Work Order Classification Method and Device

Abstract

The present invention provides a method and device for classifying work orders. A word set is obtained by segmenting the work order; then the ratio of positive part-of-speech words and negative part-of-speech words in the word set is obtained according to the part-of-speech dictionary. If the positive part-of-speech words and If the proportion of negative part-of-speech words meets the preset threshold, it is determined that the work order is the work order category corresponding to the preset threshold; if the proportion does not meet the preset threshold, the trained Naive Bayesian is used The classifier judges the word set to obtain the work order category to which the work order belongs. The method of the present invention performs preliminary classification through the proportion of positive part-of-speech words and negative part-of-speech words in the word set, thereby reducing the amount of work orders that need to be classified by a naive Bayesian classifier, thereby improving classification efficiency, and is suitable for massive Classification of work orders with high accuracy.

Description

technical field [0001] The present invention relates to the field of communication technologies, and in particular, to a work order classification method and device. Background technique [0002] Customer service representatives of mobile operators need to process work orders for public opinion evaluations from all aspects of the Internet, such as status and comments from social networks such as Weibo and Moments. Customer service representatives are faced with a large amount of information every day, and work orders may have Complaints, suggestions, consultations, praises, etc. are different categories. In order to facilitate the customer service representatives to process a certain type of work orders, such as priority processing of complaint work orders, so as to improve the efficiency of customer service representatives in handling work orders, so These work orders need to be categorized. [0003] In the prior art, the naive Bayes algorithm is usually used to classify t...

AI Technical Summary

Problems solved by technology

In the face of the classification of massive work orders, a large amount of computing resources are required. Under the premise of limited computing resources, the performance of classification efficiency is reduced, resulting in a backlog of work orders, and work orders cannot be processed in time.

Images