Method and equipment for classifying business data

Abstract

The invention relates to a method for classifying business data, which comprises the following steps of: predicting classification information corresponding to the business data by using a classification model, and calibrating the classification information of the business data during the processing of the business data of which the classification information is predicted by the classification model in a business process; and when the processing of the business data is completed, using the business data and the calibrated classification information corresponding to the business data as training data for updating the classification model, and updating the classification model.

Description

technical field [0001] This application relates to data processing, in particular to a method and device for classifying business data. Background technique [0002] In many service industries such as the catering industry, feedback (especially user complaints) is an important channel to obtain user and market responses to proposed products and / or services. Especially in the catering industry, because it involves food public health safety, user complaints must be taken seriously and handled in a timely manner. The user's complaint information may include the category corresponding to the user's complaint information, so the complaint information should be distributed to the business personnel corresponding to the category for processing. [0003] In the traditional service industry, manual methods are usually used to classify user complaint information, so a large number of customer service departments need to be maintained, resulting in high labor costs. In recent years, ...

AI Technical Summary

Problems solved by technology

Machine learning methods require the use of training data to train the parameters of a machine learning model such as a neural network, but too little known data to make up the training data still hinders parameter optimization of classification models

In addition, the artificially provided training data cannot avoid the training data containing wrong information (such as classification labels) due to omissions, so that the prediction results of the trained classification model cannot accurately reflect the category to which the complaint information belongs

Images