Personalized Search Algorithm for E-Commerce Based on Knowledge Map and Collaborative Filtering

With the rapid development of e-commerce, personalized search has become one of the important means to enhance users' shopping experience and promote transactions. Aiming at the demand of personalized search in e-commerce, this paper proposes an algorithm based on knowledge map (KM) and collaborative filtering(CF). This algorithm combines rich semantic information in KM with CF's personalized recommendation ability, aiming at improving the relevance and accuracy of search results. The algorithm firstly constructs commodity KM by using KM, and then analyzes user behavior data by CF technology to generate personalized recommendation results for users. The experimental results show that the algorithm proposed in this paper is superior to the traditional methods in key indicators such as accuracy, recall and F1 value. The integration of KM and CF technology significantly improves the relevance and accuracy of search results, and provides users with more accurate and personalized shopping recommendation services. The personalized search algorithm of e-commerce based on KM and CF has obvious application prospect and research value, which is expected to provide a better and personalized user experience for e-commerce platform.