Customer service reply quality evaluation method and system
A quality evaluation and customer service technology, applied in the field of data processing, can solve the problems of missing key information points in customer service reply evaluation, low accuracy of customer service reply evaluation, etc., to achieve the effect of reducing the omission of key information points and improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] see figure 1 , Embodiment 1 of the present invention provides a method for evaluating customer service response quality, comprising the following steps:
[0030] S1. Construct a data set: compile user questions and standard words according to customer service business requirements, summarize and mark the key points of speech contained in the standard words, and randomly write key points of false words as negative samples;
[0031] S2. Evaluation model training: the user questions, the standard vocabulary and the main points of the vocabulary are spliced into a training sequence in order to train the evaluation model, and an identifier is placed in front of each of the main points of the vocabulary. Calculation of the points of the said talk points;
[0032] S3. Evaluation model test: splicing the test questions, customer service replies and the talking points, inputting the trained evaluation model, obtaining the score and label of each talking point, according to th...
Embodiment 2
[0054] see image 3 , Embodiment 2 of the present invention also provides a customer service reply quality evaluation system, which adopts the customer service reply quality evaluation method of Embodiment 1 or any possible implementation manner thereof, including:
[0055] The data set construction unit 1 is used for compiling user questions and standard vocabulary according to customer service business requirements, summarizing and marking the main points of the vocabulary contained in the standard vocabulary, and randomly writing the key points of the false speech as a negative sample;
[0056] The model training unit 2 is used for splicing the user questions, the standard vocabulary and the vocabulary points into a training sequence in order to perform evaluation model training, and an identifier is placed in front of each of the vocabulary points. The identifier calculates the score for said talk point;
[0057] The model testing unit 3 is used for splicing test question...
Embodiment 3
[0079] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, where a program code of a method for evaluating customer service response quality is stored in the computer-readable storage medium, and the program code includes a method for executing Embodiment 1 or any The customer service of the possible implementation replies to the instruction of the quality evaluation method.
[0080] A computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that includes an integration of one or more available media. The usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (SSD)), and the like.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


