CN117371683A

CN117371683A - Customer service scheduling method and device

Info

Publication number: CN117371683A
Application number: CN202311212170.1A
Authority: CN
Inventors: 李孔语; 胡明锋; 曾凡雄; 林陈胜
Original assignee: Zhongdian Jinxin Software Co Ltd
Current assignee: Zhongdian Jinxin Software Co Ltd
Priority date: 2023-09-19
Filing date: 2023-09-19
Publication date: 2024-01-09

Abstract

The disclosure provides a customer service scheduling method and device, wherein the method comprises the following steps: acquiring a plurality of class types of a first set period; for any one of a plurality of first sub-periods in a second set period, predicting the predicted incoming power of the any one first sub-period according to the first historical incoming power of a plurality of first historical sub-periods in synchronization with any one first sub-period, determining the number of to-be-scheduled customer service of a plurality of class types in the second set period according to the predicted incoming power and the first set service level corresponding to the plurality of first sub-periods and according to the first average call duration corresponding to the plurality of first historical sub-periods; according to the number of customer service to be scheduled of the plurality of classes, the plurality of classes are subjected to customer service scheduling to obtain scheduling results of the plurality of classes, so that automatic customer service scheduling based on actual service requirements is realized, the scheduling results can meet the actual service requirements, meanwhile, the manual mode is not required to be adopted for customer service scheduling, and the scheduling efficiency is improved.

Description

Customer service scheduling method and device

Technical Field

The disclosure relates to the technical field of data processing, in particular to a customer service scheduling method and device.

Background

Currently, a customer service center is a department or an organization that provides services for customers specifically, and provides consultation, solves problems, provides after-sales services, etc. for customers through customer service personnel, so it is very important how to reasonably arrange the customer service in each time period in order to meet the service requirements of customers in time.

In the related art, a manual mode is mainly adopted for customer service scheduling, however, the manual scheduling mode may cause the problems of low efficiency, long time consumption and difficulty in meeting actual service requirements of scheduling results.

Disclosure of Invention

The present disclosure provides a customer service scheduling method and apparatus to solve at least one of the technical problems in the related art to a certain extent. The technical scheme of the present disclosure is as follows:

according to a first aspect of an embodiment of the present disclosure, there is provided a customer service scheduling method, including: acquiring a plurality of class types of a first set period; predicting a predicted power consumption of any one of a plurality of first sub-periods within a second set period according to a first historical power consumption of a plurality of first historical sub-periods contemporaneous with the any one first sub-period, wherein the second set period is within the first set period; determining the quantity of the to-be-scheduled class customer service of a plurality of class types in a second set period according to the predicted incoming electricity quantity corresponding to the plurality of first sub-periods and a first set service level and according to a first average call duration corresponding to the plurality of first historical sub-periods; and performing customer service scheduling on the plurality of class types according to the number of the to-be-scheduled customer service of the plurality of class types so as to obtain scheduling results of the plurality of class types.

According to a second aspect of the embodiments of the present disclosure, there is provided a customer service scheduling apparatus, including: an acquisition module for acquiring a plurality of class types of the first set period; a prediction module, configured to predict, for any one of a plurality of first sub-periods within a second set period, a predicted power consumption of the any one of the first sub-periods according to a first historical power consumption of a plurality of first historical sub-periods that are contemporaneous with the any one of the first sub-periods, where the second set period is located within the first set period; the determining module is used for determining the quantity of the to-be-scheduled class service of a plurality of class types in a second set period according to the predicted incoming electricity quantity corresponding to the plurality of first sub-periods and a first set service level and according to a first average call duration corresponding to the plurality of first historical sub-periods; and the shift module is used for carrying out the customer service shift on the plurality of shift types according to the number of the customer service to be shifted of the plurality of shift types so as to obtain shift shifting results of the plurality of shift types.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to generate a customer service scheduling method as described in an embodiment of the first aspect of the disclosure.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform a customer service scheduling method as described in the embodiments of the first aspect of the present disclosure.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising: a computer program which, when executed by a processor, implements a customer service scheduling method as described in an embodiment of the first aspect of the present disclosure.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

1. according to the predicted incoming electricity quantity and the first set service level corresponding to the first sub-periods and the first average call duration corresponding to the first historical sub-periods, the number of the to-be-scheduled service of the plurality of classes in the second set period is determined together, and the accuracy of the number of the to-be-scheduled service of the plurality of classes in the second set period is improved; furthermore, according to the number of customer service to be scheduled of the plurality of class types, the plurality of class types are automatically scheduled to obtain the scheduling results of the plurality of class types, so that the automatic customer service scheduling based on actual service requirements is realized, the scheduling results can meet the actual service requirements, meanwhile, the manual mode is not required to be adopted for the customer service scheduling, and the scheduling efficiency is improved;

2. According to the set scheduling rules, determining second to-be-scheduled customer service meeting various types from a plurality of first to-be-scheduled customer service in the to-be-scheduled object sequence, and adding the second to-be-scheduled customer service to the scheduling results corresponding to any type of the classes, so that the scheduling results of the various types can be accurately generated, and the rationality of the scheduling results is improved;

3. when an incoming call request sent by an active calling party at a target moment is received, a corresponding target class type can be determined according to the target moment, and a target customer service is determined from at least one candidate customer service of a scheduling result of the target class type, so that the incoming call request is transferred to the target customer service, the timeliness of incoming call transfer and processing is improved, the incoming call is not required to be manually transferred, missed transfer and incorrect transfer of the incoming call caused by manual transfer are avoided, and the incoming call transfer accuracy is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

Fig. 1 is a flow chart of a customer service scheduling method according to a first embodiment of the present disclosure;

FIG. 2 is a flow chart of a customer service scheduling method according to a second embodiment of the present disclosure;

FIG. 3 is a flow diagram of customer service scheduling for a plurality of class types, as shown in an embodiment of the present disclosure;

FIG. 4 is a flow chart of a customer service scheduling method according to a third embodiment of the present disclosure;

FIG. 5 is a flow chart of a customer service scheduling method according to a fourth embodiment of the present disclosure;

FIG. 6 is a flow chart of a customer service scheduling method according to a fifth embodiment of the present disclosure;

FIG. 7 is a flow chart of a customer service scheduling method shown in an embodiment of the present disclosure;

fig. 8 is a schematic structural view of an incoming call processing apparatus according to a sixth embodiment of the present disclosure;

fig. 9 is a schematic structural view of an electronic device according to an exemplary embodiment of the present disclosure.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

It should be noted that, in the technical solution of the present disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing, etc. of the personal information of the user are all performed on the premise of proving the consent of the user, and all conform to the rules of the related laws and regulations, and do not violate the popular regulations of the public order.

