General recommendation method and system based on object tags

Abstract

The invention relates to a general recommendation method and a system based on object tags. The general recommendation method the based on the object tags comprises the following steps of obtaining a user tag and candidate recommendation object tags; obtaining correlation between the user tag and the candidate recommendation object tags; and choosing candidates and recommending the candidates to a user according to the correlation. The invention provides a unified object correlation calculation method based on the object tags and a general recommendation theory model based on the correlation calculation, and a practical recommendation system is built to prove the validity of the method. The general recommendation system can be applied to almost all the personalized recommendation occasions and part non-personalized recommendation occasions, and has the advantages of being general in data, easy and convenient to deploy, and flexible to expand, and can be deployed and used very conveniently.

Description

technical field [0001] The invention relates to the field of Internet information mining, in particular to a general recommendation method and system based on object tags. Background technique [0002] The existing non-personalized recommendation methods mainly include hotspot recommendation and manual recommendation, both of which recommend the recommendation results to all users indiscriminately. The results of the former come from the choices of most users, while the results of the latter are Rely on artificial selection. [0003] Existing personalized recommendation systems are mainly divided into the following different systems: [0004] Statistical system: This system directly recommends the target object to the right person by mining social information such as the user's age, address, and income. For example, some personalized advertising products, most advertising emails, etc. [0005] Advantages: The method is simple and the amount of calculation is small; [00...

AI Technical Summary

Problems solved by technology

[0006] Disadvantages: 1. The recommended object must be classified and mapped in advance. If the number of entities is large, it will face the problem of high mapping cost and low accuracy; 2. It is difficult to obtain user information, with low credibility and high user resistance; 3. Recommendation accuracy low, poor effect

[0009] Disadvantages: 1. The recommended object must be classified and mapped in advance. If the number of entities is large, it will face the problem of high mapping cost and low precision; 2. The flexibility is not enough, and the change of user interest cannot be correctly reflected, resulting in too rigid recommendation results; 3. The number of categories is limited, and users' interests cannot be described in detail, resulting in inaccurate recommendation results

[0012] Disadvantages: 1. The recommendation for niche users is not good; 2. The data cannot be reused or generalized, and the data in each field can only be applied to the field itself

Images