CN117198265A - Customer service training system, method, electronic equipment and storage medium - Google Patents

Customer service training system, method, electronic equipment and storage medium Download PDF

Info

Publication number
CN117198265A
CN117198265A CN202311138675.8A CN202311138675A CN117198265A CN 117198265 A CN117198265 A CN 117198265A CN 202311138675 A CN202311138675 A CN 202311138675A CN 117198265 A CN117198265 A CN 117198265A
Authority
CN
China
Prior art keywords
customer service
content
training
dialogue
trained
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311138675.8A
Other languages
Chinese (zh)
Inventor
李笑宇
唐雪涛
徐梓丞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202311138675.8A priority Critical patent/CN117198265A/en
Publication of CN117198265A publication Critical patent/CN117198265A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G06Q50/2057—Career enhancement or continuing education service
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/225—Feedback of the input speech

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Child & Adolescent Psychology (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The application provides a customer service training system, a customer service training method, an electronic device and a storage medium, which can be applied to the field of artificial intelligence or the field of finance, wherein the customer service training system comprises: a dialogue generating module and a text voice converting module; the dialogue generation module is used for generating dialogue content according to the exercise scene and the response technology, and sending the dialogue content to the text-to-speech conversion module, wherein the dialogue content comprises dialogue content texts, mood state parameters and speech speed parameters; the text-to-speech conversion module is used for converting text and speech of the dialogue content to obtain first audio information corresponding to the dialogue content; the text-to-speech conversion module is further configured to play the first audio information to a customer service to be trained, so that the customer service to be trained performs training according to the first audio information. According to the customer service training method and the customer service training system, customer service is trained by simulating dialogue contents of customers in various scenes, and training efficiency of customer service personnel is improved.

