基于知识元语义组合差异的专利新颖性细粒度测度方法——以工业机器人领域为例

Fine-grained Measure Method of Patent Novelty Based on Knowledge Element Semantic Combination Differences:Taking Industrial Robotics for Example

[目的/意义]科技成果的新颖性是科技成果价值的重要属性,测度专利新颖性有利于从众多专利中筛选出与以往技术存在显著差异的专利,对专利评价具有重要意义。[方法/过程]提取专利方案、功效、应用以及“方案—功效”“方案—应用”和“功效—应用”等知识元语义组合;计算各类知识元语义组合差异,包括语义差异、频次高低、年龄大小、IPC分类号差异;测度专利整体新颖性和知识元语义组合新颖性,并采用工业机器人领域发明专利数据进行实验。[结果/结论]所提出的方法能够有效实现专利新颖性细粒度测度。研究成果丰富了专利新颖性测度方法,有助于对专利新颖性进行更客观、全面、及时、细粒度的审查与评价。

[Purpose/significance]The novelty of scientific and technical achievements is an important attribute of their value.Measuring patent novelty is useful for screening out patents that are significantly different from previous technologies from a large number of patents,which is important for patent evaluation.[Method/process]Extract knowledge element semantic combination such as solution,efficacy,application,“solution-efficacy”“solution-application”and“efficacy-application”.Calculate the differences of various knowledge element semantic combination,including semantic differences,frequency,age and IPC classification number differences.Measure the overall patent novelty and knowledge element semantic combination novelty.The patent data from industrial robotics are used for experiments.[Result/conclusion]The experimental results show that the method proposed in this study can effectively realize the fine-grained measurement of patent novelty.This study enriches the patent novelty measurement method and helps to examine and evaluate patent novelty more objectively,comprehensively,timely and fine-grained.