An advertising recommendation method based on feature cross joint deep neural network
A technology of deep neural network and recommendation method, which is applied in the field of advertisement recommendation based on feature intersection combined with deep neural network, which can solve cumbersome problems and achieve the effect of reducing the cost of artificial design features.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0046] The present invention will be further described below in conjunction with specific examples.
[0047] Such as figure 1 As shown, the advertisement recommendation method based on the feature cross joint deep neural network provided in this embodiment includes the following steps:
[0048] 1) The server collects the advertising logs of the advertising platform for data cleaning, adds the data samples into the sample stream, and stores the data in the storage module of the distributed file system;
[0049] 1.1) Data cleaning of advertising logs, including filtering of cheating data and noise data, filtering of cheating data and noise data mainly refers to all records in the advertising log, according to the set time granularity, the advertising Advertising actions such as displaying and clicking frequently appear on the advertising platform, and the frequency of the above-mentioned advertising actions exceeds the normal user’s interaction frequency with the advertisements...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