Description

Customer service training system, method, electronic equipment and storage medium
Technical Field
The application relates to the field of artificial intelligence, in particular to a customer service training system, a customer service training method, electronic equipment and a storage medium.
Background
The customer service center of the bank is used as one of the most important service windows of the bank, and the quality of customer service staff can influence the core competitiveness of the bank and the brand image of the bank. The customer consultation quantity is large, the accuracy and timeliness requirements of the customer on consultation reply are high, the mobility of the manual customer service personnel is large, the time and the labor are consumed in the manual customer service training time, and the like, so that the satisfaction degree of the service of the bank customer service faces the test.
At present, in the training process of the bank manual customer service personnel, the speech skill recitation and one-to-one dialogue training are adopted to improve the speech skill level of the manual customer service personnel, but various clients encountered in actual work cannot be simulated when one-to-one dialogue training is carried out, so that the training efficiency is low.
Disclosure of Invention
In view of the above, the application provides a customer service training system, a customer service training method, an electronic device and a storage medium, which aim to improve training efficiency of customer service personnel.
A first aspect of the present application provides a customer service training system, the system comprising: a dialogue generating module and a text voice converting module;
the dialogue generation module is used for generating dialogue content according to the exercise scene and the response technology, and sending the dialogue content to the text-to-speech conversion module, wherein the dialogue content comprises dialogue content texts, mood state parameters and speech speed parameters;
the text-to-speech conversion module is used for converting text and speech of the dialogue content to obtain first audio information corresponding to the dialogue content;
the text-to-speech conversion module is further configured to play the first audio information to a customer service to be trained, so that the customer service to be trained performs training according to the first audio information.
Optionally, the system further comprises: a speech surgery detection evaluation module;
the text-to-speech conversion module is further used for collecting second audio information of the customer service to be trained, wherein the second audio information is answer content of the first audio information by the customer service to be trained according to answering operation;
the text-to-speech conversion module is further configured to perform text-to-speech conversion on the second audio information to obtain answering content corresponding to the second audio information, and send the answering content to the speech detection and evaluation module, where the answering content includes answering content text, speech speed parameters, intonation parameters and emotion parameters;
and the conversation detection evaluation module is used for scoring the answer content to obtain the training score of the customer service to be trained.
Optionally, the speaking detection and evaluation module is specifically configured to analyze the answer content, and score the answer content according to a scoring manner, where the scoring manner includes speech recognition, sensitive word recognition, and emotion recognition.
Optionally, the text-to-speech conversion module is further configured to send the answer content to the dialogue generation module;
and the dialogue generating module is also used for training the training scene generating model according to the answering content.
Optionally, the speaking detection evaluation module is configured to perform speaking detection according to the answer content, and obtain speaking suggestions.
Optionally, the system further comprises a training management module;
the training management module is used for distributing the training scene for the customer service to be trained according to the training record of the customer service to be trained and sending the training scene to the dialogue generation module.
The second aspect of the present application provides a customer service training method, which is applied to a customer service training system provided by an embodiment of the present application, where the method includes:
generating dialogue content according to the exercise scene and the answering operation, and sending the dialogue content to a text-to-speech conversion module, wherein the dialogue content comprises dialogue content texts, mood state parameters and speech speed parameters;
text-to-speech conversion is carried out on the dialogue content to obtain first audio information corresponding to the dialogue content;
and playing the first audio information to a customer service to be trained, so that the customer service to be trained trains according to the first audio information.
Optionally, the method further comprises:
collecting second audio information of the customer service to be trained, wherein the second audio information is answering content of the first audio information by the customer service to be trained according to answering operation;
performing text-to-speech conversion on the second audio information to obtain answering contents corresponding to the second audio information, and sending the answering contents to the speech detection and evaluation module, wherein the answering contents comprise answering content texts, speech speed parameters, intonation parameters and emotion parameters;
and scoring the answer content to obtain the training score of the customer service to be trained.
Optionally, the method further comprises:
and analyzing the answer content, and grading the answer content according to grading modes, wherein the grading modes comprise voice recognition, sensitive word recognition and emotion recognition.
Optionally, the method further comprises:
transmitting the answer content to the dialogue generating module;
and training the training scene generation model according to the answering content.
Optionally, the method further comprises:
and performing speaking detection according to the answering content to obtain speaking suggestions.
Optionally, the method further comprises:
and distributing the training scene to the customer service to be trained according to the training record of the customer service to be trained, and sending the training scene to the dialogue generating module.
A third aspect of the present application provides an electronic device comprising: a memory, and at least one processor. The memory is configured to store a program, and the at least one processor is configured to run the program to cause the electronic device to implement the customer service training method provided in the second aspect of the present application.
A fourth aspect of the present application is a computer storage medium storing a computer program for implementing the customer service training method provided in the second aspect of the present application when the computer program is executed.
