Call task processing method, device and equipment, computer readable storage medium and computer program product

Abstract

The invention provides a call task processing method, device and equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring an allocation weight of a call task to an idle seat; acquiring call parameters for executing the call task in the first time period; determining the number of calls in the second time period based on the distribution weight and the call parameters; and executing the call task based on the call number and the distribution weight. According to the invention, the processing efficiency of the call task can be improved.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly to a call task processing method, apparatus, device, computer-readable storage medium, and computer program product. Background Technology

[0002] Call centers serve as a vital bridge between businesses and their customers, and fluctuations in call volume directly impact the quality and efficiency of service. With the advancement of information technology and digitalization, the need for call center call volume forecasting is growing. Call center systems typically rely on experience to adjust call resources, such as increasing or decreasing the number of agents and adjusting call times, to cope with fluctuations in call volume.

[0003] In related technologies, call center systems predict call volume based on a fixed number of calls made. That is, they determine the number of calls to be made in the next time period based on the number of users who connected in the previous time period. The accuracy of call volume prediction is not high, resulting in too many idle agents or too many users hearing waiting tone, which reduces the call efficiency and utilization rate of agents. Summary of the Invention

[0004] This application provides a call task processing method, apparatus, device, computer-readable storage medium, and computer program product, which can improve the processing efficiency of call tasks.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides a call task processing method, the method comprising:

[0007] Obtain the allocation weight of call tasks to available agents;

[0008] Obtain the call parameters for executing the call task during the first time period;

[0009] Based on the allocation weights and the call parameters, the number of calls in the second time period is determined, wherein the first time period and the second time period are adjacent time periods.

[0010] The call task is executed based on the number of calls and the allocation weight.

[0011] This application provides a call task processing device, including:

[0012] The first acquisition module is used to acquire the allocation weight of call tasks to available agents;

[0013] The second acquisition module is used to acquire the call parameters of the call task executed in the first time period;

[0014] The quantity determination module is used to determine the number of calls in the second time period based on the allocation weight and the call parameters, wherein the first time period and the second time period are adjacent time periods;

[0015] The task execution module is used to execute the call task based on the number of calls and the allocation weight.

[0016] This application provides an electronic device, the electronic device comprising:

[0017] Memory is used to store executable instructions or computer programs.

[0018] The processor, when executing computer-executable instructions or computer programs stored in the memory, implements the call task processing method provided in the embodiments of this application.

[0019] This application provides a computer-readable storage medium storing computer-executable instructions or computer programs, which, when executed by a processor, implement the call task processing method provided in this application.

[0020] This application provides a computer program product, including computer-executable instructions or a computer program, which, when executed by a processor, implements the call task processing method provided in this application.

[0021] The embodiments of this application have the following beneficial effects:

[0022] By applying the embodiments of this application, the allocation weights of call tasks to idle agents are obtained. Then, the call parameters for executing call tasks in the first time period are obtained. Based on the allocation weights and call parameters, the number of calls in the second time period is determined. The first and second time periods are adjacent time periods. Then, the call tasks are executed based on the number of calls and the allocation weights. Thus, by combining the allocation weights of call tasks to idle agents and the call parameters for executing call tasks in the first time period to determine the number of calls in the second time period, the accuracy of predicting the number of calls is improved by considering both the agent task allocation weight dimension and the call parameter dimension. By using the number of calls and the allocation weights of call tasks to idle agents, idle agents can be allocated to execute call tasks, avoiding an excessive number of idle agents, improving agent utilization, and thus improving the processing efficiency of call tasks. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the application mode of the call task processing method provided in the embodiments of this application;

[0024] Figure 2 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0025] Figure 3A This is a first flowchart illustrating the call task processing method provided in this application embodiment;

[0026] Figure 3B This is a second flowchart illustrating the call task processing method provided in the embodiments of this application;

[0027] Figure 3C This is a schematic diagram of the third process of the call task processing method provided in the embodiments of this application;

[0028] Figure 4 This is a flowchart illustrating the process of predicting call volume provided in related technologies;

[0029] Figure 5 This is a schematic diagram of the process for predicting the number of calls provided in an embodiment of this application.

[0030] It should be noted that the terms "first" and "second" mentioned above are only used to distinguish between different options and do not represent the degree of superiority or inferiority of the options or their priority in the implementation process. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0033] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0034] In the implementation of this application, the collection and processing of relevant data should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0035] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0036] Unless otherwise defined, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the embodiments of this application is for the purpose of describing the embodiments of this application only and is not intended to limit this application.

[0037] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0038] 1) Seat: Also known as call center seat, desk seat or seat representative, it generally consists of a seat computer, seat software, seat headset, service personnel, etc. The seat uses seat software and hardware to realize related control functions in order to achieve customer service objectives.

[0039] 2) Number of calls connected: The total number of users who received the call.

[0040] 3) Number of connections: refers to the total number of users who are connected to the agent within 5 seconds.

[0041] 4) Connection rate: The ratio of the number of calls connected to the number of calls made.

[0042] 5) Reach rate: The ratio of the number of users whose calls are connected to the total number of users.

[0043] 6) Completion rate: The ratio of the number of users who have been called to the total number of users.

[0044] 7) Call task: This is the task of the call center to initiate a call to the user through the agents.

[0045] 8) Allocation weight: This is the probability of each agent executing a call task pre-configured. It is a value in the range of 0 to 1 and is used to determine the priority or importance of assigning call tasks to agents. Factors affecting the allocation weight of call tasks include the agent's historical performance and the agent's working hours.

[0046] 9) Skill Group: This is a group of callers divided according to their business skills.

[0047] In related technologies, call center systems predict call volume based on a fixed number of calls made, and predict the number of calls to be made in the next time period based on the number of users who connected in the previous time period. This leads to too many idle agents or too many users hearing waiting tone, reducing agent call efficiency and utilization. Furthermore, the prediction of call volume does not consider the agent dimension, resulting in low accuracy.

[0048] This application provides a call task processing method, apparatus, device, computer-readable storage medium, and computer program product, which can improve the processing efficiency of call tasks.

[0049] The following describes exemplary applications of the electronic devices provided in the embodiments of this application. These electronic devices can be implemented as various types of terminals such as laptops, tablets, desktop computers, set-top boxes, smartphones, smart speakers, smartwatches, smart TVs, and in-vehicle terminals, or as servers. The following will describe exemplary applications when the device is implemented as a server.

[0050] See Figure 1 , Figure 1 This is a schematic diagram illustrating the application mode of the call task processing method provided in the embodiments of this application, for example. Figure 1 The system involves a call center server 200, a network 300, a call dispatch terminal 400-1, and agent terminals 400-2. The call dispatch terminal 400-1 and agent terminals 400-2 are connected to the server 200 via the network 300, which can be a wide area network (WAN), a local area network (LAN), or a combination of both.

[0051] In the call task processing process, for example, in a call center scenario, call dispatch terminal 400-1 acquires a call task and sends a call task processing request to server 200. Server 200 responds to the request by acquiring the allocation weight of the call task to available agents, then acquiring the call parameters for executing the call task in the first time period. Based on the allocation weight and call parameters, it determines the number of calls in the second time period. Then, based on the number of calls and the allocation weight, it executes the call task using the agent terminal 400-2 corresponding to the available agents, obtaining the call task processing result, and outputting the result to call dispatch terminal 400-1. Call dispatch terminal 400-1 receives and displays the call task processing result. In this way, callers can understand the call task processing results of the call center through call dispatch terminal 400-1.

[0052] In some embodiments, the server (e.g., server 200) can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The call dispatch terminal 400-1 and the agent terminal 400-2 can be smartphones, tablets, laptops, desktop computers, etc., but are not limited to these. The terminals and servers can be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment.

[0053] See Figure 2 , Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may be a terminal or a server. Figure 2 The illustrated electronic device 500 includes at least one processor 410, a memory 450, and at least one network interface 420. The various components in the electronic device 500 are coupled together via a bus system 440. It is understood that the bus system 440 is used to implement communication between these components. In addition to a data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 2 The general labeled all buses as Bus System 440.

[0054] The processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0055] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices physically located away from the processor 410.

[0056] The memory 450 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory. ，The volatile memory can be random access memory (RAM). The memory 450 described in the embodiments of this application is intended to include any suitable type of memory.

[0057] In some embodiments, memory 450 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0058] Operating system 451 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, and driver layer, for implementing various basic business functions and handling hardware-based tasks.

[0059] The network communication module 452 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 including Bluetooth, WiFi, and Universal Serial Bus (USB).

[0060] In some embodiments, the apparatus provided in this application can be implemented in software. Figure 2 A call task processing device 455 stored in memory 450 is shown. It can be software in the form of programs and plug-ins, including the following software modules: a first acquisition module 4551, a second acquisition module 4552, a quantity determination module 4553, and a task execution module 4554. These modules are logical and can therefore be arbitrarily combined or further divided according to the functions they implement. The functions of each module will be described below.

[0061] The call task processing method provided in this application will be described in conjunction with exemplary applications and implementations of the server equipment provided in the embodiments of this application.

[0062] The call task processing method provided in the embodiments of this application will be described below. As mentioned above, the electronic device implementing the call task processing method of the embodiments of this application can be a terminal, a server, or a combination of both. Next, taking an electronic device as a server as an example, the call task processing method provided in the embodiments of this application will be described. See also... Figure 3A , Figure 3A This is a first flowchart illustrating the call task processing method provided in this application embodiment, which will be combined with... Figure 3A The steps shown are explained.

[0063] In step 301, the allocation weight of the call task to the idle agent is obtained.

[0064] Here, a call task is a task initiated by a call center through agents to make calls to users. Call tasks can include different types of users and the number of calls. Callers use agents to execute call tasks. The weight assigned to each agent for a call task is a pre-configured probability of executing the call task, a value ranging from 0 to 1. The weight assigned to each agent for a call task is usually determined based on a series of factors, such as: agents' historical performance, such as problem resolution rate and customer satisfaction ratings, are divided into different performance levels based on their historical performance. Each performance level corresponds to a different weight range. The weight assigned to an agent for a call task can be a random value obtained from the weight range corresponding to the agent's performance level. For example, performance levels include low, medium, and high levels. The weight range for low level can be 0.1 to 0.3, for medium level it can be 0.4 to 0.7, and for high level it can be 0.8 to 1. When an idle agent's performance level is high, a random value between 0.8 and 1 can be determined as the weight assigned to that idle agent; for example, the weight could be 0.9. Agents can be categorized into different efficiency levels based on factors such as call duration and processing speed. Each efficiency level corresponds to a different weight range, and the weight assigned to an agent by a call task can be a random value obtained from the weight range corresponding to the agent's efficiency level. In some embodiments, a comprehensive level can be determined based on the agent's efficiency level and performance level. For example, the higher of the efficiency level and performance level can be determined as the comprehensive level, or the lower of the efficiency level and performance level can be determined as the comprehensive level, or the efficiency level and performance level can be averaged to obtain the comprehensive level. Each comprehensive level corresponds to a different weight range, and the weight assigned to an agent by a call task can be a random value obtained from the weight range corresponding to the agent's comprehensive level.

[0065] In some embodiments, a mapping relationship can be established between at least one factor affecting the agent's historical performance and the weights assigned to the agent by the call task. A mapping function can be defined to characterize this mapping relationship; the mapping function can be linear or nonlinear. The factor values ​​corresponding to at least one factor affecting the agent's historical performance are used as input data to determine the weights assigned to the agent by the call task in the historical performance dimension. Alternatively, a machine learning model can be used to fit the mapping relationship. The factor values ​​corresponding to at least one factor affecting the agent's historical performance and the weights assigned to the agent by the call task are used as samples to train the machine learning model, resulting in a trained machine learning model. Using the trained machine learning model and the factor values ​​corresponding to at least one factor affecting the agent's historical performance, the weights assigned to the agent by the call task in the historical performance dimension are then determined.

[0066] The weighting of idle agents in a call task refers to the weight assigned to agents who are currently idle and not performing call tasks. For example, a call task might involve making 100 calls and assigning agents 1, 2, and 3 to perform the calls. The weight assigned to agent 1 is 0.1, to agent 2 is 0.5, and to agent 3 is 0.4. If agent 3 is idle, the weight assigned to idle agents is 0.4.

[0067] In step 302, the call parameters for the call task executed in the first time period are obtained.

[0068] Here, the total number of calls to be executed is determined by dividing the day into multiple equal-length time periods, which can be at the second, minute, or clock level. The first time period is set to begin executing the call task. A pre-set number of call tasks (less than the total number of calls) is selected from multiple options for the first time period. 3-5 seconds after the first time period begins executing the call task, events such as ringing and answering occur, allowing the acquisition of call parameters for that time period. Call parameters refer to various call parameters involved in making a telephone call. After each time period's call task is completed, the next time period begins, and the call parameters from the previous time period can be acquired in the next time period.

[0069] Call parameters can include the number of calls made, the number of calls connected, the number of calls disconnected, and the call duration. The number of calls made is the number of calls that have been dialed, the number of calls connected is the number of calls that have been answered, the number of calls disconnected is the number of calls that were disconnected within 1 second of being connected, and the call duration is the time from when the call is connected to when it ends.

[0070] For example, let's take a task involving making 100 phone calls as an example. The total number of calls to be made is 100. The day is divided into multiple 5-minute time slots. Ten calls are selected from the 100 calls as the first time slot's call task. After 3-5 seconds of execution within each 5-minute time slot, the call parameters for that time slot are retrieved. After each 5-minute time slot's call task is completed, the next 5-minute time slot's call task begins.

[0071] In step 303, the number of calls in the second time period is determined based on the assigned weights and call parameters.

[0072] Here, the first and second time periods are adjacent, with the first time period preceding the second. The number of calls executed in the second time period is determined based on the allocation weight of call tasks to available agents within the second time period and the call parameters of the call tasks executed in the first time period. The second time period is the same length as the first time period.

[0073] In some embodiments, see Figure 3B , Figure 3B This is a second flowchart of the call task processing method provided in the embodiments of this application. Figure 3A Step 303 shown can be achieved through Figure 3B Steps 3031 to 3034 are implemented, and will be explained in detail below.

[0074] In step 3031, the allocation weights of the call task to different available agents are accumulated to obtain the sum.

[0075] Determine the allocation weight of the call task to different available seats, and add up the allocation weights of the call task to all available seats to obtain the sum of the allocation weights of the call task to all available seats.

[0076] For example, taking agents 1, 2, and 3 as examples of executing a call task, the weight assigned to agent 1 is determined to be 0.1, the weight assigned to agent 2 is determined to be 0.5, and the weight assigned to agent 3 is determined to be 0.4. If agents 1 and 2 are idle, the weights assigned to agents 1 and 2 are added together, resulting in a total weight of 0.6 for all idle agents.

[0077] In step 3032, the first number of calls is determined based on the cumulative sum.

[0078] Here, the first call count is used to predict the number of calls executed in the second time period based on the task allocation weights of the agents. The first call count is obtained by summing the allocation weights of the call tasks to all idle agents and rounding them up.

[0079] For example, taking agents 1, 2, and 3 as the basis for executing a call task, the call task is assigned a weight of 0.1 to agent 1, 0.5 to agent 2, and 0.4 to agent 3. If agents 1 and 2 are idle, the weights assigned to agents 1 and 2 are added together. The sum of the weights assigned to all idle agents is 0.6. Rounding up the sum, the first call count is 1.

[0080] In this embodiment of the application, the first number of calls is determined by summing the allocation weights of all idle agents for the call task. This can predict the first number of calls from the dimension of agent task allocation weights, thus improving the accuracy of predicting the first number of calls.

[0081] In step 3033, the second number of calls is determined based on the call parameters.

[0082] Here, the second call count is used to predict the number of calls executed in the second time period based on the call parameters. The second call count for the second time period is calculated based on the call parameters from the first time period.

[0083] In some embodiments, the call parameters include: number of calls made, number of calls connected, number of calls disconnected, average ringing time, and service time. The second call count can be determined based on these call parameters by performing the following steps: obtaining the number of calls in progress, the number of first agents in a call state, the number of second agents with available seats, and the number of third agents in a post-call state; determining the connection success rate based on the number of calls made and the number of calls connected, and determining the predicted connection count based on the number of calls in progress and the connection success rate; determining a first predicted value based on service time, average ringing time, and the number of first agents; determining a call abandonment rate based on the number of calls connected and the number of calls disconnected, and determining the predicted connection success rate based on the call abandonment rate and the connection success rate; and determining the second call count based on the number of second agents, the number of third agents, the predicted connection count, the first predicted value, and the predicted connection success rate.

[0084] To determine the call success rate, obtain the number of calls made and the number of calls connected during the first time period, and calculate the ratio of the number of connected calls to the number of calls made. For example, the call success rate can be determined using the following formula (1):

[0085] SR = NCC / NOC (1)

[0086] SR represents the call connection success rate, NCC represents the number of calls connected, and NOC represents the number of calls made.

[0087] In some embodiments, the number of ongoing calls during a first time period is obtained, and the predicted number of connected calls is determined based on the product of the number of ongoing calls and the connection success rate. For example, the predicted number of connected calls can be determined using the following formula (2):

[0088] PNC = NC * SR (2)

[0089] Where PNC represents the predicted number of connected calls, NC represents the number of calls in progress, and SR represents the connection success rate.

[0090] Obtain the call duration, call end time, call ringing time, call connection time, and the number of first agents in a call state for each call executed during the first time period. The call end time is the preset time of 0-100 seconds after the call ends. Add the call duration and call end time of each call to obtain the service time. Subtract the call connection time and call ringing time of each call to obtain the ringing duration of each call, and add the ringing durations of each call to obtain the cumulative ringing duration. Divide the number of calls made by the cumulative ringing duration to obtain the average ringing time. For example, the average ringing time can be determined by the following formula (3):

[0091] TR = NOC / SCR (3)

[0092] Where TR represents the average ringing time, NOC represents the number of calls made, and SCR represents the sum of ringing times.

[0093] The first forecast value is calculated based on the business hours, average ring time, and number of first agents. For example, the first forecast value can be determined using the following formula (4):

[0094] FPV=AC*(1-e^(-TR / TC)) (4)

[0095] Wherein, FPV represents the first forecast value, AC represents the first number of seats, and TC represents the service time.

[0096] The call abandonment count is the number of calls that the user actively hangs up within one second of the call being connected. The call abandonment rate is calculated by dividing the number of call hang-ups by the number of call connections during the first time period. For example, the call abandonment rate can be determined using the following formula (5):

[0097] UR = NDC / NCC (5)

[0098] Wherein, UR represents the call abandonment rate, NDC represents the number of call hang-ups, and NCC represents the number of call connections.

[0099] The predicted connection success rate is calculated by multiplying the call abandonment rate and the connection success rate. For example, the predicted connection success rate can be determined using the following formula (6):

[0100] PCS = UR * SR (6)

[0101] Where PCS represents the predicted call success rate, UR represents the call abandonment rate, and SR represents the call success rate.

[0102] In this embodiment, the number of second calls is calculated based on call parameters such as the number of calls made, the number of calls connected, the number of calls hung up, the average ringing time, and the business time. This allows for the prediction of the number of second calls from the perspective of telephone call parameters, thereby improving the accuracy of the prediction of the number of second calls.

[0103] In some embodiments, the second number of calls can be determined by performing the following steps based on the second number of agents, the third number of agents, the predicted number of connected calls, the first predicted value, and the predicted connection success rate: the difference between the second number of agents and the predicted number of connected calls is determined as the number of available agents; the sum of the number of available agents, the first predicted value, and the third number of agents is determined as the number of candidate calls; the number of candidate calls is adjusted using a preset adjustment coefficient to obtain the predicted number of calls; and the second number of calls is determined based on the predicted number of calls and the predicted connection success rate.

[0104] Obtain the number of second agents with available seats and the number of third agents in the post-call state during the first time period. Calculate the difference between the number of second agents and the predicted number of connected calls, and determine the number of available seats based on this difference. Calculate the sum of the number of available seats, the first predicted value, and the number of third agents, and determine the candidate number of calls based on this sum. The preset adjustment coefficient is a value in the range of 0 to 100. Multiply the preset adjustment coefficient by the candidate number of calls to obtain the predicted number of calls. Divide the predicted number of calls by the predicted connection success rate, and round up the result to obtain the number of second calls. For example, the number of second calls can be determined by the following formula (7):

[0105] NSC=FA-NC*SR+AC*(1-e^(-TR / TC))+AP)*MAP / (UR*SR) (7)

[0106] Wherein, NSC represents the number of second calls, FA represents the number of second agents, NC represents the number of calls in progress, SR represents the connection success rate, AC represents the number of first agents, TR represents the average ringing time, TC represents the service time, AP represents the number of third agents, MAP represents the adjustment factor, and UR represents the call abandonment rate.

[0107] In this embodiment, the second number of calls is determined based on the number of second agents, the number of third agents, the predicted number of connected calls, the first predicted value, and the predicted connection success rate. This method can combine multiple call parameters to improve the accuracy of calculating the number of second calls.

[0108] Continue to refer to Figure 3B In step 3034, the minimum value between the first number of calls and the second number of calls is determined, and the minimum value is determined as the number of calls in the second time period.

[0109] Here, the minimum value is determined from the first call count and the second call count, and this minimum value is used as the call count corresponding to the call task performed in the second time period. For example, the call count for the second time period can be determined using the following formula (8):

[0110] OCP = min(NFC, NSC) (8)

[0111] Wherein, OCP represents the number of calls in the second time period, NFC represents the number of calls in the first time period, and NSC represents the number of calls in the second time period.

[0112] In this embodiment, the number of calls in the second time period is determined based on the allocation weight of idle agents to the call task and the call parameters. The minimum of the first and second call numbers is determined as the number of calls in the second time period. This takes into account both the agent task allocation weight dimension and the telephone call parameter dimension, thereby improving the accuracy of predicting the number of calls in the second time period.

[0113] Continue to refer to Figure 3A In step 304, a call task is executed based on the number of calls and the assigned weights.

[0114] Here, the call tasks for the second time period are executed based on the number of calls in the second time period and the weight of call tasks allocated to available agents.

[0115] In some embodiments, a call task corresponds to multiple agent sets, see [link to documentation]. Figure 3C , Figure 3C This is a schematic diagram of the third process of the call task processing method provided in the embodiments of this application. Figure 3A Step 304 shown can be achieved through Figure 3C Steps 3041 to 3044 are implemented, and will be explained in detail below.

[0116] In step 3041, the number of the fourth available seat in the seat set is obtained.

[0117] Here, at least one agent set is configured for each call task. An agent set, also known as a skill group, is a skill group formed based on the callers' professional skills. Each agent set contains a preset number of callers and can handle one or more call tasks. Each agent set also contains a preset number of agents and a weight assigned to each agent for each call task. The fourth agent number is the number of available agents in each agent set corresponding to the call task. For example, taking agent set 1 and agent set 2 as examples, agent set 1 is configured with agents 1, 2, and 3. If agents 1 and 2 are available, the fourth agent number for available agents in agent set 1 is 2. Agent set 2 is configured with agents 4, 5, and 6. If agent 6 is available, the fourth agent number for available agents in agent set 2 is 1.

[0118] In step 3042, the task weights corresponding to the seat set are determined based on the number of fourth and second seats.

[0119] In some embodiments, the task weight corresponding to each seat set in the second time period is determined based on the number of fourth seats among the available seats in each seat set during the second time period and the number of second seats among the available seats performing the call task during the second time period. The ratio obtained by dividing the number of fourth seats and the number of second seats in each seat set is determined as the task weight corresponding to each seat set.

[0120] For example, taking the execution of a call task by seat set 1 and seat set 2 as an example, if the number of the fourth idle seat in seat set 1 is 2, the number of the fourth idle seat in seat set 2 is 1, and the number of the second idle seat in the second time period is 3, then the task weight corresponding to seat set 1 in the second time period is 2 / 3, and the task weight corresponding to seat set 2 is 1 / 3.

[0121] In step 3043, the number of calls allocated to the agent set is determined based on the task weight and the number of calls corresponding to the agent set.

[0122] Multiply the task weight corresponding to each agent set by the number of calls corresponding to the second time period, and round the result to determine the number of calls allocated to each agent set.

[0123] For example, taking agent set 1 and agent set 2 as examples of executing call tasks, if the number of calls in the second time period is 30, the task weight of agent set 1 in the second time period is 2 / 3, and the task weight of agent set 2 in the second time period is 1 / 3, then the number of calls allocated to agent set 1 in the second time period is 20, and the number of calls allocated to agent set 2 in the second time period is 10.

[0124] In step 3044, call tasks are assigned to idle agents in the agent set based on the number of calls allocated to the agent set and the allocation weight.

[0125] After determining the number of calls allocated to each agent set in the second time period and the allocation weight of call tasks to idle agents in each agent set, the allocation weights of call tasks to idle agents in each agent set are summed to obtain the summed allocation weights. The ratio of the allocation weight of call tasks to each idle agent to the summed allocation weights is calculated to obtain the call quantity allocation proportion for each idle agent. The number of calls allocated to each agent set in the second time period and the call quantity allocation proportion are multiplied to obtain the number of calls allocated to each idle agent. At this point, the number of calls allocated to each idle agent can also be adjusted according to the allocation weight of call tasks to idle agents.

[0126] For example, if the number of calls allocated to agent set 1 in the second time period is 100, and agents 1 and 2 in agent set 1 are idle, the weight of the call task allocation for agent 1 is 0.6, and the weight of the call task allocation for agent 2 is 0.5. Adding the weights of the call task allocation for the idle agents yields a sum of weights of 1.1. Therefore, the call allocation ratio for agent 1 is 6 / 11, and the call allocation ratio for agent 2 is 5 / 11. Multiplying the call quantity of 100 by the call allocation ratios gives approximately 50 calls allocated to each idle agent. Since the call task allocation weight for agent 1 is greater than that for agent 2, the number of calls allocated to each idle agent is adjusted. Agent 1 could be allocated 60 calls, and agent 2 could be allocated 40 calls. If there are 20 callers in agent set 1, one caller can be assigned to perform the call task assigned by agent 1, and another caller can be assigned to perform the call task assigned by agent 2, based on the callers' skills and experience.

[0127] In this embodiment of the application, based on the number of calls allocated to the agent set and the allocation weight of call tasks to idle agents in the agent set, call tasks are allocated to idle agents in the agent set, which can improve the utilization rate of agents and thus improve the efficiency of call task processing.

[0128] In some embodiments, the following steps may be performed: when an idle agent is assigned to at least two call tasks, randomly select one call task from the at least two call tasks as the target call task for the idle agent; or, obtain the allocation weight of each call task to the idle agent; and determine the call task with the highest allocation weight as the target call task for the idle agent.

[0129] Here, the target call task is the call task to be executed by an idle agent in each agent set during the second time period. Since two or more call tasks may be assigned to an agent set, an idle agent in that set may be assigned at least two call tasks. If an idle agent in each agent set is assigned at least two call tasks, one call task can be randomly selected from the two tasks as the call task to be executed by an idle agent in that agent set during the second time period. Alternatively, the allocation weight of each call task to an idle agent can be obtained, and the call task with the highest allocation weight can be determined as the call task to be executed by an idle agent in that agent set during the second time period.

[0130] For example, agent set 1 is assigned to call task 1 and call task 2. Agents 1 and 2 in agent set 1 are in an idle state. Call task 1 has a weight of 0.6 for agent 1, call task 2 has a weight of 0.4 for agent 1, call task 1 has a weight of 0.4 for agent 2, and call task 2 has a weight of 0.6 for agent 2. Agents 1 and 2 can randomly select one call task from call task 1 and call task 2 respectively as the call task to be executed in the second time period, or determine that call task 1 has the highest weight for agent 1 and select call task 1 as the call task to be executed by agent 1 in the second time period. Similarly, determine that call task 2 has the highest weight for agent 2 and select call task 2 as the call task to be executed by agent 2 in the second time period.

[0131] In this embodiment of the application, when an idle agent is assigned to at least two call tasks, one call task can be randomly selected as the target call task, or the call task with the highest task allocation weight of the idle agent can be selected as the target call task. In this way, the idle agent can choose to handle different call tasks, which improves the utilization rate of the agent and thus improves the efficiency of call task processing.

[0132] In some embodiments, Figure 3A Before step 301 shown, the following steps may be performed to determine the allocation weight of the call task to the agent in the agent set: for each agent, obtain at least one agent set to which the agent belongs, and obtain the target call task assigned to the agent set; determine the allocation weight of the target call task to the agent in the agent set to which it belongs.

[0133] Each agent can be configured in multiple agent sets. At least one agent set to which each agent belongs is obtained, and the target call task assigned to the agent set is obtained. Based on the allocation weight of the target call task for each agent in its respective agent set, the allocation weight of the target call task for each idle agent in its respective agent set is determined, and the target call task is executed, which is the agent's cross-modal cross strategy.

[0134] For example, the target call task is Task 1. Taking the execution of Call Task 1 using Agent Set 1 and Agent Set 2 as an example, Agent Set 1 is configured with Agent 1, Agent 2, and Agent 3, and Agent 1 and Agent 2 are in an idle state. Call Task 1 assigns a weight of 0.1 to Agent 1, a weight of 0.5 to Agent 2, and a weight of 0.4 to Agent 3. Call Task 1 is executed based on the weights assigned to Agent 1 and Agent 2 in Agent Set 1. Agent Set 2 is configured with Agent 2 and Agent 3, and Agent 3 is in an idle state. Call Task 1 assigns a weight of 0.3 to Agent 2 and a weight of 0.7 to Agent 3. Call Task 1 is executed based on the weights assigned to Agent 3 in Agent Set 2.

[0135] In this embodiment of the application, for each seat to which at least one seat set belongs, the target call task is executed based on the target call task assigned to the seat set and the allocation weight of the target call task to the seat in the seat set to which it belongs. In this way, the same seat can execute call tasks in different seat sets, which improves the efficiency of task processing.

[0136] In some embodiments, the call task processing method provided in this application can be applied to the cloud technology field. The method involves obtaining the allocation weights of call tasks to idle agents on a cloud platform, then obtaining the call parameters for executing call tasks in a first time period. Based on the allocation weights and call parameters, the number of calls in a second time period is determined. The first and second time periods are adjacent time periods. Then, the call tasks are executed based on the number of calls and the allocation weights. Thus, by combining the allocation weights of call tasks to idle agents and the call parameters for executing call tasks in the first time period, the cloud server determines the number of calls in the second time period, taking into account both the agent task allocation weight dimension and the call parameter dimension to predict the number of calls, thereby improving the accuracy of predicting the number of calls. By using the number of calls and the allocation weights of call tasks to idle agents, the cloud server can allocate idle agents to execute call tasks, avoiding an excessive number of idle agents, improving agent utilization, and thus improving the efficiency of call task processing.

[0137] By applying the above embodiments of this application, the allocation weight of call tasks to idle agents is obtained, then the call parameters for executing call tasks in the first time period are obtained, and then the number of calls in the second time period is determined based on the allocation weight and call parameters. The first and second time periods are adjacent time periods, and then the call tasks are executed based on the number of calls and the allocation weight. Thus, by combining the allocation weight of call tasks to idle agents and the call parameters for executing call tasks in the first time period to determine the number of calls in the second time period, the prediction of the number of calls is improved by considering both the agent task allocation weight dimension and the call parameter dimension. Accurate call number prediction provides strategic support for call center operation management. Call resources in the call center system can be optimized and configured based on the predicted call number, ensuring stable system operation and avoiding system crashes caused by surges in call volume, which would lead to excessively long user waiting times and affect user experience. By using the call number and the allocation weight of call tasks to idle agents, idle agents can be allocated to execute call tasks, avoiding an excessive number of idle agents, improving agent utilization, and thus improving the efficiency of call task processing.

[0138] The following will describe an exemplary application of the call task processing method provided in the embodiments of this application in the scenario of predicting the number of calls in a call center.

[0139] A call center is a relatively centralized service organization comprised of a group of service personnel. Call centers typically utilize computer communication technology to handle telephone inquiries from businesses and users. Incoming calls can be automatically assigned to personnel with the appropriate skills, and all call information can be recorded and stored. Call centers can handle both inbound and outbound calls, processing user inquiries and consultations while simultaneously conducting outbound calls such as user follow-ups and satisfaction surveys.

[0140] The call center makes a certain number of calls to users daily, establishing contact through agents. Each call needs to be sent to the operator, who submits pre-defined signaling to the call center. The call center receives the signaling, converts it into a corresponding event, and the event determines the agent's status, such as eating, attending a meeting, or resting. Ideally, if a call center agent continuously answers calls during working hours (although it's a call, the system automatically dials, so the agent perceives it as answering), the agent's status will cycle through "Ready" – "In Call" – "After Call (fixed X seconds)" – "Ready" – "...". Only agents in the "Ready" state can answer new calls. If the number of concurrent batch calls made by the call center is too large, the number of users who get through at the same time may exceed the number of agents in the ready state. In this case, some users will hear a waiting voice message saying "Please wait...". If the number of concurrent batch calls made by the call center is too small, the number of users who get through at the same time may be less than the number of agents in the ready state. In this case, some agents will still be in the ready state, and the agents in the ready state are idle agents.

[0141] In related technologies, call center systems predict call volume based on a fixed number of calls made, but they do not consider or weight human factors. The goal is to achieve efficient call volume prediction under a relatively standardized model, reducing the number of users hearing the "Please wait..." message, while simultaneously reducing idle agents and improving agent utilization. The following problems exist in the call volume prediction process of call centers:

[0142] 1) Using the number of users connected in the previous time period to predict the number of calls to be made in the next time period can lead to too many idle agents or too many users hearing waiting tone, which reduces the calling efficiency and utilization rate of agents.

[0143] 2) The number of calls was not predicted by the agent dimension, resulting in low accuracy in predicting the number of calls.

[0144] Example, reference Figure 4 , Figure 4 This is a flowchart illustrating the process of predicting call volume provided in related technologies. In step 401, the call center is activated; in step 402, the next batch of calls is made based on the previous batch of call volume; in step 403, the user's phone rings; in step 404, the user answers; and in step 405, the agent answers.

[0145] This application proposes a call task processing method to address the problems existing in related technologies, which includes the following improvements compared to related technologies:

[0146] The task allocation weight dimension of the agents is increased, and the actual effective output of the agents is used as the assessment indicator to realize the prediction of the number of calls. That is, an agent may be assigned to multiple skill groups (i.e. agent sets), and the same agent can perform multiple call tasks, which helps to improve the overall call detail record connection volume.

[0147] The embodiments of this application can be applied to call center back-end services, in call scenarios where the call center system makes a predicted number of calls to contact users, or uses virtual robots, or interactive voice response systems, etc.

[0148] For example, at 7:00 AM every day, the call center system stores the list of calls to be dialed that day in the business database. A day includes multiple time periods, and the number of calls to be dialed that day is the total number of calls across all these time periods. The number of calls is allocated according to the total number of people in each skill group. For example, skill group 1 has 50 people, and skill group 2 has 30 people. Call task lists are created; for example, call task 1 is to make 50,000 calls, and call task 2 is to make 100,000 calls. Skill groups 1 and 2 can be assigned to execute call task 1, and the task allocation weight for each agent within their respective skill group can be configured. For example, call task 1 might assign agent 1 a weight of 0.4 within skill group 1, and call task 1 might assign agent 1 a weight of 0.6 within skill group 2.

[0149] For example, in Call Task 2, 100,000 calls can be dialed automatically through the call center system. It's not necessary to complete all 100,000 calls. If the calls are not completed, strategies such as increasing the number of skilled workers or adjusting the dialing time for the day can be considered. During the call process, as the call is transmitted to the operator, events such as call arrival, ringing, and rejection occur simultaneously. Accumulating these events over 3-5 seconds, the number of calls in the next time period for each call task is calculated using a cross-modal cross-strategy algorithm, i.e., a formula for predicting the number of calls.

[0150] For example, the predicted number of calls can be determined using the following formula (8):

[0151] OCP = min(NFC, NSC) (8)

[0152] Wherein, OCP represents the predicted number of calls, NFC represents the first number of calls, and NSC represents the second number of calls. The first number of calls is the sum of the task allocation weights of each available agent in the call task.

[0153] For example, skill group 1 is designated to execute call task 1. Skill group 1 is configured with agent 1, agent 2, and agent 3. The weight assigned to agent 1 for call task 1 is 1, the weight assigned to agent 2 is 0.5, and the weight assigned to agent 3 is 0.5. If agents 1, 2, and 3 are all idle agents, the sum of the task assignment weights assigned to each idle agent by call task 1 is 2. If agent 3 is an idle agent, the sum of the task assignment weights assigned to each idle agent by call task 1 is 0.5.

[0154] For example, the number of second calls can be determined using the following formula (7):

[0155] NSC=FA-NC*SR+AC*(1-e^(-TR / TC))+AP)*MAP / (UR*SR) (7)

[0156] Wherein, NSC represents the number of second calls, FA represents the number of second agents, NC represents the number of calls in progress, SR represents the connection success rate, AC represents the number of first agents, TR represents the average ringing time, TC represents the service time, AP represents the number of third agents, MAP represents the adjustment factor, and UR represents the call abandonment rate.

[0157] Available agent information can be uploaded to the call platform. The number of available agents refers to the number of agents who are actually available and can communicate directly with users. The adjustment coefficient is a value within the range of 0-100. The service time includes the call time and the post-call time. The post-call time is a uniformly configured time of 0-100 seconds for each skill group.

[0158] For example, the connection success rate can be determined using the following formula (1):

[0159] SR = NCC / NOC (1)

[0160] SR represents the call connection success rate, NCC represents the number of calls connected, and NOC represents the number of calls made.

[0161] For example, the call abandonment rate can be determined using the following formula (5):

[0162] UR = NDC / NCC (5)

[0163] Wherein, UR represents the call abandonment rate, NDC represents the number of call hang-ups, and NCC represents the number of call connections.

[0164] For example, the average ringing time can be determined using the following formula (3):

[0165] TR = NOC / SCR (3)

[0166] Where TR represents the average ringing time, NOC represents the number of calls made, and SCR represents the sum of ringing times.

[0167] Example, reference Figure 5 , Figure 5 This is a flowchart illustrating the process of predicting the number of calls provided in an embodiment of this application. In step 501, the call center is activated; in step 502, the number of calls is predicted, wherein the number of calls is predicted using a cross-modal cross-strategy algorithm; in step 503, available agents are identified; in step 504, the user's phone rings; in step 505, the user answers; and in step 506, an available agent answers.

[0168] In the aforementioned application scenario of predicting call volume in call centers, the cross-modal cross-strategy pattern algorithm is used to predict call volume. By combining different call tasks and agent task allocation weights, the number of idle agents is reduced, the agent connection rate and utilization rate are improved, and the user experience is enhanced.

[0169] The following continues to describe the exemplary structure of the call task processing device 455 provided in the embodiments of this application as a software module. In some embodiments, such as Figure 2 As shown, the software modules stored in the call task processing device 455 in the memory 450 may include: a first acquisition module 4551, used to acquire the allocation weight of the call task to the idle agent; a second acquisition module 4552, used to acquire the call parameters for executing the call task in a first time period; a quantity determination module 4553, used to determine the number of calls in a second time period based on the allocation weight and the call parameters, wherein the first time period and the second time period are adjacent time periods; and a task execution module 4554, used to execute the call task based on the number of calls and the allocation weight.

[0170] In some embodiments, the quantity determination module 4553 is further configured to accumulate the allocation weights of the call task to different available agents to obtain a sum; determine a first call quantity based on the sum; determine a second call quantity based on the call parameters; determine the minimum value between the first call quantity and the second call quantity, and determine the minimum value as the call quantity for the second time period.

[0171] In some embodiments, the call parameters include: number of calls made, number of calls connected, number of calls disconnected, average ringing time, and service time. The quantity determination module 4553 is further configured to acquire the number of calls in progress, the number of first agents in a call state, the number of second agents with available seats, and the number of third agents in a post-call state; determine the connection success rate based on the number of calls made and the number of calls connected, and determine the predicted number of connected calls based on the number of calls in progress and the connection success rate; determine a first predicted value based on service time, average ringing time, and the number of first agents; determine the call abandonment rate based on the number of calls connected and the number of calls disconnected, and determine the predicted connection success rate based on the call abandonment rate and the connection success rate; and determine a second number of calls based on the number of second agents, the number of third agents, the predicted number of connected calls, the first predicted value, and the predicted connection success rate.

[0172] In some embodiments, the quantity determination module 4553 is further configured to determine the difference between the second number of agents and the predicted number of connected calls as the number of available agents; determine the sum of the number of available agents, the first predicted value, and the third number of agents as the number of candidate calls; adjust the number of candidate calls using a preset adjustment coefficient to obtain the predicted number of calls; and determine the second number of calls based on the predicted number of calls and the predicted connection success rate.

[0173] In some embodiments, a call task corresponds to multiple agent sets. The task execution module 4554 is further configured to obtain the number of fourth agents with free seats in the agent set; determine the task weight corresponding to the agent set based on the number of fourth agents and the number of second agents; determine the number of calls to be allocated to the agent set based on the task weight corresponding to the agent set and the number of calls; and allocate call tasks to the free seats in the agent set based on the number of calls allocated to the agent set and the allocation weight.

[0174] In some embodiments, the task execution module 4554 is further configured to, when at least two call tasks are assigned to an idle agent, randomly select one call task from the at least two call tasks as the target call task for the idle agent; or, obtain the allocation weight of each call task to the idle agent; and determine the call task with the highest allocation weight as the target call task for the idle agent.

[0175] This application provides a computer program product, which includes computer-executable instructions or a computer program stored in a computer-readable storage medium. The processor of an electronic device reads the computer-executable instructions or computer program from the computer-readable storage medium and executes the computer-executable instructions or computer program, causing the electronic device to perform the call task processing method described above in this application.

[0176] This application provides a computer-readable storage medium storing computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are executed by a processor, the processor will execute the call task processing method provided in this application. For example, ... Figure 3A The call task processing method is shown.

[0177] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0178] In some embodiments, computer-executable instructions may take the form of programs, software, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

[0179] As an example, computer-executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple co-located files (e.g., files that store one or more modules, subroutines, or code sections).

[0180] As an example, computer-executable instructions can be deployed to execute on a single electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0181] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A call task processing method, characterized in that, The method includes: Obtain the allocation weight of call tasks to available agents; Obtain the call parameters for executing the call task during the first time period; Based on the allocation weights and the call parameters, the number of calls in the second time period is determined, wherein the first time period and the second time period are adjacent time periods. The call task is executed based on the number of calls and the allocation weight.

2. The method according to claim 1, characterized in that, Determining the number of calls in the second time period based on the allocation weights and the call parameters includes: The weights assigned to different available agents for the call task are summed to obtain the cumulative sum; Based on the sum, the first number of calls is determined; Based on the call parameters, determine the second number of calls; Determine the minimum value between the first number of calls and the second number of calls, and set the minimum value as the number of calls in the second time period.

3. The method according to claim 2, characterized in that, The call parameters include: number of calls made, number of calls connected, number of calls disconnected, average ringing time, and service time. Determining the second number of calls based on these call parameters includes: Get the number of agents currently making calls, the number of first agents in a call state, the number of second agents with available seats, and the number of third agents in a post-call state; The connection success rate is determined based on the number of calls made and the number of calls connected, and the predicted number of connected calls is determined based on the number of calls in progress and the connection success rate. A first predicted value is determined based on the business hours, the average ringing time, and the number of the first agents; The call abandonment rate is determined based on the number of calls connected and the number of calls hung up, and the predicted connection success rate is determined based on the call abandonment rate and the connection success rate. The second number of calls is determined based on the second number of agents, the third number of agents, the predicted number of connected calls, the first predicted value, and the predicted connection success rate.

4. The method according to claim 3, characterized in that, The step of determining the second number of calls based on the second number of agents, the third number of agents, the predicted number of connected calls, the first predicted value, and the predicted connection success rate includes: The difference between the second number of seats and the predicted number of connected calls is determined as the number of available seats; The sum of the number of available seats, the first predicted value, and the third number of seats is determined as the number of candidate calls; The number of candidate calls is adjusted using a preset adjustment coefficient to obtain the predicted number of calls; The second number of calls is determined based on the predicted number of calls and the predicted connection success rate.

5. The method according to claim 3 or 4, characterized in that, The call task corresponds to multiple agent sets, and the execution of the call task based on the number of calls and the allocation weight includes: Obtain the number of the fourth available seat in the seat set; Based on the number of the fourth seat and the number of the second seat, the task weight corresponding to the seat set is determined; Based on the task weight corresponding to the agent set and the number of calls, the number of calls allocated to the agent set is determined. The call task is assigned to an idle agent in the agent set based on the number of calls allocated to the agent set and the allocation weight.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: If at least two call tasks are assigned to an available agent, one call task is randomly selected from the at least two call tasks as the target call task for the available agent; or... Obtain the allocation weight of each call task to an available agent; The call task with the highest assigned weight is identified as the target call task for the available agent.

7. A call task processing device, characterized in that, The device includes: The first acquisition module is used to acquire the allocation weight of call tasks to available agents; The second acquisition module is used to acquire the call parameters of the call task executed in the first time period; The quantity determination module is used to determine the number of calls in the second time period based on the allocation weight and the call parameters, wherein the first time period and the second time period are adjacent time periods; The task execution module is used to execute the call task based on the number of calls and the allocation weight.

8. An electronic device, characterized in that, The electronic device includes: Memory is used to store executable instructions or computer programs. A processor, when executing computer-executable instructions or computer programs stored in the memory, implements the call task processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or computer program are executed by a processor, the call task processing method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or computer program are executed by a processor, the call task processing method according to any one of claims 1 to 6 is implemented.

Images