人工智能产品质量的法律规制研究

Research on Legal Regulation of Artificial Intelligence Product Quality

人工智能在本质上属于产品,应接受《产品质量法》对其生产、设计的规制以规避应用中的风险,但人工智能替代人类决策的特性,决定了《产品质量法》必须予以改进,进而规制人工智能产品质量。传统产品的质量标准可以继续适用人工智能产品的制造与警示环节,但人工智能的自动化决策要直接处理人类社会问题,应以人类行为的标准要求其算法运行规则。质量监管部门应明确人工智能自动化决策的终极伦理标准,并在人工智能上市前对其进行算法检测检验。人工智能的自动化决策若违反法律、社会伦理规则,应属于产品质量缺陷。因人工智能产品设计造成他人损害的,生产者应对产品是否存在设计缺陷承担举证责任。

Artificial intelligence is a product in essence and should be subject to the regulations of the Product Quality Law on its production and design to avoid risks in application.However,the characteristic of artificial intelligence replacing human decision-making determines that the Product Quality Law must be improved to regulate the quality of artificial intelligence products.The quality standards of traditional products can continue to apply to the manufacturing and warning processes of artificial intelligence products.Since the automated decision-making of artificial intelligence directly deals with human social issues,its algorithm operation rules should be required by the standards of human behavior.The quality supervision department should clarify the ultimate ethical standards for artificial intelligence automation decision-making and conduct algorithm testing on artificial intelligence before it enters the market.If the automated decision-making of artificial intelligence violates legal and social ethical rules,it should be considered a product quality defect.If the design of an artificial intelligence product causes damage to others,the producer shall bear the burden of proof for whether the product has design defects.