Designing And Implementing Search System Aiming At Diversifying Structured Product Search Results

In recent years, online shopping is becoming more and more popular. Users type keyword queries on product search systems to find relevant products, accessories, and even related products. However, existing product search systems always return very similar products on the first several pages instead of taking diversity into consideration. In this paper, we propose a novel approach to address the diversity issue in the context of product search. We transform search result diver-sification into a combination of product attribute diversification, product category diversification and product source diversification. In the attribute diversification phase, we choose the number of distinct attribute values as the objective. The problem can be reduced to Weighted Maximum Coverage Problem, so can be solved using greedy-based approximation algorithms. In the cate-gory diversification phase, the average distance among the search results is taken into the objective function. Then the problem can be reduced to Facility Dispersion Problem, and can also be solved using approximation algorithms. In the source diversification phase, we introduce source penalty score for products from the same source, then propose a merge-sort based algorithms to solve the optimization problem. Based on the re-ranking algorithms, we further propose a diversity oriented product search system. The diversification algorithms act as the post query processing part of the system. The experiments on real product data show the effectiveness of the algorithms and the system.