Service grade dividing method and system for digital human customer service

Abstract

The invention discloses a service grade dividing method and system for digital human customer service staff. The method comprises the following steps: acquiring service data of a certain digital human customer service staff within a preset service duration; analyzing and processing the service data to obtain service evaluation index data of the digital human customer service; based on the preset weight coefficient of each piece of service evaluation index data and a preset service coefficient formula, calculating to obtain a service coefficient of the digital human customer service; grading the service coefficient of the digital human customer service according to a preset grading rule so as to determine the service grade of the digital human customer service; according to the method, service grade division is carried out on each digital human customer service, so that subsequent service quality monitoring, optimization or reward measures are facilitated, subsequent distribution of different service tasks for the digital human customer services with different service grades is facilitated, the service efficiency is improved, customer service resources are reasonably utilized, unnecessary waste is avoided, and the service quality of the digital human customer services is improved. And the performance and the user satisfaction of the whole service system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital human service evaluation, and more specifically, to a service level classification method and system for digital human customer service. Background Art

[0002] Virtual digital human assisted service based on video customer service application is an innovative service model that combines video customer service technology and virtual digital human technology to provide a more efficient, convenient and personalized customer service experience. In this service model, virtual digital humans can act as assistants or representatives of video customer service to interact and communicate with users in real time. Virtual digital humans use artificial intelligence technology to achieve automated and intelligent services, and can handle a large number of repetitive questions and requests, reducing the burden on manual customer service and improving service efficiency.

[0003] However, due to differences in training data, technical implementation, application scenarios, and personalized settings of different digital human customer service personnel, the service effects of different digital human customer service personnel are not the same. When different digital human customer service personnel provide services, random matching is used to determine the digital human customer service personnel who provides services. The problem with this allocation method is that it is not conducive to the allocation of different service tasks and cannot reasonably utilize customer service resources.

[0004] In summary, at this stage, there is an urgent need to develop a service level classification method and system for digital human customer service to solve the above-mentioned technical problems. Summary of the invention

[0005] An object of the present invention is to provide a new technical solution for a service level classification method, system, electronic device and storage medium for digital human customer service.

[0006] According to a first aspect of the present invention, a service level classification method for digital human customer service is provided, the method comprising: Obtain service data of a digital customer service representative within the preset service duration; Analyze and process the service data to obtain service evaluation index data of the digital human customer service, wherein the service evaluation index data includes standard response time, standard resolution time, repeated request rate, manual transfer rate and one-time resolution rate; The service coefficient of the digital human customer service is calculated based on the preset weight coefficient of each of the service evaluation index data and the preset service coefficient formula; The service coefficient of the digital human customer service is graded according to a preset grade classification rule to determine the service grade of the digital human customer service.

[0007] Optionally, the service data includes: the number of receptions, the response time of each reception, the resolution time of each reception, the number of one-time resolutions, the number of repeated requests and the number of transfers to manual services.

[0008] Optionally, analyzing and processing the service data to obtain service evaluation index data of the digital human customer service specifically includes: Determine the standard response time of the digital human customer service and the standard resolution time of the digital human customer service based on the number of receptions and the response time of each reception, and the number of receptions and the resolution time of each reception, respectively; The repetition request rate of the digital human customer service is determined by calculating the ratios of the number of repetition requests, the number of transfers to human services, and the number of one-time solutions to the number of receptions. The transfer rate of the digital human customer service to manual service and the one-time resolution rate of the digital human customer service.

[0009] Optionally, the virtual number is determined based on the number of receptions and the response time of each reception. The standard response time of human customer service includes: The average response time of the digital human customer service is calculated based on the number of receptions and the response time of each reception; Calculate the absolute value of the difference between the response time of each reception and the average response time to obtain a corresponding plurality of first absolute values ​​of the difference; Counting the number e of the absolute values ​​of the multiple first differences that are greater than or equal to a first preset value; If the number e is less than the second preset value, the average of the response time is determined as the standard response time of the digital human customer service; otherwise, the average of the maximum and minimum response times of each reception is determined as the standard response time of the digital human customer service; Determining the standard resolution time of the digital human customer service based on the number of receptions and the resolution time of each reception specifically includes: The average resolution time of the digital human customer service is calculated based on the number of receptions and the resolution time of each reception; Calculate the absolute value of the difference between the resolution time of each reception and the mean resolution time to obtain a corresponding plurality of second absolute values ​​of the difference; Counting the number e' of the plurality of second difference absolute values ​​that are greater than or equal to a third preset value; If the number e' is less than the fourth preset value, the mean of the resolution time is determined as the standard resolution time of the digital human customer service; otherwise, the mean of the maximum and minimum resolution times of each reception is determined as the standard resolution time of the digital human customer service; Wherein, the second preset value and the fourth preset value are both greater than or equal to 1.

[0010] Optionally, the preset service coefficient formula is expressed as: X r =T Ar ×w1+T Br ×w2+(1-F Ar )×w3+(1-F Br )×w4+E r ×w5 Among them, X r is the service factor, T Ar is the standard response time, T Br is the standard solution time, F Ar is the repeated request rate, F Br is the transfer rate to manual service, Er is the one-time resolution rate, and the corresponding preset weight coefficients are w1, w2, w3, w4 and w5, w1+w2+w3+w4+w5=1, r is the corresponding number of digital human customer service, r≥1.

[0011] Optionally, the preset level division rule is: the level of the digital human customer service whose service coefficient is greater than the first coefficient threshold preset value is marked as the first-level service level, the level of the digital human customer service whose service coefficient is greater than the second coefficient threshold preset value and is less than or equal to the first coefficient threshold is marked as the second-level service level, and the level of the digital human customer service whose service coefficient is less than or equal to the second coefficient threshold is marked as the third-level service level; wherein the first-level service level is higher than the second-level service level, and the second-level service level is higher than the third-level service level.

[0012] Optionally, the digital human customer service whose service coefficient is less than a third coefficient threshold is marked as a digital human in need of improvement.

[0013] According to a second aspect of the present invention, a service level classification system for digital human customer service is provided, the system comprising: An acquisition module is configured to acquire service data of a digital human customer service within a preset service time; A processing module is configured to analyze and process the service data to obtain service evaluation index data of the digital human customer service, wherein the service evaluation index data includes standard response time, standard resolution time, repeated request rate, manual transfer rate and one-time resolution rate; A calculation module, configured to calculate the service coefficient of the digital human customer service based on the preset weight coefficient of each service evaluation index data and the preset service coefficient formula; The classification module is configured to classify the service coefficient of the digital human customer service according to a preset classification rule to determine the service level of the digital human customer service.

[0014] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in the service level classification method for digital human customer service as described in the first aspect of the present invention are implemented.

[0015] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the service level classification method for digital human customer service as described in the first aspect of the present invention are implemented.

[0016] According to an embodiment disclosed in the present invention, a service level classification method and system for digital human customer service of the present invention has the following beneficial effects: The present invention provides a service level classification method for digital human customer service, which obtains and analyzes the historical service data of digital human customer service in the service system, obtains the service coefficient corresponding to each digital human customer service, and then classifies the service level of each digital human customer service. The service level of each digital human customer service is output for subsequent service quality monitoring, optimization or reward measures, which is conducive to the subsequent allocation of different service tasks to digital human customer service at different service levels, thereby improving service efficiency and ensuring that high-priority service requests are responded to in a timely manner. At the same time, it can also reasonably utilize customer service resources, avoid unnecessary waste, and improve the performance and user satisfaction of the entire service system.

[0017] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0019] Figure 1 A flow chart of a service level classification method for digital human customer service provided according to an embodiment Figure 1 ; Figure 2 A flow chart of a service level classification method for digital human customer service provided according to an embodiment Figure 2 ; Figure 3 It is a structural block diagram of a service level classification system for digital human customer service provided according to an embodiment; Figure 4 A schematic diagram of an electronic device. DETAILED DESCRIPTION

[0020] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0021] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0022] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0023] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0024] Embodiment 1: The embodiment of the present invention provides a service level classification method for digital human customer service, see Figure 1 As shown, the method includes: Step S1: Obtain service data of a certain digital human customer service within a preset service time; Optionally, the service data in step S1 of this embodiment includes: the number of receptions, the response time of each reception, the resolution time of each reception, the number of one-time resolutions, the number of repeated requests and the number of manual transfers.

[0025] It should be noted that, in this embodiment, the response time refers to the length of time from the user initiating a request to the digital human customer service responding; the resolution time refers to the time required for the digital human customer service to completely resolve the user's problem, including the time difference between the user raising the question and the problem being finally resolved; the number of resolutions refers to the number of times the digital human customer service and the user successfully resolved the problem in the first interaction, the number of repeated requests refers to the number of times the user raises the same or related questions again due to unsatisfactory solutions, and the number of manual transfers refers to the number of times the user needs to be transferred from the digital human customer service to the manual customer service for manual service.

[0026] Step S2: Analyze and process the service data to obtain service evaluation index data of Digital Human Customer Service, where the service evaluation index data includes standard response time, standard resolution time, repeated request rate, manual transfer rate and one-time resolution rate; The service evaluation index data in this embodiment can evaluate the service of virtual digital human customers from multiple aspects, which is helpful for the subsequent service level classification. Among them, the lower the value of the repeated request rate, the stronger the ability of the digital human customer service to effectively solve problems; the lower the value of the transfer rate, the stronger the ability of the digital human customer service to independently handle problems; the higher the value of the one-time resolution rate, the less frequent the repeated communication of the digital human customer service when serving users, and the higher the efficiency.

[0027] Optionally, in step S2 of this embodiment, the service data is analyzed and processed to obtain service evaluation index data of the digital human customer service, specifically including: Determine the standard response time of Digital Human Customer Service and the standard resolution time of Digital Human Customer Service based on the number of receptions and the response time of each reception, and the number of receptions and the resolution time of each reception; The repeated request rate, transfer rate and one-time resolution rate of digital human customer service are determined by calculating the ratio of the number of repeated requests, the number of transfers to manual services and the number of one-time resolutions to the number of receptions.

[0028] Specifically, the specific method of obtaining the repeated request rate and transfer rate corresponding to each digital human customer service is as follows; The number of receptions of each digital customer service within the preset service time T is marked as J r , the number of repeated requests and the number of transfers to human operators for each digital customer service within the preset service time T are marked as Q Ar and Q Br ; T is the preset value, which refers to the time range of T days from the moment the data is obtained. The moment the data is obtained is not included, and T≥1; The number of repeated requests and the number of manual transfers for each digital customer service within the preset service time T are respectively compared with the number of receptions J corresponding to each digital customer service within the preset service time T. r The ratio between them is marked as the repeated request rate F corresponding to each digital customer service. Ar And transfer labor rate F Br , that is, F Ar =J r / Q Ar ; F Br =J r / Q Br .

[0029] The specific method to obtain the one-time resolution rate of each digital human customer service is as follows: The number of solutions provided by each digital customer service representative within the preset service time T is marked as C. r, the number of receptions J corresponding to each digital customer service within the preset service time T r and the number of solutions C r The ratio between them is marked as the one-time resolution rate E corresponding to each digital customer service. r , that is, E r =J r / C r .

[0030] Optionally, in this embodiment, the virtual number is determined based on the number of receptions and the response time of each reception. The standard response time of Ziren customer service includes: The average response time of digital human customer service is calculated based on the number of receptions and the response time of each reception; Calculate the absolute value of the difference between the response time of each reception and the average response time to obtain a corresponding plurality of first absolute values ​​of the difference; Counting the number e of the absolute values ​​of the multiple first differences that are greater than or equal to a first preset value; If the number e is less than the second preset value, the average response time is determined as the standard response time of the digital human customer service; otherwise, the average of the maximum and minimum response times of each reception is determined as the standard response time of the digital human customer service; The standard resolution time of Digital Human customer service is determined based on the number of receptions and the resolution time of each reception. Specifically, it includes: The average resolution time of digital human customer service is calculated based on the number of receptions and the resolution time of each reception; Calculate the absolute value of the difference between the resolution time of each reception and the mean resolution time to obtain a corresponding plurality of second absolute values ​​of the difference; Counting the number e' of the plurality of second difference absolute values ​​that are greater than or equal to a third preset value; If the number e' is less than the fourth preset value, the mean of the resolution time is determined as the standard resolution time of the digital human customer service; otherwise, the mean of the maximum and minimum resolution times of each reception is determined as the standard resolution time of the digital human customer service; The second preset value and the fourth preset value are both greater than or equal to 1.

[0031] It should be noted that the specific values ​​of the first to fourth preset values ​​in this embodiment are formulated by relevant personnel according to actual needs and are not specifically limited here.

[0032] Specifically, the specific methods for obtaining the standard response time and standard resolution time corresponding to each digital human customer service are as follows: First, randomly select one of the digital customer service representatives as the target customer service representative; Then, the number of receptions of the target customer service within the preset service time T is obtained, i ≥ 1; and the response time and resolution time corresponding to each reception of the target customer service are marked as Y Ai and Y Bi ; Then for Y Ai and Y Bi Analyze and obtain the standard response time T of the target customer service A1 and standard solution time T B1 ; The specific method to obtain the standard response time and standard resolution time corresponding to the target customer service is: Get Y Ai Mean Y Ap , get each Y of the target customer service Ai Respectively with the mean Y Ap The absolute value of the difference between Ai , get G Ai The number of values ​​greater than or equal to L1 (i.e., the first preset value) is marked as e. When e is less than L2 (i.e., the second preset value), Y Ai Mean Y Ap As the standard response time T corresponding to the target customer service Ai , when e is greater than or equal to L2, then Y Ai The average of the maximum and minimum values ​​is used as the standard response time T corresponding to the target customer service A1 , that is, through T A1 =(T Amax +T Amin ) / 2, calculate the standard response time T corresponding to the target customer service A1 , where T Amax Y Ai The maximum value in T Amin Y Ai The minimum value among them, L1≥1, L2≥1; The same method as that used to obtain the standard response time of the target customer service is used to calculate the corresponding resolution time Y for each reception of the target customer service. Bi Analyze and obtain the standard resolution time T corresponding to the target customer service B1 ; Repeat the above steps to obtain the standard response time and standard resolution time T corresponding to each digital human customer service. Ar and T Br , where r refers to the number of corresponding digital human customer service in the service system, r≥1.

[0033] Step S3: Calculate the service coefficient of the digital human customer service based on the preset weight coefficient of each service evaluation index data and the preset service coefficient formula; In this embodiment, the standard response time T Ar , Standard solution time T Br , Repeat request rate F Ar , conversion rate to labor F Br and the first-time resolution rate E r Preset weight coefficients are set respectively and marked as w1, w2, w3, w4 and w5. The specific values ​​of these weight coefficients are set according to actual service requirements and satisfy w1+w2+w3+w4+w5=1.

[0034] Optionally, the preset service coefficient formula in this embodiment is expressed as: X r =T Ar ×w1+T Br ×w2+(1-F Ar )×w3+(1-F Br )×w4+E r ×w5 Among them, X r is the service coefficient, r is the number of digital human customer service, r≥1.

[0035] It should be noted that in this embodiment, (1-F Ar ) and (1-F Br ) will repeat the request rate F Ar And transfer labor rate F Ar This translates into a positive metric, as lower repeat request rates and referral rates mean better service quality.

[0036] Step S4: Classify the service coefficient of the digital human customer service according to the preset classification rules to determine the service level of the digital human customer service.

[0037] Optionally, the preset grade classification rules in this embodiment are: the grade of the digital human customer service whose service coefficient is greater than the first coefficient threshold is marked as the first-level service grade, the grade of the digital human customer service whose service coefficient is greater than the second coefficient threshold and less than or equal to the first coefficient threshold is marked as the second-level service grade, and the grade of the digital human customer service whose service coefficient is less than or equal to the second coefficient threshold is marked as the third-level service grade; wherein, the first-level service grade is higher than the second-level service grade, and the second-level service grade is higher than the third-level service grade.