The application provides a customer service training system, a customer service training method, electronic equipment and a storage medium, wherein the customer service training system comprises the following components: a dialogue generating module and a text voice converting module; the dialogue generation module is used for generating dialogue content according to the exercise scene and the response technology, and sending the dialogue content to the text-to-speech conversion module, wherein the dialogue content comprises dialogue content texts, mood state parameters and speech speed parameters; the text-to-speech conversion module is used for converting text and speech of the dialogue content to obtain first audio information corresponding to the dialogue content; the text-to-speech conversion module is further configured to play the first audio information to a customer service to be trained, so that the customer service to be trained performs training according to the first audio information. According to the customer service training method and the customer service training system, customer service is trained by simulating dialogue contents of customers in various scenes, and training efficiency of customer service personnel is improved.
Drawings
Fig. 1 is a schematic structural diagram of a customer service training system according to an embodiment of the present application;
FIG. 2 is a schematic diagram of another customer service training system according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a customer service training method according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
At present, in the training process of the manual customer service of a bank, firstly, a customer service person to be trained carries out speech operation recitation, and then, a senior customer service person carries out one-to-one dialogue training on the customer service person to be trained. However, by training the customer service personnel in this way, the customer service personnel need to call the senior customer service personnel to perform dialogue exercise, which results in wasting the human resources of banks, and the senior customer service personnel cannot simulate various customer service encountered in actual work, so that training and training for newly-entered customer service personnel cannot be unified, training quality is difficult to measure, and training efficiency of manual customer service cannot be guaranteed.
The customer service training system based on the generated artificial intelligence simulates the dialogue content of the customer in various scenes to train the customer service, and improves the training efficiency of customer service personnel.
Fig. 1 is a schematic diagram of a customer service training system according to an embodiment of the present application, including: a dialog generation module 101 and a text-to-speech module 102.
The dialogue generation module 101 is configured to generate dialogue content according to the exercise scenario and the response technology, and send the dialogue content to the text-to-speech conversion module, where the dialogue content includes dialogue content text, a mood state parameter, and a speech rate parameter.
The dialogue generation module 101 can generate dialogue content according to preset various exercise scenes and answering dialogues which the customer service personnel should possess, so as to simulate the dialogue content of the customer in various scenes.
In particular, the dialog content includes dialog content text, mood state parameters, and pace parameters. The mood state parameter is used for simulating the mood of the customer during consultation, and the speed parameter is used for adjusting the speed of text playing of the dialogue content, so that the text-to-speech conversion module is more in line with the situation of the customer consultation in an actual scene according to the first audio information generated by the dialogue content, and further the training efficiency of customer service is improved. Taking a customer with urgent need of business and a customer with simple consultation business as examples, the moods of the two customers are obviously different, the moods of the customer with urgent need of business are more urgent, the speed parameters are faster, the moods of the customer with simple inquiry business are more stable, and the mood parameters are normal. When customer service personnel are faced with these two different customers, the answer patterns used are also not the same. Therefore, through setting the mood state parameter and the speed parameter, the customer service training can be more practical, and the training quality is further improved.
The text-to-speech conversion module 102 is configured to perform text-to-speech conversion on the dialog content to obtain first audio information corresponding to the dialog content.
The text voice module can convert the dialogue content generated by the text generation module into audio information, so that the customer service to be trained can answer according to the audio information. And because the voice message is generated by combining the mood state parameter and the speed parameter, the generated voice message is more in line with the scene of customer service personnel in actual work, thereby improving training quality.
The text-to-speech conversion module 102 is further configured to play the first audio information to the customer service to be trained, so that the customer service to be trained trains according to the first audio information.
The text-to-speech conversion module plays the first audio message to the customer service to be trained, so that the customer service to be trained can answer the first audio message, and the training of how to answer the customer service under various scenes is completed.
According to the customer service training system provided by the embodiment of the application, customer service can be trained by simulating the dialogue content of customers in various scenes, so that the training efficiency of customer service personnel is improved, and the training quality in customer service training is improved.
Fig. 2 is a schematic diagram of a customer service training system according to an embodiment of the present application, including: a dialogue generation module 101, a text-to-speech module 102, a speech detection and evaluation module 203, and a training management module 204.
The dialogue generation module 101 is configured to generate dialogue content according to the exercise scenario and the response technology, and send the dialogue content to the text-to-speech conversion module, where the dialogue content includes dialogue content text, a mood state parameter, and a speech rate parameter.
The text-to-speech conversion module 102 is configured to perform text-to-speech conversion on the dialog content to obtain first audio information corresponding to the dialog content.
The text-to-speech conversion module 102 is further configured to play the first audio information to the customer service to be trained, so that the customer service to be trained trains according to the first audio information.
The text-to-speech conversion module 102 is configured to collect second audio information of the customer service to be trained, where the second audio information is answer content of the first audio information by the customer service to be trained according to answering technique.
The text-to-speech conversion module 102 is further configured to perform text-to-speech conversion on the second audio information to obtain answering content corresponding to the second audio information, and send the answering content to the speech detection evaluation module, where the answering content includes answering content text, speech rate parameters, intonation parameters and emotion parameters.
And the speaking operation detection and evaluation module 203 is used for scoring the answer content to obtain the training score of the customer service to be trained.
When the customer service to be trained answers according to the first audio information, the text-to-speech conversion module can collect second audio information when the customer service to be trained answers, and carries out speech-to-text conversion on the second audio information to obtain answering contents, and the answering contents are sent to the speaking and skill detection evaluation module.
