CN114554015A

CN114554015A - Call center system and communication establishing method

Info

Publication number: CN114554015A
Application number: CN202210181742.3A
Authority: CN
Inventors: 夏福森; 蒋宁; 吴海英; 杨锋; 刘磊; 杨砚
Original assignee: Mashang Xiaofei Finance Co Ltd
Current assignee: Mashang Xiaofei Finance Co Ltd
Priority date: 2022-02-25
Filing date: 2022-02-25
Publication date: 2022-05-27

Abstract

The embodiment of the specification discloses a call center system and a communication establishment method, wherein the call center system comprises a biological characteristic detection component, a quality inspection component and a call management component, wherein: the biological characteristic detection component is used for carrying out identity detection on the customer service when the customer service is in voice communication with a second terminal of the user through the first terminal; the call management component is used for accessing the management terminal of the management party into a first voice communication link between the first terminal and the second terminal when the customer service identity detection result determines that the identity of the customer service is abnormal; the quality inspection component is used for detecting whether the service state of the customer service corresponding to the first terminal is abnormal or not; and the call management component is also used for ending the first voice call and constructing a second voice communication link between the management terminal and the second terminal when the service state of the customer service is determined to be abnormal so as to provide the service aiming at the target service for the user of the second terminal.

Description

Call center system and communication establishing method

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a call center system and a communication establishment method.

Background

With the continuous development of internet technology, a large number of enterprises or institutions (particularly financial enterprises or banking institutions and other institutions) perform digital transformation, diversified services (such as consumption financial services and the like) are comprehensively spread, corresponding products are more and more, user groups of different products or services are larger and larger, and the service quality required by users for the services is higher and higher.

In order to meet the requirements of users for business consultation, business handling and the like on lines, a manual service is required to be provided, in order to reduce labor cost and share the pressure of manual customer service, some enterprises or institutions can introduce intelligent voice robots and the like to carry partial telephone traffic, and the manual customer service plays a very important role in the business of collection urging, return visit, telephone sales and the like in the financial industry or the banking industry. In order to improve the service quality of customer service, avoid or reduce the irregular operation of customer service, and cause economic loss of enterprises and user dissatisfaction, a technical scheme capable of solving the problem of irregular operation of customer service is needed.

Disclosure of Invention

An object of the embodiments of the present specification is to provide a technical solution that can solve the problem of customer service irregular work.

In order to implement the above technical solution, the embodiments of the present specification are implemented as follows:

in a first aspect, embodiments of the present specification provide a call center system, the system includes a biometric detection component, a quality inspection component, and a call management component, where:

the biological characteristic detection component is used for carrying out identity detection on the customer service when the customer service is in voice communication with a second terminal of the user through the first terminal and providing an identity detection result to the call management component;

the call management component is used for accessing a management terminal of a manager into a first voice communication link between the first terminal and the second terminal when the identity of the customer service is determined to be abnormal based on the identity detection result;

the quality inspection component is used for detecting whether the service state of the customer service corresponding to the first terminal is abnormal or not and providing a service state detection result to the call management component;

the call management component is further configured to, when it is determined that the service state of the customer service is abnormal based on the service state detection result, end the first voice call, and construct a second voice communication link between the management terminal and the second terminal, where the second voice communication link is used for the management party to provide, through the management terminal, a service for the target service to the user of the second terminal.

It can be seen that, in the embodiment of the present specification, when the customer service performs a voice call with the user through the biometric detection component in the call center system, the identity of the customer service is detected, and then when the call management component determines that the identity of the customer service is abnormal, the management terminal of the management party is connected to the first voice communication link between the first terminal and the second terminal, so as to perform a substitute call (i.e. replace the customer service to perform the voice call with the user) or a substitute call (i.e. replace the customer service to answer the phone of the user) on the customer service in time, thereby avoiding the above-mentioned abnormal operation, and in addition, when the call management component determines that the service state of the customer service corresponding to the first terminal is abnormal, the voice call between the first terminal and the second terminal is ended, and a second voice communication link between the management terminal and the second terminal is constructed, so as to provide a service for the target service to the user of the second terminal, therefore, the service state of the customer service can be detected, the customer service can be guided to the service of the user in time, the voice call between the customer service and the user can be cut off when necessary, and the user can be continuously provided with the service by the management party, so that the service quality of the customer service is improved, the economic loss is reduced, the service discontent of the user on the customer service is reduced, and the irregular operation of the customer service is avoided or reduced.

In a second aspect, an embodiment of the present disclosure provides a communication establishing method, where the method is applied to the call center system in the first aspect, and the method includes:

accessing a management terminal of a management party into a first voice communication link between a first terminal and a second terminal, wherein the first terminal is a terminal for providing customer service aiming at service of a target service, and the second terminal is a terminal of a user;

when the service state of the customer service corresponding to the first terminal is determined to be abnormal, the voice call between the first terminal and the second terminal is ended, and a second voice communication link between the management terminal and the second terminal is established, wherein the second voice communication link is used for the management party to provide the service aiming at the target service for the user of the second terminal through the management terminal.

It can be seen that, in the embodiment of the present specification, the management terminal of the management party is connected to the first voice communication link between the first terminal and the second terminal, so as to perform the detection on the substitute call (i.e. performing the voice call with the user instead of the customer service) or the substitute call (i.e. answering the call of the user instead of the customer service) of the customer service in time, thereby avoiding the above-mentioned irregular operation, and in addition, when the service state of the customer service corresponding to the first terminal is detected to be abnormal, the voice call between the first terminal and the second terminal is ended, and the second voice communication link between the management terminal and the second terminal is constructed, so as to provide the service for the target service to the user of the second terminal, thereby detecting the service state of the customer service, timely guiding the customer service to the user, and cutting off the voice call between the customer service and the user as necessary to continue providing the service for the user by the management party, and then promote the service quality of customer service, reduce economic loss to reduce the user and to the service that customer service provided discontented, avoid or reduce the irregular operation of customer service.

In a third aspect, the present specification also provides a storage medium for storing computer-executable instructions, where the computer-executable instructions cause a computer to perform the steps in the method as described in the second aspect.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

FIG. 1A is a schematic diagram of a call center system according to the present disclosure;

FIG. 1B is a schematic diagram of another call center system according to the present disclosure;

FIG. 1C is a schematic diagram of another call center system according to the present disclosure;

FIG. 2A is a schematic diagram of another call center system according to the present disclosure;

FIG. 2B is a schematic diagram of the operation of a call center system of the present disclosure;

fig. 3 is a diagram illustrating an embodiment of a communication establishment method according to the present disclosure;

fig. 4 is a diagram illustrating another embodiment of a communication establishment method according to the present disclosure;

fig. 5 is a diagram illustrating another embodiment of a communication establishment method according to the present disclosure;

fig. 6 is a flowchart of another embodiment of a communication establishment method according to the present disclosure.

