Customer service work order processing method and device, and server

Abstract

The invention provides a customer service work order processing method, a customer service work order processing device and a server. Based on the method, a target feature matrix associated with a plurality of customer service work order texts can be constructed according to a preset processing rule, wherein the target feature matrix may specifically comprise a plurality of word vectors, and each word vector may also comprise one or more feature values corresponding to the phrases; meanwhile, according to the plurality of customer service work order texts, word frequency and reverse file frequency which can reflect the classification effect of the phrases can be counted; according to the word frequency and the reverse file frequency of each word group, weighting processing is performed on the target feature matrix to obtain a weighted target feature matrix which is relatively more suitable for clustering processing; and clustering processing is carried out according to the weighted target feature matrix, so the plurality of customer service work order texts with relatively large data volume can be efficiently and accurately divided into corresponding work order theme groups.

Description

technical field [0001] This manual belongs to the technical field of artificial intelligence, and in particular relates to a method, device and server for processing customer service orders. Background technique [0002] The staff of the bank customer service center will receive customer service needs (or questions) fed back by a large number of users through different channels (for example, telephone, email, etc.) every day. Usually the staff cannot directly solve the customer service needs for the users, but they will first record the customer service needs and form a corresponding customer service work order. In the future, the above customer service work orders will be uniformly classified, and different types of customer service work orders will be distributed to the corresponding customer service processing personnel for specific processing. [0003] Based on the existing methods, it is often necessary to rely on the staff to manually classify the above customer servi...

AI Technical Summary

Problems solved by technology

However, when faced with a customer service work order with a large amount of data, the above method often has low efficiency and is prone to errors when implemented.

[0004] For the above problems, no effective solution has been proposed

Images