The conversation detection evaluation module can score the customer service to be trained according to the answering content after receiving the answering content. The score obtained by the conversation detection evaluation module can measure the grasp condition of the answering conversation of the customer service to be trained in various scenes.
In a possible embodiment, the speech detection and evaluation module 203 is further configured to analyze the answer content and score the answer content according to a scoring manner.
Specifically, the speech skill detection and evaluation module performs balanced analysis on the text, the speech speed parameter, the intonation parameter and the emotion parameter of the answering content contained in the answering content, and scores the answering content through scoring modes such as voice recognition, sensitive word recognition and emotion recognition.
Through the dialogue quality inspection of the answering content of the customer service to be trained in all aspects, whether the answering operation standard is met in the dialogue process of the customer service to be trained is checked, a unified check result is formed, and the training score of the customer service to be trained can more reflect the actual answering operation grasping level of the customer service to be trained.
It is understood that, when scoring the answer content, the scoring content may be adjusted according to the actual situation.
In a possible embodiment, the speech detection evaluation module 203 is configured to perform speech detection according to the answer content, and obtain a speech suggestion.
Specifically, the speaking operation detection evaluation module can analyze answering contents of customer service to be trained and emotion, mood and speech speed during answering according to answering operation, and make suggestions aiming at mastering conditions of answering operation of the customer service to be trained, so that answering operation level of the customer service to be trained is further improved.
In a possible embodiment, the text-to-speech module 102 is further configured to send the answer content to the dialogue generation module.
The dialogue generation module 101 is further configured to train the training scenario generation model according to the answer content.
The dialogue generating module can collect answering contents of customer service to be trained in various scenes, and train the training scene generating model according to the collected answering contents, so that the training scene generating model can generate dialogue scenes of customers of the banking telephone channels with various characters, attitudes and scenes based on the generated artificial intelligence, and further training of customer service personnel is achieved.
It will be appreciated that the manner in which the dialogue generation module collects training data of the training scenario generation model includes not only collecting answering content of customer service to be trained, but also obtaining from other sources, such as collecting dialogue corpus of human customer service in a banking telephone, answering operation material, etc.
In a possible embodiment, the training management module 204 is configured to allocate a training scenario for the customer service to be trained according to the training record of the customer service to be trained, and send the training scenario to the dialogue generation module.
The training management module can divide various conversation scenes of the banking telephone customer service, divide conversation scenes stored in the customer service training system into various types, and facilitate the subsequent distribution of training scenes adapting to the type of customer service to be trained according to the actual training situation of the customer service to be trained.
The training management module can record the training duration, training times and the like of each customer service to be trained, and can divide the customer service training system into training and checking modes, and when each customer service to be trained completes training or checking, the training score of the customer service to be trained is recorded.
It can be understood that in the assessment mode, the training management module can set up the standard score line for measuring the mastering condition of the customer service to be trained on the training scene.
The training management module can set a requisite repair scene, low-score scene practice recommendation and the like, and can intelligently distribute the targeted training scene of the customer service to be trained according to the training record and the assessment condition of the customer service to be trained.
For example, the score of a customer service to be trained in a training scene of a customer with poor personality and unfriendly attitude is low, and the training management module can allocate the training scene of the customer with poor personality and unfriendly attitude to the customer service to be trained according to the low-grade scene training recommendation, so that the customer service to be trained can improve the answering capability of the customer service to be trained in the unskilled training scene through repeated training.
The customer service training system provided by the embodiment of the application can simulate various telephone consultants to carry out telephone consultation, thereby realizing the telephone conversation training and inspection of the manual customer service. And the conversation quality is checked through the capabilities of voice recognition, sensitive word recognition, emotion recognition and the like, and whether the conversation process of the manual customer service meets the conversation standard is checked, so that a unified check result is formed. Plays a role in improving the training efficiency of the manual customer service, and makes the enterprise operation more efficient.
The following describes a customer service training method according to an embodiment of the present application, which is applied to a customer service training system as shown in fig. 1 or fig. 2, and can be implemented through steps S301 to S303.
S301: and generating dialogue contents according to the exercise scenes and the answering operation, and sending the dialogue contents to the text-to-speech conversion module.
Specifically, the dialogue content is generated according to preset various exercise scenes and answering dialogues which the customer service personnel should have, so that the dialogue content of the customer in various scenes is simulated.
In particular, the dialog content includes dialog content text, mood state parameters, and pace parameters. The mood state parameter is used for simulating the mood of the customer during consultation, and the speed parameter is used for adjusting the speed of text playing of the dialogue content, so that the text-to-speech conversion module is more in line with the situation of the customer consultation in an actual scene according to the first audio information generated by the dialogue content, and further the training efficiency of customer service is improved. Taking a customer with urgent need of business and a customer with simple consultation business as examples, the moods of the two customers are obviously different, the moods of the customer with urgent need of business are more urgent, the speed parameters are faster, the moods of the customer with simple inquiry business are more stable, and the mood parameters are normal. When customer service personnel are faced with these two different customers, the answer patterns used are also not the same. Therefore, through setting the mood state parameter and the speed parameter, the customer service training can be more practical, and the training quality is further improved.
In a possible embodiment, the training scenario can be allocated to the customer service to be trained according to the training record of the customer service to be trained.