Illustration of the drawings:

100-call center system, 110-biometric detection component, 120-quality inspection component, 130-call management component, 140-basic function component, 141-interactive voice response subcomponent, 142-customer service management subcomponent, 143-task management subcomponent, 144-recording subcomponent, 145-basic subcomponent, 200-server.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

The inventive concept of this specification is as follows: with the continuous development of internet technology, a large number of enterprises or institutions (particularly financial enterprises or banking institutions and other institutions) perform digital transformation, diversified services (such as consumption financial services and the like) are comprehensively spread, corresponding products are more and more, user groups of different products or services are larger and larger, and the service quality required by users for the services is higher and higher. In order to meet the requirements of users for business consultation, business handling and the like on lines, a manual service is required to be provided, in order to reduce the labor cost and share the pressure of manual customer service, some enterprises or organizations can introduce intelligent voice robots and the like to carry partial telephone traffic, and the manual customer service plays a very important role in the business of collection urging, return visit, telephone sales and the like in the financial industry or the banking industry. In order to improve the service quality of customer service, avoid or reduce the irregular operation of customer service, and cause enterprise economic loss and user dissatisfaction, a technical scheme capable of solving the problem of irregular operation of customer service is needed, based on the above problems, the technical scheme provides a call center system, through each component included in the call center system, when the customer service performs voice communication with a second terminal of a user through a first terminal, identity detection is performed on the customer service, when the identity of the customer service is determined to be abnormal, a management terminal of a management party is accessed into a voice communication link between the first terminal and the second terminal, so that the customer service can be timely checked instead of the customer service performing voice communication with the user or instead of the customer service (i.e. instead of the customer service answering the telephone of the user), the occurrence of the irregular operation is avoided, and in addition, when the service state of the customer service corresponding to the first terminal is detected to be abnormal, the voice call between the first terminal and the second terminal is ended, the voice communication link between the management terminal and the second terminal is constructed to provide the service aiming at the target service for the user of the second terminal, so that the service state of the customer service can be detected, the customer service is guided to the user in time, the voice call between the customer service and the user can be cut off if necessary, and the user is continuously provided with the service by the management party, so that the service quality of the customer service is improved, the economic loss is reduced, the discontentment of the user on the service provided by the customer service is reduced, and the irregular operation of the customer service is avoided or reduced.

As shown in fig. 1A or fig. 1B, the present specification provides a call center system, which may adopt a B/S architecture (i.e., a browser/server architecture) or other architectures, such as a C/S architecture (i.e., a client/server architecture), and the like, which may be set according to actual situations. The call center system 100 includes a biometric detection component 110, a quality inspection component 120, and a call management component 130, wherein:

each of the above components in the call center system 100 may be disposed in the same server 200 (as shown in fig. 1A), or disposed in different servers 200 (as shown in fig. 1B), where the servers may be physical servers, or virtual servers, and may be specifically set according to an actual situation, which is not limited in this embodiment of the specification.

The biometric detection component 110 may be composed of a plurality of different subassemblies, the detected biometric features are different, and the subassemblies included in the biometric detection component 110 may also be different, for example, if the biometric feature is a facial feature, the biometric detection component 110 may include a camera subassembly, the biometric feature is a voiceprint feature, the biometric detection component 110 may include a voiceprint detection subassembly (specifically, a microphone, etc.), if the biometric feature is a fingerprint feature, the biometric detection component 110 may include a fingerprint detection subassembly, etc., which may be set according to actual conditions. The biometric detection component 110 can be configured to capture a biometric of the subject and verify the identity of the subject accordingly.

It should be noted that the biometric detection component 110 can be constructed in various ways, wherein in order to make the detection result of the biometric feature more reliable, the biometric detection model can be trained in advance by a training sample containing specified biometric data, and the trained biometric detection model can be disposed in the biometric detection component 110. The biometric detection model may be constructed by a plurality of different algorithms or network models, for example, the biometric detection model may be constructed by a neural network model or a deep residual network (such as ResNet18 or ResNet 50), and may be specifically set according to actual conditions.

The quality inspection component 120 can process and analyze the voice data to obtain a corresponding analysis result during the voice call between the customer service and the user, and can perform a corresponding process based on the analysis result, for example, if a sensitive word (the sensitive word can be maintained in the call center system 100 by itself, and the sensitive word can be fraudulent or abusive), an alarm message can be sent to prompt the customer service, and a manager or a supervisor of the customer service can be reported. The quality inspection component 120 may also be composed of various sub-components, such as a voice conversion sub-component, an emotion detection sub-component, a sensitive word detection sub-component, a semantic recognition sub-component, and the like, and besides the above sub-components, various sub-components may be set according to the actual situation, where the voice conversion sub-component may convert data of a voice call between the customer service and the user into text data, and may check the service quality of the customer service based on the text data. The emotion detection sub-component can detect emotion changes of the customer service and the user in the process of voice communication between the customer service and the user so as to judge whether the customer service has irregular behaviors or not, whether the user has specified risk behavior trends (such as complaint trends and the like) or not, and the like. The sensitive word detection sub-component can detect the sensitive words of the customer service and the user in the process of voice communication between the customer service and the user so as to judge whether the customer service has an irregular behavior or not, whether the user has a designated risk behavior tendency (such as a complaint tendency) or not, determine the service quality condition of the customer service and the like. The semantic recognition sub-component can recognize semantics expressed by the customer service and the user based on the context of the customer service and the user in voice communication, and the like.

It should be noted that the voice conversion sub-component, the emotion detection sub-component, the sensitive word detection sub-component, the semantic recognition sub-component, and other sub-components may all be provided with corresponding business models, and the business models provided in the sub-components may implement corresponding functions of the sub-components. The different business models can be trained by training samples containing corresponding feature data (such as voice data, emotion feature data, sensitive words or feature data with different semantics, etc.), and the trained business models can be arranged in corresponding sub-components. Different business models can be constructed through different algorithms or network models, for example, the business model in the semantic recognition subassembly can be constructed through a convolutional neural network model and the like, and the business model can be set according to actual conditions.

The call management component 130 may be configured to perform call management and traffic distribution, for a communication request initiated by a user actively, the call management component 130 may process and receive a forwarded manual request, and perform traffic distribution, for a communication request initiated by a user, the call management component 130 may process a batch communication request initiated by the call center system 100 and a communication request initiated by a customer service, and may process a three-way voice call between a manager, the customer service, and the user.

