Efficient Knowledge Acquisition: Standard Essential Patent Analysis Based on Elephant Herding Optimized Kernel-Adaptive Support Vector Machine

Abstract

A significant area of research is the effective acquisition of knowledge via patent analysis, especially in the fast-developing sector of electric cars. As they can quickly and effectively assess massive volumes of patent data, machine learning approaches can be very useful because they can recognize patterns and developments that are challenging to spot manually. This article provides a unique elephant herding optimized kernel-adaptive support vector machine (EHO-KSVM) method for effective knowledge acquisition utilizing machine learning (ML) on electric car patent data. To evaluate the efficacy of the suggested EHO-KSVM approach, data from the G06F patents were first gathered. In this work, the raw data is first pre-processed using NLP methods, and then the important data is extracted from patent databases using principal component analysis (PCA). Then, we analyze the data using the EHO-KSVM approach to spot patterns and trends that can be utilized to forecast technological developments and offer perceptions into new markets. The outcomes show that the suggested strategy can greatly reduce the time and effort needed to acquire knowledge and provide insightful information for decision-makers in electric car technology.