And intelligently distributing the targeted training scene of the customer service to be trained according to the training record of the customer service to be trained. The customer service to be trained can improve the grasp of answering operation under various scenes.
S302: and converting the text and the voice of the dialogue content to obtain first audio information corresponding to the dialogue content.
Specifically, the dialogue content can be converted into audio information, so that the customer service to be trained can answer according to the audio information. And because the voice message is generated by combining the mood state parameter and the speed parameter, the generated voice message is more in line with the scene of customer service personnel in actual work, thereby improving training quality.
S303: and playing the first audio information to the customer service to be trained, so that the customer service to be trained trains according to the first audio information.
Specifically, by playing the first audio message to the customer service to be trained, the customer service to be trained can answer with the first audio message, and training on how to answer the customer service in various scenes is completed.
In a possible embodiment, after the customer service to be trained is trained according to the first audio information, steps S304-S308 are further included.
S304: and collecting second audio information of the customer service to be trained.
Specifically, scoring and analyzing the training situation of the customer service to be trained are achieved by collecting the second audio information of the customer service to be trained. The second audio information is the answering content of the first audio information according to answering operation by the customer service to be trained.
S305: and performing text-to-speech conversion on the second audio information to obtain answering contents corresponding to the second audio information, and sending the answering contents to a speaking and operation detection and evaluation module.
When the customer service to be trained answers according to the first audio information, the text-to-speech conversion module can collect second audio information when the customer service to be trained answers, and carries out speech-to-text conversion on the second audio information to obtain answering contents, and the answering contents are sent to the speaking and skill detection evaluation module. The answering content includes answering content text, speech rate parameters, intonation parameters, and mood parameters.
In a possible embodiment, after obtaining the answer content corresponding to the second audio information, steps S3051-S3052 are further included.
S3051: the answer content is sent to a dialog generation module.
Specifically, after the answering content corresponding to the second audio information is obtained, the answering content is sent to the dialogue generating module.
S3052: training the training scene generation model according to the answering content.
Specifically, the answering content of customer service to be trained in various scenes can be collected, and the training scene generation model is trained according to the collected answering content, so that the training scene generation model can generate a conversation scene of a banking telephone channel customer with various characters, attitudes and scenes based on the generated artificial intelligence, and further, the training of customer service personnel is realized.
S306: scoring the answer content to obtain the training score of the customer service to be trained.
Specifically, the speaking detection evaluation module can score the customer service to be trained according to the answering content after receiving the answering content. The score obtained by the conversation detection evaluation module can measure the grasp condition of the answering conversation of the customer service to be trained in various scenes.
S307: and analyzing the answer content, and scoring the answer content according to the scoring mode.
Specifically, the text, the speech speed parameter, the intonation parameter and the emotion parameter of the answering content contained in the answering content are subjected to balanced analysis, and the answering content is scored through scoring modes such as voice recognition, sensitive word recognition and emotion recognition.
Through the dialogue quality inspection of the answering content of the customer service to be trained in all aspects, whether the answering operation standard is met in the dialogue process of the customer service to be trained is checked, a unified check result is formed, and the training score of the customer service to be trained can more reflect the actual answering operation grasping level of the customer service to be trained.
S308: and performing speaking detection according to the answering content to obtain speaking suggestions.
Specifically, answering contents of customer service to be trained and emotion, mood and speech speed during answering can be analyzed according to answering operation, suggestions are made for answering operation grasping conditions of the customer service to be trained, and then answering operation level of the customer service to be trained is further improved.
The customer service training method provided by the embodiment of the application can simulate various telephone consultants to carry out telephone consultation, thereby realizing the telephone conversation training and inspection of the manual customer service. And the conversation quality is checked through the capabilities of voice recognition, sensitive word recognition, emotion recognition and the like, and whether the conversation process of the manual customer service meets the conversation standard is checked, so that a unified check result is formed. Plays a role in improving the training efficiency of the manual customer service, and makes the enterprise operation more efficient.
The electronic equipment provided by the embodiment of the application comprises: a memory, and at least one processor. The memory is used for storing a program, and the at least one processor is used for running the program to enable the electronic device to implement the customer service training method as shown in fig. 3.
Accordingly, embodiments of the present application also provide a computer-readable storage medium storing a computer program, which when executed by a processor causes the processor to perform the steps of the method shown in fig. 3.
The customer service training system, the customer service training method, the electronic equipment and the storage medium provided by the application can be used in the field of artificial intelligence or the field of finance. The foregoing is merely an example, and the application fields of the customer service training system, the customer service training method, the electronic device and the storage medium provided by the present application are not limited.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, e.g., the division of units is merely a logical service division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each service unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software business units.
The integrated units, if implemented in the form of software business units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those skilled in the art will appreciate that in one or more of the examples described above, the services described herein may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the services may be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The objects, technical solutions and advantageous effects of the present application have been described in further detail in the above embodiments, and it should be understood that the above are only embodiments of the present application.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application.