In the related art, the customer service personnel can be scheduled based on the predicted incoming electricity quantity and the average call time length so as to achieve the matching of the human resources and the incoming electricity quantity, however, the following problems exist in the scheduling of the customer service personnel based on the predicted incoming electricity quantity and the average call time length:

1. the lack of effective shift table planning, the shift arrangement of customer service personnel (to-be-shifted customer service) is only carried out based on the predicted incoming electricity quantity and the average call duration, the accuracy is poor, and the incoming call cannot be timely processed;

2. the prediction algorithm of the incoming electricity quantity is single, which may result in failure to perform customer service scheduling according to the predicted incoming electricity quantity, for example: for some special dates, historical sample data cannot be obtained, and even the sales promotion days such as 520 and 618 which are only recently appeared are extremely limited in sample, the characteristics of the data are difficult to predict by a single prediction algorithm, and therefore customer service shifts cannot be performed according to the predicted incoming electricity quantity.

Aiming at the problems, the disclosure provides a customer service scheduling method and device.

The following describes customer service scheduling methods and apparatuses according to embodiments of the present disclosure with reference to the accompanying drawings.

Fig. 1 is a flow chart of a customer service scheduling method according to a first embodiment of the present disclosure. The incoming call processing method implemented by the method can be applied to a customer service scheduling device, and the customer service scheduling device can be a scheduling system.

As shown in fig. 1, the customer service scheduling method may include the steps of:

step 101, a plurality of class types of the first set period are acquired.

In the embodiment of the present disclosure, the first set period may be a period set according to actual requirements, for example, the duration of the first set period may be one month, the first set period is 2023, 5, 1 to 2023, 5, 31, and the class type may include, but is not limited to: the method comprises the steps of early shift, middle shift and late shift, wherein each shift type further comprises a corresponding time period, for example, the time period corresponding to the early shift is 8:00-9:00, the time period corresponding to the middle shift is 10:00-14:00, and the time period corresponding to the late shift is 20:00-23:00.

In order to improve accuracy in determining the class type, the first set period may include a plurality of third sub-periods, different on-duty periods may be determined according to the number of customer service shifts required for predicting each of the third sub-periods, and the plurality of class types of the first set period may be determined according to the on-duty periods. Wherein the duration of the third sub-period may be 15 minutes.

Step 102, predicting, for any one of the plurality of first sub-periods in the second set period, a predicted power consumption of the any one of the plurality of first sub-periods according to a first historical power consumption of the plurality of first historical sub-periods contemporaneous with the any one of the first sub-periods.

Wherein the second set period is located within the first set period. For example, the first set period is 2023, 5, month, 1, to 2023, 5, month, 31, and the second set period may be 2023, 5, month, 1, to 2023, 5, month, 10.

As an example, the second set period may include a plurality of first sub-periods, and for any one of the first sub-periods, an average value of first historical power consumption amounts of a plurality of first historical sub-periods that are contemporaneous with the any one of the first sub-periods may be used as the predicted power consumption amount for the any one of the first sub-periods. Wherein the duration of the first sub-period may be set to 15 minutes.

As another example, to improve the accuracy of the predicted incoming power amount for the plurality of first sub-periods, a target prediction algorithm may be determined from a plurality of set candidate prediction algorithms for any one of the first sub-periods, and the predicted incoming power amount for any one of the first sub-periods may be predicted from the first historical incoming power amounts for the plurality of first historical sub-periods that are contemporaneous with the any one of the first sub-periods using the target prediction algorithm.

And step 103, determining the number of the to-be-scheduled class services of a plurality of class types in the second set period according to the predicted incoming electricity quantity corresponding to the plurality of first sub-periods and the first set service level and according to the first average call duration corresponding to the plurality of first historical sub-periods.

In this embodiment of the present disclosure, the second set period may include a plurality of second sub-periods, according to predicted incoming power and a first set service level corresponding to the plurality of first sub-periods, and according to a first average call duration corresponding to the plurality of first history sub-periods, a first shift service number required by the plurality of shift types in the second sub-period is predicted, and according to the first shift service number required by the plurality of shift types in each second sub-period, a to-be-shifted service number of the plurality of shift types in the first set period is determined, where a duration of the second sub-period is longer than a duration of the first sub-period, for example, a duration of the second sub-period may be one day, and a duration of the first sub-period is 15 minutes. The first set service level may be a desired service level (i.e., number of processed calls/total number of calls) corresponding to the first sub-period.

And 104, performing customer service scheduling on the plurality of class types according to the number of the to-be-scheduled customer service of the plurality of class types to obtain scheduling results of the plurality of class types.

Further, in order to improve the rationality of the scheduling result, the scheduling of the plurality of class types can be performed based on the set scheduling rules and the to-be-scheduled service sequences according to the to-be-scheduled service numbers of the plurality of class types, so as to obtain the scheduling result of the plurality of class types.

In summary, by acquiring a plurality of class types for a first set period; for any one of a plurality of first sub-periods within the second set period, predicting a predicted power consumption of the any one of the first sub-periods according to a first historical power consumption of a plurality of first historical sub-periods contemporaneous with the any one of the first sub-periods; according to the predicted incoming electricity quantity corresponding to the first sub-periods and the first set service level, and according to the first average call duration corresponding to the first historical sub-periods, determining the number of the to-be-scheduled customer service of the class types in the second set period; according to the number of the to-be-scheduled service of the plurality of classes, the plurality of classes are scheduled to obtain the scheduling results of the plurality of classes, so that the number of the to-be-scheduled service of the plurality of classes in the second set period is commonly determined according to the predicted incoming electricity quantity corresponding to the plurality of first sub-periods and the first set service level and according to the first average call duration corresponding to the plurality of first history sub-periods, and the accuracy of the number of the to-be-scheduled service of the plurality of classes in the second set period is improved; furthermore, according to the number of customer service to be scheduled of the plurality of class types, the customer service scheduling is automatically performed on the plurality of class types to obtain scheduling results of the plurality of class types, and automatic customer service scheduling based on actual service requirements is achieved, so that the scheduling results can meet the actual service requirements, meanwhile, the manual mode is not needed for customer service scheduling, and the scheduling efficiency is improved.

In order to clearly illustrate how to perform a customer service scheduling on a plurality of class types according to the number of to-be-scheduled customers of the plurality of class types in the above embodiment, another customer service scheduling method is proposed in the present disclosure.

Fig. 2 is a flow chart of a customer service scheduling method according to a second embodiment of the present disclosure.

As shown in fig. 2, the customer service scheduling method may include the following steps:

step 201, a plurality of class types of the first set period are acquired.

Step 202, for any one of a plurality of first sub-periods in the second set period, predicting a predicted power consumption of any one of the first sub-periods according to a first historical power consumption of a plurality of first historical sub-periods that are contemporaneous with the any one of the first sub-periods.

Wherein the second set period is located within the first set period.

Step 203, determining the number of the to-be-scheduled class services of the plurality of class types in the second set period according to the predicted incoming power corresponding to the plurality of first sub-periods and the first set service level, and according to the first average call duration corresponding to the plurality of first historical sub-periods.

Step 204, acquiring a set scheduling rule and a waiting-to-be-scheduled customer service sequence containing a plurality of first waiting-to-be-scheduled customer services.

The setting scheduling rules may be preset in the scheduling system, where the setting scheduling rules may be, for example: the staff can not rest for more than 10 days continuously, 24 hours after night shifts, 3 days continuously except holiday adjustment, etc.

The waiting-to-shift service sequence comprises a plurality of first waiting-to-shift service, namely, the waiting-to-shift service sequence comprises a plurality of waiting-to-shift service.

Step 205, for any class, determining a second to-be-scheduled customer service meeting any class from unlabeled first to-be-scheduled customer service in a to-be-scheduled customer service sequence according to a set scheduling rule, and adding the second to-be-scheduled customer service to a scheduling result corresponding to any class until the number of the to-be-scheduled customer service of any class is the same as the number of the to-be-scheduled customer service of any class.

That is, in order to improve the rationality of the scheduling, the to-be-scheduled service is sequentially taken out from the to-be-scheduled service sequence according to the set scheduling rule, any class is scheduled, and the service on which the scheduling has been performed is marked until the number of the services of any class is the same as the number of the to-be-scheduled services of any class.

And 206, marking the second waiting shift customer service in the waiting shift customer service sequence in the process of adding the second waiting shift customer service to the shift result corresponding to any shift type.

In order to improve the accuracy of the shift results while avoiding repeated shifts of the same customer service person, as an example, in the process of adding the second to-be-shifted customer service to the shift results corresponding to any shift type, the second to-be-shifted customer service in the to-be-shifted customer service sequence is marked.

For example, as shown in fig. 3, according to the number of to-be-scheduled service for a plurality of class types, the specific steps of performing the service scheduling for the plurality of class types may be as follows:

1. taking out the first class type (such as early class) of the class table to obtain the number of people needing to be scheduled for service;

2. taking out a customer service (to-be-scheduled customer service) and attribute information (such as whether the customer service is in lactation period) associated with the scheduling from a customer service information list (to-be-scheduled customer service sequence);

3. judging whether customer service to be scheduled exists or not;

4. and if no customer service to be scheduled exists, the process is finished, and the process is finished. At the moment, the other classes are not arranged with proper customer service, customer service can be extracted uniformly from the class list of the arranged classes and distributed uniformly to the class classes of each non-arranged person, wherein when the person is extracted, the person conforming to the class is selected by setting the arrangement rule, the person is arranged into the corresponding class, and the average square error between the number of the arranged class service of each class and the number of the to-be-arranged class service is minimized after the person is arranged;

5. Taking customer service, taking attribute information and current class type of the customer service as parameters at the moment, calling a rule engine, and operating the rule engine according to a configured rule base and formulated rule logic to obtain a result;

6. judging whether the customer service meets the current class type according to the rule operation result;

7. if the rule judges that the customer service does not meet the current class type, taking the next customer service, and restarting from the step 2;

8. if the rules determine that the customer service currently must be scheduled (e.g., the scheduling rules require that the customer service not have a rest for more than three days, and when more than three days are to be scheduled, the customer service is scheduled into the class type and identifies that the customer service has been scheduled;

9. if the rule determines that the customer service currently has to rest, the customer service is ranked into the class type and the customer service is identified to have already rest;

10. if the customer service can be assigned to the class (e.g., the scheduling rules require the customer service to rest for no more than three days, the customer service can (optionally) be scheduled for the next day of rest);

11. the customer service is scheduled for the shift and marks that the customer service has been scheduled;

12. judging whether the shifts are all covered with customer service, if not, going to step 2, and taking out the next customer service;

13. If the customer service is fully distributed, judging whether the last class type of the class list is the same;

14. if not, the next class type of the class table is taken, and the step 2 is carried out;

15. if so, the process is ended, and at the moment, various classes in the class list are exhausted, but the customer service is more, and the redundant customer service is orderly exhausted into the class with the lowest service level.

In summary, a set scheduling rule and a waiting scheduling service sequence containing a plurality of first waiting scheduling service are obtained; for any class, according to a set scheduling rule, determining second to-be-scheduled customer service meeting any class from first to-be-scheduled customer service without marks in a to-be-scheduled customer service sequence, and adding the second to-be-scheduled customer service into a scheduling result corresponding to any class until the number of the to-be-scheduled customer service of any class is the same as that of the to-be-scheduled customer service of any class; in the process of adding the second to-be-scheduled customer service to the scheduling result corresponding to any one class type, the second to-be-scheduled customer service in the to-be-scheduled customer service sequence is marked, so that the accuracy and rationality of the scheduling result can be improved by performing the to-be-scheduled scheduling on the plurality of class types based on the set scheduling rules and the number of to-be-scheduled customer service of the plurality of class types.

To clearly illustrate how the predicted incoming power of the plurality of first sub-periods is predicted from the first historical incoming power of the plurality of first historical sub-periods that is contemporaneous with the plurality of first sub-periods within the second set period in the above embodiment, another customer service scheduling method is proposed by the present disclosure.

Fig. 4 is a flow chart of a customer service scheduling method according to a third embodiment of the present disclosure.

As shown in fig. 4, the customer service scheduling method may include the following steps:

step 401, a plurality of class types of the first set period are acquired.

Step 402, for any first sub-period, obtaining a first historical power consumption of a plurality of first historical sub-periods synchronous with the first sub-period.

As an example, when the date to which the first sub-period belongs is a specified date, if the date to which the first sub-period belongs is 6.18, a plurality of history dates (e.g., a plurality of histories 6.18) that are contemporaneous with the specified date are acquired, or if the date to which the first sub-period belongs is the beginning of the year, a plurality of history dates (e.g., a plurality of history beginning of the year) contemporaneous with the specified date are acquired, and further, the first history electricity consumption amount of the first history sub-period of the plurality of history dates that matches each first sub-period may be acquired.

As another example, when the date to which the first sub-period belongs is a non-specified date, it may be determined that the date to which the first sub-period belongs is a day of the week, for example, the date to which the first sub-period belongs is a day of the week, and the first historical electricity consumption amount of the first historical sub-period matching each of the first sub-periods in the plurality of historical days of the week may be acquired.

Step 403, determining a target prediction algorithm from a plurality of set candidate prediction algorithms according to the plurality of first historical sub-moments.

As one example, a second history sub-period is determined from a plurality of first history sub-periods; according to the first historical electricity consumption of a third sub-period except for the second historical sub-period in the first historical sub-moments, respectively adopting a plurality of set candidate prediction algorithms to predict the predicted electricity consumption of the second historical sub-period; aiming at any set candidate pre-algorithm, determining a prediction mean square error corresponding to any set candidate prediction algorithm according to the prediction power consumption corresponding to any set candidate prediction algorithm and the first historical power consumption of the second historical subperiod; and determining a target prediction algorithm from the plurality of set candidate prediction algorithms according to the prediction mean square error corresponding to any set candidate prediction algorithm.

