Object quantity determination method, device, medium and product for processing incoming line tasks

Abstract

Embodiments of the present application provide a kind of object quantity determination method, equipment, medium and product for processing incoming line task.The method comprises: receiving the object quantity determination request triggered by user, and the object quantity determination request includes: the service type corresponding to incoming line task;According to object quantity determination request, obtain the historical incoming volume data corresponding to service type and the historical active user volume data of application software corresponding to service type;According to historical incoming volume data, determine the dominant incoming volume data corresponding to prediction time period, and according to historical active user volume data, determine the active user volume data corresponding to prediction time period;According to the dominant incoming volume data and active user volume data corresponding to prediction time period, determine the object quantity for processing incoming line task corresponding to prediction time period.Make the object quantity for processing incoming line task of determined prediction time period more accurate.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of data processing, and in particular, to a method, device, medium and product for determining the number of objects for processing incoming line tasks. BACKGROUND

[0002] With the development of mobile Internet, various application software in the form of services are emerging. People enjoy online services, but also face various problems in the service process that need to be solved. Therefore, incoming line services are needed to solve various problems in the service process.

[0003] However, the number of users and demand for services varies in each time period, resulting in different numbers of objects for processing incoming line tasks. In order to better provide incoming line services for users, the number of objects for processing incoming line tasks needs to be determined. In the prior art, only the amount of incoming line tasks is considered to artificially predict and determine the number of objects for processing incoming line tasks.

[0004] In the process of implementing the present application, the inventors have found that at least the following problems exist in the prior art: In the process of determining the number of objects for processing incoming line tasks, only one reference factor is considered, and the determination is artificially made by experience, resulting in low accuracy of the determination. SUMMARY

[0005] Embodiments of the present application provide a method, device, medium and product for determining the number of objects for processing incoming line tasks, to solve the technical problem that in the prior art, only one reference factor is considered in the process of determining the number of objects for processing incoming line tasks, and the determination is artificially made by experience, resulting in low accuracy of the determination.

[0006] In a first aspect, embodiments of the present application provide a method for determining the number of objects for processing incoming line tasks, comprising:

[0007] receiving an object number determination request triggered by a user, the object number determination request including a business type corresponding to an incoming line task;

[0008] According to the object number determination request, historical incoming line amount data corresponding to the business type and historical active user amount data of application software corresponding to the business type are obtained;

[0009] According to the historical incoming line amount data, dominant incoming line amount data corresponding to a prediction time period is determined, and according to the historical active user amount data, active user amount data corresponding to the prediction time period is determined;

[0010] According to the dominant incoming line amount data and active user amount data corresponding to the prediction time period, the number of objects for processing incoming line tasks corresponding to the prediction time period is determined.

[0011] In a second aspect, an embodiment of the present application provides an object quantity determination device for processing an incoming task, comprising:

[0012] a receiving module configured to receive an object quantity determination request triggered by a user, wherein the object quantity determination request comprises a service type corresponding to the incoming task;

[0013] a obtaining module configured to obtain historical incoming quantity data corresponding to the service type and historical active user quantity data of application software corresponding to the service type according to the object quantity determination request;

[0014] a determining module configured to determine dominant incoming quantity data corresponding to a prediction time period according to the historical incoming quantity data, and determine active user quantity data corresponding to the prediction time period according to the historical active user quantity data;

[0015] The determining module is further configured to determine an object quantity for processing the incoming task corresponding to the prediction time period according to the dominant incoming quantity data and the active user quantity data corresponding to the prediction time period.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor, a memory and a transceiver;

[0017] The processor, the memory and the transceiver are interconnected through a circuit;

[0018] The memory stores computer execution instructions; and the transceiver is configured to transceive data with an object management server.

[0019] The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method in any one of the first aspect.

[0020] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the method in any one of the first aspect.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the method in any one of the first aspect.

[0022] The object quantity determination method, device, medium and product for processing an incoming line task provided by the embodiment of the present application. The object quantity determination method comprises the following steps: receiving an object quantity determination request triggered by a user, wherein the object quantity determination request comprises a service type corresponding to the incoming line task; obtaining historical incoming line quantity data corresponding to the service type and historical active user quantity data of application software corresponding to the service type according to the object quantity determination request; determining dominant incoming line quantity data corresponding to a prediction time period according to the historical incoming line quantity data, and determining active user quantity data corresponding to the prediction time period according to the historical active user quantity data; and determining an object quantity for processing the incoming line task corresponding to the prediction time period according to the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period. Since the object quantity for processing the incoming line task is determined by considering not only the incoming line quantity but also the active user quantity, and the object quantity for processing the incoming line task corresponding to the prediction time period is determined by the historical incoming line quantity data and the historical active user quantity data to determine the incoming line quantity data and the active user quantity data of the prediction time period, and then the object quantity for processing the incoming line task corresponding to the prediction time period is determined by the incoming line quantity data and the active user quantity data corresponding to the prediction time period, the data corresponding to the prediction time period can be accurately determined by the historical data, and the potential relationship between the object quantity for processing the incoming line task and the incoming line quantity and the active user quantity can be determined by the historical data, so that the object quantity for processing the incoming line task of the prediction time period is more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, further serve to explain the principles of the present disclosure.

[0024] Figure 1 is a network architecture diagram of the object quantity determination method for processing an incoming line task that can be implemented by the embodiment of the present application;

[0025] Figure 2 is a flowchart of the object quantity determination method for processing an incoming line task provided by an embodiment of the present application;

[0026] Figure 3 is an operation interface diagram of the object quantity determination method for processing an incoming line task that can be implemented by the embodiment of the present application;

[0027] Figure 4 is a flowchart of the object quantity determination method for processing an incoming line task provided by another embodiment of the present application;

[0028] Figure 5 is a schematic diagram of historical incoming line quantity data curves in the embodiment of the present application;

[0029] Figure 6is a flowchart of step 206 in the object quantity determination method for processing incoming line tasks according to another embodiment of the present application;

[0030] Figure 7 is a flowchart of step 207 in the object quantity determination method for processing incoming line tasks according to another embodiment of the present application;

[0031] Figure 8 is a flowchart of step 2071 in the object quantity determination method for processing incoming line tasks according to another embodiment of the present application;

[0032] Figure 9 is a flowchart of step 209 in the object quantity determination method for processing incoming line tasks according to another embodiment of the present application;

[0033] Figure 10 is a structural diagram of the object quantity determination device for processing incoming line tasks according to an embodiment of the present application;

[0034] Figure 11 is a structural diagram of the electronic device for implementing the object quantity determination method for processing incoming line tasks according to an embodiment of the present application;

[0035] Figure 12 is a block diagram of the electronic device for implementing the object quantity determination method for processing incoming line tasks according to an embodiment of the present application.

[0036] The specific embodiments of the present disclosure have been shown through the above-described drawings, and will be described in more detail hereinafter. These drawings and written descriptions are not intended to limit the scope of the present disclosure concept in any way, but to illustrate the present disclosure concept to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0037] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same or similar components are denoted by the same or similar reference numerals throughout the drawings and the following description, unless otherwise specified. The embodiments described in the following exemplary embodiments are not representative of all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0038] First, the terms related to the embodiments of the present application are explained:

[0039] Incoming line quantity: refers to the sum of the number of connected telephone and / or the number of online chat records.

[0040] Active user quantity: refers to the number of users who log in or use certain application software, excluding the number of users who repeatedly log in.

[0041] For clearly understanding the technical solutions of the present application, the prior art solutions are introduced in detail.

[0042] In the prior art, when determining the number of objects for processing incoming tasks, the incoming volume of the incoming tasks is generally considered to artificially predict and determine the number of objects for processing the incoming tasks.

[0043] Specifically, the commonly used methods include a qualitative market survey method, a personal experience judgment method and an expert market survey method.

[0044] In the qualitative market survey method, the information, experience and comprehensive judgment ability mastered by preset personnel are mainly relied on to predict the future situation and development trend, and then determine the number of objects for processing the incoming tasks.

[0045] In the personal experience judgment method, the number of objects for processing the incoming tasks is determined by preset personnel through analysis, judgment and reasoning on the incoming volume of the incoming tasks according to personal experience and knowledge. Under the premise that the preset personnel are experienced, and the existing data are detailed and accurate, the number of objects for processing the incoming tasks determined by this method can be accurate.

[0046] In the expert market survey method, after the number of objects for processing the incoming tasks is determined, the number is collated, summarized and counted, and then anonymously fed back to each expert. Then, the opinions are again solicited, and the number is again summarized, counted and fed back to each expert until a stable number of objects for processing the incoming tasks is obtained. In order to eliminate the mutual influence among the members solicited for opinions, the participating experts can be mutually unknown. This way of using anonymity and repeatedly consulting opinions for back-to-back communication can fully exert the personal wisdom, knowledge and experience of the experts, and finally obtain a number of objects for processing the incoming tasks that can reflect the will of the group.

[0047] Therefore, in the process of determining the number of objects for processing the incoming tasks in the prior art, the reference factor is single, and the number is artificially determined through experience, which leads to low accuracy of the determination.

[0048] Therefore, in the face of the technical problems of the prior art, the inventors found through creative research that although the number of objects processing incoming line tasks is mainly related to the number of incoming lines, it is also related to the number of active users logging in or using application software. The degree of correlation between the number of objects processing incoming line tasks and the number of incoming lines and the number of active users has certain regularity. And according to the incoming line quantity data that has occurred in history, the dominant incoming line quantity data corresponding to the prediction time period can be determined. According to the active user quantity data that has occurred in history, the active user quantity data corresponding to the prediction time period can be determined. Therefore, the line quantity data and the active user quantity data of the prediction time period can be determined according to the historical data. Then, the number of objects processing incoming line tasks corresponding to the prediction time period is determined according to the potential relationship between the number of objects processing incoming line tasks and the number of incoming lines and the number of active users. Since the number of objects processing incoming line tasks is determined not only by considering the number of incoming lines, but also by considering the number of active users, and the number of objects processing incoming line tasks is determined by first determining the incoming line quantity data and the active user quantity data of the prediction time period through historical incoming line quantity data and historical active user quantity data, and then determining the number of objects processing incoming line tasks corresponding to the prediction time period through the incoming line quantity data and the active user quantity data corresponding to the prediction time period, the data corresponding to the prediction time period can be accurately determined through historical data, and the potential relationship between the number of objects processing incoming line tasks and the number of incoming lines and the number of active users can be determined through historical data, and the number of objects processing incoming line tasks corresponding to the prediction time period is more accurate.

[0049] Therefore, based on the above creative findings, the inventors propose the technical solutions of the embodiments of the present application. The network architecture of the object quantity determination method for processing incoming tasks provided by the embodiments of the present application is introduced as follows. The network architecture of the object quantity determination method for processing incoming tasks provided by the present embodiment includes an application software server 1, an incoming quantity management server 2, an electronic device 3, and an object management server 4. The electronic device 3 is in communication connection with the application software server 1, the incoming quantity management server 2, and the object management server 4 respectively. The active user quantity data of the active users logging in or using the application software can be monitored in the application software server 1. The incoming quantity data of each time period can be monitored in the incoming quantity management server 2. The electronic device 3 can provide the client of the object quantity determination method for processing incoming tasks provided by the present application to the user. The user can trigger the object quantity determination request through the operation interface of the client. The electronic device 3 receives the object quantity determination request triggered by the user. The service type in the object quantity determination request is analyzed to determine the service type. The application software server 1 and the incoming quantity management server 2 are accessed according to the service type respectively. The historical active user quantity data of the application software corresponding to the service type is obtained from the application software server 1. The historical incoming quantity data corresponding to the service type is obtained from the incoming quantity management server 2. The electronic device 3 determines the dominant incoming quantity data corresponding to the prediction time period according to the historical incoming quantity data, and determines the active user quantity data corresponding to the prediction time period according to the historical active user quantity data. The object quantity for processing incoming tasks corresponding to the prediction time period is determined according to the dominant incoming quantity data and the active user quantity data corresponding to the prediction time period. The object quantity can be sent to the object management server 4, so that the object management server 4 adjusts the object quantity in the prediction time period.

[0050] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems are described in detail in the specific embodiments below. The specific embodiments below can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0051] Embodiment one

[0052] Figure 2 is a flowchart of the object quantity determination method for processing incoming tasks provided by an embodiment of the present application, as Figure 2 shown, the execution subject of the object quantity determination method for processing incoming tasks provided by the present embodiment is an object quantity determination device for processing incoming tasks, which can be located in an electronic device. Therefore, the object quantity determination method for processing incoming tasks provided by the present embodiment includes the following steps:

[0053] In step 101, a user triggers an object quantity determination request, and the object quantity determination request includes a service type corresponding to the incoming task.

[0054] In this embodiment, a client for processing the object quantity determination method of the incoming task can be provided to the user. When the user has a demand for determining the object quantity of the incoming task in the prediction time period, the object quantity determination request is triggered by operating on the operation interface of the client.

[0055] As shown in the above table, the service type can be selected or input on the operation interface of the client, and the service type is carried into the object quantity determination request by triggering the "determine" button and sent to the electronic device. After the electronic device receives the object quantity determination request, the object quantity determination request is parsed to obtain the service type corresponding to the incoming task. Figure 3

[0056] The service type is the service type of the incoming task processed by the object. For example, the service type can be a complaint service type, a white list service type, etc. For example, the selected service type in the above table is a complaint service type. Figure 3

[0057] In step 102, according to the object quantity determination request, the historical incoming quantity data corresponding to the service type and the historical active user quantity data of the application software corresponding to the service type are obtained.

[0058] In this embodiment, the incoming quantity management server can monitor the incoming quantity data of each time period, and the electronic device can access the incoming quantity management server to obtain the historical incoming quantity data corresponding to the service type. The application software server can monitor the active user quantity data of the login or use of the application software, and the electronic device can access the application software server to obtain the historical active user quantity data of the application software corresponding to the service type.

[0059] In this embodiment, after the incoming quantity management server monitors the incoming quantity data of each time period, the incoming quantity data of each time period can be synchronized to the electronic device, and the electronic device can store the incoming quantity data of each time period. After the application software server monitors the active user quantity data of the login or use of the application software, the active user quantity data of the login or use of the application software can be synchronized to the electronic device, and the electronic device can store the active user quantity data of the login or use of the application software. When the electronic device obtains the historical incoming quantity data corresponding to the service type and the historical active user quantity data of the application software corresponding to the service type, the electronic device obtains the historical incoming quantity data corresponding to the service type and the historical active user quantity data of the application software corresponding to the service type from the local.

[0060] ​​In step 103, the dominant incoming line quantity data corresponding to the prediction time period is determined according to the historical incoming line quantity data, and the active user quantity data corresponding to the prediction time period is determined according to the historical active user quantity data.

[0061] In the embodiment, the prediction time period can be a specific time period set in advance, or can be a current time period.

[0062] The incoming line quantity data corresponding to the prediction time period determined according to the historical incoming line quantity data is the dominant incoming line quantity data.

[0063] In the embodiment, the prediction model can be used to predict the dominant incoming line quantity data corresponding to the prediction time period according to the historical incoming line quantity data, so as to determine the dominant incoming line quantity data corresponding to the prediction time period. The prediction model can also be used to predict the active user quantity data corresponding to the prediction time period according to the historical active user quantity data, so as to determine the active user quantity data corresponding to the prediction time period.

[0064] The prediction model can be any one of the following prediction models: an autoregressive model (AR for short), a moving average model (MA for short), an autoregressive moving average model (ARMA for short), or a difference integrated moving average autoregressive model (ARIMA for short).

[0065] In step 104, the number of objects processing incoming line tasks corresponding to the prediction time period is determined according to the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period.

[0066] The object processing the incoming line task can be an employee or an intelligent robot, and the embodiment does not limit the type of object processing the incoming line task.

[0067] In the embodiment, the auxiliary incoming line quantity data of the prediction time period can be determined according to the active user quantity data of the prediction time period, and then the total incoming line quantity data in the prediction time period can be determined according to the dominant incoming line quantity data and the auxiliary incoming line quantity data corresponding to the prediction time period. Finally, the number of objects processing incoming line tasks corresponding to the prediction time period is determined according to the total incoming line quantity data.

[0068] Alternatively, in the embodiment, the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period can be input into the deep learning model trained to convergence. The deep learning model trained to convergence determines the number of objects processing incoming line tasks corresponding to the prediction time period according to the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period, and outputs the number of objects processing incoming line tasks corresponding to the prediction time period.

[0069] The method for determining the number of objects to process incoming tasks provided in this embodiment receives a user-triggered object quantity determination request, which includes: the business type corresponding to the incoming task; based on the object quantity determination request, it obtains historical incoming call volume data corresponding to the business type and historical active user volume data of the application software corresponding to the business type; based on the historical incoming call volume data, it determines the dominant incoming call volume data corresponding to the prediction time period, and based on the historical active user volume data, it determines the active user volume data corresponding to the prediction time period; based on the dominant incoming call volume data and the active user volume data corresponding to the prediction time period, it determines the number of objects to process incoming tasks corresponding to the prediction time period. Because the determination of the number of objects to process incoming tasks considers not only the number of incoming calls but also the number of active users, and because the determination of the number of objects to process incoming tasks is made by first determining the number of incoming calls and active users for the prediction period using historical data, and then determining the number of objects to process incoming tasks for the prediction period using the corresponding data, it is possible to accurately determine the data for the prediction period using historical data. Furthermore, it is possible to determine the potential relationship between the number of objects to process incoming tasks and the number of incoming calls and active users using historical data, thereby making the determined number of objects to process incoming tasks for the prediction period more accurate.

[0070] Example 2

[0071] Figure 4 This is a flowchart illustrating a method for determining the number of objects for processing incoming tasks according to another embodiment of the present invention, as shown below. Figure 4 As shown, the method for determining the number of objects for processing incoming tasks provided in this embodiment is a further refinement of steps 101-104 based on Embodiment 1 of the present invention, and also includes a step of sending the number of objects to the object management server so that the object management server can adjust the number of objects within the predicted time period. Therefore, the method for determining the number of objects for processing incoming tasks provided in this embodiment includes the following steps:

[0072] Step 201: Receive a user-triggered request to determine the number of objects. The request includes the business type and predicted time period corresponding to the incoming task.

[0073] In this embodiment, the request to determine the number of objects includes not only the business type corresponding to the incoming task, but also the predicted time period.

[0074] Specifically, in this embodiment, as Figure 3 As shown, the client's user interface also allows users to select or input forecast time periods. Users can select or input the business type and forecast time period through the client's user interface, such as... Figure 3In this embodiment, the input prediction time period is October 01, 2020. The user carries these information to the object quantity determination request by triggering the "OK" button, and sends it to the electronic device.

[0075] In this embodiment, the prediction time period can be a pre-set specific time period, and can also be a current time period, which is not limited in this embodiment. The pre-set specific time period can be a special date time period, such as the Spring Festival period, the Double 11 period, the 618 period, etc.

[0076] Step 202, obtaining the prediction time period from the object quantity determination request.

[0077] In this embodiment, after the electronic device receives the object quantity determination request, the object quantity determination request is parsed to obtain the business type corresponding to the incoming task and the prediction time period.

[0078] Step 203, determining whether the prediction time period is a pre-set specific time period, if yes, executing step 204, otherwise executing step 205.

[0079] Step 204, obtaining the historical incoming quantity data and the historical active user quantity data of the specific time period in history corresponding to the business type.