[0038] Specifically, in this embodiment, the service levels corresponding to different digital human customer services are divided according to the service coefficients corresponding to different digital human customer services. The specific method is as follows: According to the calculated service coefficient X of each digital customer service r , classify the service level of digital human customer service: the service coefficient X rThe level of digital human customer service with a service coefficient greater than L3 (i.e., the first coefficient threshold) is marked as level one, and the service coefficient X r The level classification of digital human customer service with a service coefficient greater than L4 (i.e., the second coefficient threshold) and less than or equal to L3 (i.e., the first coefficient threshold) is marked as level 2, and the service coefficient X r The level classification of digital human customer service that is less than or equal to L4 (i.e., the second coefficient threshold) is marked as three levels, and the specific values ​​of L3 and L4 are formulated based on actual needs.

[0039] Among them, the first-level service level is higher than the second-level service level, and the second-level service level is higher than the third-level service level. The higher the service level, the better the service quality provided by the corresponding digital customer service, and vice versa.

[0040] Optionally, in this embodiment, a digital human customer service representative whose service coefficient is less than a third coefficient threshold is also marked as a digital human in need of improvement.

[0041] Specifically, digital human customer service with a service coefficient less than L5 (i.e., the third coefficient threshold) will be marked as a digital human that needs improvement. By marking the digital human that needs improvement, the service system will be helped to monitor and optimize the quality of digital human customer service to improve service quality and user satisfaction.

[0042] When the repeated request rate F corresponding to the digital human customer service Ar And transfer labor rate F Br When the corresponding values ​​are all large, that is, greater than L6 (the fourth coefficient threshold), it means that the interactive ability of the corresponding digital human customer service is lacking. Outputting the corresponding digital human customer service will help relevant personnel to further analyze the corresponding digital human customer service. The specific values ​​of L5 and L6 are formulated according to actual needs.

[0043] To sum up, the service level classification method for digital human customer service in the embodiment of the present invention obtains and analyzes the historical service data of digital human customer service in the service system to obtain the service coefficient corresponding to each digital human customer service, and then classifies the service level of each digital human customer service, and outputs the service level of each digital human customer service for subsequent service quality monitoring, optimization or reward measures. For example, digital human customer service with higher service levels can be rewarded, or digital human customer service with lower service levels can be trained and improved, which is conducive to the subsequent allocation of different service tasks to digital human customer service with different service levels, thereby improving service efficiency and ensuring that high-priority service requests are responded to in a timely manner. At the same time, it can also reasonably utilize customer service resources to avoid unnecessary waste, and improve the performance and user satisfaction of the entire service system.

[0044] Embodiment 2: See also Figure 3As shown, an embodiment of the present invention provides a service level classification system for digital human customer service, and the system 100 includes: The acquisition module 10 is configured to acquire service data of a certain digital human customer service within a preset service time; The processing module 20 is configured to analyze and process the service data to obtain service evaluation index data of the digital human customer service, wherein the service evaluation index data includes standard response time, standard resolution time, repeated request rate, manual transfer rate and one-time resolution rate; The calculation module 30 is configured to calculate the service coefficient of the digital human customer service based on the preset weight coefficient of each service evaluation index data and the preset service coefficient formula; The classification module 40 is configured to classify the service coefficient of the digital human customer service according to a preset classification rule to determine the service level of the digital human customer service.

[0045] Optionally, the service data in the service level classification system for digital human customer service in this embodiment includes: the number of receptions, the response time of each reception, the resolution time of each reception, the number of one-time resolutions, the number of repeated requests and the number of transfers to manual services.

[0046] Optionally, in the service level classification system for digital human customer service of this embodiment, the processing module 20 specifically includes: The first determination unit is configured to determine the standard response time of digital human customer service and the standard resolution time of digital human customer service based on the number of receptions and the response time of each reception, and the number of receptions and the resolution time of each reception, respectively; The second determination unit is configured to determine the repeated request rate of digital human customer service, the transfer rate of digital human customer service and the one-time resolution rate of digital human customer service by calculating the ratios of the number of repeated requests, the number of transfers to manual services and the number of one-time resolutions to the number of receptions respectively.

