Method, device, electronic device and storage medium for determining task incentive parameters

Abstract

The embodiments of the present disclosure provide a method, device, electronic device and storage medium for determining task incentive parameters, the method comprising: predicting the task execution parameters of each time slice of the target area within a preset time period after the current time, and obtaining the future task execution parameters of the time slice; counting the task execution parameters of each time slice of the target area within the historical time, and obtaining the historical task execution parameters of each time slice; for each time slice, determining the task execution parameter threshold of the time slice according to the historical task execution parameters; determining the task incentive parameters corresponding to the task executed at the current time according to the future task execution parameters and the task execution parameter threshold of each time slice. The embodiments of the present disclosure can dynamically determine the task execution parameter threshold, and determine the task incentive parameters according to the future task execution parameters and the task execution parameters of the target area predicted in advance, which helps to improve the accuracy of the task incentive parameters.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer processing technology, and more particularly, to a method, device, electronic device, and storage medium for determining task incentive parameters. Background Art

[0002] Crowdsourcing instant tasks such as takeout delivery, online ride-hailing, and same-city logistics have unstable supply of transportation capacity. In extreme scenarios such as holidays, bad weather, rush hours, emergencies, and hot times, there will be an imbalance between supply and demand, resulting in the inability to handle tasks on the platform in real time, affecting customer experience and platform revenue.

[0003] In the prior art, the most common solution to solve the above problem is to increase the task incentive parameter when the indicator used to evaluate the platform's handling of exceptions is greater than a preset threshold, where the task incentive parameter can be an additional fee provided to the user to incentivize the user to perform the task. However, since the indicator may fluctuate or even change dramatically, the use of a preset threshold to determine whether to increase the task incentive parameter makes the task incentive parameter less accurate, and increasing the task incentive parameter without distinguishing between regions will also result in a lower accuracy of the task incentive parameter. Summary of the invention

[0004] The embodiments of the present disclosure provide a method, device, electronic device and storage medium for determining task incentive parameters, which can dynamically determine task execution parameter thresholds and determine task incentive parameters based on pre-predicted future task execution parameters and task execution parameters of a target area, thereby helping to improve the accuracy of task incentive parameters.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for determining a task incentive parameter is provided, the method comprising:

[0006] Predicting the task execution parameters of each time slice in the target area within a preset time period after the current time, and obtaining the future task execution parameters of the time slice;

[0007] Counting the task execution parameters of each time slice in the target area during the historical time to obtain the historical task execution parameters of each time slice;

[0008] For each time slice, determining a task execution parameter threshold of the time slice according to the historical task execution parameters of the time slice;

[0009] According to the future task execution parameter of each time slice and the task execution parameter threshold, the task incentive parameter corresponding to the task executed at the current time is determined.

[0010] According to a second aspect of an embodiment of the present disclosure, there is provided a device for determining a task incentive parameter, the device comprising:

[0011] A future task execution parameter prediction module is used to predict the task execution parameters of each time slice in the target area within a preset time period after the current time, and obtain the future task execution parameters of the time slice;

[0012] A historical task execution parameter statistics module is used to count the task execution parameters of each time slice in the target area during the historical time to obtain the historical task execution parameters of each time slice;

[0013] A task execution parameter threshold determination module, used to determine, for each time slice, a task execution parameter threshold of the time slice according to the historical task execution parameters of the time slice;

[0014] The task incentive parameter determination module is used to determine the task incentive parameter corresponding to the task executed at the current time according to the future task execution parameter and the task execution parameter threshold of each time slice.

[0015] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0016] A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned method for determining task incentive parameters when executing the program.

[0017] According to a fourth aspect of an embodiment of the present disclosure, a readable storage medium is provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the aforementioned method for determining task incentive parameters.

[0018] The embodiments of the present disclosure provide a method, device, electronic device and storage medium for determining task incentive parameters, the method comprising: predicting the task execution parameters of each time slice of the target area within a preset time period after the current time, and obtaining the future task execution parameters of the time slice; counting the task execution parameters of each time slice of the target area within the historical time, and obtaining the historical task execution parameters of each time slice; for each time slice, determining the task execution parameter threshold of the time slice according to the historical task execution parameters of the time slice; and determining the task incentive parameters corresponding to the task executed at the current time according to the future task execution parameters of each time slice and the task execution parameter threshold. The embodiments of the present disclosure can dynamically determine the task execution parameter threshold, and determine the task incentive parameters according to the future task execution parameters and task execution parameters of the target area predicted in advance, which helps to improve the accuracy of the task incentive parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the description of the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 A flowchart of the method steps for determining task incentive parameters in an embodiment of the present disclosure is shown;

[0021] Figure 2 A flowchart of a method for predicting future task execution parameters in an embodiment of the present disclosure is shown;

[0022] Figure 3 A flowchart of a method for determining a task incentive parameter threshold in an embodiment of the present disclosure is shown;

[0023] Figure 4 A flowchart of the method steps for adjusting task incentive parameters in an embodiment of the present disclosure is shown;

[0024] Figure 5 A flowchart of the steps of a device for determining task incentive parameters in an embodiment of the present disclosure is shown;

[0025] Figure 6 A structural diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present disclosure.

[0027] Embodiment 1

[0028] Reference Figure 1 , which shows a flowchart of the steps of a method for determining task incentive parameters in an embodiment of the present disclosure, the method may include one or more of the following steps:

[0029] Step 101 : predicting the task execution parameters of each time slice of the target area within a preset time period after the current time, and obtaining the future task execution parameters of the time slice.

[0030] The target area may be an administrative area or a custom geographical area, which is not limited in the embodiments of the present disclosure. The embodiments of the present disclosure use the task execution parameters of the target area for analysis and subsidize the tasks in the target area, thereby making the subsidy more accurate.

[0031] In the embodiments of the present disclosure, time is divided into time slices, and the same time slices in different time periods have different guiding significance for different tasks. For example, a day is divided into 24 time slices according to one hour, so that the time slice from 12:00 to 13:00 every day has guiding significance for the food delivery task; the time slices from 7:00 to 8:00 and 18:00 to 19:00 every day have guiding significance for the taxi-hailing task.

[0032] The task execution parameter is used to indicate the degree of abnormality in task execution. The larger the task execution parameter, the higher the degree of abnormality; the smaller the task execution parameter, the lower the degree of abnormality. Among them, the task execution parameters include but are not limited to one or more of the following indicators: task completion time, uncompleted task volume, etc. For example, for a takeaway delivery task, the time from when the merchant receives the order to when the takeaway order is delivered can be used as the task completion time, or the number of uncompleted takeaway orders can be used as the uncompleted task volume; for a taxi task, the time from when the order is placed to when the passenger is delivered to the destination can be used as the task completion time, or the number of unaccepted orders can be used as the uncompleted task volume. It can be understood that the disclosed embodiments do not limit the specific expression of the task execution parameters.

[0033] The embodiments of the present disclosure can periodically predict the task execution parameters of the future time at a certain time interval to improve the real-time performance. First, determine the task execution parameters per unit time in the future time. For example, at 13:00, the task execution parameters per minute in the next 20 minutes (i.e., between 13:00 and 13:20) can be predicted. One minute later, at 13:01, the task execution parameters per minute in the next 20 minutes (i.e., between 13:01 and 13:21) can be predicted. One minute later, at 13:02, the task execution parameters per minute in the next 20 minutes (i.e., between 13:02 and 13:22) can be predicted. And so on. The task execution parameters are continuously updated in real time. Then, based on the continuously updated task execution parameters every minute, the task execution parameters preset for each time slice are updated. Specifically, the task execution parameters for a time slice may be the average value of the task execution parameters for each minute belonging to the time slice. For example, the task execution parameters for a time slice from 13:00 to 13:05 may be the average value of the task execution parameters for each minute from 13:00 to 13:01, 13:01 to 13:02, 13:02 to 13:03, 13:03 to 13:04, and 13:04 to 13:05.

[0034] It should be noted that the preset time period and time slice can be set according to the actual application scenario, and the embodiments of the present disclosure do not limit them.

[0035] Optionally, in specific implementation, refer to Figure 2 , the above step 101 may further include sub-steps 1011 to 1012:

[0036] Sub-step 1011, obtaining the task features of the target area within a preset time period after the current time.