[0080] Step 205, obtaining the historical incoming quantity data and the historical active user quantity data in a pre-set time period before the current time corresponding to the business type.

[0081] In this embodiment, the specific time period is pre-stored. The prediction time period is compared with the pre-set specific time period to determine whether the prediction time period is included in the pre-set specific time period, or whether the prediction time period is equal to the pre-set specific time period. If yes, the historical incoming quantity of the specific time period in history corresponding to the business type can be obtained from the incoming quantity management server. And the historical active user quantity data of the specific time period in history corresponding to the business type can be obtained from the application software server. If not, the historical incoming quantity data in a pre-set time period before the current time corresponding to the business type can be obtained from the incoming quantity management server, and the historical active user quantity data in a pre-set time period before the current time corresponding to the business type can be obtained from the application software server.

[0082] In this embodiment, the pre-set time period can be several days, several months or several years, which is not limited in this embodiment.

[0083] Exemplarily, if the prediction time period is November 1st and the business type is the complaint type, after judgment, the prediction time period is included in the pre-set specific time period of Double 11, the in-line volume data of the complaint type in the Double 11 period in the previous N years is obtained as the historical in-line volume data, and the active user amount data of the complaint type in the Double 11 period in the previous N years is obtained as the historical active user amount data.

[0084] wherein N is an integer greater than or equal to 1.

[0085] Exemplarily, if the prediction time period is the current day and the business type is the complaint type, after judgment, the current date is April 1st, which is not the pre-set specific time period, the in-line volume data of the previous N days before the current day is obtained as the historical in-line volume data, and the active user amount data of the previous N days before the current day is obtained as the historical active user amount data.

[0086] It should be noted that steps 202-205 are an optional implementation of step 102 in embodiment one.

[0087] Step 206, determining the dominant in-line volume data corresponding to the prediction time period according to the historical in-line volume data, and determining the active user amount data corresponding to the prediction time period according to the historical active user amount data.

[0088] wherein the historical in-line volume data is in-line volume sequence data arranged in historical time.

[0089] Exemplarily, taking October 1, 2020 as an example, the in-line volume management server counts the in-line volume every half an hour, and the historical in-line volume data table as shown in Table 1 can be obtained.

[0090] Table 1: Historical in-line volume data table

[0091]

[0092] wherein the historical in-line volume data in Table 1 is the in-line volume data of one day, and the in-line volume data of each day is arranged according to time, which can form the historical in-line volume data curve as shown in Table 1. Figure 5 From the historical in-line volume data curve, it can be observed that the historical in-line volume data changes periodically by day to some extent, and fluctuates around its mean value, which embodies the characteristics of smooth data.

[0093] Therefore, as an optional implementation, in the embodiment, step 206 of determining the dominant in-line volume data corresponding to the prediction time period according to the historical in-line volume data includes the following steps: Figure 6

[0094] ​In step 2061, it is judged whether the historical incoming line quantity data is stationary data. If yes, step 2063 is executed; otherwise, step 2062 is executed.

[0095] In this embodiment, the historical incoming line quantity data is preprocessed before it is judged whether the historical incoming line quantity data is stationary data. If there is missing data in a historical time period, the missing data is completed. The method of completion is to average the historical incoming line quantity data of the historical time period before and after the missing data. This ensures that the historical incoming line quantity data is a continuous time series data.

[0096] Specifically, in this embodiment, when the ARIMA model is used to determine the dominant incoming line quantity data corresponding to the prediction time period, the historical incoming line quantity data needs to be stationary data. Therefore, it is first judged whether the historical incoming line quantity data is stationary data.

[0097] The stationary data requires that the fitting curve obtained via the sample sequence can continue along the existing form "inertia" in the future period. It also requires that the mean and variance of the sample sequence do not change significantly. Therefore, when judging whether the historical incoming line quantity data is stationary data, it is necessary to judge whether the historical incoming line quantity data curve presents periodic variation to a certain extent and whether it fluctuates around the mean.

[0098] Alternatively, in this embodiment, a feature extraction algorithm can be used to extract features of the historical incoming line quantity data to determine whether the historical incoming line quantity data presents periodic variation and fluctuates around the mean to determine whether the historical incoming line quantity data is stationary data.

[0099] Alternatively, in this embodiment, an ADF algorithm can be used to judge whether the historical incoming line quantity data is stationary data. Specifically, the historical incoming line quantity data is input into the ADF algorithm. The ADF algorithm detects whether the historical incoming line quantity data has a unit root. If the historical incoming line quantity data is stationary data, there is no unit root. If the historical incoming line quantity data is non-stationary data, there is a unit root.

[0100] In step 2062, the historical incoming line quantity data is differentiated until the historical incoming line quantity data is stationary data.

[0101] In this embodiment, if the historical incoming traffic data is determined to be non-stationary data, the historical incoming traffic data is subjected to difference processing. First, first-order difference processing is performed. After the first-order difference processing, it is determined whether the historical incoming traffic data is stationary data. If the historical incoming traffic data is still non-stationary data, second-order difference processing is continued. After the second-order difference processing, it is continued to determine whether the historical incoming traffic data is stationary data. In this way, until the historical incoming traffic data is stationary data.

[0102] In step 2063, the stationary historical incoming traffic data is input into the fitted first difference integrated moving average autoregressive ARIMA model, and the leading incoming traffic data corresponding to the prediction time period is determined and output by the first ARIMA model.

[0103] In this embodiment, if the historical incoming traffic data is stationary data, the historical incoming traffic data is directly input into the fitted first ARIMA model, and the leading incoming traffic data corresponding to the prediction time period is determined and output by the first ARIMA model. If the historical incoming traffic data is non-stationary data, the historical incoming traffic data is subjected to d-order difference processing to form stationary data, and then the stationary historical incoming traffic data is input into the fitted first ARIMA model, and the leading incoming traffic data corresponding to the prediction time period is determined and output by the first ARIMA model.

[0104] The first ARIMA model is a prediction model for determining the leading incoming traffic data corresponding to the prediction time period. The first ARIMA model can be expressed as ARIMA1(p1, d1, q1).

[0105] In the first ARIMA model, there are three adjustable parameters, p1 is the number of autoregressive terms, q1 is the number of moving average terms, and d1 is the number of differences made to make the historical incoming traffic data stationary.

[0106] Specifically, in the fitted first ARIMA model, d1 can be determined by the number of times of difference processing of the historical incoming traffic data. After the historical incoming traffic data is stationary, the autocorrelation function graph and the partial correlation function graph of the historical incoming traffic data are constructed, and the values in the autocorrelation function graph and the partial correlation function graph are used to determine the values of p1 and q1. For example, the partial autocorrelation function Figure Two If the autocorrelation function is attenuated to 0 after the first order and basically falls within the confidence interval, then p1 = 2. The autocorrelation function is attenuated to 0 after the first order, so q1 = 0.

[0107] As an optional implementation, as shown in Figure 6 In this embodiment, the step of determining the active user data corresponding to the prediction time period according to the historical active user data in step 206 includes the following steps:

[0108] Step 2064, judging whether the historical active user amount data is stationary data, if yes, executing step 2066, otherwise executing step 2065.

[0109] The historical active user amount data is active user amount sequence data arranged according to historical time.

[0110] Step 2065, performing difference processing on the historical active user amount data until the historical active user amount data is stationary data.

[0111] Step 2066, inputting the stationary historical active user amount data into the second adaptive difference integrated moving average autoregressive ARIMA model, and determining and outputting the active user amount data corresponding to the prediction time period through the second ARIMA model.

[0112] The second ARIMA model is a prediction model for determining the active user amount data corresponding to the prediction time period. The second ARIMA model can be expressed as ARIMA2(p2, d2, q2).

[0113] In the second ARIMA model, there are three adjustable parameters, p2 is the number of autoregressive terms, q2 is the number of moving average terms, and d2 is the number of differences made to make the historical active user amount data stationary.

[0114] It should be noted that, since the historical incoming line amount data and the historical active user amount data are different, the values of the three parameters in the first ARIMA model and the second ARIMA model can be different.

[0115] In this embodiment, the implementation mode of steps 2064-2066 is similar to that of steps 2061-2063 in this embodiment, and will not be repeated here.

[0116] Step 207, converting the active user amount data corresponding to the prediction time period into auxiliary incoming line amount data in the prediction time period.

[0117] The auxiliary incoming line amount data is incoming line amount data converted from the active user amount data.

[0118] As an optional implementation mode, in this embodiment, as shown in Figure 7 Step 207 includes the following steps:

[0119] Step 2071, determining the conversion weight between the active user amount data corresponding to the prediction time period and the auxiliary incoming line amount data.

[0120] Specifically, in the embodiment, since the object quantity of the processing incoming line task in the prediction time period is closely related to the corresponding dominant incoming line quantity data and the active user quantity data in the prediction time period, and the active user quantity data in the prediction time period is also closely related to the dominant incoming line quantity data in the prediction time period, the active user quantity data in the prediction time period is first converted into auxiliary incoming line quantity data, and then the object quantity of the processing incoming line task in the prediction time period is directly determined according to the total incoming line quantity data in the prediction time period.

[0121] In the conversion of the active user quantity data in the prediction time period into the auxiliary incoming line quantity data, the conversion weight between the active user quantity data and the auxiliary incoming line quantity data is first determined.

[0122] As an optional implementation manner, as shown in the figure, Figure 8 Step 2071 includes the following steps:

[0123] Step 2071a, determining the conversion weight corresponding to the previous prediction time period.

[0124] Step 2072b, determining the adjustment weight according to the size relationship between the actual object quantity corresponding to the previous prediction time period and the determined object quantity.

[0125] Step 2072c, determining the conversion weight corresponding to the prediction time period according to the conversion weight corresponding to the previous prediction time period and the adjustment weight.

[0126] Specifically, in the embodiment, the determination of the object quantity of the processing incoming line task in the prediction time period is a continuous process. For example, the prediction time period is today. After the object quantity of the processing incoming line task in today is determined, the object of the processing incoming line task processes the incoming line task in today, and then the prediction time period becomes tomorrow, and the object quantity of the processing incoming line task in tomorrow is determined. Since the conversion weight between the active user quantity data in the prediction time period and the dominant incoming line quantity data in the prediction time period needs to be continuously debugged to make it more accurate to represent the conversion relationship between the active user quantity data in the prediction time period and the dominant incoming line quantity data in the prediction time period in the initial stage of determining the object quantity of the processing incoming line task, the conversion weight corresponding to the previous prediction time period is first determined, and then the adjustment weight is determined according to the size relationship between the actual object quantity corresponding to the previous prediction time period and the determined object quantity. The adjustment weight can be a value greater than zero or a value less than or equal to zero. Finally, the conversion weight corresponding to the previous prediction time period and the adjustment weight are summed to determine the conversion weight corresponding to the prediction time period.

[0127] Step 2072, converting the active user quantity data corresponding to the prediction time period into auxiliary incoming line quantity data according to the conversion weight.

[0128] In this embodiment, the conversion weight is multiplied by the active user amount data corresponding to the prediction time period, and the product obtained is the auxiliary incoming line amount data.

[0129] In step 208, the total incoming line amount data in the prediction time period is calculated according to the dominant incoming line amount data and the auxiliary incoming line amount data.

[0130] In this embodiment, the dominant incoming line amount data and the auxiliary incoming line amount data are summed, and the sum is determined as the total incoming line amount data.

[0131] In step 209, the object quantity for processing the incoming line task corresponding to the prediction time period is determined according to the total incoming line amount data.

[0132] As an optional implementation, in this embodiment, as shown in FIG. 9, step 209 includes the following steps: Figure 9

[0133] In step 2091, the average incoming line amount of each object for processing the incoming line task in the prediction time period is obtained.

[0134] In step 2092, the object quantity corresponding to the total incoming line amount data and the average incoming line amount is determined.

[0135] In this embodiment, the incoming line amount of each object for processing the incoming line task in the prediction time period is obtained, and the incoming line amount of each object for processing the incoming line task is averaged to obtain the average calculation amount. The quotient of the total incoming line amount data and the average incoming line amount is calculated, and the quotient is determined as the object quantity.

[0136] It can be understood that if the quotient includes a decimal, an integer operation can be performed, so that the obtained object quantity is an integer.

[0137] It should be noted that steps 207-209 are an optional implementation of step 104 in embodiment one.

[0138] In step 210, the object quantity is sent to the object management server, so that the object management server adjusts the object quantity in the prediction time period.

[0139] In this embodiment, the object quantity and the prediction time period are sent to the object management server, the object management server obtains the object quantity in the prediction time period configured in advance, and if the object quantity in the prediction time period configured in advance is different from the object quantity in the prediction time period determined, the object quantity in the prediction time period is adjusted.

[0140] ​The object quantity determination method for processing the incoming line task provided in the embodiment further includes the prediction time period in the object quantity determination request. Accordingly, when the historical incoming line quantity data corresponding to the business type and the historical active user quantity data of the application software corresponding to the business type are acquired according to the object quantity determination request, the prediction time period is acquired from the object quantity determination request. It is determined whether the prediction time period is a specific time period set in advance. If it is determined that the prediction time period is the specific time period, the historical incoming line quantity data and the historical active user quantity data of the specific time period in the history corresponding to the business type are acquired. If it is determined that the prediction time period is not the specific time period, the historical incoming line quantity data and the historical active user quantity data in a preset time period before the current time corresponding to the business type are acquired. Since the acquired historical incoming line quantity data and the historical active user quantity data are similar to the historical incoming line quantity data and the historical active user quantity data in the prediction time period, when the dominant incoming line quantity data corresponding to the prediction time period is determined according to the historical incoming line quantity data, and the active user quantity data corresponding to the prediction time period is determined according to the historical active user quantity data, the determined dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period are more accurate, and thus the determined object quantity for processing the incoming line task corresponding to the prediction time period is more accurate.

[0141] The object quantity determination method for processing the incoming line task provided in the embodiment adopts the adaptive ARIMA model to determine the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period when the dominant incoming line quantity data corresponding to the prediction time period is determined according to the historical incoming line quantity data, and the active user quantity data corresponding to the prediction time period is determined according to the historical active user quantity data. Since the ARIMA model can combine the advantages of other prediction models, the determined dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period are more accurate.

[0142] The object quantity determination method for processing the incoming line task provided in the embodiment converts the active user quantity data corresponding to the prediction time period into auxiliary incoming line quantity data in the prediction time period when the object quantity for processing the incoming line task corresponding to the prediction time period is determined according to the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period. The total incoming line quantity data in the prediction time period is calculated according to the dominant incoming line quantity data and the auxiliary incoming line quantity data. The object quantity for processing the incoming line task corresponding to the prediction time period is determined according to the total incoming line quantity data. The potential relationship between the object quantity for processing the incoming line task and the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period can be converted into the correlation between the object quantity for processing the incoming line task and the incoming line quantity, and thus the determined object quantity for processing the incoming line task is more rapid and efficient.

[0143] Embodiment three

[0144] Figure 10is a structural schematic diagram of an object quantity determination device for processing an incoming line task provided by an embodiment of the present application, as shown Figure 10 The object quantity determination device 30 for processing an incoming line task provided by the embodiment includes a receiving module 31, an obtaining module 32, and a determination module 33.

[0145] The receiving module 31 is configured to receive an object quantity determination request triggered by a user, and the object quantity determination request includes a service type corresponding to the incoming line task. The obtaining module 32 is configured to obtain historical incoming line quantity data corresponding to the service type and historical active user quantity data of application software corresponding to the service type according to the object quantity determination request. The determination module 33 is configured to determine dominant incoming line quantity data corresponding to a prediction time period according to the historical incoming line quantity data, and determine active user quantity data corresponding to the prediction time period according to the historical active user quantity data. The determination module 33 is further configured to determine an object quantity for processing the incoming line task corresponding to the prediction time period according to the dominant incoming line quantity data and the active user quantity data corresponding to the prediction time period.

[0146] Optionally, the object quantity determination request further includes the prediction time period. Correspondingly, the obtaining module 32 is specifically configured to:

[0147] obtain the prediction time period from the object quantity determination request; determine whether the prediction time period is a specific time period set in advance; if it is determined that the prediction time period is the specific time period, obtain historical incoming line quantity data and historical active user quantity data corresponding to the specific time period in the past of the service type; and if it is determined that the prediction time period is not the specific time period, obtain historical incoming line quantity data and historical active user quantity data in a preset time period before a current time corresponding to the service type.

[0148] Optionally, the historical incoming line quantity data is incoming line quantity sequence data arranged in historical time. Correspondingly, when determining the dominant incoming line quantity data corresponding to the prediction time period according to the historical incoming line quantity data, the determination module 33 is specifically configured to:

[0149] determine whether the historical incoming line quantity data is stationary data; if it is determined that the historical incoming line quantity data is non-stationary data, perform difference processing on the historical incoming line quantity data until the historical incoming line quantity data is stationary data; and input the stationary historical incoming line quantity data into an adaptive first difference integrated moving average autoregressive ARIMA model, and determine and output the dominant incoming line quantity data corresponding to the prediction time period through the first ARIMA model.

[0150] Optionally, the historical active user quantity data is active user quantity sequence data arranged in historical time. When determining the active user quantity data corresponding to the prediction time period according to the historical active user quantity data, the determination module 33 is specifically configured to:

[0151] determine whether the historical active user amount data is stationary data; if it is determined that the historical active user amount data is non-stationary data, perform difference processing on the historical active user amount data until the historical active user amount data is stationary data; input the stationary historical active user amount data into a second adaptive difference integrated moving average autoregressive ARIMA model, and determine and output the active user amount data corresponding to the prediction time period through the second ARIMA model.

[0152] Optionally, the determining module 33, in determining the number of objects processing the online task corresponding to the prediction time period according to the dominant online amount data and the active user amount data corresponding to the prediction time period, is specifically configured to:

[0153] convert the active user amount data corresponding to the prediction time period into auxiliary online amount data within the prediction time period; calculate total online amount data within the prediction time period according to the dominant online amount data and the auxiliary online amount data; and determine the number of objects processing the online task corresponding to the prediction time period according to the total online amount data.

[0154] Optionally, the determining module 33, in converting the active user amount data corresponding to the prediction time period into auxiliary online amount data within the prediction time period, is specifically configured to:

[0155] determine a conversion weight between the active user amount data corresponding to the prediction time period and the auxiliary online amount data; and convert the active user amount data corresponding to the prediction time period into the auxiliary online amount data according to the conversion weight.

[0156] Optionally, the determining module 33, in determining the conversion weight between the active user amount data corresponding to the prediction time period and the auxiliary online amount data, is specifically configured to:

[0157] determine a conversion weight corresponding to a previous prediction time period; determine an adjustment weight according to a size relationship between an actual number of objects corresponding to the previous prediction time period and the determined number of objects; and determine the conversion weight corresponding to the prediction time period according to the conversion weight corresponding to the previous prediction time period and the adjustment weight.

[0158] Optionally, the determining module 33, in determining the number of objects processing the online task corresponding to the prediction time period according to the total online amount data, is specifically configured to:

[0159] obtain an average online amount of each object processing the online task within the prediction time period; and determine the corresponding number of objects according to the total online amount data and the average online amount.

[0160] Optionally, the embodiment provides a device for determining the number of objects processing the online task, which further comprises:

[0161] The sending module is configured to send the object quantity to the object management server, so that the object management server adjusts the object quantity in the prediction time period.

[0162] The object quantity determination device for processing the incoming line task provided by the embodiment can perform Figure 2 、 Figure 4 、 Figures 6-9 The technical solutions of the method embodiments shown in Figure 2 、 Figure 4 、 Figures 6-9 The implementation principles and technical effects of the method embodiments shown in

[0163] Embodiment four

[0164] Figure 11 is a structural schematic diagram of an electronic device for implementing the object quantity determination method for processing the incoming line task. As shown in Figure 11 The electronic device 40 provided by the embodiment includes a memory 41, a processor 42 and a transceiver 43.

[0165] The processor 42, the memory 41 and the transceiver 43 are interconnected by a circuit;

[0166] The memory 41 stores computer execution instructions; and the transceiver 43 is configured to transceive data with the object management server.

[0167] The at least one processor 42 executes the computer execution instructions stored in the memory, so that the at least one processor executes the method in the above-mentioned embodiment one or embodiment two.

[0168] Embodiment five

[0169] Figure 12 is a block diagram of an electronic device for implementing the object quantity determination method for processing the incoming line task. As shown in Figure 12 The electronic device 500 provided by the embodiment can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0170] The electronic device 500 can include one or more of the following components: a processing component 502, a memory 504, a power supply component 506, a multimedia component 508, an audio component 510, an input / output (I / O) interface 512, a sensor component 514, and a communication component 516.

[0171] The processing component 502 generally controls the overall operations of the device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 can include one or more processors 520 to execute instructions

[0172] The memory 504 is configured to store various types of data to support operations of the device 500. Examples of these data include instructions for any applications or methods operating on the device 500, contact data, phonebook data, messages, pictures, videos, and so on. The memory 504 can be implemented by any type of volatile or non-volatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disks, or optical disks.

[0173] The power component 506 supplies electrical power for the various components of the device 500. The power component 506 can include a power supply management system, one or more power sources, and other components associated with generating, managing, and distributing electrical power for the device 500.

[0174] The multimedia component 508 includes a screen providing an output interface between the device 500 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swiping, and gestures on the touch panel. The touch sensors can not only sense the boundary of a touch or swipe action, but also detect duration and pressure associated with the touch or swipe action. In some embodiments, the multimedia component 508 includes a front-facing camera and / or a rear-facing camera. The front-facing camera and / or the rear-facing camera can receive external multimedia data when the device 500 is in an operation mode, such as a shooting mode or a video mode. Each of the front-facing camera and the rear-facing camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0175] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC) that is configured to receive an external audio signal when the device 500 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 504 or transmitted via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0176] The I / O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which can include a keypad, a click wheel, buttons, and so on. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0177] The sensor component 514 includes one or more sensors for providing status assessments of various aspects of the device 500. For example, the sensor component 514 can detect an open / closed position of the device 500, relative positioning of components, such as a display and a keypad of the device 500, a change of position of the device 500 or a component of the device 500, presence or absence of user contact with the device 500, a change in orientation or acceleration / deceleration of the device 500, and a temperature change of the device 500, and the like. The sensor component 514 can include an orientation sensor, an altimeter, a proximity sensor, an accelerometer, a gyroscope, a magnetometer, a pressure sensor or a temperature sensor.

[0178] The communication component 516 is configured to facilitate wired or wireless communication between the device 500 and other devices. The device 500 can access a wireless network based on a corresponding communication standard, such as WiFi, 2G, or 3G, or a combination thereof. In an example embodiment, the communication component 516 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 516 further includes a Near Field Communication (NFC) module to promote short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) techniques, infrared data association (IrDA) techniques, ultra-wideband (UWB) techniques, Bluetooth (BT) techniques, and other techniques.

[0179] In an exemplary embodiment, the electronic device 500 can be implemented with one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements for performing the above-described methods.

[0180] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 504 including instructions, is also provided, which can be executed by the processor 520 of the apparatus 500 to accomplish the above-described methods. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disc, and an optical data storage device, etc.

[0181] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the object quantity determination method for processing a line task provided in Embodiment One or Embodiment Two.

[0182] In an exemplary embodiment, a computer program product is also provided, which includes a computer program that is executed by a processor to perform the object quantity determination method for processing a line task provided in Embodiment One or Embodiment Two.

[0183] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the aspects of the present disclosure disclosed herein. It is intended that the present disclosure cover any and all variations of the present disclosure including those variations that can be incorporated into other aspects of the present disclosure. It is intended that the present disclosure include modifications and variations of the application included within the scope of the appended claims and their equivalents. It is intended that the scope of the present disclosure shall be limited only by the appended claims. If any provision of the patent law or rules or any other provision of law infringes the patent rights, this patent shall be limited only by that clause and / or provision of law.

[0184] It is to be understood that the present disclosure is not limited to the precise construction herein described and as shown in the attached drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the present disclosure. The scope of the present disclosure is to be interpreted only according to the appended claims.

Claims

1. An object quantity determination method for processing an incoming line task, characterized by, The method comprises the following steps: receiving a user triggered object quantity determination request, wherein the object quantity determination request comprises a service type corresponding to an incoming line task; obtaining historical incoming line quantity data corresponding to the service type and historical active user quantity data of application software corresponding to the service type according to the object quantity determination request, wherein the active user quantity refers to the number of users who log in or use the application software, excluding the number of repeatedly logged-in users; determining dominant incoming line quantity data corresponding to a prediction time period according to the historical incoming line quantity data, and determining active user quantity data corresponding to the prediction time period according to the historical active user quantity data; converting the active user quantity data corresponding to the prediction time period into auxiliary incoming line quantity data within the prediction time period; calculating total incoming line quantity data within the prediction time period according to the dominant incoming line quantity data corresponding to the prediction time period and the auxiliary incoming line quantity data; determining the number of objects for processing the incoming line task corresponding to the prediction time period according to the total incoming line quantity data.

2. The method of claim 1, wherein, The object quantity determination request further comprises a prediction time period; The method of obtaining the historical incoming line quantity data corresponding to the service type and the historical active user quantity data of the application software corresponding to the service type according to the object quantity determination request comprises the following steps: obtaining the prediction time period from the object quantity determination request; determining whether the prediction time period is a specific time period set in advance; if it is determined that the prediction time period is the specific time period, obtaining historical incoming line quantity data and historical active user quantity data of the specific time period in the past corresponding to the service type; if it is determined that the prediction time period is not the specific time period, obtaining historical incoming line quantity data and historical active user quantity data within a preset time period before the current time corresponding to the service type.

3. The method of claim 1, wherein, The historical incoming line quantity data is incoming line quantity sequence data arranged in historical time; The method of determining the dominant incoming line quantity data corresponding to the prediction time period according to the historical incoming line quantity data comprises the following steps: determining whether the historical incoming line quantity data is stationary data; if it is determined that the historical incoming line quantity data is non-stationary data, performing difference processing on the historical incoming line quantity data until the historical incoming line quantity data becomes stationary data; inputting the stationary historical incoming line quantity data into an adapted first difference integrated moving average autoregressive ARIMA model, and determining and outputting the dominant incoming line quantity data corresponding to the prediction time period through the first ARIMA model.

4. The method of claim 1, wherein, The historical active user quantity data is active user quantity sequence data arranged in historical time; The method of determining the active user quantity data corresponding to the prediction time period according to the historical active user quantity data comprises the following steps: determining whether the historical active user quantity data is stationary data; if it is determined that the historical active user quantity data is non-stationary data, performing difference processing on the historical active user quantity data until the historical active user quantity data becomes stationary data; inputting the stationary historical active user quantity data into an adapted second difference integrated moving average autoregressive ARIMA model, and determining and outputting the active user quantity data corresponding to the prediction time period through the second ARIMA model.

5. The method of claim 1, wherein, The converting the active user quantity data corresponding to the prediction time period into auxiliary line-in quantity data in the prediction time period comprises: determining a conversion weight between the active user quantity data corresponding to the prediction time period and the auxiliary line-in quantity data; and converting the active user quantity data corresponding to the prediction time period into the auxiliary line-in quantity data according to the conversion weight.

6. The method of claim 5, wherein, The determining a conversion weight between the active user quantity data corresponding to the prediction time period and the auxiliary line-in quantity data comprises: determining a conversion weight corresponding to a previous prediction time period; determining an adjustment weight according to a size relationship between an actual object quantity corresponding to the previous prediction time period and the determined object quantity; and determining the conversion weight corresponding to the prediction time period according to the conversion weight corresponding to the previous prediction time period and the adjustment weight.

7. The method of claim 1, wherein, The determining an object quantity processing the line-in task corresponding to the prediction time period according to the total line-in quantity data comprises: acquiring an average line-in quantity of each object processing the line-in task in the prediction time period; and determining the corresponding object quantity according to the total line-in quantity data and the average line-in quantity.

8. The method according to any one of claims 1 to 4, characterized in that, After the determining an object quantity processing the line-in task corresponding to the prediction time period according to the dominant line-in quantity data corresponding to the prediction time period and the active user quantity data, the method further comprises: sending the object quantity to an object management server, so that the object management server adjusts the object quantity in the prediction time period.

9. An object quantity determining apparatus for processing an incoming line task, characterized by comprising: The method comprises: a receiving module, configured to receive a user-triggered object quantity determination request, wherein the object quantity determination request comprises a service type corresponding to a line-in task; an acquiring module, configured to acquire historical line-in quantity data corresponding to the service type and historical active user quantity data of application software corresponding to the service type according to the object quantity determination request; the active user quantity refers to a quantity of users logging in or using the application software, excluding a quantity of repeatedly logged-in users; a determining module, configured to determine dominant line-in quantity data corresponding to a prediction time period according to the historical line-in quantity data, and determine active user quantity data corresponding to the prediction time period according to the historical active user quantity data; the determining module is further configured to convert the active user quantity data corresponding to the prediction time period into auxiliary line-in quantity data in the prediction time period; calculating total line-in quantity data in the prediction time period according to the dominant line-in quantity data corresponding to the prediction time period and the auxiliary line-in quantity data; and determining an object quantity processing the line-in task corresponding to the prediction time period according to the total line-in quantity data.

10. The apparatus of claim 9, wherein, The object quantity determination request further comprises a prediction time period; the acquiring module is specifically configured to: acquire the prediction time period from the object quantity determination request; determine whether the prediction time period is a specific time period preset in advance; if the prediction time period is determined to be the specific time period, acquire historical line-in quantity data and historical active user quantity data of the specific time period in history corresponding to the service type; if the prediction time period is determined to be a non-specific time period, acquire historical line-in quantity data and historical active user quantity data in a preset time period before a current time corresponding to the service type.

11. The apparatus of claim 9, wherein, The historical line-in quantity data is line-in quantity sequence data arranged in historical time. The determining module is specifically used for: judging whether the historical in-line quantity data is stationary data; if it is determined that the historical in-line quantity data is non-stationary data, performing difference processing on the historical in-line quantity data until the historical in-line quantity data is stationary data; inputting the stationary historical in-line quantity data into an adapted first difference integrated moving average autoregressive ARIMA model, and determining and outputting the dominant in-line quantity data corresponding to the prediction time period through the first ARIMA model.

12. The apparatus of claim 9, wherein, The historical active user quantity data is active user quantity sequence data arranged in historical time; The determining module is specifically used for: judging whether the historical active user quantity data is stationary data; if it is determined that the historical active user quantity data is non-stationary data, performing difference processing on the historical active user quantity data until the historical active user quantity data is stationary data; inputting the stationary historical active user quantity data into an adapted second difference integrated moving average autoregressive ARIMA model, and determining and outputting the active user quantity data corresponding to the prediction time period through the second ARIMA model.

13. The apparatus of claim 9, wherein, The determining module is specifically used for: determining a conversion weight between the active user quantity data corresponding to the prediction time period and the auxiliary in-line quantity data; converting the active user quantity data corresponding to the prediction time period into the auxiliary in-line quantity data according to the conversion weight.

14. The apparatus of claim 13, wherein, The determining module is specifically used for: determining a conversion weight corresponding to a previous prediction time period; determining an adjustment weight according to a size relationship between an actual object quantity corresponding to the previous prediction time period and the determined object quantity; determining the conversion weight corresponding to the prediction time period according to the conversion weight corresponding to the previous prediction time period and the adjustment weight.

15. The apparatus of claim 9, wherein, The determining module is specifically used for: obtaining an average in-line quantity of each object processing an in-line task in the prediction time period; determining the corresponding object quantity according to the total in-line quantity data and the average in-line quantity.

16. The apparatus of any one of claims 9-12, wherein, Further comprising: a sending module configured to send the object quantity to an object management server, so that the object management server adjusts the object quantity in the prediction time period.

17. An electronic device, comprising: comprising: at least one processor, a memory and a transceiver; the processor, the memory and the transceiver are interconnected through a circuit; the memory stores computer execution instructions; the transceiver is configured to transceive data with an object management server; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method in any one of claims 1-8.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

19. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-8.

Images