Claims (10)

1. A customer service training system, the system comprising: a dialogue generating module and a text voice converting module;
the dialogue generation module is used for generating dialogue content according to the exercise scene and the response technology, and sending the dialogue content to the text-to-speech conversion module, wherein the dialogue content comprises dialogue content texts, mood state parameters and speech speed parameters;
the text-to-speech conversion module is used for converting text and speech of the dialogue content to obtain first audio information corresponding to the dialogue content;
the text-to-speech conversion module is further configured to play the first audio information to a customer service to be trained, so that the customer service to be trained performs training according to the first audio information.
2. The system of claim 1, wherein the system further comprises: a speech surgery detection evaluation module;
the text-to-speech conversion module is further used for collecting second audio information of the customer service to be trained, wherein the second audio information is answer content of the first audio information by the customer service to be trained according to answering operation;
the text-to-speech conversion module is further configured to perform text-to-speech conversion on the second audio information to obtain answering content corresponding to the second audio information, and send the answering content to the speech detection and evaluation module, where the answering content includes answering content text, speech speed parameters, intonation parameters and emotion parameters;
and the conversation detection evaluation module is used for scoring the answer content to obtain the training score of the customer service to be trained.
3. The system of claim 2, wherein the system further comprises a controller configured to control the controller,
the speech detection and evaluation module is specifically configured to analyze the answer content, and score the answer content according to a scoring mode, where the scoring mode includes speech recognition, sensitive word recognition, and emotion recognition.
4. The system of claim 2, wherein the system further comprises a controller configured to control the controller,
the text-to-speech conversion module is also used for sending the answering content to the dialogue generation module;
and the dialogue generating module is also used for training the training scene generating model according to the answering content.
5. The system of claim 2, wherein the system further comprises a controller configured to control the controller,
and the conversation detection evaluation module is used for carrying out conversation detection according to the answering content to obtain conversation suggestions.
6. The system of claim 1, further comprising a training management module;
the training management module is used for distributing the training scene for the customer service to be trained according to the training record of the customer service to be trained and sending the training scene to the dialogue generation module.
7. A customer service training method applied to a customer service training system as claimed in any one of claims 1 to 6, the method comprising:
generating dialogue content according to the exercise scene and the answering operation, and sending the dialogue content to a text-to-speech conversion module, wherein the dialogue content comprises dialogue content texts, mood state parameters and speech speed parameters;
text-to-speech conversion is carried out on the dialogue content to obtain first audio information corresponding to the dialogue content;
and playing the first audio information to a customer service to be trained, so that the customer service to be trained trains according to the first audio information.
8. The method of claim 7, wherein the method further comprises:
collecting second audio information of the customer service to be trained, wherein the second audio information is answering content of the first audio information by the customer service to be trained according to answering operation;
performing text-to-speech conversion on the second audio information to obtain answering contents corresponding to the second audio information, and sending the answering contents to the speech detection and evaluation module, wherein the answering contents comprise answering content texts, speech speed parameters, intonation parameters and emotion parameters;
and scoring the answer content to obtain the training score of the customer service to be trained.
9. An electronic device, comprising:
a memory and at least one processor;
the memory is used for storing programs;
the at least one processor is configured to run the program to cause the electronic device to implement the customer service training method of any one of claims 7-8.
10. A computer storage medium storing a computer program for implementing the customer service training method of any one of claims 7-8 when executed.
CN202311138675.8A 2023-09-05 2023-09-05 Customer service training system, method, electronic equipment and storage medium Pending CN117198265A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311138675.8A CN117198265A (en) 2023-09-05 2023-09-05 Customer service training system, method, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311138675.8A CN117198265A (en) 2023-09-05 2023-09-05 Customer service training system, method, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117198265A true CN117198265A (en) 2023-12-08

