Knowledge-space-based behavior result evaluation method and device

A spatial and behavioral technology, applied in the field of data analysis, can solve problems such as difficult to accurately predict results and lack of data support

Inactive Publication Date: 2016-07-13
HUAWEI TECH CO LTD
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The current system only uses the analysis results of the model, and the account manager then selects some marketing behavior methods to maintain users based on experience. The behavior selection of this maintenance method is only based on the experience of the account manager. Without certain data support, it is difficult to be accurate Predict the results of behavioral actions and conduct effective action evaluations to achieve the minimum cost and maximum customer retention effect

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
  • Knowledge-space-based behavior result evaluation method and device
  • Knowledge-space-based behavior result evaluation method and device
  • Knowledge-space-based behavior result evaluation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, a method for evaluating behavioral results based on knowledge space in Embodiment 1 of the present invention, the method includes the following steps:

[0057] Step 101: Obtain the user set with the highest predicted probability of leaving the network within the third time period in the second user concentration and obtain the user set with the highest predicted probability of leaving the network in the third time period in the third user concentration through the user departure prediction model, wherein The third user set includes at least one user who has been subjected to marketing or promotional actions within the second time period, and the second user set includes at least one user who has not been subjected to marketing or promotional actions within the second time period , the user churn prediction model is used to obtain the user churn prediction probability based on user historical data, the user historical data includes user basic i...

Embodiment 2

[0082] Such as image 3 As shown, a knowledge space-based behavior result evaluation method in Embodiment 2 of the present invention includes the following steps:

[0083] Step 101. Obtain user history data, which includes user basic information, user consumption information, user off-net information, and user historical action information, where the historical action information indicates marketing or promotional actions performed on the user;

[0084] Step 102: Using the historical data of the first user set in the user historical data in the first time period to train and generate the first user churn prediction model, the first user set includes users who have not been marketing in the first time period Or at least one user of a promotional action, the first time period is any time period in the past, and the first user churn prediction model is used to obtain the user churn probability based on user historical data except historical action information;

[0085] Step 103:...

Embodiment 3

[0093] Such as Figure 4 As shown, a behavior result evaluation system based on knowledge space in Embodiment 3 of the present invention includes:

[0094] The off-grid predictor is used to use the user historical data to train and generate the user off-grid prediction model and input the historical data of the first time period into the user off-grid prediction model to obtain the highest probability of off-grid prediction in the second time period users, the user history data includes user basic information, user consumption information, user off-net information and user historical action information, the historical action information indicates the marketing or promotional actions implemented on the user, the second time The segment is the next time segment of the first time;

[0095] An action effect evaluator, configured to establish a mapping relationship between the historical action information of the user with the highest predicted probability of leaving the network w...

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 provides a knowledge-space-based behavior result evaluation method. The method is applied based on the analysis result of a user offline prediction model provided by an operator, an airline or any other service providers, and the behavior result of a user that might be off the line is compared and evaluated finally. Through training an offline prediction model, the data of the user is subjected to offline prediction and probability prediction. Meanwhile, through evaluating the influence of marketing or promotion means on the offline prediction probability change, a most efficient marketing means is selected. Therefore, the retention is conducted for users that are mostly likely to get off the line. Meanwhile, the maximum revenue is realized on the premise that the cost is limited to a certain degree.

Description

technical field [0001] The invention relates to the field of data analysis, in particular to a knowledge space-based behavior result evaluation method and device. Background technique [0002] For any service provider, such as telecom operators (China Mobile, China Unicom, etc.), airlines and other service providers (travel services, e-commerce services, etc.), the core business model includes two parts: stock operation and growth Volume management. Inventory management refers to the maintenance and service of current users. One of the core tasks is how to keep users, especially high-value users, from being lost to the greatest extent. Incremental operation refers to the creation of new business models to obtain more profits. For example, in addition to providing basic call and data services, telecom operators provide user data analysis support for third-party service companies (such as providing information such as user classification and traffic in a certain area for thi...

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): G06Q30/02G06Q50/10G06F17/30
Inventor 杨强袁明轩曾嘉戴文渊
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap