CN116911530A - Customer service scheduling scheme evaluation method and device, electronic equipment and product - Google Patents
Customer service scheduling scheme evaluation method and device, electronic equipment and product Download PDFInfo
- Publication number
- CN116911530A CN116911530A CN202310762997.3A CN202310762997A CN116911530A CN 116911530 A CN116911530 A CN 116911530A CN 202310762997 A CN202310762997 A CN 202310762997A CN 116911530 A CN116911530 A CN 116911530A
- Authority
- CN
- China
- Prior art keywords
- customer service
- shift
- actual
- time period
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 134
- 230000000694 effects Effects 0.000 claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000004519 manufacturing process Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000009826 distribution Methods 0.000 abstract description 10
- 230000005856 abnormality Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000010801 machine learning Methods 0.000 description 6
- 238000003860 storage Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000001186 cumulative effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013468 resource allocation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013450 outlier detection Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an evaluation method, an evaluation device, electronic equipment and products of a customer service scheduling scheme, and relates to the technical field of computers, wherein the evaluation method comprises the following steps: the method comprises the steps of obtaining a class table of customer service scheduling, and inputting the class table into a fitness model to obtain a first evaluation result; and inputting the class table and customer service attendance data into the time-following model to obtain a second evaluation result. Through the mode, the pre-evaluation of the shift effect of the shift table can be realized through the fitness model, so that the dependence on personal experience of a shift man is eliminated, and the pre-evaluation result of the shift effect is more reasonable; the actual evaluation of the shift effect of the shift table can be realized through the fitness model, and the attendance data is referred to by the actual evaluation result, so that the possibility of inaccurate evaluation result caused by deviation between the human distribution condition of the actual shift service and the shift table is avoided, the actual evaluation result of the shift effect is more objective, and the reasonable distribution of human resources can be realized.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, an electronic device, and a product for evaluating a customer service scheduling scheme.
Background
The customer service system scheduling platform bears the scheduling work of the call center seat, and the generated scheduling table directly influences the seat resource proportion arranged in the traffic peak and trough time periods. In order to ensure the customer service completing rate, in the actual production and operation process, reasonable seat resource planning is required to be performed by combining the manpower condition, the staff service efficiency and the traffic flow rule.
Currently, a shift register can generate a shift table of a customer service shift through a shift platform, and evaluate the shift effect of the shift table according to the shift manpower of each period, the expected receiving flux of each period and the statistical data of the working hours of each type of shift. The scheduling manpower of each period and the expected receiving flux of each period can only show the condition that the business objective in the fixed period is achieved, but cannot show the condition of human resource matching. For example, in the case where the call completing rate is reached, there may be a case where the human resources arranged in a fixed period are higher than actually required. In addition, the existing class table data only show the class service of the staff to be on duty, and the attendance data such as leave, absent and the like of the staff after the class table is arranged are not referred to, so that the human distribution condition of the actual class service and the class table have larger deviation, the situation that the human resources are insufficient during the traffic peak period, the call completing rate cannot be ensured, and the situation that the human resources are wasted during the traffic trough period possibly exists.
The scheduling effect of the shift table is evaluated only by relying on personal experience of a shift man, whether the shift table meets traffic receiving requirements or not, the starting condition of the incoming call quantity is predicted, and the human resource utilization condition of each time interval cannot be accurately evaluated, so that reasonable distribution of human resources cannot be realized.
Disclosure of Invention
The invention provides a customer service scheduling scheme evaluation method, a customer service scheduling scheme evaluation device, electronic equipment and a customer service scheduling scheme product, which are used for solving the defect that the scheduling effect of a scheduling table is evaluated depending on personal experience of a scheduling operator in the prior art, and reasonable allocation of human resources cannot be realized.
The invention provides an evaluation method of a customer service scheduling scheme, which comprises the following steps: acquiring a class table of customer service class arrangement; the class table is input into the fitness model, and a first evaluation result output by the fitness model is obtained; the fitness model is related to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield; the class table and customer service attendance data are input into the time compliance model, and a second evaluation result output by the time compliance model is obtained; the time following model is related to the actual attendance days, the working hours of the scheduling and the actual working hours; the first evaluation result is the pre-evaluation of the scheduling effect of the shift table; the second evaluation result is the actual evaluation of the shift effect of the shift table.
According to the evaluation method of the customer service scheduling scheme provided by the invention, before the table is input into the fitness model, the evaluation method comprises the following steps: determining a first parameter according to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield; determining a second parameter according to the time interval manual request quantity, the time interval arrangement number of people and the time interval yield; respectively determining a first weight corresponding to the first parameter and a second weight corresponding to the second parameter; wherein the sum of the first weight and the second weight is 1; a fitness model is determined based on the product of the first parameter and the first weight, and the product of the second parameter and the second weight.
According to the evaluation method of the customer service scheduling scheme provided by the invention, the expression of the fitness model is as follows:
wherein Rsquared is a first evaluation result, rt is a time period manual request quantity, ccr is a preset call completing rate, nt is a time period arrangement number, ot is a time period yield, abs is an absolute value function, min is a minimum value function, and w 1 Is the first weight, w 2 Is the second weight.
According to the evaluation method of the customer service scheduling scheme provided by the invention, before the schedule and the customer service attendance data are input into the time-following model, the evaluation method comprises the following steps: determining a third parameter according to the actual attendance days and the attendance days; determining a fourth parameter according to the scheduling man-hour and the actual man-hour; respectively determining a third weight corresponding to the third parameter and a fourth weight corresponding to the fourth parameter; wherein the sum of the third weight and the fourth weight is 1; a time-of-compliance model is determined based on the product of the third parameter and the third weight, and the product of the fourth parameter and the fourth weight.
According to the evaluation method of the customer service scheduling scheme provided by the invention, the expression following the time model is:
wherein Rp units are the second evaluation result, sd is the actual attendance days, wd is the attendance days, sh is the scheduling man-hour, wh is the actual man-hour, and w 3 Is the third weight, w 4 And is the fourth weight.
According to the evaluation method of the customer service scheduling scheme provided by the invention, the method for acquiring the table of the customer service scheduling comprises the following steps: determining the telephone traffic of each time period in a future preset time period based on historical production telephone traffic sample data; splitting telephone traffic according to service types to obtain telephone traffic of different service types in each time period; determining the manpower prediction requirement of each time period according to the traffic of different service types of each time period; and determining a class list of customer service classes based on the human power prediction requirement.
According to the evaluation method of the customer service scheduling scheme provided by the invention, after the schedule of the customer service scheduling is determined based on the manpower prediction requirement, the evaluation method comprises the following steps: acquiring attendance data of customer service scheduled in a shift table; obtaining the actual attendance days of each customer service and the actual working hours of each customer service according to the attendance data; the actual attendance days of the shift table and the actual man-hours of the shift table are obtained based on the actual attendance days of each customer service and the actual man-hours of each customer service.
The invention also provides an evaluation device of the customer service scheduling scheme, which comprises the following steps: the system comprises an acquisition table module, a customer service scheduling module and a customer service scheduling module, wherein the acquisition table module is used for acquiring a table of a customer service scheduling; the first evaluation result module is used for inputting the shift table into the fitness model to obtain a first evaluation result output by the fitness model; the fitness model is related to the manual request quantity, the preset call completing rate, the number of people arranged and the yield; the second evaluation result module is used for inputting the executive list and the customer service attendance data into the time-following model to obtain a second evaluation result output by the time-following model; the time following model is related to the actual attendance days, scheduling man-hour and system signing man-hour; the first evaluation result is the pre-evaluation of the scheduling effect of the shift table; the second evaluation result is the actual evaluation of the shift effect of the shift table.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the evaluation method of the customer service scheduling scheme when executing the program.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a method of evaluating a customer service scheduling scheme as described in any one of the above.
According to the evaluation method, the device, the electronic equipment and the product of the customer service scheduling scheme, which are provided by the invention, the table of the customer service scheduling is obtained, the table is input into the fitness model, and a first evaluation result output by the fitness model is obtained; the fitness model is related to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield; the class table and customer service attendance data are input into the time compliance model, and a second evaluation result output by the time compliance model is obtained; the time following model is related to the actual attendance days, the working hours of the scheduling and the actual working hours; the first evaluation result is the pre-evaluation of the scheduling effect of the shift table; the second evaluation result is the actual evaluation of the shift effect of the shift table. Through the mode, the pre-evaluation of the shift effect of the shift table can be realized through the fitness model, the fitness model is related to the time period manual request quantity, the preset completing rate, the time period arrangement number and the time period yield, the dependence on personal experience of a shift man is eliminated, and the pre-evaluation result of the shift effect is more reasonable; the actual evaluation of the shift effect of the shift table can be realized through a fitness model, the time-following model is related to the actual attendance days, the shift man-hour and the actual man-hour, and the actual evaluation result refers to the attendance data, so that the possibility of inaccurate evaluation result caused by deviation between the manpower distribution condition of the actual shift and the shift table is avoided, the actual evaluation result of the shift effect is more objective, and the reasonable distribution of manpower resources can be realized.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for evaluating a customer service scheduling scheme provided by the invention;
FIG. 2 is a second flow chart of the evaluation method of the customer service scheduling scheme provided by the invention;
fig. 3 is a schematic structural diagram of an evaluation device of a customer service scheduling scheme provided by the invention;
fig. 4 is a schematic structural diagram of an embodiment of the electronic device of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flow chart of an evaluation method of a customer service scheduling scheme provided by the present invention, in this embodiment, the evaluation method of the customer service scheduling scheme includes steps S110 to S130, and each step is specifically as follows:
s110: and obtaining a class table of the customer service class.
The shift schedule of the customer service crew is a table or plan for scheduling the working time and rest time of the customer service crew, which determines the working schedule of each customer service crew within a specific date and time period to ensure that there are enough customer service crew to provide service within a required time period.
The class table of the customer service class at least comprises information such as date, employee name or work number, working time period, rest time period, class and the like.
The staff basic information in the staff table can include a department, a team, a name, a work number, a manpower resource number, a staff type and the like.
Alternatively, the staff basic information in the shift table may be acquired from a user center of the shift system, a crowdsourcing platform, iHR (human resource management system) platform.
The scheduling staff can maintain the data such as personnel state, scheduling attribute, scheduling team, scheduling period and the like through the scheduling system, and the inventory of the human resources is completed.
S120: and inputting the class list into the fitness model to obtain a first evaluation result output by the fitness model.
The first evaluation result is the scheduling effect pre-evaluation of the shift table.
The fitness model can be used for pre-evaluating the scheduling effect of the scheduling table so as to preliminarily judge the rationality of the scheduling.
The fitting degree refers to the matching degree or the adaptation degree between the shift table and the business requirement.
In customer service scheduling, the fitness is used for evaluating whether the human resource allocation of the scheduling table reasonably meets the service requirements.
The fit may be measured by comparing the predicted human demand with the actual shift result. If the number of people on the shift in the shift table can better meet the expected business requirement, the fitting degree value is high, and the human resource allocation of the shift table is more reasonable; if the number of people on the shift table is difficult to meet the expected business requirement, the fitting degree value is low, and the human resource allocation of the shift table is unreasonable.
The fitting degree can be used as an important index for evaluating the scheduling effect of the shift table, the problems of the current scheduling scheme can be found in time by periodically monitoring and calculating the change of the fitting degree, the scheduling scheme is correspondingly adjusted and optimized based on the fitting degree, and the operation efficiency and the service quality of the customer service system can be ensured.
The fitness model is related to the time period manual request quantity, the preset call completing rate, the number of people arranged in time periods and the time period yield, and can be constructed according to the time period manual request quantity, the preset call completing rate, the number of people arranged in time periods, the time period yield and other indexes.
It should be noted that, the fitness model is used for performing preliminary evaluation on the shift effect of the shift table, and special factors in the actual shift scene, such as employee leave, emergency, system fault, etc., are not considered, so that the first evaluation result output by the fitness model is only used as a pre-estimated reference of the shift effect.
S130: and inputting the class table and customer service attendance data into the time-following model to obtain a second evaluation result output by the time-following model.
The second evaluation result is the actual evaluation of the scheduling effect of the shift table.
The time-following model can be used for actually evaluating the scheduling effect of the scheduling table and can reflect the actual execution condition of the table.
Compliance refers to the degree of compliance of a shift man with a shift table in actual operation.
In customer service scheduling, the time compliance is used for evaluating the actual execution condition of a scheduling table, namely whether a scheduling person is on duty according to the requirements of the scheduling table.
Compliance may be measured by comparing the correspondence between actual attendance data and the shift schedule. If the scheduling staff can go out on time according to the requirement of the table, the following time is high, and the table can be effectively executed; if the staff cannot get on duty according to the requirement of the shift table, the compliance time is low, and the shift table is not effectively executed.
The time-following model is related to the actual attendance days, the working hours of the scheduling and the actual working hours, so that the time-following model needs to refer to customer service attendance data.
The problem of the scheduling scheme in the actual execution process can be found in time by periodically monitoring and calculating the change of the following time, the scheduling scheme is correspondingly adjusted and optimized based on the following time, the actual effectiveness and accuracy of the scheduling scheme can be improved, and the normal operation of a customer service system and the improvement of the working efficiency of customer service staff are facilitated.
According to the evaluation method of the customer service scheduling scheme, which is provided by the embodiment, a class table of the customer service scheduling is obtained, the class table is input into the fitness model, and a first evaluation result output by the fitness model is obtained; the fitness model is related to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield; the class table and customer service attendance data are input into the time compliance model, and a second evaluation result output by the time compliance model is obtained; the time following model is related to the actual attendance days, the working hours of the scheduling and the actual working hours; the first evaluation result is the pre-evaluation of the scheduling effect of the shift table; the second evaluation result is the actual evaluation of the shift effect of the shift table. Through the mode, the pre-evaluation of the shift effect of the shift table can be realized through the fitness model, the fitness model is related to the time period manual request quantity, the preset completing rate, the time period arrangement number and the time period yield, the dependence on personal experience of a shift man is eliminated, and the pre-evaluation result of the shift effect is more reasonable; the actual evaluation of the shift effect of the shift table can be realized through a fitness model, the time-following model is related to the actual attendance days, the shift man-hour and the actual man-hour, and the actual evaluation result refers to the attendance data, so that the possibility of inaccurate evaluation result caused by deviation between the manpower distribution condition of the actual shift and the shift table is avoided, the actual evaluation result of the shift effect is more objective, and the reasonable distribution of manpower resources can be realized.
In some embodiments, before entering the class table into the fitness model, comprising: determining a first parameter according to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield; determining a second parameter according to the time interval manual request quantity, the time interval arrangement number of people and the time interval yield; respectively determining a first weight corresponding to the first parameter and a second weight corresponding to the second parameter; wherein the sum of the first weight and the second weight is 1; a fitness model is determined based on the product of the first parameter and the first weight, and the product of the second parameter and the second weight.
The time period manual request quantity refers to the number of traffic requests received by the customer service system in a preset time period.
The preset call completing rate refers to a target client call completing rate set by a shift man in a shift system.
The number of people arranged in the time period refers to the number of customer service people arranged in the class table in the preset time period.
The period yield refers to the amount of traffic requests actually completed within a preset period.
The time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield can be obtained through prediction of a machine learning model based on historical production telephone traffic sample data.
Further, determining a first parameter according to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield; and determining a second parameter according to the time interval manual request quantity, the time interval arrangement number of people and the time interval yield.
Further, a first weight corresponding to the first parameter and a second weight corresponding to the second parameter are respectively determined; wherein the sum of the first weight and the second weight is 1.
Further, if the product of the first parameter and the first weight is a first product and the product of the second parameter and the second weight is a second product, the expression of the fitness model may be a sum of the first product and the second product.
In some embodiments, the expression of the fitness model is:
wherein Rsquared is the first evaluation result, rt isThe time period manual request quantity, ccr is a preset call completing rate, nt is the number of people distributed in the time period, ot is the time period yield, abs is an absolute value function, min is a minimum value function, and w 1 Is the first weight, w 2 Is the second weight.
Wherein the sum of the first weight and the second weight is 1.
Alternatively, the period manual request amount Rt may be obtained by prediction by a traffic prediction model.
Specifically, preprocessing historical production telephone traffic sample data through an outlier detection algorithm and feature engineering; and inputting the preprocessed historical production telephone traffic sample data into a telephone traffic prediction model to obtain a time period manual request quantity Rt, wherein the time period manual request quantity Rt is actually a telephone traffic prediction value of a preset time period in the future.
The traffic prediction model may use a tree-based LightGBM algorithm and a timing-based Seq2Seq machine learning algorithm, and use a weighted moving average algorithm to predict traffic in a preset period.
It should be noted that, according to formal definition of anomalies by probability theory, anomalies are mainly classified into the following three types: point anomalies, condition anomalies (also known as context anomalies), population anomalies (also known as sequence anomalies).
Detecting point abnormality, condition abnormality and group abnormality of historical production telephone traffic sample data through an abnormal value detection algorithm; the outlier detection algorithm may be implemented based on a statistical learning method.
For example, the 3 sigma principle in statistical learning methods may be used to detect anomalies. The 3σ principle maps each data point in the dataset to a high-dimensional space based on a normal distribution assumption and calculates the deviation of the data point from the dataset as a whole. Data points with deviations exceeding 3σ (standard deviation) may be considered outliers. Data points that differ significantly from the normal mode can be identified using statistical methods to detect isolated point anomalies.
In practical application, an appropriate abnormality detection algorithm can be selected according to specific situations, and abnormality detection and judgment can be performed by combining field knowledge and experience.
Further, for time series class data contained in the historical production traffic sample data, feature engineering can be constructed by using variance filtering and mutual information method according to time stamp derived features, time series value derived features, attribute variable derived features and special periodic features of the time series class data.
The time sequence data is a data set arranged according to time sequence, has the characteristics of sequence, time dependence, seasonality, periodicity and the like, and in the abnormality detection, the abnormality of the time sequence data generally refers to mutation, abnormality fluctuation or abnormality trend which is not consistent with the normal mode.
The period yield Ot may be predicted from historical production traffic sample data.
Alternatively, historical production traffic sample data may be obtained from a large data platform.
Specifically, historical production telephone traffic sample data in the last period of time can be obtained from a big data platform, and average call volume per hour and average call duration in the period of time are obtained and calculated, wherein the average call volume per hour and the average call duration are important indexes for measuring the period yield.
In general, the hourly traffic of people has strong stability, and the period yield of a future period can be estimated according to the hourly traffic of historical people, so in this embodiment, the hourly traffic of historical people can be calculated as the predicted value of the period yield Ot.
Preferably, the predicted values of the period manual request amount Rt and the period yield Ot may be predicted based on historical data within the last 30 days.
Alternatively, if the time period manual request amount of the plurality of time periods in the history data is to be referred to, the cumulative fitness index of the plurality of time periods may be calculated based on the history data, and the cumulative fitness index may be calculated by the following formula:
wherein Rt is the time period manual request quantity, ccr is the preset call completing rate, nt is the number of people distributed in the time period, ot is the time period yield, and abs is the absolute value function.
The cumulative fitness index may reflect the rationality of the scheduling scheme for a plurality of time periods, such as a plurality of consecutive workdays or a plurality of consecutive months, and serve as a reference index for optimizing the scheduling scheme.
Optionally, if the preset connection rates of the multiple time periods in the historical data are to be referred to, an accumulated preset connection rate index of the multiple time periods may be calculated based on the historical data, where the accumulated preset connection rate index may be calculated by the following formula:
wherein Rt is the time period manual request quantity, ccr is the preset call completing rate, nt is the number of people distributed in the time period, ot is the time period yield, and min is the minimum function.
The plurality of time periods may be consecutive days or months, or may be consecutive seasons or the like.
In some embodiments, before entering the class and customer service attendance data into the time-of-compliance model, comprising: determining a third parameter according to the actual attendance days and the attendance days; determining a fourth parameter according to the scheduling man-hour and the actual man-hour; respectively determining a third weight corresponding to the third parameter and a fourth weight corresponding to the fourth parameter; wherein the sum of the third weight and the fourth weight is 1; a time-of-compliance model is determined based on the product of the third parameter and the third weight, and the product of the fourth parameter and the fourth weight.
In an actual scheduling scene, special situations, such as employee leave, employee delay and the like, inevitably occur, so that the actual on-duty situation of a shift table is inconsistent with that of a customer service person, evaluation of a scheduling effect is affected, and therefore customer service attendance data need to be introduced as a reference.
Specifically, a ratio of the actual attendance number to the actual attendance number may be used as the third parameter, a ratio of the man-hour for scheduling to the actual man-hour may be used as the fourth parameter, and a third weight corresponding to the third parameter and a fourth weight corresponding to the fourth parameter may be determined.
Further, if the product of the third parameter and the third weight is the third product, and the product of the fourth parameter and the fourth weight is the fourth product, the expression following the time scale model may be the sum of the third product and the fourth product.
Wherein the sum of the third weight and the fourth weight is 1.
In some embodiments, the expression following the time model is:
wherein Rp units are the second evaluation result, sd is the actual attendance days, wd is the attendance days, sh is the scheduling man-hour, wh is the actual man-hour, and w 3 Is the third weight, w 4 And is the fourth weight.
Wherein the sum of the third weight and the fourth weight is 1.
Optionally, the actual attendance days Sd may be obtained from employee attendance data of the attendance platform; the attendance days Wd can be obtained from the table statistical data of the scheduling system; the Sh at the time of scheduling can be obtained from check-in data of the customer service call center.
Alternatively, if reference is made to employee dimension attendance indicators within a fixed statistical date in the historical data, the employee dimension attendance indicators within the statistical date may be calculated from the following formula:
where Sd is the actual attendance days, wd is the number of attendance days.
Optionally, if the employee dimension compliance rate index in the fixed statistics date is to be referred to in the history data, the employee dimension compliance rate index in the statistics date may be calculated by the following formula:
where Sh is the man-hour for shift scheduling, and Wh is the actual man-hour.
In some embodiments, obtaining a class table for a customer service class includes: determining the telephone traffic of each time period in a future preset time period based on historical production telephone traffic sample data; splitting telephone traffic according to service types to obtain telephone traffic of different service types in each time period; determining the manpower prediction requirement of each time period according to the traffic of different service types of each time period; and determining a class list of customer service classes based on the human power prediction requirement.
Alternatively, the traffic of each period within the future preset duration may be obtained by machine learning model prediction based on historical production traffic sample data.
Optionally, traffic of different service types can be split according to the resource pool and the channel node to obtain traffic of different service types in each period.
It should be noted that, a Resource Pool (Resource Pool) refers to grouping or classifying of customer service personnel or team, and may be classified according to different criteria, such as skills, professional fields, language capability, geographical location, etc. of the customer service personnel. The purpose of the resource pool division is to categorize customer service personnel according to their specific capabilities and attributes for more flexibility in scheduling and service allocation.
For example, a carrier may have multiple resource pools, such as technical support resource pools, billing query resource pools, complaint handling resource pools, etc., with different skills and knowledge of customer service personnel in different resource pools to address a particular type of customer problem.
Channel nodes (Channel nodes) refer to channels or platforms where clients interact with customer service teams, and different Channel nodes represent different communication modes, such as telephone, online chat, email, social media, and the like. Different channel nodes may correspond to different customer service teams or resource pools to provide an optimal customer support experience based on channel characteristics and requirements.
For example, an e-commerce company may have telephone service channels, online chat service channels, social media service channels, etc., each of which may have different business requirements and response time requirements, thus requiring a corresponding pool of service resources to be allocated and scheduled.
In the scheduling and business distribution process, customer service personnel can be reasonably distributed to corresponding business fields and communication channels according to different resource pools and channel nodes so as to meet the requirements of different business types and channels, thereby improving the efficiency and quality of customer service and ensuring that customers can be accurately and professionally supported and serviced.
For example, telephone complaint traffic may be distributed to customer service personnel responsible for telephone channels in a complaint processing resource pool for processing.
In customer service scheduling, different types of services can be split according to the proportion according to different resource pools and channel nodes, so that the skills and professional fields of customer service personnel can be better matched, and smooth processing of the services is ensured.
Specifically, the telephone traffic is split according to the service types, and after the telephone traffic of different service types in each period is obtained, the manpower prediction requirement of each period is determined according to the telephone traffic of different service types in each period.
Alternatively, the Erlang-C formula may be used to calculate the human forecast demand for each time period based on the number of agents, the call availability, the call volume per hour, the average call duration.
The Erlang-C formula is:
wherein m is the number of people in the seat; u is the traffic intensity; e (E) C Probability of waiting for a call; p is the call utilization.
Probability of waiting for a call E C If the human resources are within a reasonable range, the human resources in the time period can be allocated to meet the telephone traffic demand, and the corresponding number of people in the seatAnd m is the manpower prediction requirement in the period.
It should be noted that the Erlang-C formula is a classical queuing theory model, and is used for calculating the number of people in the seat that reaches a specific answering probability under a given call volume and call utilization rate, and the formula can help to predict and plan the human resource requirement of the customer service center.
Since Erlang-C formula is a model based on assumptions and approximate conditions, other factors may also need to be considered in practical applications, such as volatility of call traffic, service level objectives, quality of service requirements, etc.
Further, a shift table for the customer service shift is determined based on the human forecast demand.
In some embodiments, after determining the shift table for the customer service shift based on the human forecast demand, comprising: acquiring attendance data of customer service scheduled in a shift table; obtaining the actual attendance days of each customer service and the actual working hours of each customer service according to the attendance data; the actual attendance days of the shift table and the actual man-hours of the shift table are obtained based on the actual attendance days of each customer service and the actual man-hours of each customer service.
The present invention also provides a specific example of an evaluation method of a customer service scheduling scheme, referring to fig. 2, fig. 2 is a second flow chart of the evaluation method of the customer service scheduling scheme provided by the present invention, and in this embodiment, the evaluation method of the customer service scheduling scheme is specifically as follows:
basic information of customer service personnel participating in scheduling is synchronously acquired through a user center.
The basic information of the customer service personnel can comprise a department, a team, a name, a work number, a manpower resource number, a personnel type and the like.
The scheduling staff can maintain the data such as personnel state, scheduling attribute, scheduling team, scheduling period and the like through the scheduling system, and the inventory of the human resources is completed.
Further, the historical telephone traffic sample data are synchronized to the big data platform, and the average telephone traffic per hour and average telephone duration data calculated by the big data platform are obtained.
Meanwhile, the big data platform synchronizes the received historical traffic sample data to the machine learning platform, so that the traffic prediction model on the machine learning platform can predict and output traffic prediction data of each period of one month in the future based on the historical traffic sample data.
Optionally, the historical traffic sample data is preprocessed prior to prediction using the traffic prediction model.
The preprocessed historical traffic sample data is input into a traffic prediction model, and the traffic prediction model can utilize a tree-based LightGBM algorithm and a time sequence-based Seq2Seq machine learning algorithm and predict the traffic of each time period of one month in the future by using a weighted moving average algorithm.
Further, after receiving traffic prediction data of each time period of one month in the future, splitting the traffic according to the service types to obtain traffic of different service types of each time period, and calculating the manpower prediction requirement of each time period by using an Erlang-C formula.
Further, a shift table for the customer service shift is determined based on the human forecast demand.
Further, the class table is input into the fitness model, and a first evaluation result output by the fitness model is obtained.
The fitting degree model is related to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield.
Further, customer service attendance data are obtained from the attendance platform, and the class table and the customer service attendance data are input into the time compliance model, so that a second evaluation result output by the time compliance model is obtained.
The time following model is related to the actual attendance days, the working hours of the scheduling and the actual working hours.
The first evaluation result is the pre-evaluation of the scheduling effect of the shift table; the second evaluation result is the actual evaluation of the shift effect of the shift table.
The present invention also provides an evaluation device for a customer service scheduling scheme, referring to fig. 3, fig. 3 is a schematic structural diagram of the evaluation device for a customer service scheduling scheme provided by the present invention, and in this embodiment, the evaluation device for a customer service scheduling scheme includes an acquisition table module 310, a first evaluation result module 320 and a second evaluation result module 330.
The get executive module 310 is used for getting the executive list of the customer service schedule.
The first evaluation result module 320 is configured to input the table to the fitness model, and obtain a first evaluation result output by the fitness model.
The fitness model is related to the manual request quantity, the preset call completing rate, the number of people arranged and the yield.
The second evaluation result module 330 is configured to input the executive table and the customer service attendance data to the time compliance model, and obtain a second evaluation result output by the time compliance model.
The time following model is related to the actual attendance days, scheduling man-hours and system check-in man-hours.
The first evaluation result is the pre-evaluation of the scheduling effect of the shift table; the second evaluation result is the actual evaluation of the shift effect of the shift table.
In some embodiments, before the table is input to the fitness model, the first evaluation result module 320 is further configured to determine a first parameter according to a time period manual request amount, a preset call completing rate, a time period arrangement number of people, and a time period yield; determining a second parameter according to the time interval manual request quantity, the time interval arrangement number of people and the time interval yield; respectively determining a first weight corresponding to the first parameter and a second weight corresponding to the second parameter; wherein the sum of the first weight and the second weight is 1; a fitness model is determined based on the product of the first parameter and the first weight, and the product of the second parameter and the second weight.