That is, in order to improve the prediction accuracy of the predicted power consumption of any one of the first sub-periods, in the embodiment of the present disclosure, the second history sub-period may be a last time history sub-period of the plurality of first history sub-periods, further, according to the first history power consumption of a third sub-period other than the second history sub-period of the plurality of first history sub-periods, a plurality of set candidate prediction algorithms may be adopted to predict and obtain the predicted power consumption of the plurality of second history sub-periods, and further, according to the predicted power consumption corresponding to any set candidate prediction algorithm and the first history power consumption of the second history sub-period, a prediction mean square error corresponding to any set candidate prediction algorithm may be determined, and a prediction algorithm with the minimum prediction mean square error may be selected from the plurality of set candidate prediction algorithms as the target prediction algorithm.

It should be noted that the plurality of setting candidate prediction algorithms may include, but are not limited to: data regression algorithm, time series prediction algorithm, time series smooth prediction algorithm and stationary process prediction algorithm.

Step 404, based on the target prediction algorithm, predicting the predicted incoming power of any first sub-period according to the plurality of first historical incoming power.

Further, a target prediction algorithm is adopted, and the predicted incoming electricity quantity of any first sub-period is predicted according to a plurality of first historical incoming electricity quantities.

Step 405, determining the number of to-be-scheduled class services of a plurality of class types in the second set period according to the predicted incoming power corresponding to the plurality of first sub-periods and the first set service level, and according to the first average call duration corresponding to the plurality of first historical sub-periods.

And 406, performing customer service scheduling on the plurality of class types according to the number of the to-be-scheduled customer service of the plurality of class types to obtain scheduling results of the plurality of class types.

In summary, a first historical electricity consumption of a plurality of first historical subintervals contemporaneous with the first subinterval is obtained for any first subinterval; determining a target prediction algorithm from a plurality of set candidate prediction algorithms according to the plurality of first historical sub-moments; the prediction power supply quantity of any first sub-period is predicted according to the plurality of first historical power supply quantities based on the target prediction algorithm, so that the target prediction algorithm is determined from the plurality of set candidate prediction algorithms, the prediction power supply quantity of any first sub-period is predicted based on the target prediction algorithm, and the prediction accuracy of the prediction power supply quantity is improved.

In order to clearly illustrate how to determine the number of to-be-scheduled shifts of the plurality of shift types in the second set period according to the predicted incoming power and the first set service level corresponding to the plurality of first sub-periods and according to the first average call duration corresponding to the plurality of first historical sub-periods in the above embodiment, another shift scheduling method is proposed in the present disclosure.

Fig. 5 is a flow chart of a customer service scheduling method according to a fourth embodiment of the present disclosure.

As shown in fig. 5, the customer service scheduling method may include the following steps:

step 501, a plurality of class types of a first set period are acquired.

Step 502, for any one of a plurality of first sub-periods in the second set period, predicting a predicted power consumption of any one of the first sub-periods according to a first historical power consumption of a plurality of first historical sub-periods contemporaneous with the any one of the first sub-periods.

Wherein the second set period is located within the first set period.

Step 503, predicting a first shift customer service number required by a plurality of shift types in each second sub-period according to the predicted incoming power corresponding to the plurality of first sub-periods, the set first service level, and the first average call duration of the plurality of first history sub-periods.

Wherein the duration of the second sub-period is greater than the duration of the first sub-period.

As an example, for any first sub-period, determining an expected customer service amount for any first sub-period according to a predicted incoming electricity amount for any first sub-period, a first average call duration for a first historical sub-period contemporaneous with any first sub-period, and a duration for any first sub-period; according to the set initial customer service quantity and the expected customer service quantity of any first sub-period, determining the incoming call average waiting probability of any first sub-period; determining a predicted incoming call service level of any first subinterval according to the incoming call average waiting probability, the expected customer service quantity and the set initial customer service quantity corresponding to any first subinterval; according to the difference between the predicted incoming call service level and the set first service level corresponding to any first subinterval, performing at least one iteration on the set initial customer service number of any first subinterval to obtain the target customer service number required by any first subinterval; and determining the first scheduling customer service quantity required by a plurality of class types in each second subinterval according to the target customer service quantity required by any first subinterval.

For example, W (t) =prob (waitingtime <＝t)＝1-Ec(m,u)e ^{(-(m-u)*t/Ts)} ； (1)

Wherein W (T) represents a predicted incoming call service level, T represents a set unit of a first set service level, for example, the first set service level is set to be an on-coming rate of 20 seconds, T represents a first sub-period (statistical period), for example, 15 minutes, u=an incoming call amount of the statistical period (Ts) is equal to an average call duration of the first history sub-period/a duration of the first sub-period, m represents a target customer service amount required for any one of the first sub-periods, p=u/m, sum (u≡k/k|) =u+u+2/2+u+3/3 +! + … +U (m-1)/(m-1) -! The method comprises the steps of carrying out a first treatment on the surface of the

It should be noted that, based on the above formula (1) and formula (2), according to the difference between the predicted incoming call service level and the set first service level corresponding to any first sub-period (for example, the difference is smaller than the set difference threshold), at least one iteration is performed on the set initial customer service number of any first sub-period, so that m is the target customer service number required by any first sub-period.

Further, the first shift service number required by the plurality of shift types in each second sub-period is determined according to the target service number required by any one of the first sub-periods, for example, for any one of the shift types in any one of the second sub-periods, the first shift service number required by any one of the shift types in any one of the second sub-periods is confirmed according to the target customer number required by the plurality of first sub-periods corresponding to any one of the shift types.

For example, the number of second shift objects required for 8:00 to 8:15 is 1, the number of second shift objects required for 8:15 to 8:30 is 2, the number of second shift objects for 8:30 to 8:45 is 8, the number of second shift objects for 8:45 to 9:00 is 10, the number of second shift objects for 9:00 to 9:15 is 8, the number of second shift objects for 9:15 to 9:30 is 7, the number of second shift objects for 9:30 to 9:45 is 6, the number of second shift objects for 9:45 to 10:00 is 3, the number of second shift objects for 10:00 to 10:15 is 0, the number of second shift objects for 10:10 to 10:15 is 1, and then the number of first shift clients required for the early shift (shift up time is 8:30 to 10:00) can be 7 (i.e., (8+10+8+7+6)/6).

It should be noted that, in order to further determine the rationality of the first shift service number required by each class in the second sub-period, the first shift service number required by each class may be verified by using the actual shift service number of the second historical sub-period in the same period corresponding to each class, so as to determine whether the first shift service number required by each class is rational, and when the first shift service number required by each class cannot meet the actual service requirement, the first shift service number required by each class may be adjusted. In the case that the first shift service amount required by any one shift type is unreasonable, the first shift service amount required by any one shift type needs to be adjusted multiple times to be reasonable.