[0037] Among them, task characteristics include but are not limited to: the total number of tasks, the number of personnel serving the tasks, and environmental characteristics.

[0038] Sub-step 1012, inputting the task characteristics into a pre-trained task indicator prediction model to predict the task execution parameters within a preset time period after the current time, wherein the task indicator prediction model is trained by task samples including task execution parameter sample values ​​and task characteristic sample values.

[0039] Among them, the task indicator prediction model can learn the relationship between task characteristics and task execution parameters, such as a logistic regression model.

[0040] Specifically, first, the execution information of each historical task is extracted, such as the task start time, end time, task type, and task characteristics; then, the task execution parameters are counted according to the execution information as the task execution parameter sample values; finally, for each task, the corresponding task characteristics are used as the task feature sample values, and the task execution parameter sample values ​​are used as the task samples to input into the task indicator prediction model for training. When the loss value between the predicted task execution parameters and the task execution parameter sample values ​​is less than a certain loss value threshold, the training is stopped, and the task indicator prediction model at this time is used as the final model.

[0041] In practical applications, the relationship between the task characteristics and the task execution parameters may also be established in other ways, for example, by determining the relationship based on the empirical relationship between the task characteristics and the task execution parameters.

[0042] The embodiments of the present disclosure can accurately predict future task execution parameters through a pre-trained model.

[0043] Step 102 , counting the task execution parameters of each time slice in the target area during the historical time, and obtaining the historical task execution parameters of each time slice.

[0044] The length of the historical time can be set according to the actual application scenario, and the embodiments of the present disclosure do not limit it. For example, it can be 30 days, 1 year, etc.

[0045] Specifically, the historical task execution parameters of each time slice can be periodically counted at a certain time interval to improve real-time performance. For example, if the historical time is 30 days and the time interval is 1 day, the task execution parameters of each time slice between days (A-30) and (A-1) can be counted on day A to obtain the task execution parameters of the first time slice on day (A-30), the task execution parameters of the second time slice on day (A-30), ..., the task execution parameters of the Mth time slice on day (A-30), the task execution parameters of the first time slice on day (A-29), the task execution parameters of the second time slice on day (A-29), the task execution parameters of the Mth time slice on day (A-29), ..., the task execution parameters of the first time slice on day (A-1), the task execution parameters of the second time slice on day (A-1), ..., the task execution parameters of the Mth time slice on day (A-1).

[0046] For another example, for a takeout delivery task, the delivery of each order is a takeout delivery task, and the delivery time is used as the task execution parameter. Therefore, the delivery time of each order is first calculated from the delivery information of each order; then, for each time slice, the average delivery time of all orders placed within the time slice is calculated as the task execution parameter of the time slice.

[0047] Step 103 : for each time slice, determine a task execution parameter threshold of the time slice according to the historical task execution parameters of the time slice.

[0048] Among them, the task execution parameter threshold is used to determine the maximum task execution parameter of the time slice. If the task execution parameter is greater than the task execution parameter threshold, it is determined that the task execution scenario is poor and the task incentive parameter can be adjusted. It can be determined by historical task execution parameters and can be the maximum task execution parameter among the historical task execution parameters.

[0049] Optionally, in specific implementation, refer to Figure 3 , step 103 may further include sub-steps 1031 to 1032:

[0050] Sub-step 1031 , taking the historical task execution parameters of the time slice in each of the historical cycles as variables, and calculating the mean value and standard deviation of the variables.

[0051] In the disclosed embodiment, the historical time is divided into one or more historical periods, and the historical period is divided into one or more time slices, so that each time slice has historical task execution parameters of multiple historical periods, which can be regarded as variables with statistical characteristics, such as mean value, standard deviation, variance, etc. For example, the mean value and standard deviation can be the mean value and standard deviation of the historical task execution parameters of each time slice in different time periods, for example, for the following historical task execution parameters: task execution parameters of the first time slice of the (A-30)th day, task execution parameters of the second time slice of the (A-30)th day, ..., task execution parameters of the Mth time slice of the (A-30)th day, task execution parameters of the first time slice of the (A-29)th day, task execution parameters of the second time slice of the (A-29)th day, task execution parameters of the Mth time slice of the (A-29)th day, ..., task execution parameters of the first time slice of the (A-1)th day, task execution parameters of the second time slice of the (A-1)th day, ..., task execution parameters of the Mth time slice of the (A-1)th day. Therefore, based on the above data, the average value and standard deviation of the task execution parameters of the 1st time slice on the (A-30)th day, the task execution parameters of the 1st time slice on the (A-29)th day, ..., and the task execution parameters of the 1st time slice on the (A-1)th day are calculated to obtain the average value and standard deviation of the historical task execution parameters of the 1st time slice; the average value and standard deviation of the task execution parameters of the 2nd time slice on the (A-30)th day, the task execution parameters of the 2nd time slice on the (A-29)th day, ..., and the task execution parameters of the 2nd time slice on the (A-1)th day are calculated to obtain the average value and standard deviation of the historical task execution parameters of the 2nd time slice; ...; the average value and standard deviation of the task execution parameters of the Mth time slice on the (A-30)th day, the task execution parameters of the Mth time slice on the (A-29)th day, ..., and the task execution parameters of the Mth time slice on the (A-1)th day are calculated to obtain the average value and standard deviation of the historical task execution parameters of the Mth time slice.

[0052] Sub-step 1032, determining the fluctuation extreme value corresponding to the task execution parameter within the time slice according to the preset fluctuation coefficient and the standard deviation.

[0053] Specifically, for the i-th time slice, the extreme value of fluctuation can be calculated according to the following formula:

[0054] MAXW i =a·σ(IND i ) (1)

[0056] Among them, MAXW i is the fluctuation extreme value of the task execution parameter in the i-th time slice, IND iis the historical task execution parameter of the i-th time slice, σ(IND i ) is the standard deviation of the historical task execution parameters of the ith time slice, a is a coefficient, which can be set according to the actual application scenario, and the embodiment of the present disclosure does not limit its value.

[0057] It should be noted that the larger the absolute value of a is, the higher the tolerance for fluctuations in the task execution parameters is, and the smaller the absolute value of a is, the smaller the tolerance for fluctuations in the task execution parameters is.

[0058] Sub-step 1033, calculating the sum of the average value and the fluctuation extreme value to obtain the task execution parameter threshold of the time slice.

[0059] Specifically, for the i-th time slice, the task execution parameter threshold can be calculated according to the following formula:

[0060] THR i =AVR(IND i )+a·σ(IND i ) (2)

[0062] Among them, THR i is the task execution parameter threshold of the i-th time slice, AVR(IND i ) is the average value of the historical task execution parameters in the i-th time slice.

[0063] The embodiments of the present disclosure can flexibly adjust the fluctuation of the task execution parameter threshold according to a preset fluctuation coefficient.

[0064] Step 104 : determining the task incentive parameter corresponding to the task executed at the current time according to the future task execution parameter of each time slice and the task execution parameter threshold.

[0065] Among them, the task incentive parameter can be the additional income obtained from performing the task, for example, the additional delivery income obtained by food delivery personnel in addition to the delivery fee, and the additional delivery income obtained by Didi drivers in addition to the basic delivery fee.

[0066] Among them, the task incentive parameters of each time slice can be set initially according to the pre-stated historical task execution parameters. The smaller the historical task execution parameters are, the smaller the task incentive parameters can be set to; the larger the historical task execution parameters are, the larger the task incentive parameters can be set to.

[0067] Specifically, for the current time, the future task execution parameters and task execution parameter thresholds of the next few time slices can be used to determine whether the scenario for executing the task has improved or deteriorated. If it has improved, the task incentive parameters can be increased; if it has deteriorated, the task incentive parameters can be reduced; otherwise, the task incentive parameters for this time slice will not be adjusted.

