Recommendation algorithm based on information security professional social network platform

Abstract

The invention relates to a recommendation algorithm based on an information security professional social network platform. The recommendation algorithm mainly comprises the following steps: (1) collecting user preferences, namely discovering laws from user behaviors and preferences, recommending based on the laws, wherein the process of collecting user preference information is the decisive factor of a system recommendation effect basis and a user provides the preference information for a system in various ways; (2) analyzing content characteristics, namely after analyzing the user behaviors to obtain the user preferences, calculating similar users and articles according to the user preferences, and recommending based on the similar users and articles; and (3) calculating the similarity. The recommendation algorithm has the benefits as follows: a better recommendation mode is created, so that the user can experience that the recommended content in a talent community concerned by the user is more personalized; and simple collaborative filtering and content-based methods are mixed, so that the performance is improved, a more accurate recommendation can be provided, and the common problems of cold start and sparsity in the recommendation system can be solved.

Description

technical field [0001] The present invention relates to a professional social network platform in the field of information security technology to realize a recommendation implementation method for talents, friends, manufacturers, vulnerability information, etc., and in particular to a recommendation algorithm based on an information security professional social network platform. Background technique [0002] A social network is a platform for connecting with other people on the Internet. A social network site usually operates around the user's basic information, which refers to the user's likes, dislikes, interests, hobbies, school, occupation or any other set of common denominators, typically these sites offer varying levels of privacy controls. The consideration of this patent is mainly to adopt the innovation of the implementation method of improved hybrid collaborative filtering and content-based filtering algorithm. [0003] The recommendation system or recommendation ...

AI Technical Summary

Problems solved by technology

Collaborative filtering methods often have three problems: ① cold start: these systems usually require a large amount of user data to get accurate recommendations; ② performance: these systems often have hundreds of millions of users and products, therefore, often require a large number of Computing and high-performance server support; ③Sparse: The number of items sold on major e-commerce websites is very large, and the most active users will only evaluate a small part of the database as a whole

[0008] (2) Low activity level of users: In traditional recommendation systems, users log in to a recommendation system just to select some resources he wants, while in social network recommendation, many users go to SNS and spend more time in " It is difficult to directly obtain their explicit feedback information, and it is also difficult to learn and predict their interests;

[0010] (4) Dynamic changes in user interests: The vulnerabilities or topics that users care about have been closely following the development of information security. Therefore, the focus on SNS is constantly changing, and the interests of users are also changing. In traditional recommendation problems, users are often based on their interests. When selecting resources, in the recommendation process, there are constantly emerging attention loopholes that change the user's interest, and then the user chooses the loopholes to focus on. Therefore, the user's interest has been changing dynamically, and it is difficult to find a topic that the user is interested in for a long time

[0011] To sum up, in the professional social network of information security, it is not possible to only adopt the method of collaborative filtering, while ignoring the inherent complex relationship of the pushed content itself;

Images