基于专利引证网络的专利产业化评价方法研究--以燃料电池领域为例

A Patent-citation-network-based Method for Patent Industrialization Evaluation:a Case Study of Fuel Cell

运用数理统计方法衡量专利在技术发展过程中的重要性和价值,从专利引证的视角对专利产业化情况进行评价。通过专利引证分析,着重考虑专利引证质量及专利对后续技术发展的启发性,挖掘引证专利和被引专利间继承和发展的技术发展轨迹。参考连接度算法的计算原理,提出搜索路径节点统计值的概念及计算方法。沿专利引证方向,将搜索路径节点统计值最大的若干专利及其引证路径聚合起来纳入评价子集,形成若干条连续的技术发展轨迹,进而评价专利产业化的可能性。从美国专利商标局专利数据库采集1873—2002年授权的燃料电池领域专利3 054项,从美国国家经济研究局的专利数据集查询到专利引证数据14 214条,利用网络分析软件Pajek构建专利引证网络。结果表明,本文提出的专利产业化评价方法切实有效,与专利产业化的实际情况相符,可作为专利产业化可能性的一种指示。

The article uses the method of mathematical statistics to measure the importance and values of patents in the technology development process, and evaluates the situation of patent industrialization from the perspective of patent citation. The inheritance and development of technological trajectories betwean citing patents and cited patents are mined by patent citation analysis, focusing on the quality of a patent citation and the inspiring of a patent on the subsequent technology development. The concept of search path node count and its calculation method are put forward by the reference to the calculation principle of Connectivity Algorithm. The patents with the largest number of search path node count and their citation paths are collected along the direction of patent citation to the evaluation subset, forming several continuous technological trajectories. And then they can be used for evaluating the possibilities of patent industrialization. The article collects 3 054 patents related to the fuel cell which were granted between 1873 and 2002 from the database of United States Patent and Trademark Office, queries from the patent data set of National Bureau of Economic Research to get 14 214 patent citations and uses the network analysis software Pajek to build a patent citation network as the expefirnantal data. The experimental results show that, the proposed method is effective. It is consistent with the actual situations of patent industrialization, and can be used as the instructions of patent industrialization.