For example, an unreasonable first shift number of shifts may be iteratively optimized based on an annealing algorithm, where the target (energy) function may be a normalized variance of the first shift number of shifts required for any shift type and the actual shift number of shifts for a corresponding second historical sub-period, and the target (energy) function E (j) may be expressed as E (j) =sum ((|predict FTE-shift fte|/predict FTE) × (|predict FTE-shift fte|/predict FTE));

acceptance probability P (t) =exp (- (E (j) -Es)/t (k);

decay function, t (k+1) =t (k) lambda;

wherein, the predicted FTE (Full Time Equivalent, full-time man-hour) may represent a first shift service number required by any shift type, the shift FTE may be an actual shift service number of a corresponding second history sub-period, an initial value of Es is E (0), E (0) is a variance of normalized processing of the first shift service number required by any shift type of the first iteration and the actual shift service number of the corresponding second history sub-period, in a subsequent iteration process, if E (j) > = Es, es remain unchanged, otherwise, es = E (j), lanbda is an attenuation coefficient, may be set to 0.85, k is a cycle of an outer ring, t (k) represents a temperature of the current cycle, an annealing start temperature may be set to 200 degrees, and the termination criterion may be one of the following: the termination temperature threshold Te <1, the number of internal cycles is 200, and the searched optimal value is kept unchanged for a plurality of continuous steps.

Step 504, determining the number of to-be-scheduled service of the plurality of shift types in the second set period according to the number of first to-be-scheduled service required by the plurality of shift types in each second sub-period.

In an embodiment of the present disclosure, the second set period may include a plurality of second sub-periods, and in a case where the number of the plurality of classes of to-be-scheduled service for each second sub-period is determined, the number of the plurality of classes of to-be-scheduled service for the second set period may be determined. For example, the duration of the second set period may be one week, the second sub-period may be each day in the duration, and when the number of the plurality of class-type waiting for scheduling service in each day is determined, the number of the plurality of class-type waiting for scheduling service in the duration may be determined.

And 505, performing customer service scheduling on the plurality of class types according to the number of the to-be-scheduled customer service of the plurality of class types so as to obtain scheduling results of the plurality of class types.

In summary, the first scheduling customer service quantity required by the plurality of class types in each second sub-period is predicted by setting a first service level and a first average call duration of the plurality of first history sub-periods according to the predicted incoming power corresponding to the plurality of first sub-periods; according to the first scheduling customer service quantity required by the plurality of classes in each second subinterval, the to-be-scheduled customer service quantity of the plurality of classes in the second setting interval is determined, so that the first scheduling customer service quantity required by the plurality of classes in each second subinterval is jointly predicted according to the predicted incoming electricity quantity corresponding to the plurality of first subintervals, the set first service level and the first average call duration of the plurality of first historical subintervals, the accuracy of the customer service quantity required by the plurality of classes in each second subinterval is improved, and the to-be-scheduled customer service quantity of the plurality of classes in the second setting interval can be accurately determined according to the first customer service quantity required by the plurality of classes in each second subinterval.

In order to clearly explain how the plurality of class types of the first set period are acquired in the above-described embodiment, the present disclosure proposes another customer service scheduling method.

Fig. 6 is a flow chart of a customer service scheduling method according to a fifth embodiment of the present disclosure.

As shown in fig. 6, the customer service scheduling method may include the steps of:

step 601, for any third sub-period, obtaining a second historical power consumption, a second average call duration and a second service level of a plurality of second historical sub-periods contemporaneous with any third sub-period.

Wherein, the duration of the third sub-period is the same as the duration of the first sub-period.

In the embodiment of the disclosure, the first set period may include a plurality of third subperiods, where the duration of the third subperiod may be, for example, 15 minutes, for example, any third subperiod may be 2023, 5, 1, 12:00 to 12:15, and the second historical subperiod contemporaneous with any third subperiod may be 2023, 4, 1, 12: 00-12:15, 2023, 3, 1, 12:00-12:15, the second average pass duration may be determined according to a ratio of a total duration of calls to a total number of calls corresponding to the second historical subinterval, and the second set service level may be a desired service level (i.e., number of calls processed/total number of calls processed) corresponding to the third subinterval.

Step 602, predicting a second shift customer service amount required by any third sub-period according to a plurality of second historical incoming electricity amounts, a plurality of average call durations and a second set service level corresponding to any third sub-period.

Further, according to the plurality of second historical incoming charges, the plurality of average call durations and the second set service level corresponding to any third sub-period, the second shift customer service amount required for any third sub-period is predicted, which can be referred to in step 503, and will not be described in detail in the present disclosure.

Step 603, determining a plurality of class types of the first set period according to the second scheduling customer service number required by any third sub-period.

Further, according to the second shift service number required for any third sub-period, different on-duty periods may be determined, for example, the second shift service number required for 8:00 to 8:15 is 1, the second shift service number required for 8:15 to 8:30 is 2, the second shift service number required for 8:30 to 8:45 is 8, the second shift service number for 8:45 to 9:00 is 10, the second shift service number for 9:00 to 9:15 is 8, the second shift service number for 9:15 to 9:30 is 7, the second shift service number for 9:30 to 9:45 is 6, the second shift service number for 9:45 to 10:00 is 3, the second shift service number for 10:00 to 10:15 is 0, the second shift service number for 10:10 to 10:15 is 1, and then it may be determined that 8:30 to 10 is of the same type as early shift, late shift service, and the like.

In order to further determine the rationality of each class, the number of actual class objects of a plurality of history subintervals in the same period as the third subinterval corresponding to any class may be used to verify the on-duty intervals corresponding to each class so as to determine whether each class is reasonable, and when the on-duty intervals corresponding to each class cannot meet the actual incoming call demand, the on-duty intervals of each class may be adjusted. In the case where any one class type is unreasonable, it is necessary to adjust the number of times so that the any one class type is reasonable.

Step 604, for any one of the plurality of first sub-periods within the second set period, predicting a predicted power consumption of the any one of the plurality of first sub-periods according to a first historical power consumption of the plurality of first historical sub-periods contemporaneous with the any one of the first sub-periods.

Wherein the second set period is located within the first set period.

Step 605, determining the number of to-be-scheduled class services of a plurality of class types in the second set period according to the predicted incoming power corresponding to the plurality of first sub-periods and the first set service level, and according to the first average call duration corresponding to the plurality of first historical sub-periods.

And step 606, performing customer service scheduling on the plurality of class types according to the number of the to-be-scheduled customer service of the plurality of class types so as to obtain scheduling results of the plurality of class types.

In summary, by aiming at any third sub-period, obtaining a second historical electricity consumption, a second average call duration and a second service level of a plurality of second historical sub-periods which are synchronous with any third sub-period; predicting a second scheduling customer service amount required by any third subinterval according to a plurality of second historical electricity consumption amounts, a plurality of average call durations and a second set service level corresponding to any third subinterval; according to the number of second shift service required by any third subperiod, a plurality of shift types of the first set period are determined, so that the plurality of shift types of the first set period can be accurately determined based on actual service requirements, effective planning of the plurality of shift types of the first set period is realized, further, the plurality of shift types are subjected to service shift, shift results can meet actual service requirements, and shift efficiency can be improved.

