Personalized recommendation method

Abstract

The invention discloses a personalized recommendation method. The method comprises the following steps of: acquiring basic data; processing and classifying the basic data, and analyzing the interest and preference of a purchaser on the basis of historic operation behavior records of the purchaser; filtering and collecting seller information and product information according to a preset rule; correspondingly acquiring a set of products to be recommended according to the interest and preference data information of the purchaser, the seller information and the product information on the basis of a preset matching algorithm; de-duplicating, sorting, weighting and standardizing all products to be recommended, and thus obtaining N optimally-matched products which serve as a recommendation result; and displaying the final recommendation result to the purchaser. By adoption of the personalized recommendation method, the product information which is in accordance with the interest and preference of a user can be accurately recommended to the user in the conventional electronic-commerce business-to-business (B2B) website.

Description

technical field [0001] The invention relates to the field of e-commerce B2B transactions, in particular to a personalized recommendation method. Background technique [0002] E-commerce is a main manifestation of modern B2B. It closely combines the intranet of the enterprise with customers through the B2B website, provides services for customers, and promotes the business development of enterprises. In recent years, the scale of Internet transactions (B2B) of Chinese enterprises has been among the best in the global market. With the continuous expansion of e-commerce scale, the number of products has grown rapidly. It becomes more complicated. Faced with countless product information, users often get lost in a large amount of product information space and cannot find the product they need smoothly. In order to solve this problem and improve the service capability of e-commerce platform, personalized recommendation system came into being. [0003] A personalized recommendat...

AI Technical Summary

Problems solved by technology

[0004] In the existing personalized recommendation system, it is an important recommendation type in the current personalized recommendation technology to recommend products that meet the user's interests and hobbies through the analysis of the characteristics of the user's evaluation object. For example, a patent CN201010158541.9 provides a A device that recommends a product list that matches the user's preferences to a user who uses the e-commerce platform for shopping, but this recommendation method has the problem of single analysis of user operation behavior, that is, only by analyzing the user's purchase operation. interests and preferences of users, other user operations (such as searching, asking sellers, etc.) are often ignored by the system, and these neglected operations can precisely reflect the interests and preferences of users; , the existing recommendation technology often directly calculates the matching degree of user preferences and all products, without pre-screening and sorting the information of the recommended products, resulting in uneven quality of recommended product information, and cannot guarantee the quality of recommended products, such as patent CN201010251374. In 2, users are classified based on their access behavior, information resources that match the user category are determined according to the user category, and then information resources are recommended to users. There is a lack of pre-screening of recommended information resources, although a wide range of More sharing of information content among users, but the quality of recommended information resources cannot be guaranteed

Images