Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Message recommendation method and device based on neural network, equipment and storage medium

A technology of neural network and recommendation method, which is applied in the field of neural network-based message recommendation method, equipment, storage medium, and device, which can solve the problems of low click-through rate and low reach rate of push messages, so as to improve the accuracy of prediction , improve the effect of click efficiency

Pending Publication Date: 2021-12-07
WEIKUN (SHANGHAI) TECH SERVICE CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, some users will not open the push information when they receive the push information due to reasons such as work status, and even some notification channels are not owned by all users, resulting in a low reach rate of push messages, causing users to Push messages have a low click-through rate

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
  • Message recommendation method and device based on neural network, equipment and storage medium
  • Message recommendation method and device based on neural network, equipment and storage medium
  • Message recommendation method and device based on neural network, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0051] see image 3 , image 3 A specific implementation of step S1 is shown, which is described in detail as follows:

[0052] S11. Obtain user information data from the database.

[0053] Specifically, the user information data is identified from the database by using the user identity, such as user name and ID card number, by acquiring the user identity.

[0054] S12. Perform data cleaning on the user information data to obtain basic data.

[0055] S13. Using regular matching, extract identity information, work information and age information from the basic data, and convert the identity information and work information into corresponding occupation information.

[0056] Specifically, various information data of users are stored in the database, including user name, age, work unit, school, etc., and since age information needs to be extracted from user information data, in order to ensure data validity and To improve the efficiency of data extraction, first perform data...

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 relates to the technical field of artificial intelligence, and discloses a message recommendation method and device based on a neural network, equipment and a storage medium, and the method comprises the steps: obtaining user information data, carrying out feature extraction of the user information data, and vectorizing occupational information, age information and preset dimension information based on a preset sequence, obtaining initial data; inputting the initial data into an error reverse neural network model for training to obtain a prediction model; vectorizing the to-be-recommended user information data to obtain target data; performing prediction calculation on the target data through the prediction model to obtain a target prediction value; and pushing the to-be-recommended message to the to-be-recommended user based on the target predicted value. The invention further relates to a block chain technology, and the user information data is stored in the block chain. The features of the to-be-recommended user are calculated in combination with multiple dimensions, the optimal recommendation scheme is output, and the click efficiency of the recommendation information can be improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a neural network-based message recommendation method, device, equipment and storage medium. Background technique [0002] With the rapid development of the Internet, the importance of user data is increasing day by day. With in-depth insight into users' online and offline behaviors, a comprehensive, accurate and multi-dimensional user portrait system can be built to provide enterprises with rich user portrait data and real-time scene recognition capabilities. , to help companies understand users in an all-round way, and personalized recommendations came into being. Multi-dimensional label classification, real-time scene screening, and real-time operation for thousands of people. These all belong to the use of AI and machine learning for content creation, and the use of AI and machine learning for content recommendation optimization. [0003] The exi...

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 Applications(China)
IPC IPC(8): G06F16/9535G06F16/215G06N3/04G06N3/08G06Q30/06H04L29/08
CPCG06F16/9535G06F16/215G06N3/084H04L67/55G06N3/044
Inventor 刘洋
Owner WEIKUN (SHANGHAI) TECH SERVICE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products