In the embodiment of the disclosure, after the multiple shift scheduling results are obtained, service processing may be performed based on the multiple shift scheduling results, for example, an incoming call request sent by an active caller at a target time is received; determining a target class type to which the target moment belongs, and determining a class result matched with the target class type from among class results of a plurality of class types in a second set period, wherein the class result comprises at least one candidate customer service under the corresponding class type; determining a target customer service from the at least one candidate customer service; and forwarding the incoming call request to the target customer service so that the target customer service processes the incoming call request.

As one example, for any one of the at least one candidate customer service, determining an average reply duration for each historical incoming call request that any candidate object replies to within a set duration; determining the number of the pending incoming call requests which are allocated and unprocessed by any candidate object, and determining the waiting processing time length of each pending incoming call request according to the number of the pending incoming call requests; determining the adaptive score of any candidate object and the target class type according to the waiting processing time and the average reply time; and determining target customer service from at least one candidate customer service according to the adaptation score of any candidate object.

In the embodiment of the disclosure, the adaptation score is used for representing the processing efficiency of any candidate customer service on the historical incoming call request belonging to the target class type, and the adaptation score and the average reply time length are in a negative correlation relationship, namely the longer the average reply time length is, the lower the adaptation score is, otherwise, the shorter the average reply time length is, and the higher the adaptation score is; the adaptation score and the waiting duration are in a negative correlation relationship, namely, the longer the waiting duration is, the lower the adaptation score is, and conversely, the shorter the waiting duration is, the higher the adaptation score is.

In the embodiment of the disclosure, according to the fit score of any candidate customer service, at least one candidate customer service under the target class type may be ordered to obtain an arrangement sequence of at least one candidate customer service, and according to the arrangement sequence of at least one candidate customer service, determining a target customer service from at least one candidate customer service, for example, randomly selecting one candidate customer service from the candidate customer service with a set number (e.g., the first 3) arranged in front as a target object; for another example, the candidate customer service arranged in the first place is taken as the target customer service.

On the basis of any embodiment of the disclosure, as shown in fig. 7, the customer service scheduling method of the embodiment of the disclosure may be further implemented based on the following steps:

(1) The requirements of historical electricity usage, average service time and service level are written out by the class list planning rules. The contents of the class table include: a class type, wherein each class type has a corresponding on-duty time, a meal rest start time, a meal rest end time, an off-duty time, a second meal rest time, etc.;

(2) After the plan is formed into a class table, a decision-making department of a client manually decides the plan of class type in the specific class table according to staff interests, laws and regulations related to labor, traffic environment, enterprise system, regional characteristics and the like;

(3) Predicting incoming call quantity data (predicted incoming call quantity) in the shift cycle by using a historical incoming call quantity through an incoming call quantity prediction algorithm; it should be noted that, since incoming call history data on a specific day is less, the present disclosure allows the final prediction data to be determined by a customer expert decision to avoid some burrs or singularities;

(4) Estimating the required customer service quantity (FTE), namely the quantity of customer service to be scheduled, by using the predicted data, the average service duration (first average call duration) and the service level requirement (first set service level);

(5) The estimated FTEs and the shift table with definite model stages are used for acquiring the due customer service number of each shift type through a shift table customer service number scheduling algorithm;

(6) After the customer service quantity of each class table is obtained, scheduling types of each customer service are scheduled by combining with the on-duty limit (setting scheduling rules) of each customer service, and the scheduling process is completed;

the setting scheduling rules of customer service mainly consider that: employee rights, labor-related laws and regulations, traffic environment, enterprise system, regional characteristics, and the like.

Corresponding to the customer service scheduling method provided by the embodiments of fig. 1 to 7, the present disclosure also provides a customer service scheduling device, and since the customer service scheduling device provided by the embodiments of the present disclosure corresponds to the customer service scheduling method provided by the embodiments of fig. 1 to 7, the implementation of the customer service scheduling method is also applicable to the customer service scheduling device provided by the embodiments of the present disclosure, which is not described in detail in the embodiments of the present disclosure.

Fig. 8 is a schematic structural view of a customer service shift arrangement device according to a sixth embodiment of the present disclosure.

As shown in fig. 8, the customer service scheduling apparatus 800 includes: the acquisition module 810, the prediction module 820, the determination module 830, and the scheduling module 840.

Wherein, the acquiring module 810 is configured to acquire a plurality of class types of the first set period; a prediction module 820, configured to predict, for any one of a plurality of first sub-periods within a second set period, a predicted power consumption of the any one of the first sub-periods according to a first historical power consumption of the plurality of first historical sub-periods that is contemporaneous with the any one of the first sub-periods, where the second set period is located within the first set period; a determining module 830, configured to determine, according to the predicted incoming power and the first set service level corresponding to the plurality of first sub-periods, and according to the first average call duration corresponding to the plurality of first historical sub-periods, a plurality of to-be-scheduled service amounts of the class type in the second set period; the scheduling module 840 is configured to perform a service scheduling on the plurality of class types according to the number of to-be-scheduled services of the plurality of class types, so as to obtain scheduling results of the plurality of class types.

As one possible implementation of the embodiments of the present disclosure, the shift module 840 is specifically configured to: acquiring a set scheduling rule and a to-be-scheduled customer service sequence comprising a plurality of first to-be-scheduled customer services; for any class, according to a set scheduling rule, determining second to-be-scheduled customer service meeting any class from first to-be-scheduled customer service without marks in a to-be-scheduled customer service sequence, and adding the second to-be-scheduled customer service into a scheduling result corresponding to any class until the number of the to-be-scheduled customer service of any class is the same as that of the to-be-scheduled customer service of any class; and in the process of adding the second to-be-scheduled customer service to the scheduling result corresponding to any class type, marking the second to-be-scheduled customer service in the to-be-scheduled customer service sequence.

As one possible implementation of the embodiments of the present disclosure, the prediction module 820 is specifically configured to: for any first sub-period, acquiring first historical electricity consumption of a plurality of first historical sub-periods which are synchronous with the first sub-period; determining a target prediction algorithm from a plurality of set candidate prediction algorithms according to the plurality of first history subintervals; based on a target prediction algorithm, predicting the predicted incoming power of any first sub-period according to the plurality of first historical incoming power.

As one possible implementation of an embodiment of the present disclosure, the prediction module 820 is further configured to: determining a second history sub-period from a plurality of the first history sub-periods; according to the first historical electricity consumption of a third sub-moment except for the second historical sub-period in the first historical sub-period, respectively adopting a plurality of setting candidate prediction algorithms to predict the predicted electricity consumption of the second historical sub-period; aiming at any set candidate pre-algorithm, determining a prediction mean square error corresponding to any set candidate pre-algorithm according to the prediction power consumption corresponding to any set candidate pre-algorithm and the first historical power consumption of the second historical subperiod; and determining a target prediction algorithm from the plurality of set candidate prediction algorithms according to the prediction mean square error corresponding to any set candidate prediction algorithm.