[0047] Optionally, in the service level classification system for digital human customer service of this embodiment, the first determination unit is specifically configured as follows: The average response time of digital human customer service is calculated based on the number of receptions and the response time of each reception; Calculate the absolute value of the difference between the response time of each reception and the average response time to obtain a corresponding plurality of first absolute values ​​of the difference; Counting the number e of the absolute values ​​of the multiple first differences that are greater than or equal to a first preset value; If the number e is less than the second preset value, the average response time is determined as the standard response time of the digital human customer service; otherwise, the average of the maximum and minimum response times of each reception is determined as the standard response time of the digital human customer service; The average resolution time of digital human customer service is calculated based on the number of receptions and the resolution time of each reception; Calculate the absolute value of the difference between the resolution time of each reception and the mean resolution time to obtain a corresponding plurality of second absolute values ​​of the difference; Counting the number e' of the plurality of second difference absolute values ​​that are greater than or equal to a third preset value; If the number e' is less than the fourth preset value, the mean of the resolution time is determined as the standard resolution time of the digital human customer service; otherwise, the mean of the maximum and minimum resolution times of each reception is determined as the standard resolution time of the digital human customer service; The second preset value and the fourth preset value are both greater than or equal to 1.

[0048] Optionally, the preset service coefficient formula in the service level classification system for digital human customer service in this embodiment is expressed as: X r =T Ar ×w1+T Br ×w2+(1-F Ar )×w3+(1-F Br )×w4+E r ×w5 Among them, X r is the service factor, T Ar is the standard response time, T Br is the standard solution time, F Ar is the repeated request rate, F Br is the transfer rate to manual service, Er is the one-time resolution rate, and the corresponding preset weight coefficients are w1, w2, w3, w4 and w5, w1+w2+w3+w4+w5=1, r is the corresponding number of digital human customer service, r≥1.

[0049] Optionally, the preset level division rules in the service level division system for digital human customer service of this embodiment are: the level of digital human customer service whose service coefficient is greater than the preset value of the first coefficient threshold is marked as the first-level service level, the level of digital human customer service whose service coefficient is greater than the preset value of the second coefficient threshold and is less than or equal to the first coefficient threshold is marked as the second-level service level, and the level of digital human customer service whose service coefficient is less than or equal to the second coefficient threshold is marked as the third-level service level; wherein, the first-level service level is higher than the second-level service level, and the second-level service level is higher than the third-level service level.

[0050] Optionally, in the service level classification system for digital human customer service of this embodiment, a digital human customer service whose service coefficient is less than a third coefficient threshold is marked as a digital human in need of improvement.

[0051] Embodiment three: The present invention discloses an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the service level classification methods for digital human customer service in the first embodiment of the present invention are implemented.

[0052] Figure 4 is a structural diagram of an electronic device according to an embodiment of the present invention, such as Figure 4 As shown, the electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0053] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a structural diagram of the part related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0054] Embodiment 4: The embodiment of the present invention discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the service level classification methods for digital human customer service in the first embodiment of the present invention are implemented.

[0055] Please note that the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the patent in this application shall be based on the attached claims.

[0056] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0057] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will be appreciated by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A service level classification method for digital human customer service, characterized in that: Said Methods include: Obtain service data of a digital customer service representative within the preset service duration; Analyze and process the service data to obtain service evaluation index data of the digital human customer service, wherein the service evaluation index data includes standard response time, standard resolution time, repeated request rate, manual transfer rate and one-time resolution rate; The service coefficient of the digital human customer service is calculated based on the preset weight coefficient of each of the service evaluation index data and the preset service coefficient formula; The service coefficient of the digital human customer service is graded according to a preset grade classification rule to determine the service grade of the digital human customer service.

2. The service level classification method for digital human customer service according to claim 1 is characterized in that: The service data includes: the number of receptions, the response time of each reception, the resolution time of each reception, the number of one-time resolutions, the number of repeated requests and the number of transfers to manual services.