In practical applications, the call management component 130 may further be configured to monitor events triggered in the call center system 100, and send target messages corresponding to the monitored events to the message queue, where the target messages are used to trigger other components to determine events occurring in the call center system 100 through the target messages in the message queue.

In an implementation, the call management component 130 may monitor events of the call center system 100 by using a listening handler, and when an event such as a voice call request or a call connection event occurs in the call center system 100, the call management component 130 may send the monitored event message or request message (i.e., target message) to a message queue, so that other components of the call center system 100 can determine each event occurring in the call center system 100 by subscribing to the target message in the message queue. Different components can subscribe different types of messages in the message queue according to self requirements, and the message queue can be realized in a rabbitMQ mode and the like. The call management component 130 may learn whether the outbound call is connected by subscribing to a target message in the message queue, and if the outbound call is connected, the call management component 130 may allocate the telephone traffic to the telephone, and then the call management component 130 may send a message of the result of allocating the telephone traffic to the message queue, and the basic function component 140 determines the identifier of the allocated customer service through the subscribed message in the message queue (i.e., the message of the result of allocating), so that the call management component 130 may learn the number of currently ready operators and accurately allocate the call of the user to the customer service and make a call with the customer service when allocating the telephone traffic.

In addition, after the call management component 130 sends the message of the traffic distribution result to the message queue, the biometric detection component 110 determines the identity of the distributed customer service through the subscribed message (i.e. the message of the traffic distribution result) in the message queue, and can perform authentication on the customer service through the biometric.

In addition, the call management component 130 can know whether the call between a certain customer service and the user is ended by subscribing to the message in the message queue, and if the call is ended, the call management component can send the message of ending the call to the message queue, and the quality inspection component 130 can perform quality inspection on the customer service through the message subscribed in the message queue (i.e. the message of ending the call).

It should be noted that, in another embodiment, as shown in fig. 1C, the call center system 100 may further include a basic function component 140, the basic function component 140 may provide other basic functions for the call center system 100 besides the above functions, such as a recording function, a data storage and transmission function, a task management function, an interactive voice response function, and the like, the interactive voice response function may assist in transferring to manual service, the recording function may record a voice call between a customer service and a user, compress a recorded audio file, store the compressed audio file, provide subsequent listening, and the task management function may implement communication management. The basic function component 140 can implement voice communication link construction, voice call task management, voice recording, and configuration and management of data in voice call.

Based on the above components, the call center system 100 can perform monitoring, break-in (accessing the voice call between the customer service and the user to realize a three-way voice call) and whisper (sending voice data to the customer service only) processing on the voice call between the customer service and the user, and specifically, the biometric detection component 110 can be used to perform identity detection on the customer service when the customer service performs voice call with the second terminal of the user through the first terminal, and provide the identity detection result to the call management component 130.

The identity detection of the customer service may be to verify the identity of the customer service, and the identity verification of the customer service may be to verify the identity of the customer service in a biometric manner, for example, the identity of the customer service may be verified in a facial feature manner, a fingerprint feature manner, a voiceprint feature manner, and the like. It should be noted that, besides the authentication of the customer service through the above-mentioned method, the identity of the customer service may also be authenticated through other various methods, for example, the identity of the customer service may also be authenticated through a verification information method, that is, when the customer service needs to perform the identity authentication, an initiation mechanism of the identity authentication may be triggered, at this time, verification information may be sent to a verification terminal of the customer service, and the customer service may complete the identity authentication through the received verification information, which may be specifically set according to actual situations, which is not limited in the embodiments of this specification.

In implementation, when it is detected that the customer service performs a voice call with the second terminal of the user through the first terminal, the biometric detection component 110 may collect current biometric information of the customer service, and may compare the collected biometric information with pre-stored reference biometric information of the customer service, if the collected biometric information matches the reference biometric information, it indicates that the identity detection result corresponding to the customer service is normal, and if the collected biometric information does not match the reference biometric information, it indicates that the identity detection result corresponding to the customer service is abnormal.

Based on the above processing, the call management component 130 may access the management terminal of the management party to the first voice communication link between the first terminal and the second terminal when it is determined that the identity of the customer service is abnormal based on the identity detection result.

In implementation, after the biometric component 110 obtains the identity detection result, if the identity detection result indicates that the customer service has failed to perform the identity verification, it may be determined that a preemptive action may exist for the customer service, at which point, it may be determined that an anomaly exists in the identity of the customer service, the call management component 130 may then send a notification message to the management terminal of the manager, which, upon receipt, if it is confirmed that the identity of the customer service needs to be checked, the call management component 130 may access the management terminal of the management party to a first voice communication link between the first terminal and the second terminal, therefore, the management party can intervene in the voice call between the customer service and the user, at the moment, the management party can monitor the contents of the voice call between the customer service and the user, can access the voice call between the customer service and the user in a break-in mode, and can realize whisper operation on the customer service.

Based on the above processing, the call center system 100 can also perform processing such as forced disconnection of the voice call between the customer service and the user (the voice call between the customer service and the user is terminated, and the voice call between the other party and the user is performed), and specifically, the quality inspection component 120 can detect whether the service state of the customer service corresponding to the first terminal is abnormal, and provide the service state detection result to the call management component 130.

In implementation, after the management terminal accesses the voice communication link between the first terminal and the second terminal, the service state of the customer service may be detected by the quality inspection component 120, where the service state may be used to represent whether the service provided by the customer service for the user for the target service is irregular or status information causing the user to have a designated risk behavior tendency (such as a complaint tendency, etc.), in practical applications, the service state of the customer service may be detected in a plurality of different manners, for example, the service state of the customer service may be detected by determining whether a designated sensitive word exists in the content of the voice call between the customer service and the user, if the designated sensitive word exists in the content of the voice call between the customer service and the user, it indicates that the service state of the customer service is abnormal, if the designated sensitive word does not exist in the content of the voice call between the customer service and the user, it indicates that the service status of the customer service is normal.

Based on the above processing, the call management component 130 may also end the voice call between the first terminal and the second terminal when it is determined that the service state of the customer service is abnormal based on the service state detection result, and construct a second voice communication link between the management terminal and the second terminal, where the second voice communication link is used for the management party to provide a service for the target service to the user of the second terminal through the management terminal.

In implementation, when it is determined that the service state of the customer service is abnormal in the above manner, the call management component 130 may send a notification message of the abnormal service state to a management terminal of the management party, and after the management party receives the notification message, if it is determined that the service person needs to be replaced, the call management component 130 may process the voice call between the customer service and the user in a forced release manner, specifically, the call management component 130 may end the voice call between the first terminal and the second terminal and construct a second voice communication link between the management terminal and the second terminal, so that the management party may end the voice call between the customer service and the user, and the management party continues to provide corresponding services for the user, thereby reducing occurrence of irregular behaviors in the customer service.