As a possible implementation manner of the embodiment of the present disclosure, the second set period includes a plurality of second sub-periods, and the determining module 830 is specifically configured to: predicting a first scheduling customer service quantity required by a plurality of class types in each second subperiod according to the predicted incoming electricity quantity corresponding to the plurality of first subperiods, a first service level and a first average call duration of the plurality of first historical subperiods; wherein the duration of the second sub-period is greater than the duration of the first sub-period; and determining the number of the to-be-scheduled service of the plurality of the class types in the second set period according to the number of the first scheduling service required by the plurality of the class types in each second subperiod.

As one possible implementation of an embodiment of the disclosure, the determining module 830 is further configured to: for any first sub-period, determining the expected customer service quantity of any first sub-period according to the predicted incoming electricity quantity of any first sub-period, the first average call duration of the first historical sub-period synchronous with any first sub-period and the duration of any first sub-period; according to the set initial customer service quantity and the expected customer service quantity of any first sub-period, determining the incoming call average waiting probability of any first sub-period; determining a predicted incoming call service level of any first subinterval according to the incoming call average waiting probability, the expected customer service quantity and the set initial customer service quantity corresponding to any first subinterval; according to the difference between the predicted incoming call service level and the set first service level corresponding to any first subinterval, performing at least one iteration on the set initial customer service number of any first subinterval to obtain the target customer service number required by any first subinterval; and determining the first scheduling customer service quantity required by a plurality of class types in each second subinterval according to the target customer service quantity required by any first subinterval.

As one possible implementation of an embodiment of the disclosure, the determining module 830 is further configured to: acquiring a plurality of class types in any second subinterval; and for any class type in any second subinterval, confirming the first scheduling customer service quantity required by any class type in any second subinterval according to the target customer quantity required by a plurality of first subintervals corresponding to any class type.

As a possible implementation manner of the embodiment of the present disclosure, the first set period includes a plurality of third sub-periods, and the obtaining module 810 is specifically configured to: for any third sub-period, acquiring second historical electricity consumption, second average call duration and second set service level of a plurality of second historical sub-periods which are synchronous with any third sub-period, wherein the duration of the third sub-period is the same as the duration of the first sub-period; predicting a second scheduling customer service amount required by any third subinterval according to a plurality of second historical electricity consumption amounts, a plurality of average call durations and a second set service level corresponding to any third subinterval; and determining a plurality of class types of the first set period according to the second scheduling customer service quantity required by any third subperiod.

As one possible implementation manner of the embodiment of the present disclosure, the incoming call processing apparatus 800 further includes: a receiving module and a switching module.

Wherein, receiving module is used for: receiving an incoming call request sent by an active calling party at a target moment; the determining module 830 is further configured to: determining a target class type to which the target moment belongs, and determining a class result matched with the target class type from among class results of a plurality of class types in a second set period, wherein the class result comprises at least one candidate customer service under the corresponding class type; determining a target customer service from the at least one candidate customer service; the switching module is used for: and forwarding the incoming call request to the target customer service so that the target customer service processes the incoming call request.

The customer service scheduling device of the embodiment of the disclosure obtains a plurality of class types of a first set period; predicting, for any one of a plurality of first sub-periods within a second set period, a predicted power consumption of the any one of the first sub-periods according to a first historical power consumption of a plurality of first historical sub-periods contemporaneous with the any one of the first sub-periods; according to the predicted incoming electricity quantity corresponding to the first sub-periods and the first set service level, and according to the first average call duration corresponding to the first historical sub-periods, determining the number of the to-be-scheduled customer service of the class types in the second set period; according to the number of the to-be-scheduled service of the plurality of classes, the plurality of classes are scheduled to obtain the scheduling results of the plurality of classes, so that the number of the to-be-scheduled service of the plurality of classes in the second set period is commonly determined according to the predicted incoming electricity quantity corresponding to the plurality of first sub-periods and the first set service level and according to the first average call duration corresponding to the plurality of first history sub-periods, and the accuracy of the number of the to-be-scheduled service of the plurality of classes in the second set period is improved; furthermore, according to the number of customer service to be scheduled of the plurality of class types, the customer service scheduling is automatically performed on the plurality of class types to obtain scheduling results of the plurality of class types, and automatic customer service scheduling based on actual service requirements is achieved, so that the scheduling results can meet the actual service requirements, meanwhile, the manual mode is not needed for customer service scheduling, and the scheduling efficiency is improved.

In an exemplary embodiment, an electronic device is also presented.

Wherein, electronic equipment includes:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to execute the instructions to generate a customer service scheduling method as set forth in any of the foregoing embodiments.

As an example, fig. 9 is a schematic structural diagram of an electronic device 900 according to an exemplary embodiment of the disclosure, where, as shown in fig. 9, the electronic device 900 may further include:

memory 910 and processor 920, bus 930 connecting the different components (including memory 910 and processor 920), memory 910 storing a computer program that when executed by processor 920 generates a customer service scheduling method according to an embodiment of the present disclosure.

Bus 930 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 900 typically includes a variety of electronic device readable media. Such media can be any available media that is accessible by electronic device 900 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 910 may also include computer-system readable media in the form of volatile memory such as Random Access Memory (RAM) 940 and/or cache memory 950. The server 900 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 960 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 9, commonly referred to as a "hard disk drive"). Although not shown in fig. 9, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 930 via one or more data medium interfaces. Memory 910 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the various embodiments of the disclosure.

A program/utility 980 having a set (at least one) of program modules 970 may be stored, for example, in memory 910, such program modules 970 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include the generation of a network environment. Program modules 970 generally perform the functions and/or methods in the embodiments described in this disclosure.

The electronic device 900 may also communicate with one or more external devices 990 (e.g., keyboard, pointing device, display 991, etc.), one or more devices that enable a user to interact with the electronic device 900, and/or any devices (e.g., network card, modem, etc.) that enable the electronic device 900 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 992. Also, the electronic device 900 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through a network adapter 993. As shown, the network adapter 993 communicates with other modules of the electronic device 900 over the bus 930. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 900, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

The processor 920 performs various functional applications and data processing by running programs stored in the memory 910.

It should be noted that, the implementation process and the technical principle of the electronic device in this embodiment refer to the foregoing explanation of the customer service scheduling method in the embodiment of the disclosure, and are not repeated herein.

In an exemplary embodiment, a computer readable storage medium is also provided, such as a memory, comprising instructions executable by a processor of an electronic device to perform the customer service scheduling method set forth in any of the embodiments above. Alternatively, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program product is also provided, comprising a computer program/instruction, characterized in that the computer program/instruction, when executed by a processor, generates the customer service scheduling method proposed by any of the above embodiments.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A customer service scheduling method, comprising:

acquiring a plurality of class types of a first set period;

predicting a predicted power consumption of any one of a plurality of first sub-periods within a second set period according to a first historical power consumption of a plurality of first historical sub-periods contemporaneous with the any one first sub-period, wherein the second set period is within the first set period;

determining the quantity of the to-be-scheduled class customer service of a plurality of class types in a second set period according to the predicted incoming electricity quantity corresponding to the plurality of first sub-periods and a first set service level and according to a first average call duration corresponding to the plurality of first historical sub-periods;

and performing customer service scheduling on the plurality of class types according to the number of the to-be-scheduled customer service of the plurality of class types so as to obtain scheduling results of the plurality of class types.

