The invention is suitable for the technical field of commodity recommendation, and particularly relates to an intelligent recommendation method and
system based on
artificial intelligence, and the method comprises the steps: intercepting a friend
list of a user in an e-commerce platform, carrying out the statistics of the chat frequency of the user with each friend, obtaining the personal data uploaded by the user, and storing the personal data in the e-commerce platform; wherein the personal data at least comprises a preference
label, integrating the personal data and chat frequency, marking close friends, and clustering the close friends into a plurality of anonymous groups by using the preference
label. By dividing the core layer and the edge layer, the
exposure rate of preferred commodities, especially new commodities or unpopular commodities, can be remarkably improved, so that information cocoon rooms are avoided, meanwhile, the core layer focuses on group sharing more, the edge layer focuses on
privacy protection and personal experience more, balance between friend recommendation and personal privacy is achieved, and user experience is improved. Therefore, the
user satisfaction and the platform benefit are greatly improved.