It can be seen that, in the embodiment of the present specification, each component included in the call center system 100 can perform identity detection on the customer service when the customer service performs a voice call with the second terminal of the user through the first terminal, and when it is determined that the identity of the customer service is abnormal, the management terminal of the management party is connected to the first voice communication link between the first terminal and the second terminal, so as to perform substitute call (i.e. replace the customer service to perform a voice call with the user) or substitute call (i.e. replace the customer service to answer the phone of the user) on the customer service in time, thereby avoiding the above-mentioned irregular operation, and in addition, when it is detected that the service state of the customer service corresponding to the first terminal is abnormal, the voice call between the first terminal and the second terminal is ended, and a second voice communication link between the management terminal and the second terminal is constructed, so as to provide a service for the target service to the user of the second terminal, therefore, the service state of the customer service can be detected, the customer service can be guided to the service of the user in time, the voice call between the customer service and the user can be cut off when necessary, and the management party can continue to provide the service for the user, so that the service quality of the customer service is improved, the economic loss is reduced, the service discontent of the user on the customer service is reduced, and the illegal operation of the customer service is avoided or reduced.

Fig. 2A is a schematic diagram of another call center system 100 according to an embodiment of the present disclosure. The call center system 100 includes all the functional components of the call center system 100 shown in fig. 1, and is improved on the basis of the functional components, and the improvement is as follows:

first, based on the foregoing, the base functionality component 140 can include one or more of an interactive voice response subcomponent 141, an customer service management subcomponent 142, a task management subcomponent 143, a recording subcomponent 144, and a base subcomponent 145, wherein:

as shown in FIG. 2B, the interactive voice response subcomponent 141 can be divided into a front portion and a back portion, and the user's voice data can enter the front portion first, and can be forwarded to manual customer service in case the front portion cannot solve the problem posed by the user. The latter part is in a balanced position with the artificial customer service, and the artificial customer service can not be switched in when the user enters the phone, mainly aiming at delaying time or assisting services (such as satisfaction degree service, verification transaction password service and the like). In this embodiment, the interactive voice response subcomponent 141 can also construct a voice communication link with the second terminal of the user and a first voice communication link with the first terminal for the second terminal.

As shown in fig. 2B, the customer service management sub-assembly 142 can be used for performing control management on the registration of customer service, the customer service logging in the call center system 100 through the first terminal, the customer service initiating a voice call to the user, or the customer service answering the voice call of the user, specifically, in practical application, the customer service management sub-assembly 142 can be further divided into a customer service registration management module, a customer service login management module, a customer service management module, and the like, and the customer service registration management module is mainly responsible for the registration management of the communication number and the biological characteristic information (such as voiceprint information and facial information) when the customer service logs in the call center system 100 for the first time, and the registration information verification and update when the information is subsequently modified; the customer service login management module may manage the customer service login to the call center system 100 (e.g., account password verification, biometric information collection, verification information transmission and verification, etc.). The customer service management module mainly provides management configuration for customer service operation time intervals, login check rules and the like from the dimensions of roles, skill groups, customer services and the like, for example: for the customer service with the set working period, the voice call can be carried out only by logging in the call center system 100 in the working period; the customer service that logs in the call center system 100 by means of biometric authentication is started, and biometric information needs to be authenticated during login.

In practical application, the customer service management subcomponent 142 is further configured to register the customer service that logs in the call center system 100, and send a registration message of the customer service that logs in the call center system 100 to a message queue; and acquiring the registration message from the message queue, encapsulating the registration message, and sending the encapsulated registration message to the message queue, wherein the encapsulated registration message is used for determining the predicted outbound parameters.

Specifically, for example, the customer service may log in through a browser or a client corresponding to the call center system 100, and after the log-in is completed, the customer service is connected and registered to the customer service management subcomponent 142, and the registration information of the customer service is sent to the message queue, so that the call management component 130 can obtain the number of currently ready customer services and accurately allocate the call of the user to the customer service and make a call with the customer service when the traffic is allocated. The messages of the customer service management subcomponent 142 in this embodiment are not directly recognizable by other components, e.g., the customer service management subcomponent 142 is middleware written in language c that can send messages to a message queue. The customer service management sub-component 142 analyzes and encapsulates the message for the second time after subscribing the messages, and then sends the message to the message queue again, and the encapsulated message can be used for performing corresponding statistical operation, for example, the number of idle customer services can be obtained through statistics according to the customer service registration information.

In addition, as shown in fig. 2B, after the customer service successfully logs in the call center system 100, the customer service may be in a state of rest by default, for example, when the customer service is currently in a working time period, the customer service is switched to a ready state or a working state. If the state is switched to the ready state, the call management component 130 may allocate the telephone traffic to the customer service, and the page corresponding to the customer service may be flicked, the telephone rings and connected, and the voice communication link is established. If the state is switched to the outbound state, the customer service can select the communication number of the user from the distribution list to make an outbound call, and can also input the number on the dial plate to make an outbound call. If the current customer service is in the non-operation time period, even if the customer service is switched to the ready state or the outbound state, no telephone traffic is distributed to the customer service, and the customer service is not allowed to make an outbound call, so that the situation that the customer service calls the user outside the non-operation time period, the user is disturbed in the non-specified time period allowing the outbound call, and the user generates a designated risk behavior tendency (such as a complaint tendency and the like) can be avoided. Meanwhile, in order to achieve more flexible management, at the user side, the call center system 100 also performs authority control on outbound, and can be set to switch to an outbound state for outbound only when the customer service has an outbound authority, and the authority does not allow the customer service to modify, and only the manager can edit the authority.

As shown in fig. 2B, the task management subcomponent 143 may be configured and managed to perform configuration management on a voice call initiated by a customer service to a user, and specifically, when the call center system 100 performs a batch outbound call, an outbound task is created through the task management subcomponent (a task configuration item may include an outbound start time, an outbound list resource, a number sending frequency, a telephone call receiving skill set, an outbound type, and the like). For the customer service receiving the telephone traffic of the outbound task, the voice communication authority is only given after the task is started.

In addition, when creating the voice call task, the task management subcomponent 143 needs to upload an outbound list or download the outbound list from a designated server, and if the outbound list is not number-washed, the task management subcomponent 143 needs to perform a number-washing operation on the outbound list before the task starts, where the number-washing rule includes but is not limited to: the number of the blacklist, the number of repeated dialing, the number washing rule related to the service and the like, whether the number washing is carried out on the outbound list or not is identified in a specified mode, for example, distinguishing is carried out through a file name, a number washing strategy can be preset during task creation, the communication numbers of all users in the outbound list are desensitized, the uniqueness of the users can be set in a mode of not adopting identity documents, and a user ID mode can be adopted.