2. The method of claim 1, wherein said performing a service shift on the plurality of said class types according to the number of service shifts to be performed on the plurality of said class types to obtain a plurality of shift results of said class types, comprises:

acquiring a set scheduling rule and a to-be-scheduled customer service sequence comprising a plurality of first to-be-scheduled customer services;

for any class, according to the set scheduling rule, determining a second to-be-scheduled customer service meeting any class from unlabeled first to-be-scheduled customer service in the to-be-scheduled customer service sequence, and adding the second to-be-scheduled customer service to a scheduling result corresponding to any class until the number of the to-be-scheduled customer service of any class is the same as the number of the to-be-scheduled customer service of any class;

and marking the second to-be-scheduled customer service in the to-be-scheduled customer service sequence in the process of adding the second to-be-scheduled customer service to the scheduling result corresponding to any one of the class types.

3. The method of claim 1, wherein the predicting, for any one of the plurality of first sub-periods within the second set period, the predicted power consumption of the any one of the plurality of first sub-periods based on the first historical power consumption of the plurality of first historical sub-periods that are contemporaneous with the any one of the first sub-periods, comprises:

For any one of the first sub-periods, acquiring first historical electricity consumption of a plurality of first historical sub-periods which are synchronous with the first sub-period;

determining a target prediction algorithm from a plurality of set candidate prediction algorithms according to the plurality of first history subintervals;

and predicting the predicted incoming electricity quantity of any one of the first sub-periods according to a plurality of the first historical incoming electricity quantities based on a target prediction algorithm.

4. A method according to claim 3, wherein said determining a target prediction algorithm from a plurality of set candidate prediction algorithms based on a plurality of first historical subintervals comprises:

determining a second history sub-period from a plurality of the first history sub-periods;

according to the first historical electricity consumption of a third sub-period except the second historical sub-period in the first historical sub-period, respectively adopting a plurality of setting candidate prediction algorithms to predict the predicted electricity consumption of the second historical sub-period;

aiming at any set candidate pre-algorithm, determining a prediction mean square error corresponding to any set candidate prediction algorithm according to the prediction power consumption corresponding to any set candidate prediction algorithm and the first historical power consumption of the second historical subperiod;

And determining a target prediction algorithm from a plurality of set candidate prediction algorithms according to the prediction mean square error corresponding to any set candidate prediction algorithm.

5. The method of claim 1, wherein the second set period of time includes a plurality of second sub-periods of time, wherein the determining the number of to-be-scheduled class services for the second set period of time based on the predicted incoming power and the first set service level for the plurality of first sub-periods of time and based on the first average call duration for the plurality of first historical sub-periods of time includes:

predicting a first scheduling customer service quantity required by a plurality of class types in each second subperiod according to the predicted incoming electricity quantity corresponding to the plurality of first subperiods, a first service level and a first average call duration of the plurality of first historical subperiods; wherein the duration of the second sub-period is greater than the duration of the first sub-period;

and determining the number of the to-be-scheduled shift service of the plurality of shift types in the second set period according to the number of the first to-be-scheduled shift service required by the plurality of shift types in each second subperiod.

6. The method of claim 5, wherein predicting the number of first shift service required for the plurality of shift types in each of the second sub-periods based on the predicted incoming power and the set first service level for the plurality of first sub-periods and the first average call duration for the plurality of first historical sub-periods comprises:

For any first sub-period, determining the expected customer service quantity of any first sub-period according to the predicted incoming electricity quantity of any first sub-period, the first average call duration of the first historical sub-period synchronous with any first sub-period and the duration of any first sub-period;

determining the incoming call average waiting probability of any first sub-period according to the set initial customer service number and the expected customer service number of any first sub-period;

determining a predicted incoming call service level of any first sub-period according to the incoming call average waiting probability corresponding to any first sub-period, the expected customer service number and the set initial customer service number;

according to the difference between the predicted incoming call service level and the set first service level corresponding to any one of the first subintervals, performing at least one iteration on the set initial customer service number of any one of the first subintervals to obtain a target customer service number required by any one of the first subintervals;

and determining the first scheduling customer service quantity required by a plurality of class types in each second subinterval according to the target customer service quantity required by any first subinterval.

7. The method of claim 6, wherein determining the first number of shift service required for the plurality of shift types for each of the second sub-periods based on the target number of customers for any of the first sub-periods comprises:

acquiring a plurality of class types in any second subinterval;

and for any class type in any second subinterval, confirming the first scheduling customer service quantity required by any class type in any second subinterval according to the target customer service quantity required by a plurality of first subintervals corresponding to any class type.

8. The method of claim 1, wherein the first set period comprises a plurality of third sub-periods, and the obtaining the plurality of class types for the first set period comprises:

for any one of the third sub-periods, acquiring a second historical electricity consumption and a second average call duration of a plurality of second historical sub-periods which are synchronous with any one of the third sub-periods, and a second set service level of any one of the third sub-periods, wherein the duration of the third sub-period is the same as the duration of the first sub-period;

Predicting a second scheduling customer service amount required by any third sub-period according to a plurality of second historical incoming electricity amounts and a plurality of average call durations corresponding to any third sub-period and a second set service level of any third sub-period;

and determining a plurality of class types of the first set period according to the second scheduling customer service quantity required by any third sub-period.

9. The method according to claim 1, wherein the method further comprises:

receiving an incoming call request sent by an active calling party at a target moment;

determining a target class type to which the target moment belongs, and determining a class result matched with the target class type from class results of a plurality of class types in a second set period, wherein the class result comprises at least one candidate customer service under the corresponding class type;

determining a target customer service from the at least one candidate customer service;

and forwarding the incoming call request to the target customer service so that the target customer service processes the incoming call request.

10. A customer service shift arrangement device, comprising:

an acquisition module for acquiring a plurality of class types of the first set period;

A prediction module, configured to predict, for any one of a plurality of first sub-periods within a second set period, a predicted power consumption of the any one of the first sub-periods according to a first historical power consumption of a plurality of first historical sub-periods that are contemporaneous with the any one of the first sub-periods, where the second set period is located within the first set period;

the determining module is used for determining the quantity of the to-be-scheduled class service of a plurality of class types in a second set period according to the predicted incoming electricity quantity corresponding to the plurality of first sub-periods and a first set service level and according to a first average call duration corresponding to the plurality of first historical sub-periods;

and the shift module is used for carrying out the customer service shift on the plurality of shift types according to the number of the customer service to be shifted of the plurality of shift types so as to obtain shift shifting results of the plurality of shift types.