CN113342961A

CN113342961A - Customer telephone complaint processing method, system, equipment and storage medium

Info

Publication number: CN113342961A
Application number: CN202110768713.2A
Authority: CN
Inventors: 叶帅; 向凌阳
Original assignee: Shanghai Huake Information Technology Co ltd
Current assignee: Shanghai Huake Information Technology Co ltd
Priority date: 2021-07-07
Filing date: 2021-07-07
Publication date: 2021-09-03

Abstract

The present invention provides a method, system, equipment and storage medium for handling customer telephone complaints. The method includes the steps of: acquiring customer voice call data, and converting the voice call data into text data; The trained preset deep learning model obtains the complaint level corresponding to each piece of the text data; establishes a first mapping relationship between the complaint level and the handling measures; obtains the complaint according to the first mapping relationship and the complaint level target processing measures corresponding to the levels; and pushing the target processing measures to the first terminal device corresponding to the administrator; the present application increases the accuracy of customer complaint identification and improves customer experience.

Description

Customer telephone complaint processing method, system, equipment and storage medium

Technical Field

The invention relates to the technical field of computers, in particular to a method, a system, equipment and a storage medium for processing customer telephone complaints.

Background

Customer complaints are identified from a conversation of a customer with a customer service, typically with a carrier of text and speech type. It is important for the customer to automatically identify potential or existing complaint intentions of the customer with respect to the contents of the session. For example, for a hotel, customer complaints need to be handled in time to keep more customers, and the rate of the customers to stay again is improved. The complaint identification method in the prior art comprises keyword identification and regular expression matching. The methods have the defects of low recall rate and frequent occurrence of complaint misjudgment, wherein the low recall rate means that the coverage rate of the keywords is very limited, so that the identification accuracy is low. The misjudgment of the complaint refers to the misidentification under complex semantics, such as 'bad' as a keyword, if the feedback of the complaint is 'the service can not be good', the complaint cannot be attributed to the complaint, and the method in the prior art still attributes the complaint to the complaint.

On the other hand, in the prior art, all customers cannot be distinguished and processed according to different priorities, but all the customers are processed in one block, so that complaints needing priority processing cannot be processed in time, customer satisfaction is low, and customer experience is greatly influenced.

Disclosure of Invention

Aiming at the problems in the prior art, the invention aims to provide a customer complaint processing method, a customer complaint processing system, customer complaint processing equipment and a storage medium, so that the customer complaint identification accuracy rate is improved, and the customer experience is improved.

In order to achieve the above object, the present invention provides a customer telephone complaint processing method, which includes the steps of:

s110, acquiring voice call data of a client, and converting the voice call data into text data;

s120, obtaining a complaint level corresponding to each piece of text data according to the text data and a trained preset deep learning model;

s130, establishing a first mapping relation between the complaint level and the treatment measure;

s140, obtaining a target processing measure corresponding to the complaint level according to the first mapping relation and the complaint level; and

s150, pushing the target processing measure to a first terminal device corresponding to a manager.

Optionally, step S120 further includes: obtaining a complaint item according to the text data; the method further comprises the steps of:

s160, obtaining a predicted improvement time limit corresponding to the complaint item;

s170, pushing the expected improvement time limit and a preset form to second terminal equipment corresponding to the client, wherein the preset form is used for acquiring the preference degree category of the client; the preference category is either satisfied or not satisfied; and

and S180, when the preference degree category is dissatisfied, the complaint level is improved by one level.

Optionally, the method further comprises the step of:

s190, obtaining order ending time corresponding to a customer and the communication starting time of the voice communication data; and

s200, when the customer belongs to a preset group and the time difference between the order ending time and the call starting time is larger than the expected improvement time limit, improving the complaint level to the highest complaint level; each client is attributed to a packet.

Optionally, step S200 further includes:

adding the client into a priority processing group, and pushing client list information corresponding to the priority processing group to first terminal equipment corresponding to a manager; task processing in the priority processing packet takes precedence over task processing of other telephone complaints.

Optionally, the complaint levels include severe, moderate, and mild;

the treatment measures corresponding to the severe complaint level comprise the steps of treating and completing complaints within a first preset time limit;

the treatment measures corresponding to the medium complaint level comprise the steps of treating and completing complaints within a second preset time limit;

the treatment measures corresponding to the mild complaint level comprise the treatment of completing complaints within a third preset time limit;

the first preset time limit is smaller than the second preset time limit, and the second preset time limit is smaller than the third preset time limit.

Optionally, step S110 includes:

separating the customer voice data and the customer service voice data in the voice call data;

and converting the client voice data into text data.

Optionally, step S130 further includes:

establishing a database containing a second mapping relation between the complaint items and the predicted improvement time limit;

step S160 includes:

and acquiring the predicted improvement time limit according to the complaint item and the database.

The invention also provides a customer telephone complaint processing system, which is used for realizing the customer telephone complaint processing method and comprises the following steps:

the voice text acquisition module is used for acquiring voice call data of a client and converting the voice call data into text data;

the complaint level acquisition module is used for acquiring a complaint level corresponding to each piece of text data according to the text data and a trained preset deep learning model;

the first mapping relation establishing module is used for establishing a first mapping relation between the complaint level and the treatment measure;

the processing measure acquisition module is used for acquiring a target processing measure corresponding to the complaint level according to the first mapping relation and the complaint level; and

and the processing measure pushing module is used for pushing the target processing measure to the first terminal equipment corresponding to the administrator.

The present invention also provides a customer telephone complaint processing apparatus, including:

a processor;

a memory having stored therein an executable program of the processor;

wherein the processor is configured to perform the steps of any of the above customer telephone complaint handling methods via execution of the executable program.

The present invention also provides a computer-readable storage medium storing a program which, when executed by a processor, performs the steps of any of the above-described customer telephone complaint handling methods.

Compared with the prior art, the invention has the following advantages and prominent effects:

the method, the system, the equipment and the storage medium for processing the complaint of the customer telephone, which are provided by the invention, adopt the preset deep learning model to analyze the text data corresponding to the voice call data of the customer, so that the identification accuracy of the complaint telephone is improved; when the conversation is determined to be complaint, the complaint grade is obtained, different treatment measures are adopted for treatment according to different complaint grades, hierarchical treatment is realized, emergency complaints can be treated in time, and customer experience is improved.

Drawings

Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.

FIG. 1 is a schematic diagram of a customer telephone complaint handling method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a customer telephone complaint handling method according to another embodiment of the disclosure;

FIG. 3 is a schematic diagram of a customer telephone complaint processing system according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a customer telephone complaint processing apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their repetitive description will be omitted.

As shown in fig. 1, an embodiment of the present invention discloses a customer telephone complaint processing method, which includes the following steps:

s110, obtaining the voice call data of the client, and converting the voice call data into text data. Specifically, in this embodiment, step S110 includes:

and S111, separating the client voice data and the client service voice data in the voice call data. And

and S112, converting the separated client voice data into text data.

The step S111 can be implemented by using a convolutional neural network Model in the prior art, for example, an Audio-Visual Speech Separation Model (Audio-Visual Speech Separation Model) in the prior art. The implementation of step S112 can also be implemented by using the prior art, and is not described in detail in this application.

And S120, obtaining the complaint level corresponding to each piece of text data according to the text data and the trained preset deep learning model. Specifically, the above-mentioned complaint grades in this application include severe, moderate and mild. The preset deep learning model firstly determines the complaint state of the text data, wherein the complaint state comprises complaints and non-complaints. And after the trained preset deep learning model determines that the text data are complaints, acquiring the complaint level corresponding to each piece of text data.

The preset deep learning model may be a deep learning model in the prior art, such as a transform model. The process of training the preset deep learning model can be realized by adopting the prior art, a training set can be constructed by utilizing text data corresponding to historical calls and labeled complaint grades, after the complaint grades are quantized, for example, the serious value is quantized to 2, the medium value is quantized to 1, the light value is quantized to 0, and the labeled complaint grade quantized value is used as a real value for training.

In this embodiment, in the complaint task processing process, the processing priority of the severe complaint level is higher than the moderate complaint level. The medium level of complaints is prioritized over the light level of complaints.

Therefore, the complaint level of the complaint session is identified in a deep learning model mode, complex keyword matching rules do not need to be designed and maintained, and labor cost is greatly reduced. And the identification accuracy and the recall rate are improved.

S130, establishing a first mapping relation between the complaint level and the treatment measure. Specifically, in this embodiment, the first mapping relationship may be:

the handling measures corresponding to the mild complaint level include handling the complete complaint within a third predetermined period of time.

Wherein the first preset time limit is less than the second preset time limit, and the second preset time limit is less than the third preset time limit. For example, the first predetermined period may be 3 hours, the second predetermined period may be 8 hours, and the third predetermined period may be 24 hours. Therefore, complaint levels can be treated preferentially, and the customer experience is improved.

In other embodiments, the handling measures corresponding to the heavy complaint level may also include placing a phone call to a manager with the robot. The handling measures corresponding to the medium complaint level can also comprise sending short messages to management personnel by using the robot. The processing measures corresponding to the mild complaint level can further include pushing prompt information to the first terminal device corresponding to the manager, wherein the prompt information is used for informing the complaint content. Therefore, the customer experience can be improved, and different notification modes can be adopted to notify the manager according to the graded customer complaints, so that good experience is brought to the manager. The situation that poor experience is brought to managers due to the fact that the managers are notified in a unified calling mode is avoided.

And S140, acquiring the target processing measure corresponding to the complaint level according to the first mapping relation and the complaint level. That is, in the first mapping relationship, the processing measure corresponding to the complaint level in step S120 is the target processing measure.

S150, pushing the target processing measure to a first terminal device corresponding to a manager. Therefore, after the customer complains, the management personnel can be informed of appropriate treatment measures corresponding to the different levels of complains, so that the situation that the management personnel do not know how to treat the complains to generate unnecessary secondary complains of the customer can be prevented, the training for the management personnel can be reduced, and the training cost is reduced.

As shown in fig. 2, in another embodiment of the present application, on the basis of the above embodiment, step S120 further includes: and obtaining the complaint items according to the text data.

The customer telephone complaint processing method in this embodiment further includes the steps of:

and S160, acquiring the expected improvement time limit corresponding to the complaint item.

S170, pushing the expected improvement time limit and a preset form to a second terminal device corresponding to the client. The preset form is used for acquiring the preference degree category of the client; the preference categories are either satisfied or not.

And S180, when the preference degree category is unsatisfactory, increasing the complaint level by one level.

The method for obtaining the complaint items from the text data can be that keywords are extracted from the text data, then the appropriate complaint items are matched according to the keywords and a second preset database, and a third mapping relation between the complaint keywords and the complaint items is stored in the second preset database; or matching the appropriate complaint items according to a machine learning model. The complaint items can be television failure, poor sanitation and the like.

In step S170, information filled in a preset form by the client may be acquired, where the information is used to characterize whether the client is satisfied with the expected improvement time limit, that is, characterize the preference category. And after the preference degree category is obtained, sending the preset form to a server. When the above-mentioned preference level category is unsatisfactory, the previous complaint level is mild, for example, in step S180, the preference level is adjusted to be moderate. When the previous complaint level was moderate, the adjustment was severe.

The manner of obtaining the expected improvement time limit according to the complaint item in step S160 can be implemented by referring to the prior art, and for example, the method can be: step S130 further includes:

a database is established containing a second mapping between the complaint items and the expected improvement deadline.

Step S160 includes:

and acquiring the predicted improvement time limit according to the complaint items and the database.

In another embodiment of the present application, based on the above embodiment, the customer telephone complaint processing method in this embodiment further includes the steps of:

and S190, acquiring order ending time corresponding to the customer and the call starting time of the voice call data. And

and S200, when the customer belongs to a preset group and the time difference between the order ending time and the call starting time is greater than the expected improvement time limit, increasing the complaint level to the highest complaint level. Where each client is attributed to a packet.

Specifically, for example, when the customer makes a complaint during a hotel accommodation process, the end time of the accommodation order of the customer, that is, the departure time, is obtained. The call starting time is the call starting time corresponding to a complaint call corresponding to the accommodation order of the customer. That is, after a complaint is made to a customer in a predetermined group, the complaint of the customer is treated most preferentially before the order is not completed. The method and the system realize that the complaint of the customer is processed before the customer leaves the store, are favorable for improving the experience of the customer in the order service process and improving the buyback rate of the customer. For example, the preset packet may be a VIP packet or an important packet. The historical average order number of the clients in the preset group is larger than that of the clients in all other groups. That is, the preset group is the group with the highest historical average order number of clients in all the groups.

Therefore, the use experience of the clients in the preset group can be preferentially improved, the help platform is favorable for balancing the relation between the client experience and the enterprise cost, and the cost of the enterprise is reduced under the condition that the experience of all the clients is not influenced.

As an alternative embodiment, on the basis of the above embodiment, step S200 may further include:

and adding the client into a priority processing group, and pushing the client list information corresponding to the priority processing group to a first terminal device corresponding to a manager. The task processing in the priority processing packet is prioritized over the task processing of other telephone complaints. The complaint handling time limit corresponding to the priority handling packet is less than the complaint handling time limit corresponding to the severe complaint level.

That is, when the customer belongs to the preset group and the time difference between the order ending time and the call starting time is greater than the expected improvement time limit, the manager is further informed to process the complaint content of the customer in the priority processing group in the highest priority, so that the platform can conveniently maintain important customers, and the satisfaction degree of the platform can be improved.