It should be noted that all the user sensitive information in each component in the call center system 100 is desensitized, and all the customer sensitive information in the page corresponding to the customer service and the pop-up page is desensitized, such as name (x), phone (158 x 1234), id card (x), and the like.

As shown in fig. 2B, the recording subassembly 144 may be configured to record voice call data between the customer service and the user, and provide the recorded voice call data to the quality inspection subassembly 120 for quality inspection, specifically, during the process of voice call between the customer service and the user, the recording subassembly 144 may record the whole process, so as to leave a trace in the customer service call process, so that a supervision department may check the customer service and perform data check when there is an irregular term in the service process, thereby restricting the behavior specification of the customer service operation process to a certain extent, and reducing the risk of irregular operation.

Base sub-components 145 may include databases, file servers, messaging middleware, data buses, media servers, load balancers, and configuration centers, among others, that may be used to configure and manage data in a voice call.

Based on the above content, the management party may actively monitor the voice call between the first terminal and the second terminal through the call management component 130, specifically, the call management component 130 may further trigger the management terminal to monitor the content of the voice call between the first terminal and the second terminal when the management terminal is accessed to the first voice communication link between the first terminal and the second terminal; the quality inspection component 120 can detect whether the service status of the customer service corresponding to the first terminal is abnormal based on the content of the monitored voice call.

In implementation, when a management party needs to actively monitor the content of a certain voice call, the management party triggers the call management component 130 to perform a monitoring operation through the management terminal, at this time, the call management component 130 may access the management terminal to the first voice communication link between the first terminal and the second terminal, and at the same time, may trigger the management terminal to monitor the content of the voice call between the first terminal and the second terminal, at this time, the quality inspection component 120 may determine, based on the monitored content of the voice call, whether an abnormal situation such as emotional excitement occurs between the two terminals, if an abnormal situation such as emotional excitement occurs between the two terminals, it may determine that the service state of the customer service corresponding to the first terminal is abnormal, and if an abnormal situation such as emotional excitement does not occur between the two terminals, it may determine that the service state of the customer service corresponding to the first terminal is normal.

For the detection manner of the quality inspection component 120 for the service state of the customer service, in practical application, the detection manner may further include a plurality of different detection manners, which may specifically include the following contents: the quality inspection component 120 may further determine whether the content of the monitored voice call includes a preset sensitive word based on the content of the monitored voice call, and if so, determine that the service state of the customer service corresponding to the first terminal is abnormal.

In implementation, as shown in fig. 2B, in the process of voice call between the customer service and the user, the quality inspection component 120 may further perform sensitive word detection on call contents in the whole voice call process, where a detection object includes the customer service and the user, and when a preset sensitive word appears in the content of the voice call, the quality inspection component 120 immediately sends out warning information to the customer service and can send out warning information to the management party, so that the call center system 100 can find and report the management party in time when the customer service uses the sensitive word or the emotion of the user triggers the sensitive word once the customer service uses the sensitive word in the process of providing service for the user. The manager receiving the alarm information can subsequently judge and select to monitor the voice call of the customer service corresponding to the alarm information so as to further know the details, or can also select to forcibly insert the voice call of the customer service corresponding to the alarm information so as to placate the user and assist the customer service to provide the service for the user, or can also select to initiate whisper information for the customer service so as to remind the customer service of an irregular term and assist the customer service to provide the service for the user and the like.

When the quality inspection module 120 performs subsequent quality inspection processing, because there are more voice data to be quality inspected, in order to further improve quality inspection efficiency, it may further sample a plurality of voice data to obtain a sample, where the sample is the voice data to be quality inspected. The manner of sampling the plurality of voice data may include a plurality of manners, for example, the voice data in a text format may be obtained in a specified manner, and the sampling sample may be obtained by performing matching analysis on the voice data by using a preset keyword. In addition, in practical applications, the quality inspection component 120 is further configured to perform quality inspection processing on the voice data. The specific implementation manner of performing quality inspection processing on the voice data may include multiple, and the following provides a selectable processing manner, which may specifically include: respectively comparing voice data of customer service needing quality inspection with preset characters, and detecting whether the voice data contains the characters or not; and respectively scoring the voice data according to the numerical values corresponding to the detection results, and determining the quality inspection result of the customer service according to the scoring result of each voice data.

In implementation, a quality inspection item may be preset according to actual conditions, the quality inspection item may include a plurality of characters (which may be words and the like) to be quality inspected, and the content of each character may be set according to actual conditions. In order to realize the scoring of different dimensions, a character library formed by a plurality of characters can be divided into a plurality of groups according to types, and then the characters (which can be words) contained in each group are set according to the types of the groups. For example, the set character library includes databases of three indexes (i.e., sensitive words, political expressions, and work orders) such as a sensitive word library, a political expression library (e.g., greeting words), and a work order matching library, and the word library can be used as a basis for scoring indexes. And matching the acquired voice data needing quality inspection with the characters in the set word library to find out whether the voice data contains the set characters. Taking a sensitive word bank as an example, whether non-civilized words which should not appear in certain voice data are searched, and if matched characters are detected, the fact that the sensitive words appear in the voice data can be judged.

The score corresponding to each index may be set according to actual conditions, the score corresponding to each index may be set, then the corresponding score is deducted from the set basic score, or the actual score corresponding to each index may be set, for example, the score corresponding to sensitive words may be-2, the score corresponding to non-polite words may be-3, and the score corresponding to work order filling errors may be-5. When the voice data is scored, a plurality of scoring items can be set, and the score is calibrated in a deduction mode, at this time, the basic score can be predefined. Through the scoring mode, words in the voice data can be matched with each scoring item, so that the voice data can be scored.

For example, if the voice data includes a sensitive word, the corresponding numerical value is subtracted from the preset basic score to obtain the first score of the voice data. When sensitive word detection is performed, a sensitive word set can be obtained from a sensitive word bank, current voice data is obtained, then the sensitive word set and the voice data are matched to obtain the number of times that the voice data contains sensitive words, specifically, if the voice data contains sensitive words with abusive properties, 2 points are deducted from corresponding basic scores, scores which should be deducted can be set respectively according to the matching number of the sensitive words, if the sensitive words are matched to 1-5 sensitive words, 2 points are deducted from the basic scores, if the sensitive words are matched to 6-10 sensitive words, 4 points are deducted from the basic scores, and the like. Through similar processing modes, whether the voice data comprise polite words or not can be judged, if not, corresponding scores are deducted from the first scores, and in the same way, different indexes can be processed through the modes respectively, and finally, the scores of the voice data can be obtained by subtracting the scores to be deducted from the basic scores. The obtained scores of the voice data can be used as a component of a quality inspection result, the quality inspection result of the customer service can be determined by statistical analysis aiming at the scores of all the voice data in each preset time period (such as 1 month) of the customer service, and the main problems of the customer service can be judged to a certain extent through the quality inspection result so as to adjust the working state of the customer service in time.

