数字政府建设、智慧城市类评估指标敏感词脱敏数据

中国智慧城市发展水平评估指标：主要用于评估中国各城市在智慧城市建设方面的发展水平和成效。数据可以用于城市规划、政策制定、投资决策等场景，帮助政府和企业了解各城市在智慧城市建设方面的优势和不足，以便制定相应的发展战略和投资计划。 数字政府建设风向指数暨特色评选指标：主要用于评估政府在数字化转型方面的进展和成果。数据可以用于政府改革、政策制定、公共服务优化等场景，帮助政府了解自身在数字政府建设方面的优势和不足，以便制定相应的改革措施和提升公共服务质量。为了保护这些数据不被未授权人员访问，需要对敏感信息进行脱敏处理，从而保护公司数据安全。数据从智慧中国年会官网、国脉互联公众号及公司官网的历年中国智慧城市发展水平评估、数字政府建设风向指数暨特色评选等指标进行采集录入。按照预设规则建立敏感词库，对敏感词库中的词语根据所属数据字段进行分类，主要分指标名称类、指标描述类和附件地址类，确定敏感词库中每个词语所属的敏感数据类型。导入原始数据集，在敏感数据识别模型使用KNN算法将原始数据中的数据与敏感词库中的词语进行检索比对，在检索到该词语时，判断该词语是否是敏感数据，若是敏感数据则进行标记，敏感数据识别模型对待脱敏的原始数据中的每个词语进行脱敏。模型训练与优化：将更新的数据及敏感数据识别结果添加至原始数据集中，更新后的原始数据集作为部分敏感数据识别模型。例：原附件地址为[files=[{"url":"http://60.163.157.162:31683/gds-data/20240401/首届……指标.xls"}]]，包含了指标的文件地址，一旦泄露会造成公司资源流失，通过敏感数据识别模型对附件地址类信息进行标记并脱敏，脱敏后附件地址为[files=[{"url":"gds-data/20240401/首届……指标.xls"}]]

China Smart City Development Level Evaluation Indicators: Mainly used to evaluate the development level and effectiveness of various Chinese cities in smart city construction. The data can be applied to scenarios such as urban planning, policy formulation, and investment decision-making, helping governments and enterprises understand the strengths and weaknesses of each city in smart city construction, so as to formulate corresponding development strategies and investment plans.

Digital Government Construction Trend Index and Featured Selection Indicators: Mainly used to evaluate the progress and achievements of governments in digital transformation. The data can be applied to scenarios such as government reform, policy formulation, and public service optimization, helping governments understand their own strengths and weaknesses in digital government construction, so as to formulate corresponding reform measures and improve the quality of public services.

To protect these data from unauthorized access, sensitive information needs to be desensitized to ensure corporate data security. The data is collected and entered from the official website of the Smart China Annual Conference, the official account of Guomai Interconnection, and the company's official website, covering annual China Smart City Development Level Evaluation, Digital Government Construction Trend Index and Featured Selection indicators over the years.

A sensitive word library is established according to preset rules, and words in the sensitive word library are classified by their corresponding data fields, mainly divided into three categories: indicator name, indicator description, and attachment address. The sensitive data type corresponding to each word in the sensitive word library is determined.

Import the original dataset, and use the K-Nearest Neighbors (KNN) algorithm in the sensitive data recognition model to retrieve and compare the data in the original data with the words in the sensitive word library. When a word is retrieved, it is judged whether it is sensitive data. If it is sensitive data, it will be marked. The sensitive data recognition model desensitizes each word in the original data to be desensitized.

Model training and optimization: The updated data and sensitive data recognition results are added to the original dataset, and the updated original dataset is used as part of the sensitive data recognition model. For example: the original attachment address is [files=[{"url":"http://60.163.157.162:31683/gds-data/20240401/首届……指标.xls"}]], which contains the file address of the indicator. Once leaked, it will cause the loss of corporate resources. The sensitive data recognition model marks and desensitizes the attachment address type information. After desensitization, the attachment address is [files=[{"url":"gds-data/20240401/首届……指标.xls"}]]

搜集汇总

数据集介绍

特点

该数据集为数字政府建设和智慧城市类评估指标的敏感词脱敏数据，包含1827条记录，每年更新一次。数据主要用于评估智慧城市发展水平和政府数字化转型进展，敏感信息已进行脱敏处理，确保数据安全。