Recommendation model training method and device, recommendation method and device, server and medium

A model and training sample technology, applied in neural learning methods, biological neural network models, website content management, etc., can solve the problem of low flexibility of recommendation models, and achieve the effect of autonomous updating and improving flexibility

CN114462584AActive Publication Date: 2022-05-10BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2022-05-10

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a recommendation model training method and device, a recommendation method and device, a server and a storage medium. The recommendation model training method comprises the steps of obtaining training sample data; the training sample data comprises a sample account feature, a sample information feature and an actual access result of a sample account for sample recommendation information; inputting the sample account features and the sample information features into a to-be-trained recommendation model to obtain a predicted access result of the sample account for the sample recommendation information; determining a value of a first loss function based on the predicted access result and the actual access result, and determining a value of a second loss function based on the actual value and the desired value of the gating parameter; determining a total loss value based on the value of the first loss function and the value of the second loss function; and based on the total loss value, updating the recommendation model and the gating parameters to obtain a trained recommendation model. According to the method and the device, the gating parameters can be autonomously updated, so that the flexibility of the trained recommendation model can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present disclosure relates to the technical field of information recommendation, and in particular to a training method for a recommendation model, a recommendation method, a device, a server, and a storage medium. Background technique

[0002] With the development of information recommendation technology, a technology of using neural network model to realize information recommendation has emerged. By training the recommendation model, when recommending information to users, the characteristics of the recommended information and the characteristics of users can be input into the model. , the model outputs the probability of the user accessing each recommended information, so as to provide users with highly suitable recommended information.

[0003] In related technologies, in the current recommendation model, after obtaining the features of the recommended information and the features of the user, the above-mentioned features can be skipped and inp...

Examples

Embodiment Construction

[0055] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0056] It should be noted that the terms "first" and "second" in the specification and claims of the present disclosure and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consi...