Based on the above-mentioned related matters, the role of the biometric detection component 110 may include: 1. when the customer service logs in the call center system 100 through the first terminal or modifies the biological characteristics in the call center system 100, the biological characteristics of the customer service can be detected and compared with the registered biological characteristics, so that the identity of the customer service is ensured, and a detection result is returned; 2. in the process of voice communication between the customer service and the user, the recording at the customer service side may be extracted in a random sampling manner, and then biometric detection is performed again to further ensure that the customer service provides services for the user, based on which, the biometric detection component 110 may also perform identity verification on the customer service logged in the first terminal of the call center system 100 through biometric features, which include facial features and/or voiceprint features.

In practice, as shown in fig. 2B, the customer service may be provided with the affiliated skill group, affiliated workplace, role (customer service or manager, etc.), affiliated group, attribute, customer service name, job number, answering mode, workable time range, whether to use biometric login, whether to log in through authentication information, etc. To better describe the embodiment of the present specification, when the customer service logs in the call center system 100, the customer service logs in the call center system 100 by means of the biometric verification and the verification information verification, and the role is customer service, when the customer service logs in the call center system 100 for the first time through the first terminal, on the login page, the customer service may input an account password, click the login key in the login page, the call center system 100 detects that the customer service needs to further verify the verification information and the biometric information, at this time, the biometric detection component 110 may collect the biometric information of the customer service, for example, record voiceprint information and facial information through the camera component and the sound collection component (specifically, the customer service may read a randomly generated number towards the camera, etc.), after the collection is completed, the login key in the page may be clicked, if the biometric verification of the customer service passes, the first terminal of the customer service may be allowed to log into the call center system 100. The maximum number of times of authentication of the biometric feature (e.g., 3 times or 5 times) may be preset, and if the number of times of authentication of the biometric feature exceeds the maximum number of times of authentication, the first terminal of the customer service is not allowed to log in the call center system 100, and at this time, the customer service needs to wait for a set time before logging in again. In addition, when logging in the call center system 100, if the customer service logs in through the external network or the VPN, the customer service does not need to be subjected to biometric verification, so that the customer service account can be prevented from logging in by other people, and for the management party, the customer service account can be prevented from logging in by other people after the account password is leaked.

As shown in fig. 2B, in a case that the call center system 100 can also implement a forced release process for a voice call between a customer service and a user, the recording subcomponent 144 may perform a recording process in the following manner: after the voice call between the first terminal and the second terminal is finished, the administrator and the user may continue the voice call, and the recording subassembly 144 may end recording the voice call between the first terminal and the second terminal. After the voice call between the customer service and the user is forcibly disconnected, prompt can be given through a pop-up frame, such as: your current voice call has been taken over, etc. The recording subcomponent 144 can start recording a voice call between the managing party and the user by forcibly detaching (or taking over) the managing party and stop at the end of the taking over. Before the forced removal process, when the management party monitors the voice call between the first terminal and the second terminal, the recording recorded by the recording subassembly 144 includes the voice call between the first terminal and the second terminal and the voice call between the management party and the user; before the forced release processing, when the manager is forcibly connected to the voice call between the first terminal and the second terminal, the recording recorded by the recording subassembly 144 includes the voice call between the first terminal and the second terminal (including the voice call between the manager, the customer service and the user), and the voice call between the manager and the user. The recording subcomponent 144 may not record voice data that the administrator transmits to the first terminal in whisper.

Based on the above, as shown in fig. 2B, the customer service management sub-component may further determine whether the IP address used by the first terminal of the customer service is in the IP white list when the customer service logs in the call center system 100 through the first terminal, and if so, allow the first terminal to log in the call center system 100.

Based on the above, the quality inspection component 120 may further obtain the number of times of the sensitive word triggered by the customer service and the number of times of the complaint of the customer service in a preset time period, determine the probability of the quality inspection of the customer service based on the obtained number of times of the sensitive word triggered by the customer service and the number of times of the complaint of the customer service, and perform quality inspection on the customer service based on the determined probability.

In an implementation, the quality inspection component 120 may count all triggered sensitive words, and perform weighted sorting on the triggered sensitive words according to a designated risk behavior (e.g., complaints, etc.), and may select N (N is a positive integer greater than or equal to 1) sensitive words ranked first, where the N sensitive words may be divided into a plurality of groups, and after the sensitive words in each group are triggered, the corresponding scores may be different, for example, N is 50, that is, the sorted sensitive words are TOP50, different TOP values, and the subtracted scores are different, for example, the sensitive words in TOP1 to TOP10 are triggered once, the subtracted score is 10, the sensitive words in TOP11 to TOP20 are triggered once, and the subtracted score is 5, and …. In this way, the quality control component 120 can score each voice call, and the score in a certain period of time (e.g., daily) is an average of the scores of all voice calls in the period of time, and the score is extracted for performing real-time quality control on the voice calls/the number of the extracted real-time quality control calls.

If the score is higher in a certain time period of customer service and the score of one or more voice calls is not lower than the preset threshold, the proportion of the voice call quantity subjected to real-time quality inspection in the next time period of customer service is reduced, and if the score is lower than the preset threshold in a certain time period of customer service, the proportion of the voice call quantity subjected to real-time quality inspection in the next time period of customer service is increased (such as set as the maximum value).

In the embodiment of the present specification, each component included in the call center system 100 may perform identity detection on the customer service when the customer service performs a voice call with the second terminal of the user through the first terminal, and when it is determined that the identity of the customer service is abnormal, access the management terminal of the management party to the voice communication link between the first terminal and the second terminal, so as to perform substitute printing (i.e. perform a voice call with the user instead of the customer service) or substitute connection (i.e. answer the call of the user instead of the customer service) on the customer service in time, thereby avoiding the above-mentioned abnormal operation, and in addition, when it is detected that the service state of the customer service corresponding to the first terminal is abnormal, end the voice call between the first terminal and the second terminal, and construct the voice communication link between the management terminal and the second terminal, so as to provide a service for the target service to the user of the second terminal, therefore, the service state of the customer service can be detected, the customer service can be guided to the service of the user in time, the voice call between the customer service and the user can be cut off when necessary, and the user can be continuously provided with the service by the management party, so that the service quality of the customer service is improved, the economic loss is reduced, the discontent of the user on the service provided by the customer service is reduced, and the irregular operation of the customer service is avoided or reduced.

