Recommendation method and device and device for recommendation

Abstract

The embodiment of the invention provides a recommendation method and device and a device for recommendation, and the method specifically comprises the steps: determining a demand word corresponding toexpression behavior data of a user by using a preset word bank; wherein the preset lexicon is used for storing preset words, and the commercial values of the preset words accord with a first condition; determining a recommendation object according to the demand word; and providing the recommendation object to the user, or sending access entry information of the user to a supplier terminal corresponding to the recommendation object, so that the supplier terminal transmits the recommendation object to the user terminal of the user through the access entry information. According to the embodiment of the invention, the interpretability of the recommended object can be improved, and the test cost can be reduced.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a recommendation method and device, and a device for recommendation. Background technique [0002] With the rapid development of information technology, the information in the network is growing explosively, which greatly enriches the daily life of users, but on the other hand, it also makes it more difficult for users to quickly and accurately find the information they are interested in. Therefore, the method of recommending the required information to the user is particularly important. [0003] Existing recommendation methods usually use machine learning models to predict the recommended objects required by users; among them, the machine learning model can train the user's behavior data, so that it can get similar to the object corresponding to the user's behavior data. Recommended object. For example, if the user's behavior data indicates that the user has view...

AI Technical Summary

Problems solved by technology

[0004] However, the machine learning model is actually a black-box model, which usually can only give the prediction result of the recommended object, but cannot give the reason for the prediction result. Therefore, the existing recommendation methods are not very explanatory for the recommended object

In this way, the provider of the recommended object will reduce the trust of the existing recommendation method. In practical applications, it is often necessary to test the existing recommendation method through a long test cycle to improve the provider's confidence in the existing recommendation method. trustworthiness of the recommended method; however, a longer testing cycle will consume a certain amount of testing costs

Images