宇航计测技术 ›› 2025, Vol. 45 ›› Issue (2): 97-102.doi: 10.12060/j.issn.1000-7202.2025.02.08

• • 上一篇    

人工智能数据计量测试探索

林杰1,2,孙静3,冯佳楠1,胡建阳1,张修建3,金鹏1   

  1. 1.哈尔滨工业大学 微系统与微结构制造教育部重点实验室,哈尔滨 150001;
    2.哈尔滨工业大学 物理学院,哈尔滨 150001;3.北京航天计量测试技术研究所 国家市场监管重点实验室 人工智能计量测试与标准,北京 100076
  • 出版日期:2025-04-15 发布日期:2025-04-29
  • 作者简介:林杰(1979-),男,教授,博士,主要研究方向:微纳光学理论与应用。
  • 基金资助:
    国家自然科学基金(U2341245,62175050)

Metrology and Evaluation of Data for Artificial Intelligence

LIN Jie1,2,SUN Jing3,FENG Jianan1,HU Jianyang1,ZHANG Xiujian3,JIN Peng1   

  1. 1.Key Laboratory of Micro-systems and Micro-structures Manufacturing,Ministry of Education,Harbin Institute of Technology,Harbin 150001,China;2.Harbin Institute of Technology,School of Physics,Harbin 150001,China;
    3.Key Laboratory of Artificial Intelligence Measurement and Standards for State Market Regulation,Beijing Aerospace Institute for Metrology and Measurement Technology,Beijing 100076,China
  • Online:2025-04-15 Published:2025-04-29

摘要: 当前,人工智能技术蓬勃发展,国内外推出了多种人工智能模型与产品,人工智能正在不断地影响人们的生活。数据是人工智能的核心要素之一,人工智能技术的发展离不开高质量数据的支撑,因此,对人工智能数据开展测量与评估是人工智能技术合法、安全和公平的重要前提。本研究围绕数据计量测试探讨了以数据的合法性、真实性、多样性、平衡性、数据隐私保护和伦理及数据量作为人工智能数据测量与评估的依据,并进行了讨论和分析。

关键词: 人工智能, 深度学习, 训练数据, 数据安全评估

Abstract: At present, artificial intelligence technology is booming, and a variety of artificial intelligence models and products are launched at home and abroad,and artificial intelligence has constantly influence on people’s lives.Data is one of the core factors in artificial intelligence,and the development of artificial intelligence technology benefits from the high-quality data.Therefore,the measurement and evaluation of data for artificial intelligence is an important precondition to achieve legality,safety and fairness of artificial intelligence.For the metrology and evaluation of data,the legitimacy,authenticity,diversity,balance,data privacy protection and ethics,data quantity are proposed as the fundamental contents of measurement and evaluation of data.

Key words: Artificial intelligence, Deep learning, Training data, Data security evaluation

中图分类号: