基于尺度自适应核相关滤波的专利数据挖掘方法

Patented data mining method based on scale adaptive kernel correlation filtering

针对当前专利数据量庞大且难以分析的问题,基于尺度自适应核相关滤波提出一种专利数据挖掘方法。该方法在传统核相关滤波跟踪方法基础上,引入尺度自适应法进行关键词检索,给出了最佳目标尺度索引的计算方法,建立了专利数据挖掘算法,进而实现对目标关键信息的有效定位和提取,最后,通过仿真实验进行性能评价。和现有方法 KFC、K-Means进行对比,结果表明该方法在准确率、召回率和虚警率方面具有较大优势,能够有效保证专利数据挖掘精确度,并且挖掘速度也存在明显优势。

Aimed at analyzing the current patent data, a patented method for data mining is proposed by the scale adaptive kernel correlation filtering. Based on the traditional kernel correlation filtering method, a scale adaptive method is introduced to locate and extract the key information, and a calculation method for the optimal target-scale index is given. Then, the patented data mining is established. Finally, the per- formance is evaluated by the simulation experiment. Compared with the existing methods, KFC and K- Means methods, the results show that the method has great advantages in the accuracy, the recall and the false alarm rate, ensuring the accuracy of patent mining data, and has obvious advantages at the mining speed.