基于改进谱聚类算法的生物制药产业专利价值评估研究

有效评估药物专利价值有必要考虑制药基础技术细节以及新药专利保护期限较长的特殊性等有关实际，同时，利用机器学习方法开展专利价值评估的研究仍有待进一步完善，因此，针对生物制药产业专利价值评估准确性问题，结合产业技术因素及其专利特点，以及专利价值评估的共性指标和生物制药产业特征与专利技术特点的个性指标，引入自编码器（AE）模型和谱聚类算法（SC）构建专利价值评估算法模型，以药智专利通数据库的相关专利数据为样本进行实证分析，通过提取专利指标特征、专利聚类来进行专利价值评估，并运用支持向量机方法对专利价值进行分类，以验证AE-SC评估模型的有效性。结果表明：AE-SC评估模型通过自编码器提取专利特征后的专利价值聚类准确度优于谱聚类和传统K-means聚类；专利存在年数、药物专利类型、适应证类别等是评价生物制药产业专利价值必要考虑因素。

Research on Patent Value Evaluation of Bio-pharmaceutical Industry Based on Improved Spectral Clustering Algorithm

Aiming at the accuracy of patent value evaluation in bio-pharmaceutical industry, combining industrial technology factors and patent characteristics, the patent value evaluation index system and its industrial patent value evaluation model were constructed to reflect the characteristics of industry individuality. The auto encoder (AE) was used to reduce the dimension of the original patent information, and then the patent value evaluation model was established based on the spectral clustering algorithm (SC), and the support vector machine (SVM) was used to classify the patent information, so as to verify the validity of the model. The results show that the model can effectively reflect the level of patent value, and effectively verify that relevant information such as patent years, drug patent types and indications are necessary factors to consider in the evaluation of bio-pharmaceutical industry technology patents. This study provides a new perspective and method for the evaluation of industrial patent value.