Unlock instant, AI-driven research and patent intelligence for your innovation.

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.

Active Publication Date: 2020-05-12
GUANGZHOU PACIFIC COMP INFORMATION CONSULTINGCO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art, and propose an advertisement recommendation method based on feature cross joint deep neural network, which can effectively solve the shortcomings of feature engineering work being too cumbersome, and has achieved automatic feature mining to improve the accuracy of advertisement placement degree, thereby improving the effectiveness of advertising recommendations and improving the advertising CTR index

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An advertising recommendation method based on feature cross joint deep neural network
  • An advertising recommendation method based on feature cross joint deep neural network
  • An advertising recommendation method based on feature cross joint deep neural network

Examples

Experimental program
Comparison scheme
Effect test

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...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an advertisement recommendation method based on a feature cross joint deep neural network. The method comprises the steps that 1) a server collects advertisement logs of an advertisement platform for data cleaning; data samples are added into a sample stream; data are stored in a storage module of a distributed file system; 2) the server uses a recall layer to filter the data of the sample stream to acquire preliminary candidate recommendation advertisement ID subsets for a user; and 3) the server sorts and predicts the candidate recommendation advertisement ID subsetsto acquire a corresponding user advertisement push subset. According to the invention, the effectiveness of advertisement recommendation is improved, and an advertisement CTR index is improved.

Description

technical field [0001] The invention relates to the technical field of an online programmatic advertising platform, in particular to an advertisement recommendation method based on a feature cross joint deep neural network. Background technique [0002] With the popularity and rapid development of the mobile Internet, online advertising has emerged as the times require. Online advertising, also known as online advertising, Internet advertising, as the name suggests, refers to the advertisements placed on online media. Different from traditional advertising, online advertising has formed a technology-based delivery model that targets people and is product-oriented in its short ten years of development. Online advertising not only brings advertisers a brand-new marketing channel based on the methodology of accurately reaching the target audience, but also finds a means of large-scale realization for Internet free products and media providers. [0003] At present, programmati...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q30/02G06F16/182
CPCG06Q30/0271
Inventor 余志文麦文军张乙东郭丽娟郑洁纯施一帆
Owner GUANGZHOU PACIFIC COMP INFORMATION CONSULTINGCO LTD