Family

ID=88984444

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311138675.8A Pending CN117198265A (en) 2023-09-05 2023-09-05 Customer service training system, method, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117198265A (en)

Similar Documents

Publication Publication Date Title
US11501656B2 (en) Interactive and automated training system using real interactions
US10038784B2 (en) System and method for providing agent guidance
Ward et al. My science tutor: A conversational multimedia virtual tutor for elementary school science
US20080300874A1 (en) Speech skills assessment
CN111242515A (en) Classroom teaching quality evaluation system and method based on education big data
CN106663383A (en) Method and system for analyzing subjects
US20150037765A1 (en) System and method for interactive electronic learning and assessment
CN107133303A (en) Method and apparatus for output information
CN113377200B (en) Interactive training method and device based on VR technology and storage medium
WO2006125347A1 (en) A homework assignment and assessment system for spoken language education and testing
CN108766113B (en) Method and device for monitoring classroom performance of students
CN109785683A (en) For simulating method, apparatus, electronic equipment and the medium at speaking test scene
Ward et al. My science tutor and the myst corpus
KR100995847B1 (en) Language training method and system based sound analysis on internet
CN113257060A (en) Question answering solving method, device, equipment and storage medium
KR20070006742A (en) Language teaching method
US20190362737A1 (en) Modifying voice data of a conversation to achieve a desired outcome
CN116030788B (en) Intelligent voice interaction method and device
GB2513354A (en) Automated Training System
CN117198265A (en) Customer service training system, method, electronic equipment and storage medium
CN110826796A (en) Score prediction method
KR100385892B1 (en) Foreign Language Speaking Assessment System
Chen [Retracted] Design of Piano Intelligent Teaching System Based on Neural Network Algorithm
Chen Entertainment social media based on deep learning and interactive experience application in English e-learning teaching system
CN112767932A (en) Voice evaluation system, method, device, equipment and computer readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination