Network satisfaction prediction model construction method and device, and network satisfaction prediction method and device

Abstract

The invention relates to a network satisfaction prediction model construction method comprising the following steps: obtaining user data, and constructing a sample data set, the user data comprising at least two kinds of index data; classifying the user data in the sample data set according to different user types; for each user type, constructing at least two sub-models of the user type according to at least two kinds of index data included in the user data under the user type; and for each user type, constructing a hybrid model according to the at least two sub-models of the user type, and taking the hybrid model as a network satisfaction prediction model of the user type. The invention also provides a network satisfaction prediction method using the constructed model. According to the method and the device, the network satisfaction of the user can be predicted more accurately.

Description

technical field [0001] The present application relates to the technical fields of communication network and machine learning modeling, and in particular to a method and device for constructing a network satisfaction prediction model, a method and device for network satisfaction prediction, a computing device, and a computer-readable storage medium. Background technique [0002] In the research scenario of user network satisfaction of telecom operators, the current research method is a research on all users as a whole. However, usually different user groups may have different satisfaction feelings. For example, users with different network behaviors (network behaviors such as voice calls, online games, and online videos, etc.) often have different experience perceptions for the same level of objective network performance. For example, under the same network conditions with medium response delay and high download rate, users who prefer online games may have a poor experience ...

AI Technical Summary

Problems solved by technology

For example, under the same network conditions with medium response delay and high download rate, users who prefer online games may have a poor experience perception, but users who prefer movies and TV may have relatively better experience perception

[0003] On the other hand, when studying the user's network satisfaction, the current main method is to use the decision tree algorithm as the prediction model, which can only predict the user's satisfaction category by binary classification, that is, satisfied or dissatisfied, and cannot accurately predict network satisfaction. Degree Specific Score

[0004] To sum up, in the current research on user network satisfaction, there is a lack of detailed classification of users, and the method of predicting network satisfaction is relatively simple, resulting in inaccurate user network satisfaction prediction results.

Images