人工智能创作物可版权化及权属问题研究

Research on the Copyright and Ownership of Artificial Intelligence Creations

随着人工智能产业在中国蓬勃发展并产出了一系列的科技成果,现行法律却尚未对人工智能程序在“高效计算”、“自主模拟”后所产出的创作物进行可版权化定性及权属确立,故由权属交叉、授权主体指向不明等权属边界模糊问题引发的权属纠纷成为阻碍人工智能向前发展的绊脚石。本文在对现行法律分析以及利益考量的基础上,意在通过拟制“不完整著作权”与“思想表达二分法”等新的思路解决人工智能创作物在可版权化认定中存在的难题,并提出在合理的限度内将之拟制为委托作品,探索具体权属的可行性方法。

Existing laws haven’t established copyrightability and ownership of creations by artificial intelligence programs after "efficient computing" and "independent simulation", therefore, ownership disputes resulted from the blurred boundary of ownership, overlapping ownership and vaguely-referred authorization subject, and conflicts among interest subjects of artificial intelligence are undermining the development of artificial intelligence. On the basis of analyzing and considering existing laws and benefits, the aim herein is to address difficulties in identifying copyrightability of AI creations through formulating new ideas including "incomplete copyright" and "dichotomy of thoughts and expressions", and at the same time, the idea of considering them as commissioned work to the extent of reasonable identification of copyright is put forward to explore feasible methods of specific ownership.