人工神经网络在渔业高价值专利筛选中的应用——以中国水产科学研究院为例

Application of artificial neural networks in the screening of high-value fisheries patents--Taking Chinese Academy of Fishery Sciences as an example

为了从大量专利数据中筛选渔业高价值专利,提高专利管理效率,从而间接促进专利转化,对中国水产科学研究院2008—2018年5404项专利进行价值高中低分类标注,获取这些专利在商业数据库Patentics中的16个参数并进行归一化处理,合并专利信息和对应的专利参数并利用人工神经网络建模。合并的数据中随机抽取70%的数据用于训练,30%的数据用于测试。结果表明:单隐层5个节点的人工神经网络模型准确度为73.59%,可以用于后续高价值专利辅助筛选工作。

In order to screen high-value fisheries patents from massive patent data for improving the efficiency of patent management, and thus indirectly promoting patent conversion, 5 404 patents of Chinese Academy of Fishery Sciences from 2008 to 2018 were categorized and artificially labeled as high, middle and low value, and 16 parameters of these patents in the commercial database Patentics were obtained and normalized to merge patent information and corresponding patent parameters. 70% merged data were selected randomly for training, and 30% for testing. The results show that the accuracy of the artificial neural network model with 5 nodes in a single hidden layer is 73.59%, which can be used for subsequent screening of high-value patents.