Network scheduling method, device, equipment and storage medium

Abstract

The embodiments of this specification relate to the field of big data processing technology, and provide a method, device, equipment, and storage medium for scheduling outlets, the method comprising: selecting a target outlet from an outlet set; obtaining the historical business volume of the target outlet, and the scheduling impact factor of the target outlet in a target time period; using the historical business volume and the scheduling impact factor as input, calling an autoregressive moving average model to predict the predicted business volume of the target outlet in the target time period; obtaining the scheduling constraints of the target outlet; constructing a scheduling objective function based on the predicted business volume and the scheduling constraints; and determining the scheduling data of the target outlet by optimizing the scheduling objective function. The embodiments of this specification can improve the efficiency of outlet scheduling, and can improve the matching degree between the scheduling results and the actual business volume requirements.

Description

Technical Field

[0001] The present invention relates to the field of big data processing technology, and in particular to a method, device, equipment and storage medium for scheduling network points. Background Art

[0002] At present, branch scheduling is mostly done manually. For example, taking the human resource scheduling of bank branches (hereinafter referred to as scheduling) as an example, the scheduling of bank branches is generally manually planned by managers based on their experience and the actual rest needs of employees. However, this manual planning method is not only inefficient, but also easily leads to a mismatch between the scheduling results and the actual business volume demand, which easily leads to the problem of excess or insufficient human resources in branches. Summary of the invention

[0003] The purpose of the embodiments of this specification is to provide a network scheduling method, device, equipment and storage medium to improve the efficiency of network scheduling and improve the matching degree between scheduling results and actual business volume requirements.

[0004] To achieve the above objectives, on the one hand, an embodiment of this specification provides a method for scheduling network points, including:

[0005] Select a target point from the point set;

[0006] Obtaining the historical business volume of the target outlet and the scheduling influencing factor of the target outlet in the target time period;

[0007] Taking the historical business volume and the scheduling influencing factor as input, calling the autoregressive moving average model to predict the predicted business volume of the target network point in the target time period;

[0008] Obtaining the scheduling constraints of the target outlet;

[0009] Constructing a scheduling objective function according to the predicted business volume and the scheduling constraints;

[0010] The scheduling data of the target network point is determined by optimizing the scheduling objective function.

[0011] In the embodiments of this specification, the autoregressive moving average model includes any one of the following models:

[0012] ARMA model;

[0013] ARIMA model.

[0014] In the embodiment of this specification, the scheduling objective function includes:

[0015]

[0016] In the above formula, min means minimizing the scheduling objective function, t j represents the jth day within n days, represents the predicted business volume of the outlet on the jth day within n days, M represents the number of people on duty at the outlet, I represents the number of posts at the outlet, It means that for any, P mi represents the average business volume handled by the mth person in the ith position, c i represents the labor cost coefficient required for the i-th position, x i represents the number of people working in the i-th position, x ia Represents x i The a character in x ib Represents x i The b role in , st represents the scheduling constraints.

[0017] In the embodiments of this specification, the scheduling constraints include:

[0018]

[0019] Among them, P k represents the kth person, X k Indicates P k Qualifications, T k Indicates P k Available working days, R i Represents x i The value range of S indicates the specified multiple x i The sum, R s Indicates the value range of S.

[0020] In an embodiment of this specification, determining the scheduling data of the target network point by optimizing the scheduling objective function includes:

[0021] The scheduling data of the target network point is determined by optimizing the scheduling objective function through a nonlinear programming algorithm.

[0022] In the embodiments of this specification, the scheduling influencing factors include any one or more combinations of the following:

[0023] Weather conditions;

[0024] Holidays;

[0025] Network level.

[0026] In the embodiments of this specification, the scheduling constraints include any one or more combinations of the following:

[0027] Personnel qualifications;

[0028] Number of personnel;

[0029] Personnel leave information;

[0030] Personnel priority.

[0031] On the other hand, the embodiment of this specification also provides a network scheduling device, including:

[0032] A selection module, used for selecting a target network point from a network point set;

[0033] A first acquisition module is used to acquire the historical business volume of the target network point and the scheduling influencing factor of the target network point in the target time period;

[0034] A calling module, used to use the historical business volume and the scheduling influencing factor as inputs, and call an autoregressive moving average model to predict the predicted business volume of the target network point in the target time period;

[0035] A second acquisition module is used to acquire the scheduling constraint conditions of the target network point;

[0036] A construction module, used to construct a scheduling objective function according to the predicted business volume and the scheduling constraint conditions;

[0037] The optimization module is used to determine the scheduling data of the target network point by optimizing the scheduling objective function.

[0038] On the other hand, an embodiment of the present specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein when the computer program is executed by the processor, the instructions of the above method are executed.

[0039] On the other hand, an embodiment of the present specification further provides a computer storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer device, the instructions of the above method are executed.

[0040] It can be seen from the technical solutions provided by the above embodiments of this specification that in the embodiments of this specification, the historical business volume of the target outlet and the scheduling influencing factors of the target outlet in the target time period can be used as inputs, and the autoregressive moving average model can be called to predict the predicted business volume of the target outlet in the target time period, and then the scheduling objective function is automatically constructed according to the predicted business volume and the scheduling constraints, and then the scheduling data of the target outlet is determined by optimizing the scheduling objective function, thereby realizing automatic scheduling of outlets. Compared with manual scheduling, the embodiments of this specification greatly improve the scheduling efficiency; and, when performing automatic scheduling, the embodiments of this specification comprehensively consider various factors such as the historical business volume of the outlet, the scheduling influencing factors of the outlet in the target time period, and the scheduling constraints; thereby, the scheduling results are more closely matched with the actual business volume demand, that is, the matching degree between the scheduling results and the actual business volume demand is improved, and the problem of excess or insufficient human resources in outlets is alleviated or avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0042] Figure 1 A schematic diagram of a network scheduling system in some embodiments of this specification is shown;

[0043] Figure 2 A flowchart of a method for scheduling network points in some embodiments of this specification is shown;

[0044] Figure 3 It shows a structural block diagram of a network point scheduling device in some embodiments of this specification;

[0045] Figure 4 The structure block diagram of the computer device in some embodiments of the present specification is shown.

[0046] [Description of Reference Numerals]

[0047] 1. Scheduling system;

[0048] 2. Scheduling client;

[0049] 3. Business database;

[0050] 4. Weather forecast system;

[0051] 5. Human resource management system;

[0052] 6. Channel management system;

[0053] 31. Select module;

[0054] 32. A first acquisition module;

[0055] 33. Call module;

[0056] 34. Second acquisition module;

[0057] 35. Building modules;

[0058] 36. Optimization module;

[0059] 402. Computer equipment;

[0060] 404, processor;

[0061] 406. Memory;

[0062] 408, driving mechanism;

[0063] 410, input / output interface;

[0064] 412. Input devices;

[0065] 414. Output device;

[0066] 416. Presentation equipment;

[0067] 418. Graphical user interface;

[0068] 420, network interface;

[0069] 422. Communication link;

[0070] 424. Communication bus. DETAILED DESCRIPTION

[0071] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0072] The embodiments of this specification relate to automatic (or intelligent) scheduling technology for outlets. Among them, outlets generally refer to business outlets (such as bank business outlets, etc.). Scheduling generally refers to planning the shift rotation of enterprise employees. In view of the low efficiency of manual scheduling in the prior art, and the mismatch between outlet scheduling and actual business volume demand, which easily leads to the problem of excess or insufficient human resources in outlets, the embodiments of this specification provide an automated (or intelligent) technical solution for outlet scheduling.

[0073] Figure 1 The network scheduling system of some embodiments of this specification includes a scheduling system 1 and a scheduling client 2; the scheduling client 2 can provide user login or other human-computer interactions (such as sending a scheduling request to the scheduling system 1, etc.); the scheduling system 1 can communicate with the scheduling client 2 and other systems. Specifically, the scheduling system 1 can select a target outlet from the outlet set based on a scheduled task or when receiving a scheduling request sent by the scheduling client 2; obtain the historical business volume of the target outlet from the business database 3, and obtain the scheduling influence factor of the target outlet in the target time period from the weather forecast system 4, the human resources management system 5 and / or the channel management system 6, etc.; then use the historical business volume and the scheduling influence factor as input, call the autoregressive moving average model to predict the predicted business volume of the target outlet in the target time period; obtain the scheduling constraints of the target outlet from the human resources management system 5; construct a scheduling objective function based on the predicted business volume and the scheduling constraints; determine the scheduling data of the target outlet by optimizing the scheduling objective function; and output the scheduling data of the target outlet (for example, return a scheduling response carrying the scheduling data of the target outlet to the scheduling client 2); thereby realizing automatic scheduling of outlets.

[0074] In some embodiments, the scheduling system can be an electronic device with computing and network interaction functions; it can also be software running in the electronic device to provide business logic for data processing and network interaction. The scheduling user terminal can be a mobile terminal (i.e., a smart phone), a display, a desktop computer, a tablet computer, a laptop computer, a digital assistant or a smart wearable device, etc. Among them, smart wearable devices can include smart bracelets, smart watches, smart glasses or smart helmets, etc. Of course, the user terminal is not limited to the above-mentioned electronic devices with a certain entity, it can also be software running in the above-mentioned electronic devices.

[0075] The embodiments of this specification also provide a method for scheduling network points, which can be applied to the scheduling system mentioned above. Figure 2 As shown, in some embodiments, the network scheduling method may include the following steps:

[0076] S201: Select a target network point from a network point set.

[0077] S202: Acquire the historical business volume of the target outlet and the scheduling influencing factor of the target outlet in the target time period.

[0078] S203: Using the historical business volume and the scheduling influencing factor as input, calling the autoregressive moving average model to predict the predicted business volume of the target network point in the target time period.

[0079] S204: Obtain the scheduling constraints of the target network point.

[0080] S205: Constructing a scheduling objective function according to the predicted business volume and the scheduling constraint conditions.

[0081] S206: Determine the scheduling data of the target network point by optimizing the scheduling objective function.

[0082] In the embodiments of the present specification, the historical business volume of the target outlet and the scheduling influencing factors of the target outlet in the target time period can be used as inputs, and the autoregressive moving average model can be called to predict the predicted business volume of the target outlet in the target time period. Then, the scheduling objective function is automatically constructed according to the predicted business volume and the scheduling constraints. Then, the scheduling data of the target outlet is determined by optimizing the scheduling objective function, thereby realizing automatic scheduling of outlets. Compared with manual scheduling, the embodiments of the present specification greatly improve the scheduling efficiency; and, when performing automatic scheduling, the embodiments of the present specification comprehensively consider various factors such as the historical business volume of the outlet, the scheduling influencing factors of the outlet in the target time period, and the scheduling constraints; thereby, the scheduling results are more closely matched with the actual business volume demand, that is, the matching degree between the scheduling results and the actual business volume demand is improved, and the problem of excess or insufficient human resources in outlets is alleviated or avoided.

[0083] In some embodiments, the scheduling system can execute the network scheduling method based on the scheduled task, that is, whenever the scheduled time arrives, the scheduling system can automatically execute the network scheduling method to obtain the scheduling result. For example, in an exemplary embodiment, the scheduling system can be executed once a day to obtain the scheduling results for the next 7 days (where 7 days is used as the predicted duration, that is, 7 days is used as the target period). In this scenario, whenever the scheduled time arrives, the scheduling system can select a target network from the network set.

[0084] In other embodiments, the scheduling system may also execute the network scheduling method when triggered by a specific random event, that is, when a specific random event occurs, the scheduling system may execute the network scheduling method once to obtain a scheduling result. For example, in an exemplary embodiment, the specific random event may be receiving a scheduling request sent by a client, that is, when the scheduling system receives the scheduling request sent by the client, the network scheduling method is executed once to obtain a scheduling result.

[0085] The branch set is a set of branches that need to be scheduled; the branch range of the branch set can be selected according to actual needs. For example, taking the MM City Branch of XX Bank as an example, when the branches of the MM City Branch of XX Bank need to be uniformly scheduled, the branch range of the branch set can include all branches of the MM City Branch of XX Bank. When the MM City Branch of XX Bank allows its branches to schedule their own branches, then for the NN branch of the MM City Branch of XX Bank, the branch range of the branch set can be all branches of the NN branch of the MM City Branch of XX Bank. Of course, this is just an example, and according to actual needs, the branch range of the branch set can be larger or smaller, and this manual does not make specific limitations on this.

[0086] In the embodiments of this specification, the target network point is the currently selected network point. When there are multiple network points in the network point set, in order to realize the automatic scheduling of each network point in the network point set, in some embodiments, the scheduling can be performed one by one by random selection or sequential selection. Of course, in other embodiments, the selection of the target network point from the network point set can also be completed under manual intervention, that is, the network point option page is provided to the scheduling client for the user to select the target network point.

[0087] In some embodiments, the historical business volume of the target outlet can be obtained from a business database, etc. The historical business volume of the target outlet can be the historical business volume of the target outlet within a specified time range. For example, the historical business volume of the target outlet in the last six months, the last year, the last three years, etc. The historical business volume can include the historical business volume of all businesses (such as account opening / closing business, deposit business, loan business, financial management business, fund business, etc.) or a specified part of the business of the target outlet.

[0088] In some embodiments, the scheduling influencing factors of the target outlets in the target time period can be obtained from the weather forecast system, the human resources management system 5 and / or the channel management system 6. Among them, the target time period is the set prediction time, that is, the scheduling of the target outlets in the future can be predicted at one time. For example, in an exemplary embodiment, the target time period can be the next day, the next week, the next month, etc., which can be selected according to needs. The scheduling influencing factors refer to the factors that have an important impact on the scheduling results. If these shift influencing factors are not considered, the scheduling results will deviate greatly from the actual business volume demand.

[0089] In some embodiments, factors affecting scheduling may include, but are not limited to, weather conditions, holidays, and branch levels, etc. (described in detail below).

[0090] 1. Weather conditions

[0091] Statistical studies have shown that weather conditions are one of the important factors affecting the business volume of outlets. In order to make the scheduling results more closely match the actual business volume demand, the degree of influence of different weather on the number of customers in the store can be obtained in advance by comparing the changes in the number of customers in the same period under different weather conditions (i.e., the number of customers who go to the outlets to handle business). For example, in an exemplary embodiment, the weather forecast data for the recent month can be compared with the historical weather data for the same period. If the predicted weather is severe weather (e.g., high temperature above 35°C, freezing, heavy rain, typhoon, sandstorm, etc.), the scheduling system will appropriately reduce the predicted business volume (e.g., a reduction of 10% to 30%); if the predicted weather is normal weather (i.e., weather other than severe weather), there is no need to reduce the business volume. Weather conditions can be obtained from a weather forecast system, etc. Among them, the weather forecast system is a system that provides weather forecast information.

[0092] (II) Holidays

[0093] Holidays are also one of the important factors that affect the business volume of outlets. For example, for most users, they may not have time to go to the outlets to handle business due to working on weekdays, and they have to wait until the weekend to go to the outlets to handle business. Therefore, compared with the business demand of outlets during normal working days, the business demand of outlets on weekends may be higher; in addition, when holidays (especially relatively long holidays such as National Day and Spring Festival) come, many customers may have to travel far away or go on vacation. Therefore, compared with the business demand of outlets during normal working days, the business demand of outlets during this period may be lower. Therefore, the scheduling system can appropriately increase or decrease the predicted business volume according to the holiday situation corresponding to the target period. Holiday information can be obtained from the human resources management system and external systems that provide holiday information services.

[0094] (III) Network level

[0095] The level of outlets is one of the important factors affecting the scheduling of outlets. The level of outlets is mainly determined by the size of outlets, the type of outlets, etc. Among them, the size of outlets can be determined by information such as business scope and resource allocation. Resource allocation can include: the number of self-service terminals and smart counters, counter settings (i.e. counters involving physical currency) and non-cash counters (generally consulting and selling financial products, the work performed does not involve physical currency). The type of outlet refers to whether the outlet is an accounting outlet; an accounting outlet means that in addition to performing the relevant business functions of a general outlet, the outlet also takes into account the accounting, statistics, and collection of all outlets within the jurisdiction of the area where it is located. Obviously, the size of the outlet will have a direct impact on the ratio of the number of personnel in the scheduling; given that the accounting outlets need to undertake additional business, their manpower investment is more than that of general outlets when scheduling; therefore, the type of outlet is one of the important factors affecting the scheduling of outlets. The level of outlets can be obtained from the channel management system, etc. Among them, the channel management system refers to the system that maintains the resource configuration information of outlets.

[0096] The above-mentioned scheduling influence factors are only for illustrative purposes; however, this should not be understood as a limitation on the scheduling influence factors in the embodiments of this specification; considering that there are many scheduling influence factors, in other embodiments of this specification, according to actual needs, the scheduling influence factors of the target outlets in the target time period can also be selected to be more or less.

[0097] In some embodiments, the Autoregressive Moving Average model (ARMA) is an algorithm for studying time series. Its core idea is to learn the law of change over time from historical time series data, and predict the future time series based on this law. The autoregressive moving average model must meet the requirements of stationarity. Among them, stationarity means that the fitting curve obtained by the sample time series can continue inertia along the existing form for a period of time in the future. Specifically, whether the time series has stationarity can be evaluated by whether the mean and variance of the time series change significantly. With regard to the application scenario of the network scheduling of the embodiment of this specification, since the business volume of the network generally meets the stationarity requirements, the autoregressive moving average model can be used to predict the network scheduling. Obviously, in the embodiment of this specification, when the autoregressive moving average model is used to predict the network scheduling, the input historical business volume and the output predicted business volume are also time series data.

[0098] In other embodiments, the ARMA model can be replaced by ARIMA (Autoregressive Integrated Moving Average model). Unlike the ARMA model applied to a stable time series of original data, the ARIMA model is applied to a stable time series after the original data is differentiated. In other embodiments, the ARMA model can also be replaced by any other suitable time series prediction model. It can be seen that in the embodiments of this specification, the ARMA model is only an illustrative example, not a sole limitation, and can be selected as needed in actual implementation.

[0099] In order to further improve the accuracy of the prediction results, in addition to considering the above-mentioned factors affecting the scheduling, restrictive conditions such as the qualifications of the personnel, the number of personnel, the vacation information of the personnel, and the priority of the personnel can also be considered. Among them, the qualifications of the personnel reflect the business scope, business level, work efficiency, etc. of the personnel, and the vacation information of the personnel reflects the actual rest day arrangement of the personnel. Obviously, these restrictive conditions will have an impact on the scheduling, so they can be called scheduling constraints. In some embodiments, the scheduling constraints can be obtained from the human resources management system.

[0100] In some embodiments, based on the predicted business volume, the constructed scheduling objective function can be expressed as: The scheduling objective function means: for the jth day in the next n days, the predicted business volume The difference between the average business volume of all scheduled staff and the total business volume is the smallest; in this way, the business volume demand of the jth day can be met without wasting human resources. Among them, min represents the minimization of the scheduling objective function, t j represents the jth day within n days, represents the predicted business volume of the outlet on the jth day within n days, M represents the number of people on duty at the outlet, I represents the number of posts at the outlet, It means that for any, P mi represents the average business volume handled by the mth person in the ith position, c i represents the labor cost coefficient required for the i-th position, x i represents the number of people working in the i-th position, x ia Represents x i The a character in x ib Represents x i The b role in , st represents the scheduling constraints.

[0101] In some embodiments, the scheduling constraints may include

[0102] Among them, P krepresents the kth person, X k Indicates P k Qualifications, T k Indicates P k Available working days, R i Represents x i The value range of S indicates the specified multiple x i The sum, R s Indicates the value range of S.

[0103] For example, in an exemplary embodiment, the scheduling constraints may be:

[0104]

[0105] In the above scheduling constraints, p1~p5 represent different employees (for example, p1 is Xiao Ming, p2 is Xiao Hua, etc.), x1, x2, x3, x4 represent different positions in the target outlets (for example, x1 is cash business, x2 is fund business, etc.), x 1a and x 1b It means that a position x1 can be composed of two or more different roles, a and b (not necessarily every position), that is, x 1a represents the a role in x1, x 1b represents the b role in x1; the others can be referred to for explanation. 1b ,x 2a ,x3},p2∈{x3,x4},p3∈{x2,x3,x4},p4∈{x2,x5},p5∈{x 1a}) reflects the personnel qualifications, which is equivalent to the personnel who can take up each position: x1 = {p1, p5}, x2 = {p1, p3, p4}, x3 = {p1, p2, p3}, x4 = {p2, p3}, x5 = {p4}. p1∈{t1, t2, t3, t4, t5}, p2∈{t1, t2, t4, t5, t6}, p3∈{1, t2, t3, t4, t5, t6, t7}, p4∈{1, t2, t3, t4, t5, t6}, p5∈{t1, t2, t3, t4, t5} reflects the available working days of each employee. For example, taking p1∈{t1,t2,t3,t4,t5} as an example, p1∈{t1,t2,t3,t4,t5} means that employee p1 can work from the first to the fifth day in the future. x1≥1,x2=1,x3≤2 represent the number of personnel constraints for each position; for example, taking x3≤2 as an example, x3≤2 means that the number of people on duty at position x3 cannot exceed 2 people per day. (x1+x2+x4)≤3 reflects the priority of personnel at each position.

[0106] In some embodiments, for scenarios where there are relatively few scheduling influencing factors and relatively simple scheduling constraints, the scheduling objective function can be solved by deterministic algorithms such as the benders algorithm, DW algorithm, cutting plane method, branch and bound method, branch and price method, or Lagrangian relaxation algorithm to determine the scheduling data of the target network point. Moreover, since these algorithms are all deterministic algorithms, they have good convergence and are easy to obtain the global optimal solution.

[0107] In contrast, for scenarios where there are relatively more factors affecting scheduling and the scheduling constraints are relatively complex, the business demand or personnel needs to be reasonably predicted or simplified, and the feasible solutions and their cost evaluations require computer program-assisted calculations. Therefore, it is possible to consider using nonlinear programming algorithms such as column generation algorithms, genetic algorithms, simulated annealing algorithms, and tabu algorithms to solve the scheduling objective function, so that the scheduling data of the target outlets can also be determined.

[0108] In some cases, when it may be difficult to ensure the global optimum by solving or optimizing the scheduling objective function, the scheduling constraints can be appropriately modified (for example, some less important scheduling constraints are discarded) or the optimization algorithm is replaced, and the solution or optimization can be performed again. If it is still difficult to ensure the global optimum, the scheduling data of the target network point can be selectively determined based on the solution results corresponding to the local optimum. In special cases, if it is difficult to obtain the local optimum by solving or optimizing the scheduling objective function, an error can be thrown.

[0109] In addition, in some embodiments, the scheduling system can also provide an emergency maintenance interface to facilitate modification of scheduling constraints when optimizing the scheduling objective function, or to manually input or adjust scheduling influencing factor parameters when business volume may suddenly change due to certain reasons (such as promotional activities, sudden weather, etc.), thereby making the scheduling system more flexible.

[0110] Although the process flows described above include multiple operations that occur in a particular order, it should be clearly understood that the processes may include more or fewer operations, which may be performed sequentially or in parallel (eg, using parallel processors or a multi-threaded environment).

[0111] Corresponding to the above-mentioned network scheduling method, the embodiment of this specification also provides a network scheduling device, which can be configured in the above-mentioned scheduling system. Figure 3 As shown, in some embodiments, the network scheduling device may include a selection module 31, a first acquisition module 32, a call module 33, a second acquisition module 34, a construction module 35 and an optimization module 36. Among them:

[0112] A selection module 31 may be used to select a target network point from a network point set;

[0113] The first acquisition module 32 may be used to acquire the historical business volume of the target outlet and the scheduling influencing factor of the target outlet in the target time period;

[0114] The calling module 33 may be used to use the historical business volume and the scheduling influencing factor as inputs to call the autoregressive moving average model to predict the predicted business volume of the target network point in the target time period;

[0115] The second acquisition module 34 may be used to acquire the scheduling constraint conditions of the target outlet;

[0116] A construction module 35 may be used to construct a scheduling objective function according to the predicted business volume and the scheduling constraint condition;

[0117] The optimization module 36 may be used to determine the scheduling data of the target network point by optimizing the scheduling objective function.

[0118] In some embodiments, the autoregressive moving average model includes any one of the following models:

[0119] ARMA model;

[0120] ARIMA model.

[0121] In the embodiment of this specification, the scheduling objective function includes:

[0122]

[0123] Among them, min means minimizing the scheduling objective function, t j represents the jth day within n days, represents the predicted business volume of the outlet on the jth day within n days, M represents the number of people on duty at the outlet, I represents the number of posts at the outlet, It means that for any, P mi represents the average business volume handled by the mth person in the ith position, c i represents the labor cost coefficient required for the i-th position, x i represents the number of people working in the i-th position, x ia Represents x i The a character in x ib Represents x i The b role in , st represents the scheduling constraints.

[0124] In some embodiments, the scheduling constraints include:

[0125]

[0126] Among them, P k represents the kth person, X k Indicates Pk Qualifications, T k Indicates P k Available working days, R i Represents x i The value range of S indicates the specified multiple x i The sum, R s Indicates the value range of S.

[0127] In some embodiments, determining the scheduling data of the target network point by optimizing the scheduling objective function may include:

[0128] The scheduling data of the target network point is determined by optimizing the scheduling objective function through a nonlinear programming algorithm.

[0129] In some embodiments, the scheduling influencing factors include any one or more combinations of the following:

[0130] Weather conditions;

[0131] Holidays;

[0132] Network level.

[0133] In some embodiments, the scheduling constraints include any one or more combinations of the following:

[0134] Personnel qualifications;

[0135] Number of personnel;

[0136] Personnel leave information;

[0137] Personnel priority.

[0138] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0139] The embodiments of this specification also provide a computer device. Figure 4As shown, in some embodiments of the present specification, the computer device 402 may include one or more processors 404, such as one or more central processing units (CPUs) or graphics processing units (GPUs), and each processing unit may implement one or more hardware threads. The computer device 402 may also include any memory 406, which is used to store any kind of information such as code, settings, data, etc. In a specific embodiment, the computer program on the memory 406 and can be run on the processor 404, when the computer program is run by the processor 404, can execute the instructions of the network scheduling method described in any of the above embodiments. Non-limiting, for example, the memory 406 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 402. In one case, when the processor 404 executes the associated instructions stored in any memory or combination of memories, the computer device 402 can perform any operation of the associated instructions. The computer device 402 also includes one or more drive mechanisms 408 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0140] The computer device 402 may also include an input / output interface 410 (I / O) for receiving various inputs (via input device 412) and for providing various outputs (via output device 414). A specific output mechanism may include a presentation device 416 and an associated graphical user interface 418 (GUI). In other embodiments, the input / output interface 410 (I / O), input device 412, and output device 414 may not be included, and the computer device 402 may be used as a computer device in a network. The computer device 402 may also include one or more network interfaces 420 for exchanging data with other devices via one or more communication links 422. One or more communication buses 424 couple the components described above together.

[0141] The communication link 422 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 422 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0142] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of some embodiments of the present specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processor to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processor generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0143] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processor to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0144] These computer program instructions can also be loaded onto a computer or other programmable data processor so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0145] In a typical configuration, a computer device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0146] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0147] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computer device. As defined in this specification, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0148] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0149] The present specification embodiments may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present specification embodiments may also be practiced in distributed computing environments where tasks are performed by remote processors connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0150] It should also be understood that in the embodiments of this specification, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0151] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, in the absence of contradiction, a person skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0152] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for scheduling network points, characterized in that: include: Select a target point from the point set; Obtaining the historical business volume of the target outlet and the scheduling influencing factor of the target outlet in the target time period; Taking the historical business volume and the scheduling influencing factor as input, calling the autoregressive moving average model to predict the predicted business volume of the target network point in the target time period; Obtaining the scheduling constraints of the target outlet; Constructing a scheduling objective function according to the predicted business volume and the scheduling constraints; The scheduling objective function includes: Among them, min means minimizing the scheduling objective function, t j represents the jth day within n days, represents the predicted business volume of the outlet on the jth day within n days, M represents the number of people on duty at the outlet, I represents the number of posts at the outlet, It means that for any, P mi represents the average business volume handled by the mth person in the ith position, c i represents the labor cost coefficient required for the i-th position, x i represents the number of people working in the i-th position, x ia Represents x i The a character in x ib Represents x i The b role in the table, st represents the scheduling constraints; The scheduling data of the target network point is determined by optimizing the scheduling objective function.

2. The method for scheduling network points according to claim 1, characterized in that: The autoregressive moving average model includes any one of the following models: ARMA model; ARIMA model.

3. The method for scheduling network points according to claim 1, characterized in that: The scheduling constraints include: Among them, P k represents the kth person, X k Indicates P k Qualifications, T k Indicates P k Available working days, R i Represents x i The value range of S indicates the specified multiple x i The sum, R s Indicates the value range of S.

4. The method for scheduling network points according to claim 1, characterized in that: The step of determining the scheduling data of the target network point by optimizing the scheduling objective function includes: The scheduling data of the target network point is determined by optimizing the scheduling objective function through a nonlinear programming algorithm.

5. The method for scheduling network points according to claim 1, characterized in that: The scheduling influencing factors include any one or more combinations of the following: Weather conditions; Holidays; Network level.

6. The method for scheduling network points according to claim 1, characterized in that: The scheduling constraints include any one or more combinations of the following: Personnel qualifications; Number of personnel; Personnel leave information; Personnel priority.

7. A network scheduling device, characterized in that: include: A selection module, used for selecting a target network point from a network point set; A first acquisition module is used to acquire the historical business volume of the target network point and the scheduling influencing factor of the target network point in the target time period; A calling module, used to use the historical business volume and the scheduling influencing factor as inputs, and call an autoregressive moving average model to predict the predicted business volume of the target network point in the target time period; A second acquisition module is used to acquire the scheduling constraint conditions of the target network point; A construction module, used to construct a scheduling objective function according to the predicted business volume and the scheduling constraint conditions; The scheduling objective function includes: Among them, min means minimizing the scheduling objective function, t j represents the jth day within n days, represents the predicted business volume of the outlet on the jth day within n days, M represents the number of people on duty at the outlet, I represents the number of posts at the outlet, It means that for any, P mi represents the average business volume handled by the mth person in the ith position, c i represents the labor cost coefficient required for the i-th position, x i represents the number of people working in the i-th position, x ia Represents x i The a character in x ib Represents x i The b role in the table, st represents the scheduling constraints; The optimization module is used to determine the scheduling data of the target network point by optimizing the scheduling objective function.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the computer program is executed by the processor, the computer program executes the instructions of the method according to any one of claims 1 to 6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor of a computer device, the computer program executes instructions of the method according to any one of claims 1 to 6.

Images