Based on the call center system 100 and the composition structure thereof provided in the foregoing embodiments, an embodiment of the present disclosure further provides a communication establishment method, where an execution main body of the method may be the call center system 100 provided in the foregoing embodiments, and the composition structure of the call center system 100 may refer to the above-mentioned related contents, and is not described herein again. As shown in fig. 3, the method may specifically include the following steps:

in step S302, a management terminal of a management party is accessed to a first voice communication link between a first terminal and a second terminal, where the first terminal is a terminal providing customer service of a service for a target service, and the second terminal is a terminal of a user.

In implementation, the call center system 100 may access the management terminal of the management party to the first voice communication link between the first terminal and the second terminal, so that the management party may monitor the voice call between the first terminal and the second terminal, and may also send voice data to the customer service in a whisper manner when the customer service needs to be assisted to serve the user, or the management party also participates in a line serving the user, thereby implementing the voice call among the management party, the customer service, and the user.

In step S304, when it is determined that the service state of the customer service corresponding to the first terminal is abnormal, the voice call between the first terminal and the second terminal is ended, and a second voice communication link between the management terminal and the second terminal is established, where the second voice communication link is used for the management party to provide a service for the target service for the user of the second terminal through the management terminal.

It can be seen that, in the embodiment of the present specification, each component included in the call center system 100 can perform identity detection on the customer service when the customer service performs a voice call with the second terminal of the user through the first terminal, and when it is determined that the identity of the customer service is abnormal, the management terminal of the management party is connected to the first voice communication link between the first terminal and the second terminal, so as to perform substitute call (i.e. replace the customer service to perform a voice call with the user) or substitute call (i.e. replace the customer service to answer the phone of the user) on the customer service in time, thereby avoiding the above-mentioned irregular operation, and in addition, when it is detected that the service state of the customer service corresponding to the first terminal is abnormal, the voice call between the first terminal and the second terminal is ended, and a second voice communication link between the management terminal and the second terminal is constructed, so as to provide a service for the target service to the user of the second terminal, therefore, the service state of the customer service can be detected, the customer service can be guided to the service of the user in time, the voice call between the customer service and the user can be cut off when necessary, and the user can be continuously provided with the service by the management party, so that the service quality of the customer service is improved, the economic loss is reduced, the service discontent of the user on the customer service is reduced, and the irregular operation of the customer service is avoided or reduced.

In one or more embodiments of the present specification, the manner of determining that the service state of the customer service corresponding to the first terminal is abnormal in step S304 may be various, and an alternative processing manner is provided below, as shown in fig. 4, for specific reference, the processing of step S306 and step S308 may be described below.

In step S306, it is determined whether the content of the voice call between the first terminal and the second terminal includes a preset sensitive word.

In implementation, the call center system 100 may record the content of the voice call between the first terminal and the second terminal, convert the recorded voice call into text data through a pre-trained voice conversion model, and then perform sensitive word detection on the converted text data, thereby determining whether the content of the voice call between the first terminal and the second terminal includes a preset sensitive word.

In step S308, if yes, it is determined that the service state of the customer service corresponding to the first terminal is abnormal.

The processing of step S302 may include a plurality of different manners, and the following provides an optional processing manner, which may specifically include the following: and the management terminal is accessed to a first voice communication link between the first terminal and the second terminal in a monitoring mode so as to monitor the content of the voice call between the first terminal and the second terminal.

In implementation, a management party may actively monitor a voice call between a first terminal and a second terminal, specifically, an application program with call management set in advance may be included in the application program, the application program may include a trigger mechanism for monitoring a voice call, and may be provided with a corresponding trigger button, when the management party needs to monitor the content of the voice call between the first terminal and the second terminal, the management party may click the trigger button in the application program, at this time, the call center system 100 may start the trigger mechanism, and may access the management terminal to a first voice communication link between the first terminal and the second terminal in a monitoring manner, so that the management party may monitor the voice call between the first terminal and the second terminal through the management terminal.

In practical applications, the above process of accessing the management terminal to the first voice communication link between the first terminal and the second terminal in the monitoring manner may be various, and the following provides an optional processing manner, which may specifically include the following: when the fact that the identity of a customer service corresponding to a first terminal is abnormal is detected in a voice call between the first terminal and a second terminal, a management terminal is accessed to a first voice communication link between the first terminal and the second terminal in a monitoring mode.

For the above specific processing procedure, reference may be made to the foregoing related contents, which are not described herein again.

In one or more embodiments of the present specification, the above-mentioned manner of detecting whether the identity of the customer service corresponding to the first terminal is abnormal may be various, and an optional processing manner is provided below, which may specifically refer to the processing of step a2 to step a6 below.

In step a2, biometric information of the customer service is acquired during a voice call between the first terminal and the second terminal.

The biometric information may include information of facial features and/or information of voiceprint features, and may further include information of fingerprint features, information of iris features, information of palm print features, and the like.

In step a4, the identity of the customer service is verified based on the biometric information.

In step a6, if the verification result is failed, it is determined that the identity of the customer service is abnormal.

The specific processing procedures of the above steps can refer to the related contents, and are not described herein again.

The processing of step S302 may include a plurality of different manners, and the following provides another optional processing manner, which may specifically include the following: and when the identity of the customer service corresponding to the first terminal is detected to be abnormal in the voice communication between the first terminal and the second terminal, the management terminal is accessed into a first voice communication link between the first terminal and the second terminal.

In practical applications, in order to ensure the security of the call center system 100, an IP white list may be preset, and the terminal device that logs in the call center system 100 is verified through the IP white list, as shown in fig. 5, which may specifically include the following processing of step S310 and step S312.

In step S310, an IP address used by the first terminal is acquired.

In step S312, if the IP address is in the IP white list, the first terminal is allowed to log in the call center system 100.

Besides the processes of monitoring, forced insertion, forced disconnection and the like of the voice call between the first terminal and the second terminal, the manager can perform whisper operation on the customer service, and specifically, the following processes of step B2 and step B4 can be included.

In step B2, voice data transmitted by the management terminal for the customer service of the first terminal is received.

In implementation, the application program of the call management may further include a triggering mechanism for whisper to the customer service, and may be provided with a corresponding trigger button, and when the manager needs to perform whisper operation on a certain customer service, the trigger button in the application program may be clicked, at this time, the call center system 100 may start the triggering mechanism, and may enable the whisper function of the call center system 100 to be in an enabled state, and at this time, may receive voice data sent by the management terminal for the customer service of the first terminal.

