Offline interactive content recommendation method and system and storage medium

Abstract

The invention discloses an offline interactive content recommendation method and system, and a storage medium. The method comprises the following steps: acquiring a target image corresponding to an offline user; according to the target image, obtaining attribute information and face features of the offline user; according to the face features of the offline user, determining whether the offline user belongs to an old user recorded by an offline user system; and if the offline user does not belong to the old user recorded by the offline user system, recommending corresponding content to the offline user according to the attribute information of the offline user. By implementing the embodiment of the invention, even in scenes such as shopping malls, book cities, tourist attractions and the like which do not have online systems and cannot acquire behavior data of the users, content (such as commodities) can be effectively recommended to the offline users; in addition, the accuracy of content recommendation can be improved, and wrong recommendation can be reduced; and the cold start problem is solved.

Description

technical field [0001] The present application relates to the technical field of human-computer interaction, and in particular to an offline interactive content recommendation method, system, and storage medium. Background technique [0002] Traditional content recommendation systems (such as product recommendation systems) generally mine user content preferences by obtaining user behavior data in the online system (such as search times, page views, page stay time, page access times, etc.), and then Then further recommend content to the user according to the content preference of the user. In practice, it is found that traditional content recommendation systems have at least the following technical defects: [0003] 1. Completely rely on the online system to capture user behavior data. If the recommended scene is offline, such as shopping malls, bookstores, tourist attractions and other scenes that do not have an online system, the user's behavior data will not be obtained,...

AI Technical Summary

Problems solved by technology

[0003] 1. Completely rely on the online system to capture user behavior data. If the recommended scene is offline, such as shopping malls, bookstores, tourist attractions and other scenes that do not have an online system, the user's behavior data will not be obtained, resulting in the inability to carry out content recommend;

[0004] 2. Only by analyzing user behavior data in the online system and recommending content, it is difficult to obtain attribute information such as user gender, age, expression, etc., which affects the accuracy of content recommendation

[0005] 3. When users with different interests use the same online account, it is easy to make wrong recommendations

[0006] 4. Cold start problem, when the user is a non-registered user without any behavior data, effective recommendation cannot be made

Images