In some embodiments, the expression of the fitness model is:
Wherein Rsquared is a first evaluation result, rt is a time period manual request quantity, ccr is a preset call completing rate, nt is a time period arrangement number, ot is a time period yield, abs is an absolute value function, min is a minimum value function, and w 1 Is the firstA weight, w 2 Is the second weight.
In some embodiments, the second assessment results module 330 is further configured to determine a third parameter based on the actual attendance days and the number of attendance days prior to entering the class and customer attendance data into the time-in-line model; determining a fourth parameter according to the scheduling man-hour and the actual man-hour; respectively determining a third weight corresponding to the third parameter and a fourth weight corresponding to the fourth parameter; wherein the sum of the third weight and the fourth weight is 1; a time-of-compliance model is determined based on the product of the third parameter and the third weight, and the product of the fourth parameter and the fourth weight.
In some embodiments, the expression following the time model is:
wherein Rp units are the second evaluation result, sd is the actual attendance days, wd is the attendance days, sh is the scheduling man-hour, wh is the actual man-hour, and w 3 Is the third weight, w 4 And is the fourth weight.
In some embodiments, the get shift table module 310 is configured to determine traffic for each period within a future preset time period based on historical production traffic sample data; splitting telephone traffic according to service types to obtain telephone traffic of different service types in each time period; determining the manpower prediction requirement of each time period according to the traffic of different service types of each time period; and determining a class list of customer service classes based on the human power prediction requirement.
In some embodiments, after determining the shift table of the customer service shift based on the human forecast demand, the get shift table module 310 is further configured to obtain the attendance data of the customer service shifted in the shift table; obtaining the actual attendance days of each customer service and the actual working hours of each customer service according to the attendance data; the actual attendance days of the shift table and the actual man-hours of the shift table are obtained based on the actual attendance days of each customer service and the actual man-hours of each customer service.
The invention also provides an electronic device, referring to fig. 4, fig. 4 is a schematic structural diagram of an embodiment of the electronic device of the invention. In this embodiment, the electronic device may include a memory (memory) 410, a processor (processor) 420, and a computer program stored on the memory 410 and executable on the processor 420. The processor 420, when executing the program, implements the method for evaluating the customer service scheduling scheme provided by the methods described above.
Optionally, the electronic device may further comprise a communication bus 430 and a communication interface (Communications Interface) 440, wherein the processor 420, the communication interface 440, and the memory 410 complete communication with each other via the communication bus 430. The processor 420 may invoke logic instructions in the memory 410 to perform a method of evaluation of a customer service scheduling scheme, the method comprising: acquiring a class table of customer service class arrangement; the class table is input into the fitness model, and a first evaluation result output by the fitness model is obtained; the fitness model is related to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield; the class table and customer service attendance data are input into the time compliance model, and a second evaluation result output by the time compliance model is obtained; the time following model is related to the actual attendance days, the working hours of the scheduling and the actual working hours; the first evaluation result is the pre-evaluation of the scheduling effect of the shift table; the second evaluation result is the actual evaluation of the shift effect of the shift table.
Further, the logic instructions in the memory 410 described above may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present invention also provides a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, when the computer program is executed by a processor, the computer can execute the method for evaluating the customer service scheduling scheme provided by the above methods, and the steps and principles of the method are described in detail in the above methods and are not repeated herein.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The evaluation method of the customer service scheduling scheme is characterized by comprising the following steps of:
acquiring a class table of customer service class arrangement;
inputting the class table into a fitness model to obtain a first evaluation result output by the fitness model; the fitness model is related to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield;
inputting the class table and customer service attendance data into a time compliance model to obtain a second evaluation result output by the time compliance model; the time following model is related to the actual attendance days, the working hours of the scheduling and the actual working hours;
the first evaluation result is a shift arrangement effect pre-evaluation of the shift table; the second evaluation result is an actual evaluation of the shift arrangement effect of the shift table.
2. The method of claim 1, wherein before entering the class table into the fitness model, comprising:
determining a first parameter according to the time period manual request quantity, the preset call completing rate, the time period arrangement number of people and the time period yield;
determining a second parameter according to the time interval manual request quantity, the time interval arrangement number of people and the time interval yield;
respectively determining a first weight corresponding to the first parameter and a second weight corresponding to the second parameter; wherein the sum of the first weight and the second weight is 1;
the fitness model is determined based on the product of the first parameter and the first weight, the product of the second parameter and the second weight.
3. The method for evaluating a customer service scheduling scheme according to claim 2, wherein the expression of the fitness model is:
wherein Rsquared is a first evaluation result, rt is a time period manual request quantity, ccr is a preset call completing rate, nt is a time period arrangement number, ot is a time period yield, abs is an absolute value function, min is a minimum value function, and w 1 Is the first weight, w 2 Is the second weight.
4. The method of claim 1, wherein before entering the class and attendance data into the time-compliance model, comprising:
determining a third parameter according to the actual attendance days and the attendance days;
determining a fourth parameter according to the working hours of the shift and the actual working hours;
respectively determining a third weight corresponding to the third parameter and a fourth weight corresponding to the fourth parameter; wherein the sum of the third weight and the fourth weight is 1;
determining the time-following model based on the product of the third parameter and the third weight, and the product of the fourth parameter and the fourth weight.
