• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Problems of Economic Transition >Technologies for Identifying and Scrubbing Personal Data from Open Sources
【24h】

Technologies for Identifying and Scrubbing Personal Data from Open Sources

机译：从开放来源识别和擦洗个人数据的技术

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This article examines the basic tasks involved in identifying personal data in a mass of unstructured information, as well as depersonalization of that data. Accomplishing these tasks allows for a qualitative leap in issues related to prompt identification of violations against the federal laws "On Personal data," "On Mass Information Resources" (about mass media), and "On Information, Information Technologies, and Protection of Information." The main advantages of the technologies suggested in this article lie in its use of computer linguistics to extract entities (persons, brands, organizations, geographic entities), their attributes, and facts associated with them from unstructured information resources, as well as the latest linguistic and analytic processing for extracting information. These kinds of technologies can be used in information and analytic systems that are intended for prompt and accurate identification of personal data, in the interests both of government agencies and of commercial organizations and natural persons.
机译：本文介绍了识别识别大量非结构化信息中的个人数据的基本任务，以及该数据的代名化。完成这些任务允许在与联邦法律“关于个人数据”（关于大众信息资源）（关于大众媒体）和“信息，信息技术以及信息保护”中的“关于大众信息资源”（关于大众媒体）和“信息保护以及信息保护和保护信息的情况下的问题中的质量跳跃。“本文建议的技术的主要优势在于利用计算机语言学，从非结构化信息资源以及最新语言中提取与他们相关的实体（人员，品牌，组织，地理实体），他们的属性和事实。提取信息的分析处理。这些技术可用于信息和分析系统，旨在提示和准确地确定个人数据，以获得政府机构和商业组织和自然人的兴趣。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号