3. The service level classification method for digital human customer service according to claim 2 is characterized in that: The analyzing and processing of the service data to obtain the service evaluation index data of the digital human customer service specifically includes: Determine the standard response time of the digital human customer service and the standard resolution time of the digital human customer service based on the number of receptions and the response time of each reception, and the number of receptions and the resolution time of each reception, respectively; The repetition request rate of the digital human customer service is determined by calculating the ratios of the number of repetition requests, the number of transfers to human services, and the number of one-time solutions to the number of receptions. The transfer rate of the digital human customer service to manual service and the one-time resolution rate of the digital human customer service.

4. The service level classification method for digital human customer service according to claim 3 is characterized in that: Determining the standard response time of the digital human customer service based on the number of receptions and the response time of each reception specifically includes: The average response time of the digital human customer service is calculated based on the number of receptions and the response time of each reception; Calculate the absolute value of the difference between the response time of each reception and the average response time to obtain a corresponding plurality of first absolute values ​​of the difference; Counting the number e of the absolute values ​​of the multiple first differences that are greater than or equal to a first preset value; If the number e is less than the second preset value, the average of the response time is determined as the standard response time of the digital human customer service; otherwise, the average of the maximum and minimum response times of each reception is determined as the standard response time of the digital human customer service; Determining the standard resolution time of the digital human customer service based on the number of receptions and the resolution time of each reception specifically includes: The average resolution time of the digital human customer service is calculated based on the number of receptions and the resolution time of each reception; Calculate the absolute value of the difference between the resolution time of each reception and the mean resolution time to obtain a corresponding plurality of second absolute values ​​of the difference; Counting the number e' of the plurality of second difference absolute values ​​that are greater than or equal to a third preset value; If the number e' is less than the fourth preset value, the mean of the resolution time is determined as the standard resolution time of the digital human customer service; otherwise, the mean of the maximum and minimum resolution times of each reception is determined as the standard resolution time of the digital human customer service; Wherein, the second preset value and the fourth preset value are both greater than or equal to 1.

5. The service level classification method for digital human customer service according to claim 1 is characterized in that: The preset service coefficient formula is expressed as: X r =T Ar ×w1+T Br ×w2+(1-F Ar )×w3+(1-F Br )×w4+E r ×w5 Among them, X r is the service factor, T Ar is the standard response time, T Br is the standard solution time, F Ar is the repeated request rate, F Br is the transfer rate to manual service, Er is the one-time resolution rate, and the corresponding preset weight coefficients are w1, w2, w3, w4 and w5, w1+w2+w3+w4+w5=1, r is the corresponding number of digital human customer service, r≥1.

6. The service level classification method for digital human customer service according to claim 1 is characterized in that: The preset level division rule is: the level of the digital human customer service whose service coefficient is greater than the first coefficient threshold is marked as the first-level service level, the level of the digital human customer service whose service coefficient is greater than the second coefficient threshold and less than or equal to the first coefficient threshold is marked as the second-level service level, and the level of the digital human customer service whose service coefficient is less than or equal to the second coefficient threshold is marked as the third-level service level; wherein the first-level service level is higher than the second-level service level, and the second-level service level is higher than the third-level service level.

7. The service level classification method for digital human customer service according to claim 6 is characterized in that: The digital human customer service whose service coefficient is less than the third coefficient threshold is marked as a digital human in need of improvement.

8. A service level classification system for digital human customer service, characterized in that: The system comprises: An acquisition module is configured to acquire service data of a digital human customer service within a preset service time; A processing module is configured to analyze and process the service data to obtain service evaluation index data of the digital human customer service, wherein the service evaluation index data includes standard response time, standard resolution time, repeated request rate, manual transfer rate and one-time resolution rate; A calculation module, configured to calculate the service coefficient of the digital human customer service based on the preset weight coefficient of each service evaluation index data and the preset service coefficient formula; The classification module is configured to classify the service coefficient of the digital human customer service according to a preset classification rule to determine the service level of the digital human customer service.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps in the service level classification method for digital human customer service described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps in the service level classification method for digital human customer service described in any one of claims 1 to 7 are implemented.

Images