In step B4, the voice data is transmitted to the first terminal.

In the embodiment of the present specification, each component included in the call center system 100 can perform identity detection on the customer service when the customer service performs a voice call with the second terminal of the user through the first terminal, and when it is determined that the identity of the customer service is abnormal, the management terminal of the management party is connected to the first voice communication link between the first terminal and the second terminal, so as to perform substitute call (i.e. replace the customer service to perform a voice call with the user) or substitute call (i.e. replace the customer service to answer the phone of the user) on the customer service in time, thereby avoiding the above-mentioned abnormal operation, and in addition, when it is detected that the service state of the customer service corresponding to the first terminal is abnormal, the voice call between the first terminal and the second terminal is ended, and a second voice communication link between the management terminal and the second terminal is constructed, so as to provide a service for the target service to the user of the second terminal, therefore, the service state of the customer service can be detected, the customer service can be guided to the service of the user in time, the voice call between the customer service and the user can be cut off when necessary, and the user can be continuously provided with the service by the management party, so that the service quality of the customer service is improved, the economic loss is reduced, the service discontent of the user on the customer service is reduced, and the irregular operation of the customer service is avoided or reduced.

The communication establishment method is described in detail below through specific application scenarios, which may include: the target data may be represented by a target domain name corresponding to the target data, and the verification information is described by taking a key as an example, as shown in fig. 6, the following may be specifically included:

in step S602, an IP address used by a first terminal is acquired, where the first terminal is a terminal that provides customer service for a service of a target service.

In step S604, if the IP address is in the IP white list, the biometric information of the customer service is obtained.

In step S606, the identity of the customer service is verified based on the biometric information.

In step S608, if the verification result is "pass", the first terminal is allowed to log in the call center system 100.

The processing of step S602 to step S608 is a processing procedure of the customer service logging in the call center system 100 through the first terminal, and subsequently, when the customer service performs a voice call with the user, the customer service may also perform secondary authentication, which may be specifically referred to the processing of step S610 to step S614 below.

In step S610, when the first terminal performs a voice call with a second terminal, the biometric information of the customer service is obtained, and the second terminal is a terminal of the user.

In step S612, the identity of the customer service is verified based on the biometric information.

In step S614, if the verification result is failed, it is determined that the identity of the customer service is abnormal.

In step S616, the management terminal is connected to the first voice communication link between the first terminal and the second terminal in a listening manner.

In step S618, it is determined whether the content of the voice call between the first terminal and the second terminal includes a preset sensitive word.

In step S620, if yes, it is determined that the service state of the customer service corresponding to the first terminal is abnormal.

In step S622, the voice call between the first terminal and the second terminal is ended, and a second voice communication link between the management terminal and the second terminal is established, where the second voice communication link is used for the manager to provide a service for the target service for the user of the second terminal through the management terminal.

Further, based on the methods described in fig. 3 to fig. 6, one or more embodiments of the present specification further provide a storage medium for storing computer-executable instruction information, in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, or the like, and when executed by a processor, the storage medium stores the computer-executable instruction information, which can implement the following processes:

It should be noted that the storage medium provided in this embodiment of the present disclosure can implement each process implemented by the communication establishing device in the foregoing communication establishing method embodiment, and for avoiding repetition, details are not described here again.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A call center system, the system comprising a biometric detection component, a quality inspection component, and a call management component, wherein:

the call management component is further configured to, when it is determined that the service state of the customer service is abnormal based on the service state detection result, end the voice call between the first terminal and the second terminal, and construct a second voice communication link between the management terminal and the second terminal, where the second voice communication link is used for the management party to provide a service for a target service to a user of the second terminal through the management terminal.

2. The system of claim 1, wherein the call management component is further configured to trigger the management terminal to monitor the content of the voice call between the first terminal and the second terminal when the management terminal is connected to the first voice communication link;

and the quality inspection component is used for detecting whether the service state of the customer service corresponding to the first terminal is abnormal or not based on the content of the monitored voice call.

3. The system of claim 1, further comprising a base functionality component comprising one or more of an interactive voice response subcomponent, an customer service management subcomponent, a task management subcomponent, a recording subcomponent and a base subcomponent, wherein:

the interactive voice response subassembly is used for establishing a voice communication link with the second terminal and establishing a first voice communication link between the second terminal and the first terminal;

the customer service management subassembly is used for controlling and managing the registration of customer service, the login of the customer service to the call center system through a terminal, the initiation of voice communication to a user by the customer service or the answering of the voice communication of the user by the customer service;

the task management subcomponent is used for carrying out configuration management on voice call initiated by the customer service to the user;

the recording subassembly is used for recording voice call data between the customer service and the user and providing the recorded voice call data to the quality inspection subassembly for quality inspection;

and the basic sub-component is used for configuring and managing voice call data.

4. The system of claim 3, wherein the customer service management subcomponent is further configured to register customer services logged into the call center system and send a registration message of the customer services logged into the call center system to a message queue; and acquiring the registration message from the message queue, packaging the registration message, and sending the packaged registration message to the message queue, wherein the packaged registration message is used for determining the predicted outbound parameters.

5. The system of claim 1, wherein the quality inspection component is further configured to:

acquiring the number of times of sensitive words triggered by the customer service and the number of times of complaints of the customer service in a preset time period; determining the probability that the customer service needs to be subjected to quality inspection based on the acquired times of the sensitive words triggered by the customer service and the obtained times of complaints of the customer service; and performing quality inspection on the customer service based on the determined probability.

6. The system of claim 5, wherein the quality inspection component is further configured to: comparing the voice data of the customer service, which needs quality inspection, with preset characters respectively, and detecting whether the voice data contains the characters or not; and respectively scoring the voice data according to the numerical values corresponding to the detection results, and determining the quality inspection result of the customer service according to the scoring result of each voice data.

7. A communication establishment method applied to the call center system according to any one of claims 1 to 6, the method comprising:

8. The method of claim 7, wherein accessing the management terminal of the management party to the first voice communication link between the first terminal and the second terminal comprises:

and when the identity of the customer service corresponding to the first terminal is detected to be abnormal in the voice call between the first terminal and the second terminal, accessing the management terminal to a first voice communication link between the first terminal and the second terminal in a monitoring mode.

9. The method of claim 7, wherein accessing the management terminal of the management party to the first voice communication link between the first terminal and the second terminal comprises:

when the identity of the customer service corresponding to the first terminal is detected to be abnormal in the voice call between the first terminal and the second terminal, the management terminal is accessed to a voice communication link between the first terminal and the second terminal so as to establish the call among the manager, the user and the customer service.

10. A storage medium for storing computer-executable instructions for causing a computer to perform the method of any one of claims 7 to 9.