Advertisement click rate estimation method based on improved Transformer

Abstract

The invention discloses an advertisement click rate estimation method based on an improved Transformer, and the method is characterized in that the method comprises the steps: obtaining a historical behavior record of a user, constructing a historical click sequence of the user, and obtaining a target advertisement feature vector, a context feature vector and a user portrait feature vector; inputting into an embedded layer, and obtaining a corresponding embedded vector through an Embedded technology of the embedded layer; and inputting the embedded vector of the historical click sequence of the user into an improved Transformer network, carrying out improved coding on the article position of the click sequence of the user, extracting the historical interest of the user, and extracting theembedded vector of the historical interest of the user and the embedded vector of the target advertisement through an attention mechanism by adopting Sampleoff supervision interest; otaining user historical interests after target advertisement relevancy weighting; and splicing the weighted embedded vectors of the user historical interests, the target advertisement features, the context features and the user portrait features, then inputting the spliced embedded vectors into a subsequent multilayer perceptron, and obtaining an estimated advertisement click probability through a softmax activation function.

Description

technical field [0001] The invention belongs to the field of advertising click-through rate estimation, in particular to an advertising click-through rate estimation method based on an improved Transformer. Background technique [0002] Advertisement click-through rate refers to the probability that an ad is clicked by a user during an ad display. Advertisement click-through rate estimation refers to estimating the probability of a target advertisement being clicked based on user data and advertisement data. In the current big data scenario, advertising is changing from the "extensive" delivery in the past to the "precise" delivery. Data-driven precise advertising has become the mainstream method of current advertising. Programmatic buying on the advertising demand side In the process of advertising and online delivery, it is necessary to pre-evaluate the user's preference for advertisements, and the process of measuring this important indicator is the advertisement click-t...

AI Technical Summary

Problems solved by technology

[0005] However, the current method mainly has the following problems: 1) The current advertising click-through rate estimation method directly regards the user's click behavior as the user's interest, and lacks the modeling of the user's behavior sequence; 2) The user's behavior is extensive and dynamic Changes, the previous method is to treat the interests of users equally, which is obviously inconsistent with the facts

[0008] However, combining the timeliness of user historical behavior, the relevance of target advertisements, improving the Transformer and attention mechanism, etc., the technology to further explore the method of predicting the click-through rate of advertisements needs to be further innovated.

Images