It should be noted that all terms and time periods mentioned in the present application are long periods and do not refer to specific dates.

All the above embodiments disclosed in the present application can be combined arbitrarily, and the technical solutions obtained by combining them are also within the scope of the present application.

As shown in fig. 3, an embodiment of the present invention further discloses a customer telephone complaint processing system 3, which includes:

the voice text acquisition module 31 acquires voice call data of a client and converts the voice call data into text data.

And the complaint level acquisition module 32 is used for acquiring a complaint level corresponding to each piece of text data according to the text data and the trained preset deep learning model.

The first mapping relation establishing module 33 establishes a first mapping relation between the complaint level and the treatment measure.

And the processing measure obtaining module 34 is configured to obtain a target processing measure corresponding to the complaint level according to the first mapping relationship and the complaint level. And

and the processing measure pushing module 35 is used for pushing the target processing measure to the first terminal device corresponding to the administrator.

It will be appreciated that the customer telephone complaint processing system of the present invention also includes other existing functional modules that support the operation of the customer telephone complaint processing system. The customer telephone complaint handling system shown in FIG. 3 is only an example and should not impose any limitation on the functionality or scope of use of embodiments of the invention.

The customer telephone complaint processing system in this embodiment is used to implement the method for processing customer telephone complaints, so for the specific implementation steps of the customer telephone complaint processing system, reference may be made to the description of the method for processing customer telephone complaints, and details are not described here.

The embodiment of the invention also discloses customer telephone complaint processing equipment which comprises a processor and a memory, wherein the memory stores an executable program of the processor; the processor is configured to perform the steps in the customer telephone complaint handling method described above via execution of the executable program. Fig. 4 is a schematic structural diagram of a customer telephone complaint processing apparatus disclosed in the present invention. An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 4. The electronic device 600 shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 4, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, etc.

Where the storage unit stores program code that may be executed by processing unit 610 to cause processing unit 610 to perform steps according to various exemplary embodiments of the present invention as described in the customer telephone complaint handling method section above in this specification. For example, processing unit 610 may perform the steps as shown in fig. 1.

The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.

The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 630 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.

The invention also discloses a computer readable storage medium for storing a program, which when executed implements the steps of the customer telephone complaint handling method. In some possible embodiments, aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned customer telephone complaint handling methods of the present specification, when the program product is run on the terminal device.

As shown above, when the program of the computer-readable storage medium of this embodiment is executed, the preset deep learning model is used to analyze the text data corresponding to the voice call data of the customer, so as to improve the recognition accuracy of the complaint call; when the conversation is determined to be complaint, the complaint grade is obtained, different treatment measures are adopted for treatment according to different complaint grades, hierarchical treatment is realized, emergency complaints can be treated in time, and customer experience is improved.

Fig. 5 is a schematic structural diagram of a computer-readable storage medium of the present invention. Referring to fig. 5, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The method, the system, the equipment and the storage medium for processing the complaint of the customer telephone, which are provided by the embodiment of the invention, adopt the preset deep learning model to analyze the text data corresponding to the voice call data of the customer, so that the identification accuracy of the complaint telephone is improved; complex keyword matching rules do not need to be designed and maintained, and labor cost is greatly reduced; when the conversation is determined to be complaint, the complaint grade is obtained, different treatment measures are adopted for treatment according to different complaint grades, hierarchical treatment is realized, emergency complaints can be treated in time, and customer experience is improved.

The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.

Claims

1. A customer telephone complaint handling method, comprising the steps of:

2. The customer telephone complaint processing method of claim 1, wherein step S120 further includes: obtaining a complaint item according to the text data; the method further comprises the steps of:

3. The customer telephone complaint handling method of claim 2, characterized in that the method further comprises the steps of:

4. The customer telephone complaint processing method of claim 3, wherein step S200 further includes:

5. The customer telephone complaint handling method of claim 1, wherein the complaint levels include severe, moderate, and mild;

6. The customer telephone complaint processing method of claim 1, wherein step S110 includes:

and converting the client voice data into text data.

7. The customer telephone complaint processing method of claim 2, wherein step S130 further includes:

step S160 includes:

8. A customer telephone complaint processing system for realizing the customer telephone complaint processing method according to claim 1, characterized by comprising:

9. A customer telephone complaint processing apparatus, comprising:

a processor;

a memory having stored therein an executable program of the processor;

wherein the processor is configured to perform the steps of the customer telephone complaint handling method of any of claims 1-7 via execution of the executable program.

10. A computer-readable storage medium storing a program which, when executed by a processor, implements the steps of the customer telephone complaint processing method of any one of claims 1 to 7.