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

Off-network prediction method and device, server and storage medium

A prediction method and off-grid technology, applied in the field of mobile communications, can solve problems such as prone to prediction errors and low accuracy

Inactive Publication Date: 2020-04-07
北京红山信息科技研究院有限公司
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Traditional forecasting methods have low accuracy and are prone to forecast errors

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
  • Off-network prediction method and device, server and storage medium
  • Off-network prediction method and device, server and storage medium
  • Off-network prediction method and device, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] figure 1 The flow chart of an off-grid prediction method provided in Embodiment 1 of the present invention is applicable to the case where the off-grid prediction model has been trained in advance, and specifically includes the following steps:

[0059] S101. Obtain user data of a mobile account, where the user data includes personal information characteristics, consumption behavior characteristics, call behavior characteristics, complaint times and / or network speed.

[0060] The user data described in this step includes but is not limited to personal information characteristics, consumption behavior characteristics, call behavior characteristics, number of complaints and / or network speed, and may also include some relatively static characteristics, such as the customer’s gender, age, etc., as well as Dynamic features, such as the user's number of calls, call time, etc. The user data used in off-grid prediction can be divided into categories such as user personal infor...

Embodiment 2

[0067] Such as image 3 As shown, this embodiment adds the training steps of the off-grid prediction model on the basis of the above-mentioned embodiments, wherein the modeling process of the off-grid prediction model uses a stacking layered algorithm, and the hierarchical structure of the algorithm is similar to that of a neural network. In theory, It can be superimposed to any number of layers. Specifically, for the test set, we first use the primary learner to predict once to obtain the input samples of the secondary learner, and then use the secondary learner to predict once to obtain the final prediction result.

[0068] In this embodiment, it is preferable to use a two-layer algorithm to achieve a better integration effect on the basis of the algorithm being as concise as possible. The second-level classification is performed on the basis of the first-level classifier, and the second-level classifier obtained by training is The classifier is used as the final off-grid pr...

Embodiment 3

[0101] Such as Figure 4 As shown, the present embodiment provides an off-grid prediction device 3, including:

[0102] The first acquisition module 301 is configured to acquire user data of a mobile account, the user data including personal information characteristics, consumption behavior characteristics, call behavior characteristics, number of complaints and / or network speed;

[0103] Prediction module 302, inputting the user data into the pre-trained off-network prediction model to obtain the off-network prediction result of the mobile account;

[0104] A determination module 303, configured to determine whether the mobile account will be offline at the time point to be tested according to the off-network prediction result.

[0105] Such as Figure 5 As shown, in an alternative embodiment, the training process of the off-grid prediction model in the prediction module 302 includes the following modules:

[0106] The second acquisition module 304 is used to acquire histo...

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 off-network prediction method, which is used for acquiring user data of a mobile account, and the user data comprises personal information characteristics, consumption behavior characteristics, call behavior characteristics, complaint times and / or network speed. The user data is input into a pre-trained off-network prediction model to obtain an off-network prediction result of the mobile account; and whether the mobile account is off-network at the to-be-tested time point is determined according to the off-network prediction result. The invention further discloses anoff-network prediction device, a server and a storage medium. According to the off-network prediction method provided by the invention, the off-network prediction model is used, and the user data isinput into the model to obtain the off-network prediction result, so that whether the mobile account is off-network or not is accurately predicted, and the off-network prediction accuracy is improved.

Description

technical field [0001] The embodiments of the present invention relate to technologies in the field of mobile communications, and in particular to an off-grid prediction method, device, server and storage medium. Background technique [0002] In the field of communications, customers can be said to be the main source of revenue for operators. Both the communication charges of customers and the data generated by them have huge economic value for operators. Therefore, how to win the favor of customers has become a problem for operators. [0003] Therefore, how to retain old customers, how to discover the trend of customers leaving the network early and propose various preferential policies to retain customers are the problems that major operators must concentrate on solving. At this time, off-grid prediction comes into being. It refers to predicting whether the user will leave the grid in advance through various data of the user, such as age, gender, calling habits, geographic...

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): H04L12/24G06K9/62
CPCH04L41/147H04L41/145G06F18/24
Inventor 张英乔向阳林昀
Owner 北京红山信息科技研究院有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com