Take-out number identification method and device, electronic equipment and storage medium

Abstract

The invention relates to a take-out number identification method and device, electronic equipment and a storage medium, and the method comprises the steps: S1, inputting take-out number black and white list data and signaling ticket data, cleaning the data, and obtaining an original data set needed by a model through data association fusion; s2, performing comprehensive sampling on the original data set by adopting an SMOTE TomeK algorithm to form a model sample data set; s3, dividing the model sample data set into a training set and a verification set, then dividing a remaining set on the training set, and performing model training on the remaining sample training set by adopting an XGboost model, an NGboost model and a Catboost model to form a first-layer basic classifier model; s4, respectively inputting the set left on the training set and all the verification sets into a first-layer base classifier model so as to respectively output a training set predicted value set and a verification set predicted value set; s5, combining to form a new verification set prediction value set; and S6, constructing a second layer model based on a LightGBM algorithm, thereby forming an XNCLBoost model.

Description

technical field [0001] The present invention relates to network communication technology, and in particular, to a method, device, electronic device and storage medium for identifying a takeaway number. Background technique [0002] With the continuous development of the new generation of 5G communication technology, communication users experience communication technology to bring convenience to life and work; at the same time, harassing calls cause trouble to people, not only disrupting the normal life and work order of communication users, but also Greatly endangers the calls of some normal numbers. If takeaway calls are identified as harassing calls, it will harm the vital interests of the people. How to identify the takeaway number from the existing network, so as to provide users with accurate identification and prompting of the incoming call number, has become a technical issue that communication operators are generally concerned about. However, because the problem of...

AI Technical Summary

Problems solved by technology

Patent application title: A courier number identification method, equipment and computer storage medium (CN110519466A), in which, the XGB model is used to train the communication index information data to identify the courier number. Because the XGB model has many hyperparameters, it is easy to fall into a local optimal solution. Performance degrades when dealing with very high dimensional feature variables

Images