Outbound call control method and device

Abstract

An embodiment of the present application provides an outbound call control method and device, the method comprising: pre-configuring corresponding outbound call number determination methods for different target outbound call services; in the process of determining the outbound call number, utilizing the outbound call number determination method corresponding to the target outbound call service, determining the target outbound call number based on two dimensions of data, namely, agent dimension data and customer dimension data; that is, in the application scenario of predictive outbound calls, combining the differences of different outbound call services, configuring corresponding outbound call number determination methods for different outbound call services in a targeted manner, thereby improving the accuracy of the target outbound call number, so that the number of currently connected customers and the currently available number of seats will not deviate too much, thereby achieving the effect of balancing the supply and demand of seats. In this way, since the number of currently connected customers is equivalent to the currently available number of seats, not only can the idle seats due to too few numbers being sent be avoided, but also the problem of customer line overflow due to too many numbers being sent can be avoided.

Description

Technical Field

[0001] The present application relates to the field of outbound call center communication technology, and in particular to an outbound call control method and device. Background Art

[0002] At present, with the rapid development of Internet technology and voice network communication technology, not only is the volume of inbound services handled by agents, such as customer information inquiries, consultations, and complaints, relatively large, but the volume of outbound services handled by agents, such as customer return visits, satisfaction surveys, business promotions, and telephone collections, is also increasing. Based on this, in order to improve the service efficiency of agents, the call center system can automatically assign incoming or outgoing calls to customer service personnel with corresponding skills for processing, so as to realize automatic and flexible processing of a large number of various incoming and outgoing telephone services and services.

[0003] However, in actual application, in order to further improve the service efficiency of agents, predictive outbound calling technology came into being. Predictive outbound calling is a type of batch outbound calling in call centers. This outbound dialing method can effectively filter out invalid numbers and immediately assign connected calls to agents. Agents can communicate with customers as soon as possible, greatly improving work efficiency. Specifically, the predictive outbound calling algorithm is used each time to automatically determine the number of numbers to be sent for the next outbound call, automatically send the numbers in batches to the customer's mobile phone, and then assign the connected calls to idle agents. However, the accuracy of determining the number of numbers to be sent for the next outbound call in the existing technology is low. There are problems such as idle ready agents due to too few numbers sent, or excessive customer line overflow due to too many numbers sent (that is, the customer has answered the call, but there is no agent to serve him). Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide an outbound call control method and device, which can improve the accuracy of the target outbound call number delivery, so that the number of customers currently connected and the number of currently available seats will not deviate too much, thereby achieving the effect of balancing the supply and demand of seats. In this way, since the number of customers currently connected is equivalent to the number of currently available seats, it can not only avoid the idleness of ready seats due to too few numbers delivered, but also avoid the problem of customer line overflow due to too many numbers delivered.

[0005] In order to implement the above technical solution, the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides an outbound call control method, the method comprising:

[0007] Determining a method for determining the number of outbound calls corresponding to a target outbound calling service; and obtaining agent dimension data and customer dimension data; the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound calling service;

[0008] Determining a target outbound call volume based on the outbound call volume determination method, the agent dimension data, and the customer dimension data;

[0009] Make outbound calls to M client terminals, and assign the connected client terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number.

[0010] In a second aspect, an embodiment of the present application provides an outbound call control device, the device comprising:

[0011] An information acquisition module is configured to determine a method for determining the number of outbound calls corresponding to a target outbound service; and to obtain agent dimension data and customer dimension data; the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound service;

[0012] a number delivery quantity determination module, configured to determine a target number of outbound calls based on the outbound number delivery quantity determination method, the agent dimension data, and the customer dimension data;

[0013] The outbound call control module is used to make outbound calls to M customer terminals and allocate the connected customer terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number.

[0014] In a third aspect, an embodiment of the present application provides an outbound call control device, the device comprising:

[0015] A processor; and a memory arranged to store computer executable instructions, the executable instructions being configured to be executed by the processor, the executable instructions comprising instructions for executing the steps in the method as described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a storage medium, wherein the storage medium is used to store computer-executable instructions, and the executable instructions enable a computer to execute the steps in the method described in the first aspect.

[0017] It can be seen that in the embodiment of the present application, corresponding outbound call delivery number determination methods (i.e., predictive outbound call algorithms) are pre-configured for different target outbound call services, wherein the values ​​of multiple parameter items in the outbound call delivery number determination methods corresponding to different target outbound call services may be different, and are determined in a targeted manner based on the historical outbound call data of the target outbound call service; based on this, in the application scenario of predictive outbound calling, in the process of determining the outbound call delivery number, the outbound call delivery number determination method corresponding to the target outbound call service is used to determine the target outbound call delivery number based on the two dimensions of agent dimension data and customer dimension data. That is, in the predicted outbound call application scenario, combined with the differences of different outbound call services, corresponding methods for determining the number of outbound call numbers to be delivered are configured for different outbound call services in a targeted manner, thereby improving the accuracy of the target number of outbound call numbers to be delivered, so that the number of currently connected customers and the currently available number of seats will not deviate too much, thereby achieving the effect of balancing the supply and demand of seats. In this way, since the currently connected number of customers is equivalent to the currently available number of seats, not only can the problem of idle ready seats due to too few numbers delivered be avoided, but also the problem of customer line overflow (that is, the customer’s call is connected, but there is no agent to serve him) due to too many numbers delivered can be avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in one or more of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A schematic diagram of a first flow chart of the outbound call control method provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the first implementation principle of the outbound call control method provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of a second implementation principle of the outbound call control method provided in an embodiment of the present application;

[0022] Figure 4 A schematic diagram of a third implementation principle of the outbound call control method provided in an embodiment of the present application;

[0023] Figure 5 A second flow chart of the outbound call control method provided in an embodiment of the present application;

[0024] Figure 6 A schematic diagram illustrating the implementation principle of the parameter configuration process of the predictive outbound call algorithm in the outbound call control method provided in an embodiment of the present application;

[0025] Figure 7 A schematic diagram of the module composition of the outbound call control device provided in an embodiment of the present application;

[0026] Figure 8 A schematic diagram of the structure of the outbound call control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions in one or more of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of one or more embodiments of the present application, rather than all embodiments. Based on one or more embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0028] It should be noted that, in the absence of conflict, one or more embodiments and features in the embodiments of the present application may be combined with each other. The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] One or more embodiments of the present application provide an outbound call control method and device, taking into account that there are certain differences in influencing factors such as call connection rate and average call duration for different outbound call services, that is, different average call durations will affect the number of idle ready seats, and different call connection rates will affect the number of connected clients. If a unified predictive outbound call algorithm is used to calculate the target outbound call delivery volume, then the accuracy of the target outbound call delivery volume is relatively low, and there is bound to be a problem of customer line overflow due to too many numbers being delivered, or agents being idle due to the delivery process. That is, if the accuracy of the target outbound call delivery volume is low, it is impossible to take into account both agent utilization and user experience at the same time. Based on the above problem, the present technical solution pre-configures corresponding outbound call delivery volume determination methods (that is, predictive outbound call algorithms) for different target outbound call services, wherein the values ​​of multiple parameter items in the outbound call delivery volume determination method corresponding to different target outbound call services may be different, which is based on the target outbound call service. Based on this, in the application scenario of predictive outbound calling, in the process of determining the outbound call delivery volume, the outbound call delivery volume determination method corresponding to the target outbound calling business is used to determine the target outbound call delivery volume based on the two dimensions of agent dimension data and customer dimension data. That is, in the predicted outbound calling application scenario, combined with the differences of different outbound calling businesses, the corresponding outbound call delivery volume determination method is configured for different outbound calling businesses in a targeted manner, thereby improving the accuracy of the target outbound call delivery volume, so that the current number of connected customers and the current number of available seats will not deviate too much, thereby achieving the effect of balancing the supply and demand of agents. In this way, since the current number of connected customers is equivalent to the current number of available seats, it can not only avoid the problem of idle ready agents due to too few numbers being delivered, thereby improving the agent utilization rate, but also avoid the problem of customer line overflow due to too many numbers being delivered, thereby improving the user experience, thereby achieving both the agent utilization rate and the user experience.

[0030] Specifically, Figure 1 A first flow chart of the outbound call control method provided in one or more embodiments of the present application is provided. Figure 1 The method in can be executed by a preset server of a call center, such as Figure 1 As shown, the method comprises at least the following steps:

[0031] S102, determining a method for determining the number of outbound calls corresponding to the target outbound service; and obtaining agent dimension data and customer dimension data; wherein the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound service;

[0032] The target outbound call service may be a first-category outbound call service. Specifically, the outbound call service may be divided according to the service type. For example, the target outbound call service may be any one of a telephone collection service, a telephone push service, and a telephone return service. Furthermore, corresponding methods for determining the number of outbound call transmissions are configured for different first-category outbound call services.

[0033] Furthermore, considering that factors such as customer connection rate and average call duration may vary for different groups of people under the same first-category outbound call service, the first-category outbound call service can be further refined. Specifically, the first-category outbound call service can be further refined according to the agent skill group. The above-mentioned target outbound call service can also be the second-category outbound call service. For example, the above-mentioned target outbound call service can be the premium customer collection service (i.e., loan collection service for VIP users) that is in charge of the first agent skill group in the telephone collection service, the premium customer collection service (i.e., loan collection service for VIP users) that is in charge of the second agent skill group in the telephone collection service, and the premium customer collection service (i.e., loan collection service for VIP users) that is in charge of the second agent skill group in the telephone collection service. The above-mentioned target outbound call service can also be any one of the common customer collection services in the telephone push service that the first agent skill group is responsible for (i.e., pushing target products to potential users), or any one of the lost customer push services that the second agent skill group is responsible for in the telephone push service (i.e., pushing target products to lost users again). Furthermore, corresponding methods for determining the number of outbound calls sent are respectively configured for different second-category outbound call services under the same first-category outbound call service (i.e., different agent skill groups under the same first-category outbound call service can correspond to different methods for determining the number of outbound calls sent).

[0034] In addition, it should be noted that the above-mentioned target outbound call business can also be divided in other ways. The specific division basis of the target outbound call business can be to consider the differences in influencing factors such as customer connection rate and average call duration, so as to configure a more suitable predictive outbound call algorithm for the target outbound call business in a targeted manner to ensure the final target outbound call number. Therefore, how the target outbound call business is divided can be based on actual needs, and this application does not limit this.

[0035] Specifically, before the predictive outbound call is executed, a corresponding method for determining the number of outbound calls (i.e., a predictive outbound call algorithm) is pre-configured for each target outbound call service; wherein, the method for determining the number of outbound calls may include preset key parameter items, and the preset key parameter items include at least one of a balanced agent utilization rate, a first correction coefficient, a second correction coefficient, and a method for slowing down the number delivery; in specific implementation, the value of each preset key parameter item may be set by the user based on the historical outbound call data of the target outbound call service, or may be automatically set by the system based on the historical outbound call data of the target outbound call service.

[0036] Specifically, during the execution of the predictive outbound call, the outbound call delivery logic is triggered and executed according to the preset time interval, that is, the predictive outbound call algorithm is used to calculate the next outbound call delivery number (that is, the target outbound call delivery number); in the specific implementation, if the current time reaches the outbound call delivery trigger time, the outbound call delivery number determination method corresponding to the target outbound call service is first determined, and the seat dimension data and customer dimension data are obtained, and then the following step S104 is executed; wherein, the seat dimension data and customer dimension data can be obtained by other data processing modules in the outbound call system based on real-time seat status information and customer The above-mentioned agent dimension data is automatically obtained by counting the customer status information. The above-mentioned agent dimension data may include at least one of the number of agents in call and the total number of online agents in the agent terminal group corresponding to the target outbound call service (that is, the number of agents in the agent skill group responsible for the target outbound call service whose working status is online, that is, including the number of agents in call and the number of idle and ready agents, but excluding the number of agents in offline or short break status); the above-mentioned customer dimension data may include at least one of the number of customer phones in ringing state, the total number of numbers sent in a preset historical time period, and the total number of customer calls in a preset historical time period.

[0037] S104, determining a target outbound call volume based on the above-mentioned outbound call volume determination method, agent dimension data, and customer dimension data;

[0038] Specifically, the above-mentioned method for determining the outbound call volume may include a target call volume calculation formula, wherein a first implementation method is that the target call volume calculation formulas corresponding to different target outbound call services may be different, that is, different call volume calculation formulas are set for different target outbound call services; a second implementation method is that the target call volume calculation formulas corresponding to different target outbound call services may be the same, and the target call volume calculation formulas corresponding to different target outbound call services are all preset call volume calculation formulas, that is, the same preset call volume calculation formula is used for different target outbound call services, and the values ​​of multiple parameters in the preset call volume calculation formula may be different, and are determined in a targeted manner based on the historical outbound call data of the target outbound call service.

[0039] For the second implementation, the multiple parameters in the above-mentioned preset number delivery calculation formula include the number of idle ready agents, the customer connection rate, the number of customers waiting for connection, and at least one correction factor. That is, the value of the at least one correction factor can be different for different target outbound call services. The number of idle ready agents is determined based on agent dimension data, and the customer connection rate and the number of customers waiting for connection are determined based on customer dimension data.

[0040] Specifically, the above-mentioned preset number delivery calculation formula may include a first summation item and a second summation item. The first summation item may include the quotient of the number of idle ready seats and the customer connection rate, and the second summation item may include the product of the number of waiting customers connected and -1. Furthermore, considering that not all customer calls in the number of waiting customers are connected, only when the customer is connected will an agent be assigned to it, and in order to improve the dynamic adjustment flexibility of the outbound call delivery quantity, at least one correction coefficient may be introduced. For example, a correction coefficient (i.e., a target correction coefficient) may be introduced. The first summation item may be the quotient of the number of idle ready seats and the customer connection rate, and the second summation item may be the product of the number of waiting customers connected and the target correction coefficient, and then multiplied by -1. The preset number delivery calculation formula may be expressed as N=( Number of idle ready seats / customer connection rate - number of waiting customers connected * target correction coefficient); further, considering that only by correcting the number of waiting customers connected, there may be a situation where the target correction coefficient is adjusted to the maximum value, and the outbound call number calculated using the preset number delivery calculation formula is still relatively large. Therefore, two correction coefficients are introduced (i.e., the first correction coefficient and the second correction coefficient). The first summation item can be the product of the number of idle ready seats and the first correction coefficient, and then divided by the customer connection rate. The second summation item can be the product of the number of waiting customers connected and the second correction coefficient, and then multiplied by -1. That is, the preset number delivery calculation formula can be expressed as N = (number of idle ready seats * first correction coefficient / customer connection rate - number of waiting customers connected * second correction coefficient).

[0041] S106: Make outbound calls to M client terminals, and assign the connected client terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number.

[0042] Specifically, after determining the target outbound call volume, M phone numbers are selected from the waiting outbound call list, and calls are made to the corresponding clients in batches based on the phone numbers. The idle agent terminals (i.e., the currently ready agent terminals) are determined in the agent terminal group (i.e., the agent skill group) corresponding to the target outbound call service, and then the connected customer terminals are assigned to the idle agent terminals.

[0043] That is to say, for the application scenario of predictive outbound calling (i.e., first use the outbound dialing method to make batch outbound calls, and then assign the connected calls to the agents), by pre-configuring the corresponding predictive outbound calling algorithm for each target outbound calling business (such as any first-category outbound calling business or second-category outbound calling business), then, during the predictive outbound calling process, based on the real-time agent status information and customer status information, determine the customer dimension data and agent dimension data; then, using the predictive outbound calling algorithm corresponding to the target outbound calling business that the currently connected agent skill group is responsible for, based on the customer dimension data and agent dimension data, determine the number of numbers to be delivered for the next outbound call. This can improve the accuracy of the number of numbers to be delivered for the outbound calls, and fundamentally ensure the supply and demand balance between the currently ready agents and the currently connected customers.

[0044] In an embodiment of the present application, corresponding methods for determining the number of outbound call deliveries (i.e., a predictive outbound call algorithm) are pre-configured for different target outbound call services. The values ​​of multiple parameter items in the methods for determining the number of outbound call deliveries corresponding to different target outbound call services may be different, and are specifically determined based on the historical outbound call data of the target outbound call service. Therefore, in the application scenario of predictive outbound calling, in the process of determining the number of outbound call deliveries, the method for determining the number of outbound call deliveries corresponding to the target outbound call service is utilized to determine the target number of outbound call deliveries based on data from two dimensions, namely, agent dimension data and customer dimension data. That is, in the application scenario of predictive outbound calling, corresponding methods for determining the number of outbound call deliveries are specifically configured for different outbound call services, taking into account the differences between different outbound call services. This improves the accuracy of the target number of outbound call deliveries, ensures that the number of currently connected customers does not deviate too much from the number of currently available agents, and thereby achieves a balance between agent supply and demand. In this way, since the number of currently connected customers is equivalent to the number of currently available agents, not only can the problem of idle ready agents due to too few delivered numbers be avoided, but also the problem of customer line overflow due to too many delivered numbers be avoided.

[0045] It should be noted that the number M of actual outbound call numbers each time (i.e., the number of telephone numbers to be called out in batches) can be equal to the target outbound call number number N, or can be less than the target outbound call number number N. The following detailed explanation is given using the example of the actual number M of outbound call numbers being equal to the target outbound call number number N, but this does not limit the scope of protection of this application; that is, after determining the target outbound call number number, outbound calls can be made directly to N customer terminals, or the difference P between the target outbound call number number and a preset value (i.e., an integer greater than 0) can be used as the actual outbound call number number, and outbound calls can be made to P customer terminals, i.e., M=N or P.

[0046] In a specific embodiment, Figure 2 As shown in FIG, a specific implementation process of an outbound call control method is given, which specifically includes:

[0047] When the outbound call delivery trigger time is reached at the current moment, a method for determining the number of outbound calls corresponding to the target outbound call service is determined based on a pre-stored predictive outbound call algorithm, and agent dimension data and customer dimension data are obtained. Specifically, during the execution of the predictive outbound call, the outbound call delivery can be performed according to a preset delivery frequency, for example, once every 5 seconds. The pre-stored predictive outbound call algorithm may include a predictive outbound call algorithm corresponding to each agent skill group. The predictive outbound call algorithm corresponding to the target agent skill group is the method for determining the number of outbound calls corresponding to the target outbound call service for which the target agent skill group is responsible.

[0048] Based on the above seat dimension data, determine the number of idle and ready seats;

[0049] Based on the above customer dimension data, determine the customer connection rate and the number of customers waiting to be connected;

[0050] Based on the above-mentioned outbound call volume determination method, the number of idle ready seats, the customer connection rate, and the number of customers waiting to be connected, the target outbound call volume is determined; the value of the target outbound call volume can be N;

[0051] An outbound call is made to N customer terminals (ie, customer terminals 1 to N), and the connected customer terminal i is assigned to an idle agent terminal j in the agent skill group corresponding to the target outbound call service.

[0052] In particular, with respect to the process of determining the target outbound call delivery volume, the above-mentioned outbound call delivery volume determination method may include multiple preset key parameter items, and the multiple preset key parameter items may include a balanced seat utilization rate, a first correction coefficient, a second correction coefficient, and a method for slowing down the delivery of numbers;

[0053] Correspondingly, the above S104 determines the target outbound call volume based on the above outbound call volume determination method, the agent dimension data, and the customer dimension data, specifically including:

[0054] Step A1: Based on the above-mentioned agent dimension data, determine the current agent utilization rate and the number of idle ready agents; and based on the above-mentioned customer dimension data, determine the customer connection rate and the number of customers waiting to be connected;

[0055] Specifically, the above-mentioned agent dimension data may include the number of agents in active calls and the total number of online agents in the agent terminal group (i.e., agent skill group) corresponding to the target outbound call service. Therefore, the current agent utilization rate can be obtained based on the number of agents in active calls and the total number of online agents. The number of idle and ready agents can be obtained based on the difference between the total number of online agents and the number of agents in active calls.

[0056] Specifically, the above-mentioned customer dimension data may include the number of customer phones in ringing state, the total number of numbers sent in a preset historical time period, and the total number of customers connected in the preset historical time period. Therefore, based on the total number of numbers sent in the preset historical time period and the total number of customers connected in the preset historical time period, the customer connection rate (that is, the customer connection rate in the preset historical time period, for example, the customer connection rate in the past 5 minutes or 10 minutes) can be obtained; based on the number of customer phones in the ringing state, the number of customers waiting to be connected can be determined; among them, the number of customers waiting to be connected may refer to the number of customer phones that have been dialed but not connected, that is, the number of customer phones in the ringing state.

[0057] Step A2: If the current agent utilization is less than the equilibrium agent utilization, then determining a target outbound call volume based on the number of available ready agents, the first correction factor, the customer connection rate, the number of waiting customers, and the second correction factor.

[0058] Specifically, after determining the current agent utilization rate, the current agent utilization rate is compared with the equilibrium agent utilization rate. If the current agent utilization rate is less than the equilibrium agent utilization rate, a preset outbound call volume calculation formula can be used to calculate the target outbound call volume based on the number of idle ready agents, the first correction coefficient, the customer connection rate, the number of waiting customers, and the second correction coefficient.

[0059] It should be noted that the above-mentioned preset key parameter items may include any one of the first correction coefficient and the second correction coefficient, or may include the first correction coefficient and the second correction coefficient; wherein the values ​​of the first correction coefficient and the second correction coefficient belong to the range of 0 to 100%.

[0060] In specific implementation, taking the above-mentioned preset outbound call volume calculation formula N = (number of idle ready seats * first correction coefficient / customer connection rate - number of waiting customers connected * second correction coefficient) as an example, since the lower the current seat utilization rate, the larger the number of idle ready seats, the larger the calculated target outbound call volume will be, thereby increasing the number of currently connected customer terminals.

[0061] Among them, the above-mentioned number of waiting customers for connection is the cumulative number of calls that have been dialed but not connected since the start of the predicted outbound call to the current moment. Since a part of the waiting customers will be assigned seats immediately after the connection (that is, this part needs to occupy a certain number of idle ready seats), and another part of the customers hang up during the ringing period or hang up automatically after the ringing ends (that is, this part does not need to occupy idle ready seats), the number of waiting customers for connection can be corrected by the second correction coefficient, so that the product of the number of waiting customers for connection and the second correction coefficient is closer to the actual number of customers connected; on the other hand, since the initial setting values ​​of the first correction coefficient and the second correction coefficient are pre-configured based on the historical outbound call data of the target outbound call business (such as historical customer connection rate, historical average call duration), however, in the process of predicting the execution of the outbound call, there may be certain fluctuations in influencing factors such as real-time customer connection rate, average call duration, etc., therefore, it is necessary to speed up the number delivery (for example, when the customer In the case of a sudden drop in the connection rate or a shortening of the average call duration, the seat utilization rate is low. When the number is assigned next time, more customer calls need to be made to reduce the number of idle seats, that is, the number of numbers assigned for the next outbound call is increased), or the number assignment needs to be slowed down (for example, when the customer connection rate increases sharply or the average call duration becomes longer, the seat utilization rate is relatively high. When the number is assigned next time, fewer customer calls need to be made to reduce the number of connected calls, that is, the number of numbers assigned for the next outbound call is reduced). At this time, the speed of outbound call assignment can be controlled by adjusting the size of at least one of the first correction coefficient and the second correction coefficient; for example, increasing the second correction coefficient increases the product of the number of waiting customers connected and the second correction coefficient, and the outbound call assignment is controlled to be slower. Conversely, decreasing the second correction coefficient controls the outbound call assignment to be faster. For another example, decreasing the first correction coefficient reduces the product of the number of idle and ready agents and the first correction coefficient, and the outbound call assignment is controlled to be slower. Conversely, increasing the first correction coefficient controls the outbound call assignment to be faster.

[0062] Among them, the number of idle ready seats refers to the number of seats that can immediately serve customers. Since not all customers will answer the phone in each outbound call, only the customer terminals that are connected will be assigned seats for them, that is, the influencing factor of customer connection rate needs to be considered. Therefore, the first summation item includes the quotient of the number of idle ready seats and the customer connection rate (that is, the converted number of idle seats). In other words, considering the customer connection rate, it is equivalent to expanding the number of idle ready seats according to the customer connection rate to expand the number of outbound calls; further, considering that the customer connection rate is based on the customer connection data in the preset historical time period, it is different from the actual There may be a certain deviation in the international connection rate. Therefore, the converted number of idle seats can be corrected by the first correction coefficient to improve the accuracy of the converted number of idle seats, thereby improving the accuracy of the target outbound call delivery number. On the other hand, in the case where the outbound call delivery cannot be slowed down by adjusting the size of the second correction coefficient, for example, when the second correction coefficient is increased to 100%, but the current seat utilization rate is still too high and the current seat utilization rate cannot be controlled within a certain range, the speed of the outbound call delivery can be controlled by adjusting the size of the first correction coefficient. By reducing the first correction coefficient, the above-mentioned first summation item becomes smaller, and the outbound call delivery is controlled to be slower. Conversely, the outbound call delivery is controlled to be faster.

[0063] That is to say, in the embodiment of the present application, by adding the first correction coefficient and the second correction coefficient, on the one hand, in the process of predicting the execution of outbound calls, if the actual outbound call data does not deviate much from the historical outbound call data and the initial setting values ​​are relatively accurate, the initial setting values ​​of the first correction coefficient and the second correction coefficient will remain unchanged, which can realize the correction of the outbound call number delivery from the agent dimension and the customer dimension; on the other hand, in the process of predicting the execution of outbound calls, once the actual outbound call data deviates greatly from the historical outbound call data or the initial setting value is not accurate enough, the speed of the outbound call delivery can be controlled by adjusting the size of at least one of the first correction coefficient and the second correction coefficient, thereby dynamically avoiding the problem of idle agents or customer line overflow.

[0064] It should be noted that the above-mentioned slowdown in outbound call delivery does not mean a reduction in the frequency of delivery. Rather, it means that while the frequency of delivery remains unchanged, the second correction coefficient is increased or the initial setting value of the first correction coefficient is reduced to reduce the amount of outbound call delivery calculated using the above-mentioned preset number delivery calculation formula, thereby achieving the purpose of slowing down the delivery of numbers and preventing customer line overflow, and vice versa.

[0065] Step A3: If the current agent utilization rate is greater than or equal to the equilibrium agent utilization rate, a target outbound call delivery volume is determined based on the slow delivery method.

[0066] Specifically, after determining the current agent utilization rate, the current agent utilization rate is compared with the balanced agent utilization rate. If the current agent utilization rate is greater than or equal to the balanced agent utilization rate, the target outbound call delivery volume can be determined based on the slowdown delivery method configured in the outbound call delivery volume determination method corresponding to the target outbound call service; wherein, the slowdown delivery method may include stopping delivery or reducing the delivery volume; in specific implementation, if the slowdown delivery method is stopping delivery, the corresponding formula for calculating the slowdown delivery volume can be expressed as N=0; if the slowdown delivery method is reducing the delivery volume, the corresponding formula for calculating the slowdown delivery volume can be expressed as N=max(number of idle ready agents-number of waiting customers connected, 0), that is, if the number of idle ready agents is less than or equal to the number of waiting customers connected, the delivery of numbers is stopped; if the number of idle ready agents is greater than the number of waiting customers connected, the difference between the number of idle ready agents and the number of waiting customers connected is determined as the target outbound call delivery volume.

[0067] In the embodiment of the present application, for the process of determining the target outbound call delivery volume, a judgment condition of the maximum balanced seat utilization rate is introduced, that is, according to the relationship between the current seat utilization rate and the balanced seat utilization rate, it is decided to use the preset delivery volume calculation formula or the reduced delivery volume calculation formula to calculate the target outbound call delivery volume. Specifically, if the current seat utilization rate is less than the balanced seat utilization rate, the target outbound call delivery volume can be calculated based on the preset delivery volume calculation formula and the value of the parameter item configured in the outbound call delivery volume determination method corresponding to the target outbound call service; if the current seat utilization rate is greater than or equal to the balanced seat utilization rate, the reduced delivery volume corresponding to the reduced delivery method configured in the outbound call delivery volume determination method corresponding to the target outbound call service can be used. The number calculation formula is used to calculate the target outbound call number. In this way, the relationship between the current agent utilization rate (i.e. the proportion of agents in the current call) and the balanced agent utilization rate is combined to determine whether to start the slowdown in number delivery. Specifically, considering that the customer connection rate has been maintained near the upper limit of the preset connection rate range for a period of time, the number of customer connections has been continuously squeezed, resulting in the current agent utilization rate being greater than the maximum balanced agent utilization rate. If the number delivery continues according to the normal number delivery logic, it will inevitably lead to the problem of customer line overflow. Therefore, by introducing the judgment condition of the maximum balanced agent utilization rate, it is possible to further deal with the problem of customer line overflow caused by the number of customer connections continuously being at the upper limit during the outbound call delivery process.

[0068] In a specific embodiment, in the above Figure 2 On this basis, in the process of determining the target outbound call volume, the judgment condition of the maximum balanced agent utilization rate is introduced to decide whether to use the preset call volume calculation formula or the slowed call volume calculation formula to calculate the target outbound call volume; specifically, Figure 3As shown in FIG, a specific implementation process of an outbound call control method is given, which specifically includes:

[0069] When the outbound call delivery trigger time is reached at the current moment, the method for determining the outbound call delivery number corresponding to the target outbound call service is determined based on the pre-stored predictive outbound call algorithm, and the agent dimension data and customer dimension data are obtained;

[0070] Based on the above seat dimension data, determine the current seat utilization rate and the number of idle ready seats;

[0071] Based on the above customer dimension data, determine the customer connection rate and the number of customers waiting to be connected;

[0072] If the current agent utilization rate is less than the balanced agent utilization rate in the method for determining the number of outbound call numbers, the normal number delivery logic is executed. That is, the number of idle ready agents, the value of the first correction coefficient, the customer connection rate, the number of waiting customers, and the value of the second correction coefficient are substituted into the preset number delivery calculation formula to obtain the target number of outbound call numbers. The target number of outbound call numbers can be N.

[0073] If the current agent utilization rate is greater than or equal to the balanced agent utilization rate in the method for determining the number of outbound calls, the logic for slowing down the number delivery is executed. That is, the target number of outbound calls is determined based on the slowing down number delivery calculation formula corresponding to the slowing down number delivery method in the method for determining the number of outbound calls. The value of the target number of outbound calls may be N.

[0074] An outbound call is made to N customer terminals (ie, customer terminals 1 to N), and the connected customer terminal i is assigned to an idle agent terminal j in the agent skill group corresponding to the target outbound call service.

[0075] Furthermore, considering that if the current agent utilization rate is lower than the equilibrium agent utilization rate, there may also be a problem of customer line overflow if the number of outbound calls is too large. Therefore, the above-mentioned preset key parameters also include a maximum outbound call limit;

[0076] Correspondingly, the step A2 of determining the target outbound call volume based on the number of idle ready seats, the first correction coefficient, the customer connection rate, the number of waiting customers to be connected, and the second correction coefficient specifically includes:

[0077] Step A21, determining the initial outbound call delivery number based on the number of available ready seats, the first correction coefficient, the customer connection rate, the number of customers waiting to be connected, and the second correction coefficient;

[0078] In the process of determining the initial outbound call number quantity, the above step A21 specifically includes:

[0079] A211 determines the converted number of idle seats based on the number of idle ready seats and the customer connection rate. Furthermore, based on the converted number of idle seats and a first correction coefficient, determines the corrected number of idle seats. For details, see the calculation process of the first summation item above.

[0080] A212, based on the number of waiting customers and the second correction coefficient, determines the corrected number of waiting customers; for details, please refer to the calculation process of the second summation item.

[0081] A213, based on the above-mentioned corrected number of idle seats and the above-mentioned corrected number of waiting customers, determines the initial number of outbound call numbers.

[0082] Specifically, the above-mentioned preset formula for calculating the number of numbers sent is used to calculate the initial number of numbers sent for outbound calls based on the above-mentioned number of idle ready seats, the first correction coefficient, the customer connection rate, the number of customers waiting to be connected, and the second correction coefficient. Please refer to the specific implementation process in the above-mentioned step A2 and will not be repeated here.

[0083] Step A22, determining a target outbound call number based on the initial outbound call number and the maximum outbound call limit;

[0084] Specifically, if the above-mentioned initial outbound call sending quantity is greater than or equal to the above-mentioned maximum outbound call limit quantity, the above-mentioned maximum outbound call limit quantity will be determined as the target outbound call sending quantity; that is, when the outbound call sending quantity calculated using the preset sending quantity calculation formula is relatively large, the numbers will be sent according to the maximum outbound call limit quantity to avoid sending too many numbers due to sudden abnormalities, which will lead to the problem of customer line overflow.

[0085] Specifically, if the above-mentioned initial outbound call sending amount is less than the above-mentioned maximum outbound call limit, the above-mentioned initial outbound call sending amount will be determined as the target outbound call sending amount; that is, when the outbound call sending amount calculated using the preset sending amount calculation formula does not exceed the maximum outbound call limit, the outbound call sending amount will be calculated according to the initial outbound call sending amount calculated using the preset sending amount calculation formula.

[0086] In the embodiment of the present application, by configuring corresponding balanced agent utilization, maximum outbound call limit, slowdown number delivery method, first correction coefficient and second correction coefficient for different target outbound call services, it is possible to prevent agents from being idle or customer line overflow from multiple aspects and angles; and, in the process of predicting outbound call execution, it is also possible to dynamically adjust the value of at least one of the first correction coefficient and the second correction coefficient to timely adjust the speed of outbound call delivery, so that the agent utilization is controlled within a preset utilization range, thereby dynamically preventing agents from being idle or customer line overflow.

[0087] Furthermore, with respect to the specific implementation process of dynamically adjusting the value of at least one of the first correction coefficient and the second correction coefficient to timely adjust the speed of outbound call delivery so that the agent utilization rate is controlled within a preset utilization rate range, it is considered that the initial setting values ​​of the first correction coefficient and the second correction coefficient are pre-set based on historical outbound call data. However, in the actual outbound call delivery process, due to fluctuations in various influencing factors such as customer connection rate and call duration, as the number of outbound call delivery rounds increases, the agent utilization rate may be too high or too low. Therefore, the speed of outbound call delivery can be timely controlled by adjusting the value of at least one of the first correction coefficient and the second correction coefficient, thereby ensuring that the agent utilization rate is controlled within a preset utilization rate range. That is, the minimum value of the preset utilization rate range is the lower utilization limit value, which can be the difference between the balanced agent utilization rate and the first value a; the maximum value of the preset utilization rate range is the upper utilization limit value, which can be the sum of the balanced agent utilization rate and the second value b.

[0088] Specifically, in step A2, after determining the current agent utilization rate and the number of idle and ready agents based on the agent dimension data, and determining the customer connection rate and the number of customers waiting to be connected based on the customer dimension data, the process further includes:

[0089] Determining values ​​of the first correction coefficient and the second correction coefficient based on the current seat utilization rate; wherein the value of at least one of the first correction coefficient and the second correction coefficient is the sum of an initial setting value and a target adjustment value, and the target adjustment value is determined based on whether the current seat utilization rate is within a preset utilization rate range; the target adjustment value can be positive or negative, the minimum value of the preset utilization rate range is the difference between the balanced seat utilization rate and the first value, and the maximum value of the preset utilization rate range is the sum of the balanced seat utilization rate and the second value;

[0090] Specifically, if the current balanced agent utilization rate is within the preset utilization rate range, the target adjustment value is the same as the target adjustment value determined by the previous round of calculation of the number sending volume, that is, when calculating the current off-round number sending volume, the values ​​of the first correction coefficient and the second correction coefficient are not adjusted; if the current balanced agent utilization rate is not within the preset utilization rate range, the target adjustment value is obtained by adding or subtracting a specified value on the basis of the target adjustment value determined by the previous round of calculation of the number sending volume, that is, when calculating the current off-round number sending volume, the value of at least one of the first correction coefficient and the second correction coefficient is increased or subtracted. Less adjustment is made to control the speed of the next outbound call transmission; wherein, the specified value can be a fixed value, or can be determined based on the utilization difference between the current balanced seat utilization and the minimum value or maximum value in the preset utilization range; for example, if the current balanced seat utilization is less than the minimum value in the preset utilization range and the utilization difference between the two is larger, or if the current balanced seat utilization is greater than the maximum value in the preset utilization range and the utilization difference between the two is larger, then the corresponding specified value is larger, that is, the adjustment range of at least one of the first correction coefficient and the second correction coefficient is larger.

[0091] The current balanced seat utilization rate is not within the preset utilization rate range, which includes the current seat utilization rate being greater than the upper utilization rate limit, or the current seat utilization rate being less than the lower utilization rate limit. For example, if the balanced seat utilization rate is 75%, the first value a is 10%, and the second value b is 15%, then the current seat utilization rate needs to be controlled to be within the preset utilization rate range of (65%, 90%).

[0092] Specifically, if the current seat utilization rate is less than the utilization lower limit (such as less than 65%), the value of at least one of the first correction coefficient and the second correction coefficient is adjusted, and the above step A2 is executed; if the current seat utilization rate is in the first utilization rate range (such as the range of 65% to 75%), the above step A2 is directly executed; if the current seat utilization rate is in the second utilization rate range (such as the range of 75% to 90%), the above step A3 is executed; if the current seat utilization rate is greater than the utilization upper limit (such as greater than 90%), the value of at least one of the first correction coefficient and the second correction coefficient is adjusted, and the above step A3 is executed.

[0093] That is to say, if the current seat utilization rate is greater than the equilibrium seat utilization rate (such as in the range of 75% and 100%), the number delivery amount is reduced by slowing down the number delivery; and if the current seat utilization rate is in the second utilization rate range (such as in the range of 75% to 90%), that is, the current seat utilization rate is in the preset utilization rate range, then the value of at least one of the first correction coefficient and the second correction coefficient is not adjusted, and only the number delivery is reduced by slowing down the number delivery; if the current seat utilization rate is greater than the utilization rate upper limit value (such as greater than 90%), that is, the current seat utilization rate is not in the preset utilization rate range and the current seat utilization rate is relatively high, then it is necessary to adjust the value of at least one of the first correction coefficient and the second correction coefficient, and use slowing down the number delivery to reduce the number delivery amount.

[0094] During specific implementation, for the specific implementation process of adjusting the value of at least one of the first correction coefficient and the second correction coefficient, one correction coefficient can be fixed first, and the value of the other correction coefficient can be adjusted; for example, the first correction coefficient is fixed first, and the second correction coefficient is adjusted first to control the speed of number transmission; for another example, the second correction coefficient is fixed first, and the first correction coefficient is adjusted first to control the speed of number transmission; wherein, considering that the first summation item involves the customer connection rate and serves as a divisor, adjusting the first correction coefficient will make the calculated value more jumpy. Based on this, it is preferred to fix the first correction coefficient first, and adjust the second correction coefficient first. If the second If the correction coefficient is adjusted to its maximum value (e.g., 100%), but the current agent utilization is still greater than the maximum value in the preset utilization range, the agent utilization is still relatively high. Alternatively, if the second correction coefficient is adjusted to its minimum value, but the current agent utilization is still less than the minimum value in the preset utilization range, the agent utilization is still relatively low, and the agent utilization cannot be controlled to be within the preset utilization range simply by adjusting the second correction coefficient. In this case, the first correction coefficient can be further adjusted to improve the controllability of the outbound call delivery speed while ensuring the adjustment accuracy of the outbound call delivery volume, so that the agent utilization is controlled within the preset utilization range.

[0095] Specifically, if the current seat utilization rate is greater than the maximum value in the preset utilization rate range (i.e., the utilization rate upper limit) and the second correction coefficient is less than the maximum correction coefficient value, the first correction coefficient is set to the initial setting value, and the second correction coefficient is set to min (the sum of the initial setting value and the target adjustment value, or the maximum correction coefficient value); if the current seat utilization rate is greater than the maximum value in the preset utilization rate range and the second correction coefficient is equal to the maximum correction coefficient value, the first correction coefficient is set to the sum of the initial setting value and the target adjustment value, and the second correction coefficient is set to the maximum correction coefficient value (i.e., the second correction coefficient is adjusted first; if the second correction coefficient has been adjusted to the maximum correction coefficient value, the first correction coefficient is adjusted to a smaller value instead). Correspondingly, if the current seat utilization rate is less than the minimum value in the preset utilization rate range (i.e., the lower limit of utilization rate) and the second correction coefficient is greater than the minimum value of correction coefficient, the value of the first correction coefficient is the initial setting value, and the value of the second correction coefficient is max (the sum of the initial setting value and the target adjustment value, the minimum value of correction coefficient); if the current seat utilization rate is less than the minimum value in the preset utilization rate range and the second correction coefficient is equal to the minimum value of correction coefficient, the value of the first correction coefficient is the sum of the initial setting value and the target adjustment value, and the value of the second correction coefficient is the minimum value of correction coefficient (i.e., the second correction coefficient is adjusted first, and if the second correction coefficient has been adjusted to the minimum value of correction coefficient, the first correction coefficient is increased instead).

[0096] Furthermore, still taking the example of the preset key parameter items including both the first correction coefficient and the second correction coefficient, considering that the initial setting values ​​of the above-mentioned first correction coefficient and the second correction coefficient are pre-configured based on the historical outbound call data of the target outbound call service (such as the historical customer connection rate within the first connection rate range), however, in the process of predicting the execution of the outbound call, there may be a situation where the real-time customer connection rate, average call duration and other influencing factors fluctuate greatly. For example, the customer connection rate is no longer within the first connection rate range. Based on this, considering whether the current utilization rate is within the preset utilization rate range, and also considering whether the current customer connection rate belongs to the first connection rate range, it is determined how to adjust the value of at least one of the first correction coefficient and the second correction coefficient, so as to more quickly control the speed of the number transfer, and further achieve more quickly and dynamically avoid the problem of idle agents or customer call overflow; specifically, in the above-mentioned step A2, after determining the current agent utilization rate and the number of idle and ready agents based on the above-mentioned agent dimension data; and determining the customer connection rate and the number of waiting customers to be connected based on the above-mentioned customer dimension data, it also includes:

[0097] Determine the values ​​of the first correction coefficient and the second correction coefficient based on the customer connection rate and the current agent utilization rate;

[0098] Among them, if the above-mentioned customer connection rate does not belong to the first connection rate interval, the value of at least one of the above-mentioned first correction coefficient and the second correction coefficient is the sum of the updated value and the target adjustment value, and the above-mentioned updated value is determined based on the second connection rate interval to which the above-mentioned customer connection rate belongs; if the above-mentioned customer connection rate belongs to the above-mentioned first connection rate interval, the value of at least one of the above-mentioned first correction coefficient and the second correction coefficient is the sum of the initial setting value and the target adjustment value, and the above-mentioned initial setting value is determined based on the above-mentioned first connection rate interval, and the above-mentioned target adjustment value is determined based on whether the current seat utilization rate is within the preset utilization rate interval; the above-mentioned target adjustment value can be positive or negative;

[0099] Specifically, if the current balanced agent utilization rate is within the preset utilization rate range, the target adjustment value is the same as the target adjustment value determined by the previous round of calculation of the number sending volume, that is, when calculating the current off-round number sending volume, the values ​​of the first correction coefficient and the second correction coefficient are not adjusted; if the current balanced agent utilization rate is not within the preset utilization rate range, the target adjustment value is obtained by adding or subtracting a specified value on the basis of the target adjustment value determined by the previous round of calculation of the number sending volume, that is, when calculating the current off-round number sending volume, the value of at least one of the first correction coefficient and the second correction coefficient is increased or subtracted. Less adjustment is made to control the speed of the next outbound call transmission; wherein, the specified value can be a fixed value, or can be determined based on the utilization difference between the current balanced seat utilization and the minimum value or maximum value in the preset utilization range; for example, if the current balanced seat utilization is less than the minimum value in the preset utilization range and the utilization difference between the two is larger, or if the current balanced seat utilization is greater than the maximum value in the preset utilization range and the utilization difference between the two is larger, then the corresponding specified value is larger, that is, the adjustment range of at least one of the first correction coefficient and the second correction coefficient is larger.

[0100] That is to say, when the customer connection rate calculated for the current off-cycle calling number is in the first connection rate interval, that is, in the process of predicting outbound calls, the actual connection rate is relatively close to the historical connection rate based on which the correction coefficient is set, and they belong to the same connection rate interval. Therefore, the values ​​of the first correction coefficient and the second correction coefficient used in calculating the current off-cycle calling number volume can be directly determined based on the initial setting values ​​of the first correction coefficient and the second correction coefficient, and then the outbound calling number volume used by the current off-cycle calling number is calculated based on the values ​​of the first correction coefficient and the second correction coefficient; in the case of the customer connection rate calculated for the current off-cycle calling number When it is not in the first connection rate interval, that is, the actual connection rate in the process of predicting outbound calls is quite different from the historical connection rate based on which the correction coefficient is set, and they are not in the same connection rate interval. Therefore, it is necessary to first adjust the values ​​of the first correction coefficient and the second correction coefficient to the updated values ​​(that is, the target setting values ​​corresponding to the second connection rate interval), and based on the updated values ​​of the first correction coefficient and the second correction coefficient, determine the values ​​of the first correction coefficient and the second correction coefficient used in calculating the current out-of-rotation call number volume, and then calculate the outbound call number volume used by the current out-of-rotation call number based on the values ​​of the first correction coefficient and the second correction coefficient.

[0101] Specifically, the correspondence between the connection rate interval and the values ​​of the first correction coefficient and the second correction coefficient can be pre-set, so that the first target setting value of the first correction coefficient and the second target setting value of the second correction coefficient corresponding to the second connection rate interval can be determined based on the correspondence.

[0102] In addition, it should be noted that, in the specific implementation, in the process of dynamically adjusting the value of at least one of the first correction coefficient and the second correction coefficient during the outbound call delivery process, the customer connection rate may be ignored, and the value of at least one of the first correction coefficient and the second correction coefficient may be fine-tuned directly on the basis of the initial setting value and based on whether the current agent utilization rate is within the preset utilization rate range. That is, before calculating the target outbound call delivery volume each time, it is first determined whether the current agent utilization rate is within the preset utilization rate range. If not, the value of at least one of the first correction coefficient and the second correction coefficient determined by the previous round of calculation of the delivery volume is fine-tuned, and then the target outbound call delivery volume of the current round is calculated based on the fine-tuned first correction coefficient and the second correction coefficient, so that the speed of the outbound call delivery is controlled by fine-tuning the initial setting value of at least one of the first correction coefficient and the second correction coefficient at least once, so as to control the current agent utilization rate within the preset utilization rate range. The customer connection rate may also be considered. For example, in the case of the customer connection rate, When the connection rate interval changes from the first connection rate interval to the second connection rate interval, the values ​​of the first correction coefficient and the second correction coefficient are roughly adjusted, and the values ​​of the first correction coefficient and the second correction coefficient are updated to the initial setting values ​​corresponding to the second connection rate interval (i.e., the updated values). Then, on the basis of the updated values, based on the current agent utilization rate, the value of at least one of the first correction coefficient and the second correction coefficient is fine-tuned; for example, when the connection rate interval to which the customer connection rate belongs changes from the first connection rate interval to the second connection rate interval and is maintained for a preset time, the values ​​of the first correction coefficient and the second correction coefficient are roughly adjusted, and the values ​​of the first correction coefficient and the second correction coefficient are updated to the initial setting values ​​corresponding to the second connection rate interval (i.e., the updated values). Then, on the basis of the updated values, based on the current agent utilization rate, the value of at least one of the first correction coefficient and the second correction coefficient is fine-tuned; which specific implementation method to be adopted can be set according to actual needs, and this application does not limit this.

[0103] Furthermore, the initial setting values ​​of the first correction coefficient and the second correction coefficient can be adjusted regularly or on demand before the outbound call is sent. For example, if the historical connection rate has changed from the first connection rate interval to the second connection rate interval, the target setting value corresponding to the second connection rate interval can be directly used as the initial setting value of the first correction coefficient and the second correction coefficient, or a parameter adjustment prompt message can be sent to the target management terminal to trigger the target management user to adjust the initial setting values ​​of the first correction coefficient and the second correction coefficient based on the parameter adjustment prompt message; then, in the process of predicting outbound calls, it is sufficient to monitor whether the customer connection rate belongs to the second connection rate interval.

[0104] That is to say, the adjustment timing of the values ​​of the first correction coefficient and the second correction coefficient can be to dynamically adjust the parameter values ​​during the stage of calculating the initial outbound call number quantity for the current outbound call number, or to update the parameter values ​​before the predicted outbound call is executed.

[0105] In a specific embodiment, in the above Figure 3 On this basis, in the process of determining the target outbound call volume, a judgment condition of whether the customer connection rate is within the preset connection rate range and a constraint condition of determining whether the current agent utilization rate is within the preset utilization rate range are introduced to determine how to adjust the value of at least one of the first correction coefficient and the second correction coefficient. Then, based on the finally determined values ​​of the first correction coefficient and the second correction coefficient, the target outbound call volume is calculated; specifically, Figure 4 As shown in FIG, a specific implementation process of an outbound call control method is given, which specifically includes:

[0106] When the outbound call delivery trigger time is reached at the current moment, the method for determining the outbound call delivery number corresponding to the target outbound call service is determined based on the pre-stored predictive outbound call algorithm, and the agent dimension data and customer dimension data are obtained;

[0107] Based on the above seat dimension data, determine the current seat utilization rate and the number of idle ready seats;

[0108] Based on the above customer dimension data, determine the customer connection rate and the number of customers waiting to be connected;

[0109] Determine the values ​​of the first correction coefficient and the second correction coefficient based on the customer connection rate and the current agent utilization rate. Specifically, if the customer connection rate does not fall within the first connection rate range, then the value of at least one of the first correction coefficient and the second correction coefficient is the sum of the updated value and the target adjustment value. If the customer connection rate falls within the first connection rate range, then the value of at least one of the first correction coefficient and the second correction coefficient is the sum of the initial setting value and the target adjustment value.

[0110] If the current agent utilization rate is less than the balanced agent utilization rate in the method for determining the number of outbound call numbers, the normal number delivery logic is executed. That is, the number of idle ready agents, the value of the first correction coefficient, the customer connection rate, the number of waiting customers, and the value of the second correction coefficient are substituted into the preset number delivery calculation formula to obtain the target number of outbound call numbers. The target number of outbound call numbers can be N.

[0111] If the current agent utilization rate is greater than or equal to the balanced agent utilization rate in the method for determining the number of outbound calls, the logic for slowing down the number delivery is executed. That is, the target number of outbound calls is determined based on the slowing down number delivery calculation formula corresponding to the slowing down number delivery method in the method for determining the number of outbound calls. The value of the target number of outbound calls may be N.

[0112] That is to say, before calculating the target outbound call volume each time, first determine whether the customer connection rate is within the first connection rate range, and determine whether the current agent utilization rate is within the preset utilization rate range, and determine the values ​​of the first correction coefficient and the second correction coefficient based on the two judgment results; then, if the current agent utilization rate is less than the balanced agent utilization rate, the target outbound call volume is calculated based on the values ​​of the first correction coefficient and the second correction coefficient that are finally determined; if the current agent utilization rate is less than or equal to the balanced agent utilization rate, the target outbound call volume is calculated based on the corresponding slow-down method; that is, if the above-mentioned current agent utilization rate is greater than or equal to the maximum value in the preset utilization rate range, adjust the value of at least one of the first correction coefficient and the second correction coefficient, and execute the logic of slow-down to send the number to send the outbound call;

[0113] After determining the target outbound call number N, outbound calls are made to N customer terminals (ie, customer terminals 1 to N), and the connected customer terminal i is assigned to an idle agent terminal j in the agent skill group corresponding to the target outbound call service.

[0114] Furthermore, the configuration process of the predictive outbound call algorithm can be completed automatically by the system or by the target user. Figure 5 As shown, before determining the method for determining the number of outbound call delivery numbers corresponding to the target outbound call service in S102, the method further includes:

[0115] S108, receiving a predicted outbound call parameter configuration request from a target management terminal;

[0116] S110, in response to the predicted outbound call parameter configuration request, controlling the target management terminal to display a predicted outbound call parameter configuration interface;

[0117] S112, receiving the predicted outbound call parameter configuration information sent by the target management terminal; the predicted outbound call parameter configuration information includes the agent skill group information and parameter item configuration information entered by the target management user on the predicted outbound call parameter configuration interface;

[0118] S114: Determine a target outbound skill group based on the agent skill group information.

[0119] S116: Based on the above parameter configuration information, a corresponding method for determining the number of outbound call delivery numbers is constructed for the target outbound call service corresponding to the above target outbound call skill group.

[0120] Among them, the above-mentioned method for determining the number of outbound calls includes at least one of a balanced agent utilization rate, a first correction coefficient, a second correction coefficient and a method for slowing down the number delivery; specifically, the target management user can select the target outbound call skill group that needs to be configured with a method for determining the number of outbound calls based on a visual interface, and associate the corresponding method for determining the number of outbound calls with the target outbound call skill group, thereby establishing an association relationship between the agent skill group, the target outbound service, the outbound call list and the method for determining the number of outbound calls; subsequently, in the process of predicting the execution of outbound calls, the method for determining the number of outbound calls corresponding to the target outbound service that the currently connected agent skill group is responsible for is called based on the association relationship to determine the target number of outbound calls required for each round of outbound call delivery.

[0121] In specific implementation, Figure 6 As shown in the figure, a schematic diagram of the interface for the target management user to configure the predictive outbound call algorithm for the target agent skill group on the visual interface is given, specifically:

[0122] After the target management user logs in with their respective account and password on the visual interface, the target management terminal detects that the target management user clicks on the predictive outbound call parameter configuration control and sends a predictive outbound call parameter configuration request to the backend server of the outbound call center. The backend server controls the target management terminal to display the predictive outbound call parameter configuration interface.

[0123] The target management terminal obtains the agent skill group information and parameter item configuration information input by the target management user on the above-mentioned predicted outbound call parameter configuration interface; and sends the agent skill group information and parameter item configuration information to the background server; wherein the parameter item configuration information includes the value of the maximum outbound call limit, the value of the balanced agent utilization rate, the initial setting value of the first correction coefficient, the initial setting value of the second correction coefficient and the method of slowing down the number delivery; so that the background server determines the target outbound skill group based on the above-mentioned agent skill group information; and based on the above-mentioned parameter item configuration information, constructs a corresponding outbound number delivery determination method for the target outbound call business corresponding to the above-mentioned target outbound skill group.

[0124] In specific implementation, the above-mentioned parameter item configuration information can be input by the target management user based on his or her own experience, or can be input by the target management user based on the target prompt information. The target prompt information includes optional setting values ​​of key parameter items (such as target value range or multiple alternative items); specifically, the background server automatically determines the optional setting value of at least one preset key parameter item in the outbound call number determination method based on the historical outbound call data of the target outbound call service, and generates target prompt information based on the optional setting value; then controls the target management terminal to display the target prompt information on the predicted outbound call parameter configuration interface, so that the target management user can set the value of at least one preset key parameter item in the outbound call number determination method based on the target prompt information.

[0125] The outbound call control method in the embodiment of the present application is pre-configured with a corresponding outbound call delivery number determination method (i.e., a predictive outbound call algorithm) for different target outbound call services, wherein the values ​​of multiple parameter items in the outbound call delivery number determination method corresponding to different target outbound call services may be different, and are determined in a targeted manner based on the historical outbound call data of the target outbound call service; based on this, in the application scenario of predictive outbound calls, in the process of determining the outbound call delivery number, the outbound call delivery number determination method corresponding to the target outbound call service is used, based on the two dimensions of agent dimension data and customer dimension data. The target outbound call delivery volume is determined based on the data. That is, in the predicted outbound call application scenario, combined with the differences between different outbound call services, the corresponding outbound call delivery volume determination method is configured for different outbound call services in a targeted manner, thereby improving the accuracy of the target outbound call delivery volume, ensuring that the number of currently connected customers and the currently available number of seats do not deviate too much, thereby achieving the effect of balancing the supply and demand of seats. In this way, since the currently connected number of customers is equivalent to the currently available number of seats, not only can the problem of idle ready seats due to too few delivery numbers be avoided, but also the problem of customer line overflow due to too many delivery numbers can be avoided.

[0126] Corresponding to the above Figures 1 to 6 The outbound call control method described above is based on the same technical concept. The embodiment of the present application also provides an outbound call control device. Figure 7 This is a schematic diagram of the module composition of the outbound call control device provided in the embodiment of the present application, which is used to execute Figures 1 to 6 The outbound call control method described, such as Figure 7 As shown, the device includes:

[0127] Information acquisition module 702, for determining a method for determining the number of outbound calls corresponding to a target outbound service; and obtaining agent dimension data and customer dimension data; the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound service;

[0128] The outbound call quantity determination module 704 is configured to determine a target outbound call quantity based on the outbound call quantity determination method, the agent dimension data, and the customer dimension data;

[0129] The outbound call control module 706 is configured to make outbound calls to M client terminals and assign the connected client terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number.

[0130] The outbound call control device in the embodiment of the present application is pre-configured with a corresponding outbound call delivery number determination method (i.e., a predictive outbound call algorithm) for different target outbound call services, wherein the values ​​of multiple parameter items in the outbound call delivery number determination method corresponding to different target outbound call services may be different, and are determined in a targeted manner based on the historical outbound call data of the target outbound call service; based on this, in the application scenario of predictive outbound calls, in the process of determining the outbound call delivery number, the outbound call delivery number determination method corresponding to the target outbound call service is used, based on the two dimensions of the agent dimension data and the customer dimension data. The target outbound call delivery volume is determined based on the data. That is, in the predicted outbound call application scenario, combined with the differences between different outbound call services, the corresponding outbound call delivery volume determination method is configured for different outbound call services in a targeted manner, thereby improving the accuracy of the target outbound call delivery volume, ensuring that the number of currently connected customers and the currently available number of seats do not deviate too much, thereby achieving the effect of balancing the supply and demand of seats. In this way, since the currently connected number of customers is equivalent to the currently available number of seats, not only can the problem of idle ready seats due to too few delivery numbers be avoided, but also the problem of customer line overflow due to too many delivery numbers can be avoided.

[0131] It should be noted that the embodiment of the outbound call control device in this application and the embodiment of the outbound call control method in this application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding outbound call control method mentioned above, and the repeated parts will not be repeated.

[0132] Furthermore, corresponding to the above Figures 1 to 6 The method shown in FIG. 1 is based on the same technical concept. The embodiment of the present application further provides an outbound call control device, which is used to execute the outbound call control method described above. Figure 8 shown.

[0133] The outbound call control device may have relatively large differences due to different configurations or performances, and may include one or more processors 801 and memory 802, and the memory 802 may store one or more storage applications or data. Among them, the memory 802 can be a temporary storage or a permanent storage. The application stored in the memory 802 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the outbound call control device. Furthermore, the processor 801 can be configured to communicate with the memory 802 to execute a series of computer-executable instructions in the memory 802 on the outbound call control device. The outbound call control device may also include one or more power supplies 803, one or more wired or wireless network interfaces 804, one or more input and output interfaces 805, one or more keyboards 806, etc.

[0134] In a specific embodiment, the outbound call control device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions in the outbound call control device, and the one or more programs are configured to be executed by one or more processors, including computer-executable instructions for performing the following:

[0135] Determining a method for determining the number of outbound calls corresponding to a target outbound calling service; and obtaining agent dimension data and customer dimension data; the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound calling service;

[0136] Determining a target outbound call volume based on the outbound call volume determination method, the agent dimension data, and the customer dimension data;

[0137] Make outbound calls to M client terminals, and assign the connected client terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number.

[0138] The outbound call control device in the embodiment of the present application is pre-configured with a corresponding outbound call delivery number determination method (i.e., a predictive outbound call algorithm) for different target outbound call services, wherein the values ​​of multiple parameter items in the outbound call delivery number determination method corresponding to different target outbound call services may be different, and are determined in a targeted manner based on the historical outbound call data of the target outbound call service; based on this, in the application scenario of predictive outbound calls, in the process of determining the outbound call delivery number, the outbound call delivery number determination method corresponding to the target outbound call service is used, based on the two dimensions of seat dimension data and customer dimension data. The target outbound call delivery volume is determined based on the data. That is, in the predicted outbound call application scenario, combined with the differences between different outbound call services, the corresponding outbound call delivery volume determination method is configured for different outbound call services in a targeted manner, thereby improving the accuracy of the target outbound call delivery volume, ensuring that the number of currently connected customers and the currently available number of seats do not deviate too much, thereby achieving the effect of balancing the supply and demand of seats. In this way, since the currently connected number of customers is equivalent to the currently available number of seats, not only can the problem of idle ready seats due to too few delivery numbers be avoided, but also the problem of customer line overflow due to too many delivery numbers can be avoided.

[0139] It should be noted that the embodiment of the outbound call control device in this application and the embodiment of the outbound call control method in this application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding outbound call control method mentioned above, and the repeated parts will not be repeated.

[0140] Furthermore, corresponding to the above Figures 1 to 6The method shown is based on the same technical concept. The embodiment of the present application also provides a storage medium for storing computer-executable instructions. In a specific embodiment, the storage medium can be a USB flash drive, an optical disk, a hard disk, etc. When the computer-executable instructions stored in the storage medium are executed by the processor, the following process can be implemented:

[0141] Determining a method for determining the number of outbound calls corresponding to a target outbound calling service; and obtaining agent dimension data and customer dimension data; the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound calling service;

[0142] Determining a target outbound call volume based on the outbound call volume determination method, the agent dimension data, and the customer dimension data;

[0143] Make outbound calls to M client terminals, and assign the connected client terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number.

[0144] The computer executable instructions stored in the storage medium in the embodiment of the present application are pre-configured with corresponding outbound call delivery number determination methods (i.e., predictive outbound call algorithms) for different target outbound call services when executed by the processor, wherein the values ​​of multiple parameter items in the outbound call delivery number determination methods corresponding to different target outbound call services may be different, and are determined in a targeted manner based on the historical outbound call data of the target outbound call service; based on this, in the application scenario of predictive outbound calling, in the process of determining the outbound call delivery number, the outbound call delivery number determination method corresponding to the target outbound call service is used, based on the agent dimension data and the customer dimension data, the outbound call delivery number determination method is used, and the outbound call delivery number determination method is used based on the agent dimension data and the customer dimension data. The target outbound call delivery volume is determined based on the data from these two dimensions. That is, in the predicted outbound call application scenario, combined with the differences between different outbound call services, corresponding outbound call delivery volume determination methods are configured for different outbound call services in a targeted manner, thereby improving the accuracy of the target outbound call delivery volume, ensuring that the number of currently connected customers does not deviate too much from the currently available number of seats, thereby achieving a balance between agent supply and demand. In this way, since the number of currently connected customers is equivalent to the currently available number of seats, not only can the problem of idle ready seats due to too few delivery numbers be avoided, but also the problem of customer line overflow due to too many delivery numbers can be avoided.

[0145] It should be noted that the embodiment of the storage medium in this application and the embodiment of the outbound call control method in this application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding outbound call control method mentioned above, and the repeated parts will not be repeated.

[0146] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multi-tasking and parallel processing are also possible or may be advantageous. Those skilled in the art will understand that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the embodiments of the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the application can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0149] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-permanent storage in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium. Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition in this article, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, product, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, product, or device. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, product, or device comprising the element. The embodiments of the present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of the present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In distributed computing environments, program modules may be located in local and remote computer storage media, including storage devices. The various embodiments in this application are described in a progressive manner, and similar parts between the various embodiments may be referenced. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0151] The foregoing description is merely an example of the present invention and is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of the claims herein.

Claims

1. An outbound call control method, characterized in that: The method comprises: Determining a method for determining the number of outbound calls corresponding to a target outbound calling service; and obtaining agent dimension data and customer dimension data; the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound calling service; Determining a target outbound call volume based on the outbound call volume determination method, the agent dimension data, and the customer dimension data; Make outbound calls to M customer terminals and assign the connected customer terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number; The method for determining the number of outbound calls includes preset key parameter items, and the preset key parameter items include balanced seat utilization, a first correction coefficient, a second correction coefficient, and a method for slowing down the number delivery; The determining of the target outbound call number quantity based on the outbound call number quantity determination method, the agent dimension data, and the customer dimension data includes: Determine the current agent utilization rate and the number of idle ready agents based on the agent dimension data; and determine the customer connection rate and the number of customers waiting to be connected based on the customer dimension data; If the current agent utilization rate is less than the equilibrium agent utilization rate, determining a target outbound call volume based on the number of idle ready agents, the first correction coefficient, the customer connection rate, the number of waiting customers to be connected, and the second correction coefficient; If the current agent utilization rate is greater than or equal to the equilibrium agent utilization rate, a target outbound call delivery volume is determined based on the slow delivery method.

2. The method according to claim 1, characterized in that The preset key parameter items also include the maximum outbound call limit; The step of determining a target outbound call volume based on the number of idle ready seats, the first correction coefficient, the customer connection rate, the number of waiting customers to be connected, and the second correction coefficient includes: Determining an initial outbound call number based on the number of idle ready seats, the first correction coefficient, the customer connection rate, the number of waiting customers to be connected, and the second correction coefficient; Based on the initial outbound call number quantity and the maximum outbound call limit quantity, a target outbound call number quantity is determined.

3. The method according to claim 2, characterized in that The determining of a target outbound call number based on the initial outbound call number and the maximum outbound call limit includes: If the initial outbound call number quantity is greater than or equal to the maximum outbound call limit quantity, the maximum outbound call limit quantity is determined as the target outbound call number quantity; If the initial outbound call number quantity is less than the maximum outbound call limit quantity, the initial outbound call number quantity is determined as the target outbound call number quantity.

4. The method according to claim 2, characterized in that The determining of the initial outbound call number based on the number of idle ready seats, the first correction coefficient, the customer connection rate, the number of waiting customers to be connected, and the second correction coefficient includes: Determining a converted number of idle seats based on the number of idle ready seats and the customer connection rate; and determining a corrected number of idle seats based on the converted number of idle seats and the first correction coefficient; Determining a corrected number of waiting customers based on the number of waiting customers and the second correction coefficient; Based on the corrected number of idle seats and the corrected number of waiting customers, the initial outbound call delivery number is determined.

5. The method according to claim 1, wherein After determining the current agent utilization rate and the number of idle ready agents based on the agent dimension data; and determining the customer connection rate and the number of customers waiting to be connected based on the customer dimension data, the method further includes: Determining values ​​of the first correction coefficient and the second correction coefficient according to the customer connection rate and the current agent utilization rate; Among them, if the customer connection rate does not belong to the first connection rate interval, the value of at least one of the first correction coefficient and the second correction coefficient is the sum of the updated value and the target adjustment value, and the updated value is determined based on the second connection rate interval to which the customer connection rate belongs; if the customer connection rate belongs to the first connection rate interval, the value of at least one of the first correction coefficient and the second correction coefficient is the sum of the initial setting value and the target adjustment value, and the initial setting value is determined based on the first connection rate interval, and the target adjustment value is determined based on whether the current agent utilization rate is in a preset utilization rate interval, the minimum value of the preset utilization rate interval is the difference between the balanced agent utilization rate and the first value, and the maximum value of the preset utilization rate interval is the sum of the balanced agent utilization rate and the second value.

6. The method according to any one of claims 1 to 5, characterized in that Before determining the method for determining the number of outbound call delivery numbers corresponding to the target outbound call service, the following steps are also included: Receive a request for configuration of predicted outbound call parameters from a target management terminal; In response to the predicted outbound call parameter configuration request, controlling the target management terminal to display a predicted outbound call parameter configuration interface; Receiving the predicted outbound call parameter configuration information sent by the target management terminal; the predicted outbound call parameter configuration information includes the agent skill group information and parameter item configuration information input by the target management user on the predicted outbound call parameter configuration interface; Determine a target outbound skill group based on the agent skill group information; Based on the parameter item configuration information, a corresponding method for determining the number of outbound call numbers is constructed for the target outbound call service corresponding to the target outbound call skill group.

7. An outbound call control device, characterized in that: The device comprises: An information acquisition module is configured to determine a method for determining the number of outbound calls corresponding to a target outbound service; and to obtain agent dimension data and customer dimension data; the method for determining the number of outbound calls is pre-configured based on historical outbound call data of the target outbound service; a number delivery quantity determination module, configured to determine a target number of outbound calls based on the outbound number delivery quantity determination method, the agent dimension data, and the customer dimension data; An outbound call control module, configured to make outbound calls to M client terminals and assign the connected client terminals to idle agent terminals in the agent terminal group corresponding to the target outbound call service; M is an integer less than or equal to the target outbound call number; The method for determining the number of outbound calls includes preset key parameter items, which include a balanced agent utilization rate, a first correction coefficient, a second correction coefficient, and a method for slowing down the number delivery. The number delivery determination module determines the target number of outbound calls by: Determine the current agent utilization rate and the number of idle ready agents based on the agent dimension data; and determine the customer connection rate and the number of customers waiting to be connected based on the customer dimension data; If the current agent utilization rate is less than the equilibrium agent utilization rate, determining a target outbound call volume based on the number of idle ready agents, the first correction coefficient, the customer connection rate, the number of waiting customers to be connected, and the second correction coefficient; If the current agent utilization rate is greater than or equal to the equilibrium agent utilization rate, a target outbound call delivery volume is determined based on the slow delivery method.

8. An outbound call control device, characterized in that: The device comprises: processor; and A memory arranged to store computer executable instructions, the executable instructions being configured to be executed by the processor, the executable instructions comprising instructions for performing the steps of the method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is used to store computer-executable instructions, and the executable instructions enable a computer to execute the method according to any one of claims 1 to 6.

Images