摘要
既有事实证明,具备自主学习能力的人工智能系统在大数据训练下能够自主生成发明,如何对生成发明实现专利制度上的公开,是需要面对的重要问题之一。建立类似于微生物保藏算法的公存体系以及创新性的数据流动跟踪系统,可以解决在人工智能生成发明申请专利过程中所面临的由“黑箱现象”造成的训练数据、训练模型等公开难题。
It is proved that artificial intelligence(AI) systems with autonomous learning capabilities can generate their own innovations under the training of big data.How to realize the full disclosure of the AI-generated inventions in the patent system is one of the important issues that need to be faced.The establishment a public storage system similar to the microbial preservation algorithm and an innovative data flow tracking system can solve the full disclosure of training data and training models caused by the “black box phenomenon” in the process of patent applications involving AI-generated inventions.
作者
胡光
杨珍珠
HU Guang;YANG Zhen-zhu(School of Intellectual Property,Henan Normal University,Xinxiang 453007,China)
出处
《沈阳工业大学学报（社会科学版）》
2022年第2期104-109,共6页
Journal of Shenyang University of Technology(Social Sciences)
基金
国家知识产权局软科学研究项目(SS21-B-11)
河南省知识产权局软科学项目(20210106009)
2019年度河南省高等学校青年骨干教师培养计划项目。
关键词
人工智能
生成发明
专利
训练数据
训练模型
充分公开
artificial intelligence(AI)
generated invention
patent
training data
training model
full disclosure
