Method and device for end user loss early warning
A technology for end users and customer churn, applied in the computer field, can solve problems such as the lack of quantifiable and accurate descriptions, the constraints and limitations of human knowledge, experience and capabilities, etc.
Active Publication Date: 2017-08-08
CHINA MOBILE GROUP SICHUAN
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Existing technologies mainly rely on human experience judgments, are easily constrained and limited by the size of human knowledge, experience and ability, and lack quantifiable and precise descriptions
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] figure 1 It is a flow chart of the first embodiment of the terminal user loss early warning method of the present invention, as shown in figure 1 As shown, the end user churn early warning method provided by the embodiment of the present invention is executed by the end user churn early warning device, which is set on the server on the network side and communicated with the GB interface.
[0021] The end user churn warning device may be implemented in the form of software and / or hardware, and the method includes:
[0022] Step S100, obtain multi-dimensional user information and sampling data, the multi-dimensional user information includes user background attributes, user consumption attributes, user location attributes, and user terminal attributes, and the sample data includes the total number of off-net users, on-net The total number of users and the number of offline users and online users for each user attribute;
[0023] Step S102, calculating the information ga...
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
Login to View More Abstract
The present invention provides a terminal user loss early warning method and device, the method comprising: acquiring multi-dimensional user information and sampling data, the multi-dimensional user information includes user background attributes, user consumption attributes, user location attributes and user terminal attributes, The sampling data includes the total number of off-net users, the total number of on-net users, and the number of off-net users and on-net users of each user attribute; calculate the information gain of each user attribute in the multi-dimensional user information, and calculate the information gain of each user attribute according to the preset Set a correlation performance threshold to determine whether the information gain of each user attribute is lower than the preset correlation performance threshold; if it is higher than the preset correlation performance threshold, then use the user attribute as a strongly relevant user attributes, calculating the user churn probability of each of the strongly related user attributes. Through the analysis of historical churn data, the user attributes that are strongly related to user churn are determined, so as to give early warning of user churn.
Description
technical field [0001] The invention relates to data mining technology in the field of computers, in particular to a method and device for early warning of terminal user loss. Background technique [0002] With the diversification of mobile communication products, the loss of terminal users has become a serious problem for operators. The construction of the user loss early warning mechanism in the prior art mainly relies on the support of aggregated information and background information. Among them, the channel information support refers to the early warning of user loss based on the customer satisfaction survey during the customer consultation process. Backstage information support refers to all kinds of user information records, records the information of users in the process of network access, payment, complaint consultation and off-network, and provides them to the business and service front-end, and then relies on personnel familiar with business knowledge, rich experi...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04L12/24G06Q30/00
Inventor 谭卫郑伯勋曾为民杨荒杨霞马国军谈澄秋何清许杰叶锐曾昂黄云飞徐泗洪
Owner CHINA MOBILE GROUP SICHUAN