Research on Precision Advertising Push Method based on Neural Network
This project relates to an accurate advertising push method based on neural network, which belongs to the field of advertising technology.The method comprises the following steps: obtaining the sample vectors of each sample of potential users corresponding to the target advertisement;The sample vector is used to train the depth Q network, and the target depth Q network corresponding to the trained target advertisement is obtained;Obtain the target vector of each potential user corresponding to the target advertisement;According to the target vector and target depth Q network of potential users corresponding to the target advertisement, the target potential users to be pushed by the target advertisement at the next push time are obtained.This project can reduce the advertising expenses of enterprises, and also make the effect of enterprise advertising push better.
References
- Influenza big data analysis based on neural network [J]Lu Min;Duan Jinbin;Ge Xianshun, Chinese Journal of Medical Library and Information, 2020 (03).
- Dialogue system memory mechanism based on recurrent neural network [J]Yi Wei;He Jia;Zou Maoyang, Computer Engineering and Design, 2019 (11).
- Digital nerve extends to great wisdom -- commercial application of scanning neural network technology [J]Zhu Yan. Internet Weekly, 1999 (17).
- Session oriented demand awareness attention graph neural network recommendation model [J]Zheng Xiaoli;Wang Wei;Du Yuhui;Zhang Chuang. Computer Engineering and Application.
- Small sample face recognition based on twin neural network [J]Wan Lizhi;Zhang Yunchu; Gezhedong; Wang Chao. Journal of Shandong Jianzhu University, 2022 (01).
- Expert recommendation method of attention map neural network based on memory [J]Chen Zhuo;Zhu Miao;Du Junwei;Yuan Ximing. Journal of Hunan University (Natural Science Edition), 2022 (06).
- Research and analysis of housing price prediction based on neural network [J]Zheng Weipeng;Si Yachao. Journal of Hebei Institute of Architecture and Engineering, 2022 (01).
- Topic trend prediction method combining cyclic neural network and convolutional neural network [J]Liu Chen;Liu Chao, Industrial Control Computer, 2022 (08).
- Click rate prediction model based on deep neural network [J]Liu Hongli;Wusen;Wei Guiying;Li Xin;Gao Xiaonan. Journal of Engineering Science, 2022 (11).
- Second change makeup system based on deep neural network [J]Shen Junyu;Li Xuchen;Hu Chao; Sun Xiaoyu;Qiu Shuangfei;Nie Xiaowei;Le Optics. Computer Knowledge and Technology, 2022 (27).