CN116915905A - Outgoing call rate determination method, device, equipment, storage medium and program product - Google Patents

Abstract

The application discloses an outgoing call rate determining method, an outgoing call rate determining device, a storage medium and a program product. The method comprises the following steps: the method comprises the steps of obtaining historical incoming call quantity at a first moment, inputting the historical incoming call quantity into a differential autoregressive moving average model, predicting first incoming call quantity of a next period at the first moment through the differential autoregressive moving average model, and determining a first outgoing call rate according to the first incoming call quantity. According to the embodiment of the application, the problem of higher call loss rate under the condition of increasing the existing call quantity can be solved.

Description

Outgoing call rate determination method, device, equipment, storage medium and program product

Technical field

The present application belongs to the field of computer application technology, and in particular relates to an outgoing rate determination method, device, equipment, storage medium and program product.

Background technique

With the rapid development of customer service systems, agents need to perform outbound calls while accepting incoming calls. When executing an outbound call task, the customer service system usually calculates the number of samples that should be called out based on the agent situation under the outbound call task, and then initiates an outbound call based on the number of samples that should be called out, and then transfers the call after the user answers the call. Seat.

As a result, when the incoming call volume increases, if the outgoing call volume cannot be reduced in time, there may not be enough agents to handle outbound call tasks. As a result, in a large number of outbound call tasks, it will take a specified time after the user connects the outbound call. Agents cannot be transferred within the call period, resulting in a higher call loss rate.

Contents of the invention

Embodiments of the present application provide an outgoing call rate determination method, device, equipment, storage medium and program product, which can solve the existing problem of high call loss rate when the number of incoming calls increases.

In a first aspect, embodiments of the present application provide a method for determining an outgoing call rate. The method includes:

Obtain the historical incoming call volume of the customer service system at the first moment;

Enter the historical incoming call volume into a differential autoregressive moving average model, and predict the first incoming call volume in the next period of the first moment through the differential autoregressive moving average model;

According to the first incoming call volume, the first outgoing call rate in the next period is determined.

In some embodiments, before inputting the historical incoming call volume into a differential autoregressive moving average model and predicting the first incoming call volume through the differential autoregressive moving average model, the method further includes:

Obtain the autoregressive order and moving average order of the customer service system;

Determine an autoregressive model based on the historical incoming call volume and the autoregressive order;

Determine a moving average model based on the historical incoming call volume and the moving average order;

The differential autoregressive moving average model is obtained by merging the autoregressive model and the moving average model.

In some embodiments, the autoregressive model is:

The moving average model is:

The differential autoregressive moving average model is:

Among them, μ ₁ is the first constant term coefficient, y _t1 is the incoming call volume predicted by the autoregressive model, ∈ _t1 is the error value of the autoregressive model, μ ₂ is the second constant term coefficient, and y _t2 is the incoming call volume predicted by the moving average model. , ∈ _t2 is the moving average model error value, y _t is the first incoming call volume, μ is the constant term coefficient, p is the autoregressive order, q is the moving average order, γ _i is the autocorrelation coefficient, y _ti is the history For the incoming call volume in the tith period, ∈t is the current error value, θ _i is the correlation coefficient of the moving average model, and ∈ti is the error value in the tith period.

In some embodiments, determining the first outgoing call rate in the next period based on the first incoming call volume includes:

Obtain the number of target agents at the first moment, the number of idle target agents at the first moment, and the average service time of the target agents in the previous period. The target agents include mixed-signed agents and agents that only handle incoming calls. Mixed-signed agents An agent is an agent who handles both inbound and outbound calls;

Enter the target number of agents at the first moment, the target number of idle agents at the first moment, the average service time of the target agents in the previous period and the first incoming call volume into the pre-built first model , obtain the amount of outgoing calls at the second moment, which is any moment in the next period;

The first exhalation rate is determined based on the amount to be exhaled.

In some embodiments, determining the first outgoing call rate in the next period based on the first incoming call volume includes:

Determine the target adjustment coefficient according to the first call loss rate of the customer service system in the previous cycle;

The first outgoing call rate is determined based on the first incoming call volume and the target adjustment coefficient.

In some embodiments, determining the target adjustment coefficient based on the first call loss rate of the customer service system in the previous period includes:

Get the historical adjustment coefficient;

When the first call loss rate is greater than the maximum call loss rate threshold, reduce the historical adjustment coefficient according to a preset proportion according to the target number of seats to obtain the target adjustment coefficient;

In the case where the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold, according to the number of target agents and the average idle time of the target agent in the previous period The historical adjustment coefficient is increased according to a preset proportion to obtain the target adjustment coefficient.

In some embodiments, determining the target adjustment coefficient based on the first call loss rate of the customer service system in the previous period includes:

When the customer service system meets the rate adjustment conditions, determine the target adjustment coefficient based on the first call loss rate of the customer service system in the previous cycle;

The rate adjustment conditions include at least one of the following:

The duration for which the customer service system activates the outbound call task is greater than or equal to the first duration threshold;

The first moment is not within the adjustment observation period;

The first call loss rate is greater than the maximum call loss rate threshold, or the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold.

In the second aspect, embodiments of the present application provide an outgoing call rate determination device, which includes:

The acquisition module is used to obtain the historical incoming call volume at the first moment;

An input module configured to input the historical incoming call volume into a differential autoregressive moving average model, and predict the first incoming call volume in the next period of the first moment through the differential autoregressive moving average model;

A determining module, configured to determine a first outgoing call rate based on the first incoming call volume.

In a third aspect, embodiments of the present application provide an outgoing call rate determination device, which includes: a processor and a memory storing computer program instructions;

The processor implements the above callout rate determination method when executing computer program instructions.

In the fourth aspect, embodiments of the present application provide a computer storage medium. Computer program instructions are stored on the computer storage medium. When the computer program instructions are executed by a processor, the above outgoing call rate determination method is implemented.

In a fifth aspect, embodiments of the present application provide a computer program product. The computer program product includes computer program instructions. When the computer program instructions are executed by a processor, the above callout rate determination method is implemented.

In this application, the first incoming call volume in the next period at the first moment is predicted through the differential autoregressive moving average model and the historical incoming call volume. After the first incoming call volume is predicted, the first incoming call volume can be further predicted based on the first incoming call volume. The incoming call volume determines the first outgoing call rate in real time, which can make the outgoing call rate change with the change of the incoming call volume. When the incoming call volume increases, the outgoing call rate can be appropriately reduced to solve the problem of existing incoming call volume increasing. Technical problems with high loss rate.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the drawings required to be used in the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. Those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.

Figure 1 is a schematic flowchart of a method for determining an outbound call rate provided by an embodiment of the present application;

Figure 2 is a schematic flowchart of an outgoing call rate determination method provided by another embodiment of the present application;

Figure 3 is a schematic flowchart of an outbound call rate determination method provided by yet another embodiment of the present application;

Figure 4 is a schematic diagram of the hardware structure of an outgoing call rate determination device provided by an embodiment of the present application;

Figure 5 is a schematic structural diagram of an outgoing call rate determining device provided by an embodiment of the present application.

Detailed ways

Features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described in further detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only intended to explain the application, but not to limit the application. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of embodiments is merely intended to provide a better understanding of the present application by illustrating examples of the present application.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations are mutually exclusive. any such actual relationship or sequence exists between them. Furthermore, the terms "comprises," "comprises," or any other variations thereof are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also those not expressly listed other elements, or elements inherent to the process, method, article or equipment. Without further limitation, an element defined by the statement "including..." does not exclude the presence of additional identical elements in the process, method, article, or device that includes the element.

It should be noted that, as long as there is no conflict, the embodiments and features in the embodiments of this application can be combined with each other. The embodiments will be described in detail below with reference to the accompanying drawings.

With the rapid development of customer service systems, agents need to perform outbound calls while accepting incoming calls. When executing an outbound call task, the customer service system usually calculates the number of samples that should be called out based on the agent situation under the outbound call task, and then initiates an outbound call based on the number of samples that should be called out, and then transfers the call after the user answers the call. Seat. However, in the incoming and outgoing call integration scenario, if existing methods are used to predict the number of samples that should be called out, the outgoing call volume cannot be adjusted in real time when the incoming call volume changes.

As a result, when the incoming call volume increases, if the outgoing call volume cannot be reduced in time, there may not be enough agents to handle outbound call tasks. As a result, in a large number of outbound call tasks, it will take a specified time after the user connects the outbound call. Agents cannot be transferred within the call period, resulting in a higher call loss rate. In addition, when the incoming call volume decreases, if the outgoing call volume cannot be increased in time, agents may be idle for a long time, resulting in low utilization of agent resources.

In related technologies, the following two methods are usually used to solve the above problems. One is to flexibly set the allowed idle seat ratio. This method mainly relies on the experience of operators, the labor cost is too high, and when the incoming call volume changes too frequently, It is difficult to effectively control the situation; secondly, the outbound call rate is fixedly adjusted according to the number of mixed-signed seats. This method has a long lag, and will also cause slow registration of agents, increase agent idle time, and affect agent utilization.

Specifically, in order to solve the existing technical problems, embodiments of the present application provide an outgoing call rate determination method, device, equipment, storage medium and program product. The following first introduces the method for determining the outgoing call rate provided by the embodiment of the present application.

Figure 1 shows a schematic flowchart of an outgoing call rate determination method provided by an embodiment of the present application. The method includes the following steps:

S110: Obtain the historical incoming call volume of the customer service system at the first moment.

In this embodiment, the first time may be the current time, and the historical incoming call volume at the first time is the incoming call volume of the customer service system before the first time. Since the customer service system records the incoming calls at each moment, the historical incoming calls at the first moment can be read directly in the customer service system.

S120: Enter the historical incoming call volume into a differential autoregressive moving average model, and predict the first incoming call volume in the next period of the first moment through the differential autoregressive moving average model.

The differential autoregressive moving average model (ARIMA) can reflect the relationship between the current value and the historical value, as well as the relationship between the current value and the error term. In this embodiment, the first incoming call volume in the next period at the first moment can be predicted through the differential autoregressive moving average model and the historical incoming call volume. That is, by using the historical incoming call volume as the input of the differential autoregressive moving average model, the first incoming call volume in the next period at the first moment can be obtained. Among them, the next period is a period of time after the first moment. The length of this period can be adjusted by the user in real time, and it can be 1 minute or 30 seconds.

S130: Determine the first outgoing call rate in the next period according to the first incoming call volume.

In this embodiment, after predicting the first incoming call volume in the next period, the outgoing call volume corresponding to each moment in the next period can be determined based on the first incoming call volume. If the number of outgoing calls in the next period remains unchanged, Next, the first outgoing call rate in the next period can be determined based on the volume of outgoing calls corresponding to each moment in the next period and the number of outgoing calls in the next period.

This application uses a differential autoregressive moving average model and historical incoming call volume to predict the first incoming call volume in the next period at the first moment. After predicting the first incoming call volume, it can further predict the first incoming call volume in real time based on the first incoming call volume. Determining the first outgoing call rate can make the outgoing call rate change with the change of the incoming call volume. When the incoming call volume increases, the outgoing call rate can be appropriately reduced to solve the existing problem of relatively high call loss rate when the incoming call volume increases. High technical issues.

As an optional embodiment, in order to ensure the accuracy of predicting incoming call volume, before the above S120, the method further includes:

Obtain the autoregressive order and moving average order of the customer service system;

Determine an autoregressive model based on the historical incoming call volume and the autoregressive order;

Determine a moving average model based on the historical incoming call volume and the moving average order;

The differential autoregressive moving average model is obtained by merging the autoregressive model and the moving average model.

In this embodiment, the autoregressive model is used to describe the relationship between historical values and current values. The autoregressive model can predict the incoming call volume based on the historical incoming call volume. The autoregressive order is the order of the autoregressive model; the moving average The model is used to describe the relationship between the current value and the error term. The moving average model can predict the incoming call volume based on the error term in the historical incoming call volume. The moving average order is the order of the moving average model, the autoregressive order and the moving average. The average order can be determined based on the linear correlation and degree of correlation of historical incoming calls.

After obtaining the autoregressive order, the autoregressive model can be determined based on the historical incoming call volume and the autoregressive order; after obtaining the moving average order, the moving average model can be determined based on the historical incoming call volume and the moving average order. After obtaining the autoregressive model and the moving average model, the differential autoregressive moving average model can be obtained by combining the autoregressive model, the moving average model and the difference method. Among them, the difference method is used to smoothen the historical incoming call volume.

As shown in Figure 2, in one embodiment, a specific method for constructing a differential autoregressive moving average model is: determining a set of autocorrelation functions ACF and partial autocorrelation functions PACF based on the acquired historical incoming calls, where the autocorrelation function It is used to describe the linear correlation between the current observation value and its past observation value in the time series, and the partial autocorrelation function is used to calculate the degree of correlation between two variables. Since there is a time series in the historical incoming call volume in this embodiment, a set of autocorrelation functions and partial autocorrelation functions can be determined based on the historical incoming call volume.

After determining a set of autocorrelation functions and partial autocorrelation functions, you can draw ACF charts and PACF charts based on the autocorrelation functions and partial autocorrelation functions, and observe the stationarity of historical incoming calls through the ACF charts and PACF charts. If the history If the incoming call volume is stable, no processing is required. If the historical incoming call volume is not stable, the historical incoming call volume can be stabilized through the differential method.

After smoothing the historical incoming call volume, the autoregressive order and moving average order can be determined based on the ACF chart and PACF chart, and the autoregressive model and moving average model can be further constructed. Merge to obtain the differential autoregressive moving average model, then calculate the residual statistical value in the differential autoregressive moving average model, and further check whether the residual statistical value is appropriate. If appropriate, apply the differential autoregressive moving average model to predict the first Incoming call volume, if inappropriate, re-determine the autoregressive order and moving average order.

In one embodiment, the autoregressive model is:

The moving average model is:

The differential autoregressive moving average model is:

Among them, μ ₁ is the first constant term coefficient, y _t1 is the incoming call volume predicted by the autoregressive model, ∈ _t1 is the error value of the autoregressive model, μ ₂ is the second constant term coefficient, and y _t2 is the incoming call volume predicted by the moving average model. , ∈ _t2 is the moving average model error value, y _t is the first incoming call volume, μ is the constant term coefficient, p is the autoregressive order, q is the moving average order, γ _i is the autocorrelation coefficient, y _ti is the history The incoming call volume in the t-th period, ∈ _t is the current error value, θ _i is the correlation coefficient of the moving average model, ∈ _ti is the error value in the t-th period.

The differential autoregressive moving average model is constructed through the above method, which can not only reflect the relationship between the first incoming call volume and the historical incoming call volume, but also reflect the relationship between the first incoming call volume and the historical error value, thereby ensuring that the first call incoming call volume is accurately measured. The accuracy of the input forecast.

As an optional embodiment, in order to improve the real-time performance and accuracy of outgoing call rate adjustment, the above S130 may include:

Obtain the number of target agents at the first moment, the number of idle target agents at the first moment, and the average service time of the target agents in the previous period. The target agents include mixed-signed agents and agents that only handle incoming calls. Mixed-signed agents An agent is an agent who handles both inbound and outbound calls;

Enter the target number of agents at the first moment, the target number of idle agents at the first moment, the average service time of the target agents in the previous period and the first incoming call volume into the pre-built first model , obtain the amount of outgoing calls at the second moment, which is any moment in the next period;

The first exhalation rate is determined based on the amount to be exhaled.

In this embodiment, the agents in the customer service system are divided into three categories: one is an agent that only handles incoming calls, one is an agent that only handles outgoing calls, and the other is handles both incoming and outgoing calls. The target agents include mixed-signed agents and agents who only handle incoming calls. In this embodiment, the incoming call volume can be divided according to cycles, and the duration of each cycle can be adjusted by the user in real time. One cycle can include at least one period, and one period can include at least one moment.

The first model is a pre-built model. The first model can determine the first number of agents based on the number of target agents at the first moment, the number of target agents who are idle at the first moment, the average service time of the target agents in the previous period and the first incoming call volume. The required exhalation volume at two moments is determined, and the first exhalation rate is further determined based on the required exhalation volume.

The above method can determine the outgoing call volume at the second moment based on the agent status and the predicted first incoming call volume, and adjust the first outgoing call rate based on the outgoing call volume. That is, the first outgoing call rate can be adjusted based on the agent status and the first incoming call volume. The first exhalation rate is determined based on the amount, which improves the real-time and accuracy of the exhalation rate adjustment.

As an optional embodiment, in order to improve the real-time performance of outbound call rate adjustment, the above S130 may include:

Determine the target adjustment coefficient according to the first call loss rate of the customer service system in the previous cycle;

The first outgoing call rate is determined based on the first incoming call volume and the target adjustment coefficient.

In this embodiment, the target adjustment coefficient is a variable coefficient that adjusts the exhalation volume to be exhaled at the second moment. The target adjustment coefficient can be adjusted corresponding to the exhalation volume to obtain the actual exhalation volume at the second moment. The target adjustment coefficient can be adjusted based on the first call loss rate and the first average idle time of the customer service system in the previous period.

If the first call loss rate in the previous cycle is high, it means that the call volume in the previous cycle was too large, so the target adjustment coefficient can be appropriately lowered to appropriately reduce the call volume in this cycle and reduce the call loss rate; if If the first average idle time in the previous cycle is high, it means that the outbound call volume in the previous cycle was too small. Therefore, the target adjustment coefficient can be appropriately increased to appropriately increase the outbound call volume in this cycle and avoid wasting agent resources.

In addition, the actual exhalation volume at the second moment may be positively correlated with the target adjustment coefficient. In an embodiment, the actual exhalation volume at the second moment may be the product of the target adjustment coefficient and the expected exhalation volume.

The above method can determine the target adjustment coefficient based on the agent status of the previous cycle, and adjust the first outbound call rate based on the target adjustment coefficient. That is, the first outbound call rate can be determined based on the agent status of the previous cycle, which improves the outbound call rate adjustment. real-time.

As an optional embodiment, in order to automatically adjust the target adjustment coefficient, determining the target adjustment coefficient based on the first call loss rate of the customer service system in the previous period may include:

Get the historical adjustment coefficient;

When the first call loss rate is greater than the maximum call loss rate threshold, reduce the historical adjustment coefficient according to a preset proportion according to the target number of seats to obtain the target adjustment coefficient;

In the case where the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold, according to the number of target agents and the average idle time of the target agent in the previous period The historical adjustment coefficient is increased according to a preset proportion to obtain the target adjustment coefficient.

In this embodiment, the historical adjustment coefficient is the adjustment coefficient in the previous cycle of the first moment, and the target adjustment coefficient is the historical adjustment coefficient based on the first call loss rate of the previous cycle and the first average idle time of the previous cycle. Adjustment coefficient The adjustment coefficient obtained by adjusting.

If the first call loss rate is greater than the maximum call loss rate threshold, it means that the call loss rate caused by the call volume in the previous cycle is too high. Therefore, the historical adjustment coefficient can be reduced according to the preset proportion to appropriately reduce the call volume in this cycle. Reduce the call loss rate; if the first call loss rate in the previous cycle is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold, it means that the amount of outbound calls in the previous cycle caused too much wastage of agent resources, so The historical adjustment coefficient can be increased according to the preset proportion to appropriately increase the outbound call volume of this cycle and avoid the waste of agent resources.

The preset ratio in the above method can be set by the user and adjusted in real time. The historical adjustment coefficient can be adjusted in real time through the preset ratio, and the target adjustment coefficient can be automatically adjusted according to the status of the target agent in the previous period.

As an optional embodiment, determining the target adjustment coefficient based on the first call loss rate of the customer service system in the previous period may include:

When the customer service system meets the rate adjustment conditions, determine the target adjustment coefficient based on the first call loss rate of the customer service system in the previous cycle;

The rate adjustment conditions include at least one of the following:

The duration for which the customer service system activates the outbound call task is greater than or equal to the first duration threshold;

The first moment is not within the adjustment observation period;

The first call loss rate is greater than the maximum call loss rate threshold, or the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold.

In this embodiment, the target adjustment coefficient is adjusted only when the customer service system satisfies the rate adjustment condition; otherwise, the obtained historical adjustment coefficient can be directly determined as the target adjustment coefficient.

In one embodiment, only when the customer service system satisfies the above three rate adjustment conditions at the same time, the customer service system can be considered to meet the rate adjustment conditions. In another embodiment, when the customer service system meets any one of the above three items, it can be considered that the customer service system meets the rate adjustment condition.

As shown in Figure 3, in one embodiment, the historical adjustment coefficient is 1. When the customer service system meets the rate adjustment conditions, the target adjustment coefficient is adjusted according to the obtained real-time indicators, and the outbound call rate is calculated according to the target adjustment coefficient. Actual outbound call volume; when the customer service system does not meet the rate adjustment conditions, the historical adjustment coefficient is directly used as the target adjustment coefficient to calculate the actual outbound call volume. And further monitor real-time indicators that affect the target adjustment coefficient in real time.

Specifically, when the duration of the customer service system's opening of the outbound call task is less than the first duration threshold, the situation of the target agent is not stable, and the first call loss rate and the first average idle duration of the previous period cannot accurately reflect the previous period. The status of the target agent of the period, so the duration for the customer service system to open the outbound call task can be greater than or equal to the first duration threshold as one of the rate adjustment conditions.

The adjustment observation period is a period when the customer service system is in working condition and the target adjustment coefficient can be adjusted in real time. When the first moment is not within the adjustment observation period, the target adjustment coefficient does not need to be adjusted in time. Therefore, the first moment not within the adjustment observation period can be As one of the rate adjustment conditions.

When the first call loss rate is less than or equal to the maximum threshold of the call loss rate, and greater than or equal to the minimum threshold of the call loss rate, it means that the target agent of the customer service system in the previous cycle is in a suitable working status range, neither The call loss rate is too high because the outbound call volume is too high, and the agent resources are wasted too much because the outbound call volume is too low. In this case, there is no need to adjust the target adjustment coefficient. When the first call loss rate is greater than the maximum call loss rate threshold, the call loss rate will be too high, and the target adjustment coefficient needs to be reduced to reduce the call loss rate; when the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is If it is greater than the average idle time threshold, it will lead to excessive waste of agent resources. It is necessary to increase the target adjustment coefficient to increase the outbound call volume, thereby avoiding the waste of agent resources. Therefore, the comparison result between the first call loss rate and the call loss rate threshold, and the comparison result between the first average idle duration and the average idle duration threshold can be used as one of the rate adjustment conditions.

Based on the outgoing call rate determination method provided in the above embodiments, correspondingly, this application also provides a specific implementation of the outgoing call rate determining device. See the examples below.

Referring first to Figure 4, the outgoing call rate determination device 400 provided by the embodiment of the present application includes the following modules:

The acquisition module 401 is used to obtain the historical incoming calls of the customer service system at the first moment;

The input module 402 is configured to input the historical incoming call volume into a differential autoregressive moving average model, and predict the first incoming call volume in the next period of the first moment through the differential autoregressive moving average model;

Determining module 403, configured to determine the first outgoing call rate in the next period according to the first incoming call volume.

The device can predict the first incoming call volume in the next period at the first moment through the differential autoregressive moving average model and historical incoming call volume. After predicting the first incoming call volume, it can further predict the first incoming call volume in real time based on the first incoming call volume. Determining the first outgoing call rate can make the outgoing call rate change with the change of the incoming call volume. When the incoming call volume increases, the outgoing call rate can be appropriately reduced to solve the existing problem of relatively high call loss rate when the incoming call volume increases. High technical issues.

As an implementation manner of this application, in order to ensure the accuracy of predicting the incoming call volume, the above-mentioned outgoing call rate determining device 400 may also include:

The first acquisition unit is used to obtain the autoregressive order and moving average order of the customer service system;

A first determination unit configured to determine an autoregressive model based on the historical incoming call volume and the autoregressive order;

a second determination unit, configured to determine a moving average model based on the historical incoming call volume and the moving average order;

A merging unit configured to combine the autoregressive model and the moving average model to obtain the differential autoregressive moving average model.

As an implementation manner of this application, in order to improve the real-time performance and accuracy of outgoing call rate adjustment, the above-mentioned determination module 403 may include:

The second acquisition unit is used to acquire the number of target agents at the first moment, the number of idle target agents at the first moment, and the average service time of the target agents in the previous period of the period in which the first moment is located. Including mixed-signed agents and agents who only handle incoming call services. Mixed-signed agents are agents who handle both incoming and outgoing call services;

An input unit configured to pre-construct the target number of agents at the first moment, the target number of idle agents at the first moment, the average service time of the target agents in the previous period, and the first incoming call volume. In the first model, obtain the call-out volume at the second time, and the second time is any time in the next period;

A third determination unit is configured to determine the first exhalation rate according to the amount of exhalation to be made.

As an implementation manner of this application, in order to improve the real-time performance of outbound call rate adjustment, the above-mentioned determination module 403 may include:

The fourth determination unit is used to determine the target adjustment coefficient according to the first call loss rate of the customer service system in the previous period;

The fifth determination unit is used to determine the first outgoing call rate according to the first incoming call volume and the target adjustment coefficient.

As an implementation manner of the present application, in order to automatically adjust the target adjustment coefficient, the above-mentioned fourth determination unit may include:

Get the subunit, used to obtain the historical adjustment coefficient;

A first adjustment subunit, configured to reduce the historical adjustment coefficient according to a preset proportion according to the target number of seats to obtain the target adjustment coefficient when the first call loss rate is greater than the maximum call loss rate threshold;

The second adjustment subunit is configured to adjust the target number of agents according to the target agent number and the target agent number when the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold. The historical adjustment coefficient is increased according to a preset proportion to the average idle time of the previous period to obtain the target adjustment coefficient.

As an implementation manner of this application, the above-mentioned fourth determining unit may include:

A coefficient determination subunit, configured to determine the target adjustment coefficient based on the first call loss rate of the customer service system in the previous period when the customer service system meets the rate adjustment conditions;

The rate adjustment conditions include at least one of the following:

The duration for which the customer service system activates the outbound call task is greater than or equal to the first duration threshold;

The first moment is not within the adjustment observation period;

The first call loss rate is greater than the maximum call loss rate threshold, or the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold.

The outgoing call rate determination device provided by the embodiment of the present invention can implement each step in the above method embodiment. To avoid repetition, they will not be described again here.

Figure 5 shows a schematic diagram of the hardware structure of the outgoing call rate determination device provided by the embodiment of the present application.

The outgoing call rate determining device may include a processor 501 and a memory 502 storing computer program instructions.

Specifically, the above-mentioned processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits according to the embodiments of the present application.

Memory 502 may include bulk storage for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive or two or more A combination of many of the above. Memory 502 may include removable or non-removable (or fixed) media, where appropriate. Where appropriate, the memory 502 may be internal or external to the integrated gateway disaster recovery device. In certain embodiments, memory 502 is non-volatile solid-state memory.

Memory may include read only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical/tangible memory storage devices. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or multiple processors) operable to perform the operations described with reference to a method according to an aspect of the present disclosure.

The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any of the call rate determination methods in the above embodiments.

In one example, the outbound call rate determination device may further include a communication interface 503 and a bus 510 . Among them, as shown in Figure 5, the processor 501, the memory 502, and the communication interface 503 are connected through the bus 510 and complete communication with each other.

The communication interface 503 is mainly used to implement communication between modules, devices, units and/or equipment in the embodiments of this application.

Bus 510 includes hardware, software, or both, coupling the components of the outgoing call rate determining device to one another. By way of example, and not limitation, the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) interconnect, Industry Standard Architecture (ISA) Bus, Infinite Bandwidth Interconnect, Low Pin Count (LPC) Bus, Memory Bus, Micro Channel Architecture (MCA) Bus, Peripheral Component Interconnect (PCI) Bus, PCI-Express (PCI-X) Bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or a combination of two or more of these. Where appropriate, bus 510 may include one or more buses. Although the embodiments of this application describe and illustrate a specific bus, this application contemplates any suitable bus or interconnection.

The outgoing call rate determination device may be based on the above embodiment, thereby implementing the above outgoing call rate determining method and device.

In addition, in conjunction with the outgoing call rate determination method in the above embodiment, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the outgoing call rate determination methods in the above embodiments can be achieved, and the same technical effect can be achieved. To avoid duplication, they will not be described again here. . Among them, the above-mentioned computer-readable storage media may include non-transitory computer-readable storage media, such as read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), magnetic disks or optical disks, etc. , is not limited here.

In addition, embodiments of the present application also provide a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the steps and corresponding contents of the foregoing method embodiments can be implemented.

To be clear, this application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications and additions, or change the order between steps after understanding the spirit of the present application.

The functional blocks shown in the above structural block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, or the like. When implemented in software, elements of the application are programs or code segments that are used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted over a transmission medium or communications link via a data signal carried in a carrier wave. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. Code segments may be downloaded via computer networks such as the Internet, intranets, and the like.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps. That is to say, the steps may be performed in the order mentioned in the embodiment, or may be different from the order in the embodiment, or several steps may be performed simultaneously.

Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus, and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that execution of the instructions via the processor of the computer or other programmable data processing apparatus enables Implementation of the functions/actions specified in one or more blocks of a flowchart and/or block diagram. Such a processor may be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It will also be understood that each block in the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can also be implemented by special purpose hardware that performs the specified functions or actions, or can be implemented by special purpose hardware and A combination of computer instructions.

The above are only specific implementations of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, modules and units can be referred to the foregoing method embodiments. The corresponding process will not be described again here. It should be understood that the protection scope of the present application is not limited thereto. Any person familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and these modifications or substitutions should be covered. within the protection scope of this application.

Claims (11)

1. A method for determining outgoing call rate, characterized in that the method includes: Obtain the historical incoming call volume of the customer service system at the first moment; Enter the historical incoming call volume into a differential autoregressive moving average model, and predict the first incoming call volume in the next period of the first moment through the differential autoregressive moving average model; According to the first incoming call volume, the first outgoing call rate in the next period is determined. 2. The method for determining the outgoing call rate according to claim 1, characterized in that the historical incoming call volume is input into a differential autoregressive moving average model, and the first incoming call is predicted by the differential autoregressive moving average model. Before measuring, the method further includes: Obtain the autoregressive order and moving average order of the customer service system; Determine an autoregressive model based on the historical incoming call volume and the autoregressive order; Determine a moving average model based on the historical incoming call volume and the moving average order; The differential autoregressive moving average model is obtained by merging the autoregressive model and the moving average model. 3. The outgoing call rate determination method according to claim 2, characterized in that the autoregressive model is: The moving average model is: The differential autoregressive moving average model is: Among them, μ ₁ is the first constant term coefficient, y _t1 is the incoming call volume predicted by the autoregressive model, ∈ _t1 is the error value of the autoregressive model, μ ₂ is the second constant term coefficient, and y _t2 is the incoming call volume predicted by the moving average model. , ∈ _t2 is the moving average model error value, y _t is the first incoming call volume, μ is the constant term coefficient, p is the autoregressive order, q is the moving average order, γ _i is the autocorrelation coefficient, y _ti is the history For the incoming call volume in the tith period, ∈t is the current error value, θ _i is the correlation coefficient of the moving average model, and ∈ti is the error value in the tith period. 4. The method for determining the outgoing call rate according to claim 1, wherein determining the first outgoing call rate in the next period according to the first incoming call volume includes: Obtain the number of target agents at the first moment, the number of idle target agents at the first moment, and the average service time of the target agents in the previous period. The target agents include mixed-signed agents and agents that only handle incoming calls. Mixed-signed agents An agent is an agent who handles both inbound and outbound calls; Enter the target number of agents at the first moment, the target number of idle agents at the first moment, the average service time of the target agents in the previous period and the first incoming call volume into the pre-built first model , obtain the amount of outgoing calls at the second moment, which is any moment in the next period; The first exhalation rate is determined based on the amount to be exhaled. 5. The method for determining the outgoing call rate according to claim 1, wherein determining the first outgoing call rate in the next period according to the first incoming call volume includes: Determine the target adjustment coefficient according to the first call loss rate of the customer service system in the previous cycle; The first outgoing call rate is determined based on the first incoming call volume and the target adjustment coefficient. 6. The method for determining the outgoing call rate according to claim 5, characterized in that determining the target adjustment coefficient according to the first call loss rate of the customer service system in the previous period includes: Get the historical adjustment coefficient; When the first call loss rate is greater than the maximum call loss rate threshold, reduce the historical adjustment coefficient according to a preset proportion according to the target number of seats to obtain the target adjustment coefficient; In the case where the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold, based on the number of target agents and the average idleness of the target agents in the previous period, time, the historical adjustment coefficient is increased according to a preset proportion to obtain the target adjustment coefficient. 7. The method for determining the outbound call rate according to claim 5, characterized in that determining the target adjustment coefficient according to the first call loss rate of the customer service system in the previous cycle includes: When the customer service system meets the rate adjustment conditions, determine the target adjustment coefficient based on the first call loss rate of the customer service system in the previous cycle; The rate adjustment conditions include at least one of the following: The duration for which the customer service system activates the outbound call task is greater than or equal to the first duration threshold; The first moment is not within the adjustment observation period; The first call loss rate is greater than the maximum call loss rate threshold, or the first call loss rate is less than the minimum call loss rate threshold and the first average idle time is greater than the average idle time threshold. 8. An exhalation rate determining device, characterized in that the device includes: The acquisition module is used to obtain the historical incoming calls of the customer service system at the first moment; An input module configured to input the historical incoming call volume into a differential autoregressive moving average model, and predict the first incoming call volume in the next period of the first moment through the differential autoregressive moving average model; Determining module, configured to determine the first outgoing call rate in the next period according to the first incoming call volume. 9. An outgoing call rate determining device, characterized in that the outgoing call rate determining device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for determining the outgoing call rate according to any one of claims 1-7 is implemented. 10. A computer storage medium, characterized in that computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by a processor, the outgoing call rate as claimed in any one of claims 1-7 is achieved. Determine the method. 11. A computer program product, characterized in that the computer program product includes computer program instructions, and when the computer program instructions are executed by a processor, the method for determining the outgoing call rate according to any one of claims 1-7 is implemented.