论人工智能时代算法的法律规制

On the Legal Regulation of Algorithms in the Age of Artificial Intelligence

网络平台对日常生活的包办逐渐发展到事无巨细的程度,同时,数据采集能力和计算机算力的飞速发展使算法得以通过机器学习不断自我迭代,其不透明度和决策影响力与日俱增,算法从辅助性工具成长为“算法权力”。在算法规制中,算法的秘密性不仅关乎商业利益,也关乎算法预期功能的实现、国防安全等等。应以有限披露为原则,完善和调整商业秘密保密机制以配合算法披露机制,协调公众知情、政府监管和商业秘密多方利益,实现算法规制的最终目的,即社会福祉的稳步增长。

The impact and involvement of network platforms on daily life is getting wider and deeper.At the same time,the rapid development of data acquisition capabilities and computer computing power enables algorithms to continuously iterate themselves through machine learning.With its increasing opacity and decision-making power,algorithms grow from auxiliary tools to“algorithm power”.Inalgorithmic regulation,the confidentiality of the algorithm is not only related to commercial interests,but also to the realization of the expected function of the algorithms,national defense security and so on.Based on the principle of limited disclosure,the trade secret confidentiality mechanism should be improved and adjusted to cooperate with the algorithm disclosure mechanism,coordinate the interests of public knowledge,government supervision and trade secrets,to achieve the ultimate goal of algorithmicregulation,which is,the steady growth of social well-being.