，异常用气行为包括用气时间大于统计时间3个月及以上及用气量较之前异常变小。对异常用气行为进行报警，记录报警时间，通知燃气公司对报警用户进行安全风险排查。

As society gradually enters an aging era, the living challenges of elderly people living alone have garnered increasing attention from governments and caring individuals. Gas companies infer whether a user is an elderly person living alone by comparing the age of the household head, the household's gas consumption with the average household gas consumption level. Leveraging the continuous characteristic of daily gas consumption, they assess whether a gas user's usage is normal, and timely detect and address safety risks for indoor elderly residents by combining alarm records and alarm timestamps.
1. Collect essential field data: gas usage time, daily gas consumption, household number, address area, number of users within the address area, average normal gas consumption per household, recent payment methods (counter, online), account opening time, gas supply activation time
2. Take daily gas consumption and gas usage time as inputs, train the ARIMA model to output the average normal gas consumption per household. Group people aged 60 and above into 5-year age brackets, and calculate the average normal gas consumption per household within each bracket. Identify users who are aged 60 or above, whose gas consumption is significantly lower than the average normal gas consumption per household of their corresponding age group, and who pay via counter as elderly people living alone, then compile these users into a record list.
3. Establish a comprehensive safety risk assessment model by combining time series analysis and deep learning prediction results. Adopt the K-means clustering algorithm to identify abnormal gas usage behaviors based on the user's address area and average normal gas consumption per household. Abnormal gas usage behaviors include users whose latest gas usage timestamp is more than 3 months apart from the statistical timestamp, and those whose gas consumption has abnormally decreased compared to previous levels. Issue alarms for such abnormal gas usage behaviors, record the alarm time, and notify the gas company to conduct safety risk inspections on the alarmed users.

搜集汇总

数据集介绍

特点

该数据集包含青岛市燃气用户的用气数据，规模为8001条，每日更新。数据通过分析用气时间、日用气量等字段，结合ARIMA模型和K-means聚类算法，识别独居老人的安全风险，并及时告警。应用场景主要针对老龄化社会中的独居老人安全问题。