5. The method of claim 4, wherein the time-following model expression is:
wherein Rp units are the second evaluation result, sd is the actual attendance days, wd is the attendance days, sh is the scheduling man-hour, wh is the actual man-hour, and w 3 Is the third weight, w 4 And is the fourth weight.
6. The method for evaluating a customer service shift arrangement according to any one of claims 1 to 5, wherein the obtaining of the shift table of the customer service shift arrangement comprises:
Determining the telephone traffic of each time period in a future preset time period based on historical production telephone traffic sample data;
splitting the telephone traffic according to the service types to obtain telephone traffic of different service types in each time period;
determining the manpower prediction requirements of each time period according to the traffic of different service types of each time period;
and determining the class list of the customer service class according to the manpower prediction demand.
7. The method for evaluating a customer service shift arrangement according to claim 6, wherein after the determining of the shift table of the customer service shift based on the human predicted demand, comprising:
acquiring attendance data of the scheduled customer service in the class table;
obtaining the actual attendance days of each customer service and the actual working hours of each customer service according to the attendance data;
and obtaining the actual attendance days of the table and the actual working hours of the table based on the actual attendance days of each customer service and the actual working hours of each customer service.
8. An evaluation device for a customer service scheduling scheme, comprising:
the system comprises an acquisition table module, a customer service scheduling module and a customer service scheduling module, wherein the acquisition table module is used for acquiring a table of a customer service scheduling;
the first evaluation result module is used for inputting the shift table into the fitness model to obtain a first evaluation result output by the fitness model; the fitness model is related to the manual request quantity, the preset call completing rate, the number of people arranged and the yield;
The second evaluation result module is used for inputting the class table and customer service attendance data into the time-following model to obtain a second evaluation result output by the time-following model; the time following model is related to actual attendance days, scheduling man-hour and system signing man-hour;
the first evaluation result is a shift arrangement effect pre-evaluation of the shift table; the second evaluation result is an actual evaluation of the shift arrangement effect of the shift table.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of evaluating a customer service scheduling scheme according to any one of claims 1 to 7 when the program is executed by the processor.
10. Computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements a method of evaluating a customer service scheduling scheme according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762997.3A CN116911530A (en) | 2023-06-26 | 2023-06-26 | Customer service scheduling scheme evaluation method and device, electronic equipment and product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762997.3A CN116911530A (en) | 2023-06-26 | 2023-06-26 | Customer service scheduling scheme evaluation method and device, electronic equipment and product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116911530A true CN116911530A (en) | 2023-10-20 |
Family
ID=88363937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310762997.3A Pending CN116911530A (en) | 2023-06-26 | 2023-06-26 | Customer service scheduling scheme evaluation method and device, electronic equipment and product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911530A (en) |
-
2023
- 2023-06-26 CN CN202310762997.3A patent/CN116911530A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10896203B2 (en) | Digital analytics system | |
| US20210224706A1 (en) | Method and system for generating staffing requirements for deferred work in a contact center environment | |
| US8015042B2 (en) | Methods for long-range contact center staff planning utilizing discrete event simulation | |
| Alfieri et al. | A project scheduling approach to production planning with feeding precedence relations | |
| CN114118496A (en) | Method and system for automatically scheduling queuing reservation based on big data analysis | |
| CN114118691A (en) | Scheduling scheme processing method, device, equipment and medium based on traffic | |
| CN109697637A (en) | Object type determination method and device, electronic equipment and computer storage medium | |
| Helber et al. | Profit-oriented shift scheduling of inbound contact centers with skills-based routing, impatient customers, and retrials | |
| CN117350640A (en) | Project progress management method and system | |
| CN115202847A (en) | Task scheduling method and device | |
| CN115471200A (en) | Cloud computing-based human resource data management system, method and device | |
| Long et al. | Pooling and balking: Decisions on COVID-19 testing | |
| CN102012902A (en) | Website visitor value estimation system and method | |
| CN113052417A (en) | Resource allocation method and device | |
| CN116630082A (en) | Method and device for allocating production resources, electronic equipment and storage medium | |
| CN116911530A (en) | Customer service scheduling scheme evaluation method and device, electronic equipment and product | |
| CN115330219A (en) | Resource scheduling method and device | |
| CN109359825B (en) | Bank digital operation product value analysis method | |
| CN112508295A (en) | Incoming call service prediction method and system based on service map and Markov model | |
| Chung et al. | Cross-trained versus specialized agents in an inbound call centre: a simulation-based methodology for trade-off analysis | |
| CN111178647A (en) | Method, system and computer storage medium for pushing work order | |
| US20220327562A1 (en) | Methods and systems for applying survival analysis models to produce temporal measures of sales productivity | |
| US20230297909A1 (en) | System and method for predicting service metrics using historical data | |
| US20240232778A1 (en) | Intelligent Forecasting with Benchmarks | |
| US11425250B1 (en) | Artificial intelligence based call handling optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |