Task Scheduling Methods

Abstract

The present application discloses a task scheduling method, which includes: obtaining the task amount of multiple task time periods of a first time granularity; determining the first task undertaking amount of each task undertaker in a unit task time period; and determining the first performance mapping relationship between multiple task undertaking time periods of a second time granularity and each task time period; determining the first corresponding relationship between the task undertaker and the task undertaking time period at least based on the task amount, the first task undertaking amount and the first performance mapping relationship. By adopting this processing method, task scheduling can be compatible with task requirements of different time granularities, such as the shift level of coarser time granularity and the hour level of fine time granularity, so as to adapt to business scenarios of refined operations such as e-commerce customer service and new retail, and can minimize early artificial settings and later manual adjustments; therefore, it can effectively improve the rationality of task scheduling and improve labor management performance.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a task scheduling method. Background Art

[0002] The service industry (such as customer service, retail enterprises, etc.) faces the pressure of increasing task volume on the one hand, and the pressure of rising labor costs on the other hand. To maintain reasonable profits and per capita task volume is a challenge that all service enterprises have to face. Therefore, the service industry is paying attention to improving the utilization rate of employees and the scientific nature of scheduling, thereby improving the efficiency of labor management.

[0003] From the perspective of task processing, the problem of personnel scheduling is the problem of task dispatching. At present, the commonly used task dispatching method is based on shift assignment, that is, the time granularity of personnel (task undertakers) and tasks is shift (such as night shift, morning shift, etc.). The method based on shift assignment can be specifically implemented by pattern repetition, historical use, rule engine, etc. The following briefly describes the technical features and shortcomings of these commonly used implementation methods.

[0004] 1. Task scheduling method with repeated patterns. The characteristics of this method are: setting a simple model for repetition, such as: morning-morning-noon-noon-evening-evening-rest. The disadvantages of this method are: it requires manual settings and is difficult to support complex scenarios.

[0005] 2. The historical task scheduling method. The characteristic of this method is: copying the shift schedule of the previous cycle. The disadvantage of this method is: it cannot support changing needs, and the workload of subsequent adjustments may be very large.

[0006] 3. Task scheduling method of rule engine. The characteristics of this method are: using multiple rules to screen out suitable personnel in turn and assign tasks. The disadvantage of this method is: it is difficult to comprehensively consider all factors, which often leads to violations of some hard constraints.

[0007] However, in the process of realizing the present invention, the inventors found that in business scenarios of refined operations such as e-commerce customer service and new retail, more and more companies can make estimates of the task demand in the future based on big data. According to the needs of refined operations, the estimated granularity can be up to one hour or even half an hour. However, on the personnel supply side, considering the management characteristics of personnel, the time granularity of human resources is still based on shifts, and the span can be as long as several hours. In addition, when arranging personnel, it is necessary to comprehensively consider the hard legal provisions such as working hours and rest, as well as soft humanized management and personalized needs such as shift fairness and shift switching preferences.

[0008] In summary, on the one hand, in the business scenario of refined operation, the time granularity of task demand is hourly, while the time granularity of human resources is shift-level; on the other hand, the existing shift-based dispatching method requires that the time granularity of both personnel and tasks is shift, which will result in the inability of existing task scheduling methods to adapt to the task demand of refined time granularity, thus reducing the rationality of task scheduling in the business scenario of refined operation. With the growth of service volume and the increase of labor costs, how to design a task scheduling system suitable for the business scenario of refined operation to improve the utilization rate and service level of human resources and obtain better user experience with less cost is the core issue of human resource scheduling in the service industry. Summary of the invention

[0009] The present application provides a task scheduling method to solve the problem of low rationality of task scheduling in the prior art.

[0010] The present application provides a task scheduling method, comprising:

[0011] Determine the task amount of multiple task time periods of the first time granularity;

[0012] Determine a first task undertaking amount of multiple task undertakers in a unit task time period; and determine a first performance mapping relationship from multiple task undertaking time periods of a second time granularity to each task time period;

[0013] A first corresponding relationship between a task undertaker and a task undertaker time period is determined at least based on the task volume, the first task undertaker volume and the first performance mapping relationship.

[0014] Optionally, the first corresponding relationship is determined in the following manner:

[0015] Determine the second task undertaking quantity of each task undertaking party group in the unit task time period according to the first task undertaking quantity and the task undertaking party group information;

[0016] Determine, based on the first performance mapping relationship, a second performance mapping relationship between a plurality of task acceptance time period groups and each task time period;

[0017] Determine a second corresponding relationship between a task undertaking party group and a task undertaking time period group according to the task amount, the second task undertaking amount and the second performance mapping relationship;

[0018] According to the second corresponding relationship, a second corresponding relationship between the task undertaker and the task undertaking time period is determined as the first corresponding relationship.

[0019] Optionally, the second performance mapping relationship is determined in the following manner:

[0020] Determine the task acceptance time period group information according to the start time and end time of the task acceptance time period;

[0021] For each task acceptance time period group, a second performance mapping relationship from the task acceptance time period group to each task time period is determined based on a first performance mapping relationship from each task acceptance time period in the task acceptance time period group to each task time period.

[0022] Optionally, the task acceptance time period group information is determined in the following manner:

[0023] Multiple task acceptance time period information with the same start time and end time are merged into task acceptance time period group information.

[0024] Optionally, a weighted average of the first performance mapping relationships is used as the second performance mapping relationship.

[0025] Optionally, obtain the task scheduling rules;

[0026] A first corresponding relationship that complies with the task scheduling rule is determined based on at least the task volume, the first task undertaking volume and the first performance mapping relationship.

[0027] Optionally, the task scheduling rule includes at least one of the following rules:

[0028] The task undertaking time periods of the same group of task undertakers with the same or similar start and end times;

[0029] Monthly / weekly task acceptance days threshold, non-task acceptance days threshold, task acceptance hours upper threshold and / or lower threshold;

[0030] The difference in the number of first shifts of each task undertaking group is less than the difference threshold;

[0031] The first shift and the second shift are not adjacent.

[0032] Optionally, the first time granularity includes hours, and the second time granularity includes shifts.

[0033] Optionally, the first corresponding relationship is determined by optimizing a solver or a heuristic algorithm at least based on the task volume, the first task undertaking volume and the first performance mapping relationship.

[0034] Optionally, determining the task amounts of multiple task time periods of the first time granularity includes:

[0035] Based on the historical task volume data, determine the task volume forecast value for each task time period on each day within the target time period.

[0036] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the computer-readable storage medium is run on a computer, the computer executes the above-mentioned various methods.

[0037] The present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the above-mentioned various methods.

[0038] Compared with the prior art, this application has the following advantages:

[0039] The task scheduling method provided in the embodiment of the present application obtains the task amount of multiple task time periods of a first time granularity; determines the first task undertaking amount of each task undertaker in a unit task time period; and determines a first performance mapping relationship from multiple task undertaking time periods of a second time granularity to each task time period; determines the first corresponding relationship between the task undertaker and the task undertaking time period based on at least the task amount, the first task undertaking amount and the first performance mapping relationship; this processing method, by introducing the first performance mapping relationship, makes task scheduling compatible with task requirements of different time granularities, such as the shift level of coarser time granularity and the hour level of fine time granularity, to adapt to business scenarios of refined operations such as e-commerce customer service and new retail, and can minimize early human settings and later manual adjustments; therefore, it can effectively improve the rationality of task scheduling and improve labor management performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flowchart of an embodiment of a task scheduling method provided by the present application;

[0041] Figure 2 It is a specific flow chart of an embodiment of a task scheduling method provided by the present application. DETAILED DESCRIPTION

[0042] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0043] First embodiment

[0044] Please refer to Figure 1 , which is a flowchart of an embodiment of a task scheduling method provided by the present application, wherein the execution subject of the method includes a task scheduling device. A task scheduling method provided by the present application includes:

[0045] Step S101: determine the task amounts of multiple task time periods of a first time granularity.

[0046] The task scheduling method provided in the embodiment of the present application does not limit the task acceptance time period and the time granularity of the task time period. The task time period can be at the hour level or the shift level, and the time granularity of the task acceptance time period can also be at the hour level or the shift level. That is, the method provided in the embodiment of the present application can be compatible with task requirements of different time granularities, so that it can adapt to the business scenarios of non-fine operations of traditional enterprises, and can also adapt to business scenarios of fine operations such as e-commerce customer service and new retail.

[0047] In this application, the time granularity of the task time period is referred to as the first time granularity, and the time granularity of the task acceptance time period is referred to as the second time granularity.

[0048] In one example, the business scenario is a business scenario where an e-commerce customer service provides users with shopping consultations and fine-grained operations on the amount of user consultations. In this case, one consultation from a user is a task, the time management granularity of the user consultation volume (first time granularity) is hourly (such as half an hour, 1 hour or 2 hours, etc.), and the time granularity of customer service scheduling (second time granularity) is shift (such as morning shift, afternoon shift, night shift, etc.).

[0049] In specific implementation, step S101 can be implemented in the following manner: according to the historical user consultation volume and / or timeliness data (such as weather, season, promotional activities, etc.), determine the task volume forecast value of each task time period in each day within the target time period (such as the next 7 days, 1 month, etc.). For example, first, based on the user consultation log data of the past 3 months, the average task volume of each task time period is counted; then, combined with the weather conditions or seasons in the next 7 days and other factors, the task volume of each task time period in the next 7 days is predicted. For example, if the weather is hot in the next 7 days, the number of consultations for air conditioners will surge. If the next 7 days are the season for lychees to mature, the number of consultations for lychees will surge. Or, if the next 7 days are the Double 11 promotion, the number of consultations for all commodities in the next 7 days will surge, and so on. Table 1 shows the task volume forecast value of this embodiment.

[0050] 2019 / 7 / 1 2019 / 7 / 9 … 2019 / 7 / 31 … 8 to 9 o'clock 23 197 27 9 to 10 o'clock 10 154 12 … 21:00 to 22:00 45 62 38 …

[0051] Table 1. Task volume forecast table

[0052] As can be seen from Table 1, the first time granularity of this embodiment is 1 hour, so 1 day is divided into 24 task time periods, and the task volume of each time period is predicted respectively, and the task volume of different time periods will be different. Since the refined operation of tasks, that is, the prediction of the task volume of the task time period of the first time granularity, is a relatively mature existing technology, it will not be repeated here.

[0053] In another example, the business scenario is a non-task refined operation business scenario for factory staff scheduling. In this case, the product output is used as the task volume, and its time management granularity (first time granularity) is usually at the shift level. For example, if a shift is 8 hours, the number of products within the working hours of a shift must be determined; similarly, the time granularity (second time granularity) for worker scheduling is also shift (such as morning shift, afternoon shift, night shift, etc.). Since the conventional operation of tasks without refinement is a relatively mature existing technology, it will not be repeated here.

[0054] After determining the task volume of multiple task time periods of the first time granularity, you can proceed to the next step to determine the first task undertaking volume of each task undertaker in the multiple task undertaker groups in the unit task time period; and determine the first performance mapping relationship from multiple task undertaking time periods of the second time granularity to each task time period.

[0055] Step S103: determining a first task undertaking quantity of multiple task undertakers in a unit task time period; and determining a first performance mapping relationship from multiple task undertaking time periods of a second time granularity to each task time period.

[0056] 1) Determine the first task undertaking quantity of multiple task undertakers in a unit task time period.

[0057] The unit task time period refers to the time unit of the task time period. For example, the time unit of the task time periods 8-9 o'clock and 10-11 o'clock is 1 hour, so the unit task time period of the personnel scheduling task is 1 hour. According to the actual situation, the unit task time period can be half an hour or two hours, etc.

[0058] The first task acceptance volume includes the task acceptance capacity of the task acceptor within a unit task time period, such as the maximum task volume that can be accepted is 30, etc.

[0059] 2) Determine a first performance mapping relationship between multiple task acceptance time periods of the second time granularity and each task time period.

[0060] The method proposed in this embodiment introduces a first performance mapping relationship table as shown in Table 2, and uses the performance function (first performance mapping relationship) to represent the mapping relationship from the task acceptance time period to the unit task time period granularity.

[0061]

[0062] Table 2: First performance mapping relationship table

[0063] As shown in Table 2, if the working time of task acceptance time period 7a is from 8 am to 5 pm, and the rest time is from 10 am to 11 pm, a vector can be used to represent the first performance mapping relationship of the task acceptance time period to the time slot (task time period): u 7a =[…0,1,1,0,1,1,1,1,1,1,0,…], where 1 represents work and 0 represents rest. The vector dimension can be the total number of time slots in a day. If the task time slot granularity is 1 hour, then 1 day includes 24 time slots. Similarly, for the task acceptance time period 7b with the same working time of 8 am to 5 pm but rest time of 11 pm to 12 pm, its mapping relationship can be expressed as: 7b =[…0,1,1,1,0,1,1,1,1,1,0,…].

[0064] After determining the first task undertaking quantity and the first performance mapping relationship, you can proceed to the next step to determine the task scheduling information for the task undertaking time period so that the task undertakers in the same group are scheduled to have the same or similar starting working time and ending working time based on the task quantity, the first task undertaking quantity and the first performance mapping relationship.

[0065] Step S105: Determine a first corresponding relationship between a task undertaker and a task undertaker time period according to the task amount, the first task undertaker amount and the first performance mapping relationship.

[0066] In one example, the task undertaker is directly used as the scheduling unit, and the task undertaking time period is directly assigned to each task undertaker according to the mapping relationship between the task amount, the first task undertaking amount and the first performance. However, even if the working time of a task undertaking time period is limited, different starting times and rest time slots will still generate several task undertaking time periods with different modes, which will lead to a huge problem scale and cause a large consumption of both computing resources and storage resources. In serious cases (such as too many task undertaking time periods), it may not even be solved directly, so it is less practical.

[0067] Please refer to Figure 2 , which is a specific flow chart of an embodiment of a task scheduling method provided by the present application. In order to reduce the scale of the problem and improve the practicality of the method, in this embodiment, step S105 may include the following sub-steps:

[0068] Step S1051: Determine the second task undertaking quantity of each task undertaking party group in a unit task time period according to the first task undertaking quantity and the task undertaking party group information.

[0069] In large-scale staff scheduling scenarios, such as e-commerce customer service scenarios, the number of service personnel can easily reach hundreds of people. For ease of management, personnel are usually divided into several small groups (staff groups) in business, and the working hours of personnel in the same staff group are as close as possible. In this case, it is required to execute the staff scheduling result obtained by the method provided in the embodiment of the present application, so that the personnel in the same group are scheduled to the same or similar task acceptance time period with the same starting working time and the same or similar ending working time, rather than assigning employees to any task acceptance time period without any restrictions, and at the same time avoid violating the basic principles of personnel management and causing confusion to the company's personnel scheduling.

[0070] In this embodiment, the human resources of the same group are first aggregated, and the employee group is regarded as a scheduling unit to participate in the allocation algorithm solution, so that the members of the same group try to go to work at the same time. Assume that the unit time efficiency (first task acceptance) of the task undertaker i is e i , then the unit time efficiency (second task undertaking amount) of task undertaking group g is e g =∑i ∈g e i .

[0071] Step S1053: Determine a second performance mapping relationship from a plurality of task acceptance time period groups to each task time period according to the first performance mapping relationship.

[0072] In actual business, there are often many task acceptance time periods with the same start and end time but different rest time, which are aggregated. As shown in Table 3, the task acceptance time period 7a and the task acceptance time period 7b have the same start and end time, and the working hours are both from 8 am to 5 pm. The only difference is the rest time in the middle, where the rest time of task acceptance time period 7a is 10-11 o'clock, and the rest time of task acceptance time period 7b is 11-12 o'clock. The method provided in the present application aggregates such task acceptance time periods with the same start and end time but different rest periods, and uses the aggregation result as the second performance mapping relationship between the task acceptance time period group and the time slot.

[0073] In specific implementation, a weighted vector can be used to represent the second performance mapping relationship of the aggregated task acceptance time period group to the time slot. For example, if the weights of two task acceptance time periods are both 0.5, then the task acceptance time period group u7 = […0,1,1,0.5,0.5,1,1,1,1,1,0,…].

[0074]

[0075] Table 3. Task acceptance time period aggregation table

[0076] Similarly, the second performance mapping relationship from all aggregated task acceptance time period groups to each task time period can be obtained, as shown in Table 4.

[0077]

[0078] Table 4: Second performance mapping relationship table

[0079] In this embodiment, similar task acceptance time periods are aggregated into task acceptance time period groups, and efficiency vectors are introduced to weight the efficiency of the task acceptance time period groups in different time periods. A mapping relationship of efficiency values ​​from task acceptance time period groups to time slots is provided. This transformation can support human resources at the granularity of task acceptance time periods to cover task requirements at fine time granularity.

[0080] Step S1055: Determine a second corresponding relationship between the task undertaking party group and the task undertaking time period group according to the task amount, the second task undertaking amount and the second performance mapping relationship.

[0081] In one example, the employee group can be used as the scheduling unit, and the task acceptance time period group can be directly assigned to each employee group according to the mapping relationship between the task volume, the first task acceptance volume and the first efficiency without considering the scheduling rules. The mathematical model of this method can be expressed as:

[0082]

[0083]

[0084]

[0085]

[0086] Among them, x represents the task scheduling result (first corresponding relationship), is a 0-1 variable, indicating whether the task undertaker group g is assigned to the task undertaker time period group s on day d; represents the efficiency value of the task acceptance time period group s in time slot t, q dt is the predicted value of the task volume of the input time slot; Formula (1) limits each task undertaking group to work at most one task undertaking time period group per day; Formula (2) indicates that the total efficiency value of the task undertaking party assigned to a specific time slot must be greater than the task volume of the time slot. Target value It is a function of the task acceptance time period allocation x, which can represent the maximum task demand coverage, the lowest labor cost, etc., where, It represents the cost of assigning the task undertaking group g to the task undertaking time period s on day d, such as labor cost, preference cost, etc.

[0087] In specific implementation, a variety of methods can be used to solve the above optimization model, such as using an optimization solver to solve it, or using a heuristic algorithm (such as a genetic algorithm), etc. Since model solving belongs to a relatively mature existing technology, it will not be described here.

[0088] However, the above-mentioned handling method does not take into account the provisions of policies and laws, such as: the number of working days, rest days, upper and lower limits of working hours in the monthly / weekly dimensions, etc.; nor does it comprehensively consider factors such as humane management and employees' personalized preferences, such as: the task acceptance time periods of the same group of task undertakers are as close as possible, the number of night shifts of each group of task undertakers is as fair as possible, and the night shift is not followed by the morning shift, etc.; therefore, it will lead to problems such as low rationality of task scheduling and violation of legal provisions, which will lead to low practicality.

[0089] In order to solve the above problems, the method provided in the embodiment of the present application may also include the following steps: obtaining task scheduling rules; correspondingly, step S1055 can be implemented in the following manner: based on the task volume, the second task acceptance volume and the second performance mapping relationship, determining the first corresponding relationship between the task acceptance party group and the task acceptance time period group that complies with the task scheduling rules.

[0090] The task scheduling rules can be read from the task scheduling rule configuration file or obtained from the database. The task scheduling rules include but are not limited to at least one of the following rules: the same group of people are scheduled to take over the task time period with the same or similar start and end working times; the working day threshold, rest day threshold, upper and / or lower working hour threshold in the monthly / weekly dimension; the difference in the number of night shifts of each employee group is less than the difference threshold; the night shift does not follow the morning shift, etc.

[0091] In this case, the mathematical model for assigning task undertaker groups to task undertaker time period groups can be expressed as:

[0092]

[0093]

[0094]

[0095] h(x)=0 (3)

[0096]

[0097] Among them, formula (3) represents the task scheduling rule restrictions of this scenario, including all hard rules, such as the provisions of policies and regulations, and some soft rules, such as the task acceptance time periods of employee groups are as close as possible.

[0098] In this embodiment, a set of modeling languages ​​can be defined in advance for formula (3), and whether to add it into the mathematical model can be determined through a configuration file as shown in Table 5.

[0099]

[0100] Table 5. Task scheduling rule configuration file

[0101] The optimization model can be solved by a flexible method, such as using an optimization solver, or using a heuristic algorithm such as a genetic algorithm, etc. This solution does not make specific formulations. The solution result obtained is the distribution relationship from the employee group to the task acceptance time period group, as shown in Table 6.

[0102] 2019 / 7 / 1 2019 / 7 / 9 2019 / 7 / 10 2019 / 7 / 11 2019 / 7 / 12 Personnel Group 1 Shift Group 7 Shift Group 8 Shift Group 10 Shift Group 5 Personnel Group 2 Shift Group 11 Shift Group 6 Shift Group 8 Shift Group 9 …

[0103] Table 6. Task undertaker group (personnel group) - task undertaker time period group (shift group) allocation plan table

[0104] In this embodiment, by aggregating the efficiency values ​​of employee groups, the employee groups are used as a scheduling unit to model the allocation problem of employee groups to shift groups, which can comprehensively consider hard rules such as legal regulations and soft rules such as shift fairness and preference. This model is flexible and extensible, and is easy to quickly adapt to different business scenarios and needs.

[0105] Step S1057: According to the second corresponding relationship, determine the second corresponding relationship between the task undertaker and the task undertaking time period as the first corresponding relationship.

[0106] Based on the distribution relationship between employee group and shift group obtained in the previous stage, the distribution relationship between employee and shift is further solved, that is, the aggregated shift group is split into shifts corresponding to each employee. Specifically, the specific shifts within the group can be assigned based on the employee's efficiency value, and the distribution relationship between each employee and the specific shift can be obtained, and finally an executable shift schedule can be obtained. Assuming that a shift group is composed of R specific shifts, considering the employee's efficiency value (the first task acceptance), the employees in the employee group are divided into R small groups, so that the sum of the efficiency values ​​of the employees in each small group is as close as possible, which can be expressed by the following mathematical model:

[0107]

[0108]

[0109]

[0110]

[0111] Among them, x iris a 0-1 variable, indicating whether employee i is in the rth group; formula (4) is the total efficiency of employees in the rth group; formula (5) restricts each employee to be assigned to only one group. In this way, the specific shift type corresponding to each employee can be obtained and the execution shift table can be generated, as shown in Table 7.

[0112] 2019 / 7 / 1 2019 / 7 / 9 2019 / 7 / 10 2019 / 7 / 11 2019 / 7 / 12 Personnel Group 1 Shift Group 7 Shift Group 8 Shift Group 10 Shift Group 5 -- Person 1 Flight 7a Flight 8a Flight 10a Flight 5 -- Person 2 Flight 7a Flight 8a Flight 10b Flight 5 -- Person 3 Flight 7a Flight 8b Flight 10b Flight 5 -- Person 4 Flight 7b Flight 8b Flight 10c Flight 5 -- Person 5 Flight 7b Flight 8b Flight 10c Flight 5 Personnel Group 2 Shift Group 11 Shift Group 6 Shift Group 8 Shift Group 9 -- Personnel 6 … -- Personnel 7 … …

[0113] Table 7. Employee Group Execution Shift Schedule

[0114] In summary, this embodiment realizes flexible task scheduling in stages through the above steps S1051-1057. Specifically, in the first stage, the personnel can be aggregated into personnel groups and the shifts can be aggregated into shift groups through the efficiency function; in the second stage, the personnel groups are assigned to the shift groups to cover the task scale; in the third stage, the assignment of personnel groups to shift groups is disassembled to obtain the execution schedule of personnel to specific shifts. This processing method can not only adapt to the task requirements of fine time granularity, but also effectively reduce the complexity of problem solving, and can ensure the quality of solution as much as possible, so that work and rest time can be reasonably arranged for hundreds of service personnel, so that the task requirements can be covered as completely as possible to adapt to large-scale scheduling scenarios. At the same time, various rule configurations can be taken into account to improve the satisfaction of staff.

[0115] It can be seen from the above embodiments that the task scheduling method provided in the embodiments of the present application obtains the task volume of multiple task time periods of the first time granularity; determines the first task undertaking volume of each task undertaker in the unit task time period; and determines the first performance mapping relationship from multiple task undertaking time periods of the second time granularity to each task time period; determines the first corresponding relationship between the task undertaker and the task undertaking time period based on at least the task volume, the first task undertaking volume and the first performance mapping relationship; this processing method, by introducing the first performance mapping relationship, makes shift task scheduling compatible with task requirements of different time granularities, such as the shift level of coarser time granularity and the hour level of fine time granularity, to adapt to business scenarios of refined operations such as e-commerce customer service and new retail, and can minimize early human settings and later manual adjustments; therefore, it can effectively improve the rationality of task scheduling and improve labor management performance.

[0116] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

[0117] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0118] 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.

[0119] 1. Computer-readable media includes 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, magnetic tape magnetic 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 computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0120] 2. Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application can 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 code.

Claims

1. A task scheduling method, characterized in that: include: Determining the task volume of multiple task time periods of a first time granularity includes: determining a task volume forecast value of each task time period in each day within a target time period according to historical task volume data, wherein the first time granularity includes hours; Determine a first task undertaking amount of multiple task undertakers in a unit task time period; and determine a first performance mapping relationship between multiple task undertaking time periods of a second time granularity and each task time period, wherein the first performance mapping relationship between the task undertaking time period and the task time period is work or rest, and the second time granularity includes shifts; Determining a first corresponding relationship between a task undertaker and a task undertaker time period at least according to the task amount, the first task undertaker amount and the first performance mapping relationship includes: Determine the second task undertaking quantity of each task undertaking party group in the unit task time period according to the first task undertaking quantity and the task undertaking party group information; Determine, based on the first performance mapping relationship, a second performance mapping relationship between a plurality of task acceptance time period groups and each task time period; Determine a second corresponding relationship between a task undertaking party group and a task undertaking time period group according to the task amount, the second task undertaking amount and the second performance mapping relationship; According to the second corresponding relationship, determining a second corresponding relationship between the task undertaker and the task undertaking time period as the first corresponding relationship; Alternatively, at least based on the task volume, the first task acceptance volume and the first efficiency mapping relationship, determine the first corresponding relationship between the task undertaker and the task acceptance time period, including: taking the task undertaker as the scheduling unit, and directly allocating the task acceptance time period to each task undertaker based on the task volume, the first task acceptance volume and the first efficiency mapping relationship.

2. The method according to claim 1, characterized in that The second performance mapping relationship is determined in the following manner: Determine the task acceptance time period group information according to the start time and end time of the task acceptance time period; For each task acceptance time period group, a second performance mapping relationship from the task acceptance time period group to each task time period is determined based on a first performance mapping relationship from each task acceptance time period in the task acceptance time period group to each task time period.

3. The method according to claim 2, characterized in that The task acceptance time period group information is determined in the following manner: Multiple task acceptance time period information with the same start time and end time are merged into task acceptance time period group information.

4. The method according to claim 3, characterized in that The weighted average of the first performance mapping relationships is used as the second performance mapping relationship.

Images