Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A text classification method for customer service online quality inspection

A text classification and customer service technology, applied in text database clustering/classification, text database query, unstructured text data retrieval, etc., can solve the problems of increased data volume requirements, limited distance of CNN capture features, etc., to increase data Quantity demand, simple and easy to achieve effect

Active Publication Date: 2021-08-03
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the distance of the feature captured by the single-layer convolutional CNN is very limited, and the data volume requirements of the multi-layer convolution will increase.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A text classification method for customer service online quality inspection
  • A text classification method for customer service online quality inspection
  • A text classification method for customer service online quality inspection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with the accompanying drawings.

[0045] refer to Figure 1 ~ Figure 3 , a text classification method for customer service online quality inspection, comprising the following steps:

[0046] Step 1. Data preparation and preprocessing

[0047] The purpose of this step is to understand the data in the actual application scenario and perform corresponding data labeling. Knowing the characteristics of the data will be helpful for the subsequent data feature representation and classification model selection. This stage mainly includes the following steps:

[0048] 1.1 Speech to text

[0049] The data to be classified comes from the communication between online customer service and customers, mainly voice data, so the first step is to convert the voice data into text data.

[0050] 1.2 Data labeling

[0051] In actual scenarios, the customer and customer service have a lot of communication content in a ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A text classification method for customer service online quality inspection, comprising the following steps: step 1. speech-to-text; step 2. data annotation; step 3. data preprocessing; step 4. selecting a feature encoding method (including one-hot (word2vec) ) + position encoding, n‑gram); Step 5. Classification model selection (starspace, CNN). The problem addressed by the present invention is how to consider the entity sequence relationship when using the classification method for online customer service quality inspection. The advantages of the invention are: the word order feature is introduced, the data volume requirement is not increased, and the implementation is simple and easy.

Description

technical field [0001] The invention belongs to the field of natural language processing, and proposes a customer service online quality inspection and classification technology for effectively identifying the order of entities. Through the analysis of the existing partial feature construction methods and classification models, it summarizes their respective advantages worth learning, and combines the actual corpus of the enterprise A simple and effective classification method that considers the order of entities can be constructed in the case of small sample size. [0002] technical background [0003] Nowadays, in order to provide better service to customers, most enterprises will provide telephone consultation. In the process of online communication between customer service and customers, judging whether the customer service provides services according to the company's requirements is called online quality inspection. The current common practice is to convert the content ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/35G06F16/33G06F16/332G06F40/289G06F40/216G06N3/04G06Q30/00
CPCG06F16/355G06F16/3343G06F16/3329G06Q30/01G06N3/045
Inventor 曹斌莫志强范菁
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products