[0068] Among them, the most stringent judgment condition for determining whether the scenario of executing the task has improved or deteriorated is: if the future task execution parameters of 5 consecutive future time slices are all greater than the task execution parameter threshold, and the future task execution parameters of the next time slice are greater than the future task execution parameters of the previous time slice, and the difference between the future task execution parameters of the next time slice and the task execution parameter threshold is greater than the difference between the future task execution parameters of the previous time slice and the task execution parameter threshold, then the scenario of executing the task has improved; if the future task execution parameters of 5 consecutive future time slices are all less than the task execution parameter threshold, and the future task execution parameters of the next time slice are less than the future task execution parameters of the previous time slice, and the difference between the future task execution parameters of the next time slice and the task execution parameter threshold is less than the difference between the future task execution parameters of the previous time slice and the task execution parameter threshold, then the scenario of executing the task has deteriorated. In this way, it is possible to accurately determine whether the future task execution parameters continue to deteriorate, so that the task incentive parameters can be accurately increased, avoiding the increase of task incentive parameters in scenarios where they do not need to be increased, which helps to reduce costs.

[0069] In addition, to determine whether the scenario of executing the task has become better or worse, the following slightly loose judgment conditions can also be used: if a certain number of target time slices in five consecutive future time slices (which can be continuous or discontinuous) have future task execution parameters that are greater than the task execution parameter threshold, and the future task execution parameter of the next time slice is greater than the future task execution parameter of the previous time slice, and the difference between the future task execution parameter of the next time slice and the task execution parameter threshold is greater than the difference between the future task execution parameter of the previous time slice and the task execution parameter threshold, then it is determined that the scenario of executing the task has become better; if a certain number of target time slices in five consecutive future time slices (which can be continuous or discontinuous) have future task execution parameters that are less than the task execution parameter threshold, and the future task execution parameter of the next time slice is less than the future task execution parameter of the previous time slice, and the difference between the future task execution parameter of the next time slice and the task execution parameter threshold is less than the difference between the future task execution parameter of the previous time slice and the task execution parameter threshold, then it is determined that the scenario of executing the task has become worse. This can reduce the judgment conditions and help increase the adjustment scenarios of the task incentive parameters.

[0070] It can be understood that the more target time slices there are, the stricter the judgment conditions are, the more accurate the judgment results are, but the fewer scenes need to be adjusted; the fewer target time slices there are, the less strict the judgment conditions are, the less accurate the judgment results are, but the more scenes need to be adjusted. Therefore, it is necessary to consider both accuracy and number to select the appropriate target time slices.

[0071] Optionally, in specific implementation, refer to Figure 4 , step 104 may include sub-step 1041:

[0072] Sub-step 1041, if the task execution parameter difference of each target time slice is greater than or equal to 0, and the task execution parameter difference of the second time slice is greater than the task execution parameter difference of the first time slice, and the future task execution parameter of the second time slice is greater than the future task execution parameter of the first time slice, then the task incentive parameter corresponding to the task executed at the current time is increased, the target time slice includes: a preset number of target time slices after the current time, the target time slice includes a first time slice and a second time slice after the first time slice, and the task execution parameter difference is obtained by subtracting the task execution parameter threshold of the target time slice from the future task execution parameter of the target time slice.

[0073] It can be seen that the conditions in step 104 are relatively strict. In practical applications, two reference time slices, namely the first time slice and the second time slice, can be selected for judgment to determine that the scenario for executing the task has improved. When the scenario has improved more, the task incentive parameters can be increased, and the number of comparisons can be reduced, thereby improving the speed.

[0074] It should be noted that when determining whether to increase the task incentive parameter, the number of reference time slices may be selected, and the number of time slices may be less than or equal to the number of time slices included in the preset time period in step 101 .

[0075] Optionally, in another embodiment of the present disclosure, step 1041 includes sub-step 10411:

[0076] Sub-step 10411, setting the task incentive parameter corresponding to the task executed at the current time to the maximum task incentive parameter, or increasing the task incentive parameter corresponding to the task executed at the current time by a preset adjustment step.

[0077] Among them, the maximum task incentive parameter and the adjustment step size can be set according to the actual application scenario, and the embodiments of the present disclosure do not limit them.

[0078] The embodiments of the present disclosure can directly increase the task incentive parameter to the maximum task incentive parameter, or can increase it according to a preset adjustment step size, thereby achieving flexible adjustment of the current task incentive parameter.

[0079] Optionally, in another embodiment of the present disclosure, the first time slice is the time slice to which the current time belongs or the first time slice after it, and the second time slice is the last time slice after the current time.

[0080] The embodiments of the present disclosure can accurately increase or decrease the task incentive parameters only according to the future task execution parameters of the first time slice and the last time slice after the current time.

[0081] Optionally, in specific implementation, refer to Figure 4 , step 104 may further include sub-step 1042:

[0082] Sub-step 1042, if the task execution parameter difference of each target time slice is less than 0, and the task execution parameter difference of the second time slice is less than the task execution parameter difference of the first time slice, and the future task execution parameter of the second time slice is less than the future task execution parameter of the first time slice, then the task incentive parameter corresponding to the task executed at the current time is reduced.

[0083] In an embodiment of the present disclosure, it is possible to accurately determine whether to reduce the task incentive parameter based on the relationship between the future task execution parameters of multiple target time slices and the task execution parameter threshold. For example, if the future task execution parameters of five consecutive time slices are all less than the task execution parameter threshold, and the future task execution parameters of the next time slice are less than the future task execution parameters of the previous time slice, and the difference between the future task execution parameters of the next time slice and the task execution parameter threshold is less than the difference between the future task execution parameters of the previous time slice and the task execution parameter threshold, then it is determined that the future task execution parameters of five consecutive time slices continue to deteriorate, so that the task incentive parameter can be reduced. In this way, it is possible to accurately determine whether the future task execution parameters continue to improve, so that the task incentive parameter can be accurately reduced, avoiding reducing the task incentive parameter in a scenario where the future task execution parameters have not improved, which helps to shorten the time it takes for delivery personnel to receive the task.

[0084] It can be seen that the conditions of the above scheme are relatively strict. In practical applications, two reference time slices can be selected for judgment, which can reduce the task incentive parameters in more cases, reduce the number of comparisons, and improve the speed.

[0085] Optionally, in another embodiment of the present disclosure, the sub-step 1042 includes sub-step 10421:

[0086] Sub-step 10421, setting the task incentive parameter corresponding to the task executed at the current time to the minimum task incentive parameter, or reducing the task incentive parameter corresponding to the task executed at the current time by a preset adjustment step.

[0087] Among them, the minimum task incentive parameter can be set according to the actual application scenario, and the embodiments of the present disclosure do not limit it.

[0088] The embodiments of the present disclosure can directly reduce the task incentive parameter to the minimum task incentive parameter, or can reduce it according to a preset adjustment step, thereby achieving flexible adjustment of the current task incentive parameter.

[0089] In summary, the embodiments of the present disclosure provide a method for determining task incentive parameters. In addition to determining the task execution parameter threshold and determining the task incentive parameters based on the pre-predicted future task execution parameters and task execution parameters of the target area, which helps to improve the accuracy of the task incentive parameters, the method can also accurately predict future task execution parameters through a pre-trained model; it can also accurately predict future task execution parameters through a pre-trained model; it can also accurately determine to increase or decrease the task incentive parameters based on the relationship between the future task execution parameters of the first time slice and the second time slice and the task execution parameter threshold; it can also accurately increase or decrease the task incentive parameters based only on the future task execution parameters of the first time slice and the last time slice after the current time; it can also directly increase the task incentive parameters to the maximum task incentive parameters or decrease them to the minimum task incentive parameters, and it can also increase or decrease according to a preset adjustment step size, thereby realizing flexible adjustment of the current task incentive parameters.

[0090] Embodiment 2

[0091] Reference Figure 5 , which shows a structural diagram of a device for determining task incentive parameters in another embodiment of the present disclosure, as follows.

[0092] The future task execution parameter prediction module 201 is used to predict the task execution parameters of each time slice of the target area within a preset time period after the current time, and obtain the future task execution parameters of the time slice; optionally, in an embodiment of the present disclosure, the future task execution parameter prediction module 201 includes:

[0093] The task feature acquisition submodule 2011 is used to acquire the task features of the target area within a preset time period after the current time.

[0094] The future task execution parameter prediction submodule 2012 is used to input the task characteristics into a pre-trained task indicator prediction model to predict the task execution parameters within a preset time period after the current time. The task indicator prediction model is obtained by training task samples containing task execution parameter sample values ​​and task feature sample values.

[0095] The historical task execution parameter statistics module 202 is used to count the task execution parameters of each time slice in the target area during the historical time to obtain the historical task execution parameters of each time slice.

[0096] The task execution parameter threshold determination module 203 is used to determine the task execution parameter threshold of each time slice according to the historical task execution parameters of the time slice; optionally, in another embodiment of the present disclosure, the task execution parameter threshold determination module 203 includes:

[0097] The statistical information calculation submodule 2031 is used to use the historical task execution parameters of the time slice in each historical period as variables, and calculate the average value and standard deviation of the variables.

[0098] The fluctuation extreme value determination submodule 2032 is used to determine the fluctuation extreme value corresponding to the task execution parameter within the time slice according to a preset fluctuation coefficient and the standard deviation.

[0099] The task execution parameter threshold determination submodule 2033 is used to calculate the sum of the average value and the fluctuation extreme value to obtain the task execution parameter threshold of the time slice.

[0100] The task incentive parameter determination module 204 is used to determine the task incentive parameter corresponding to the task executed at the current time according to the future task execution parameter and the task execution parameter threshold of each time slice; optionally, in an embodiment of the present disclosure, the task incentive parameter determination module 204 includes:

[0101] The task incentive parameter increasing submodule 2041 is used to increase the task incentive parameter corresponding to the task executed at the current time if the task execution parameter difference of each target time slice is greater than or equal to 0, and the task execution parameter difference of the second time slice is greater than the task execution parameter difference of the first time slice, and the future task execution parameter of the second time slice is greater than the future task execution parameter of the first time slice. The target time slice includes: a preset number of target time slices after the current time, the target time slice includes a first time slice and a second time slice after the first time slice, and the task execution parameter difference is obtained by subtracting the task execution parameter threshold of the target time slice from the future task execution parameter of the target time slice.

[0102] The task incentive parameter reduction submodule 2042 is used to reduce the task incentive parameter corresponding to the task executed at the current time if the task execution parameter difference of each target time slice is less than 0, and the task execution parameter difference of the second time slice is less than the task execution parameter difference of the first time slice, and the future task execution parameter of the second time slice is less than the future task execution parameter of the first time slice.

[0103] Optionally, in another embodiment of the present disclosure, the task incentive parameter increasing submodule 2041 includes:

[0104] The task incentive parameter increasing unit is used to set the task incentive parameter corresponding to the task executed at the current time to the maximum task incentive parameter, or to increase the task incentive parameter corresponding to the task executed at the current time by a preset adjustment step.

[0105] Optionally, in another embodiment of the present disclosure, the first time slice is the time slice to which the current time belongs or the first time slice after it, and the second time slice is the last time slice after the current time.

[0106] Optionally, in another embodiment of the present disclosure, the task incentive parameter reduction submodule 2042 includes:

[0107] The task incentive parameter reduction unit is used to set the task incentive parameter corresponding to the task executed at the current time to the minimum task incentive parameter, or to reduce the task incentive parameter corresponding to the task executed at the current time by a preset adjustment step.

[0108] In summary, the embodiments of the present disclosure provide another device for determining task incentive parameters. In addition to determining the task execution parameter threshold and determining the task incentive parameters based on the pre-predicted future task execution parameters and task execution parameters of the target area, which helps to improve the accuracy of the task incentive parameters, the device can also accurately predict future task execution parameters through a pre-trained model; it can also accurately predict future task execution parameters through a pre-trained model; it can also accurately determine to increase or decrease the task incentive parameters based on the relationship between the future task execution parameters of the first time slice and the second time slice and the task execution parameter threshold; it can also accurately increase or decrease the task incentive parameters based only on the future task execution parameters of the first time slice and the last time slice after the current time; it can also directly increase the task incentive parameters to the maximum task incentive parameters or decrease them to the minimum task incentive parameters, and it can also increase or decrease according to a preset adjustment step size, thereby realizing flexible adjustment of the current task incentive parameters.

[0109] Embodiment 2 is a device embodiment corresponding to Embodiment 1. The detailed description may refer to Embodiment 1 and will not be repeated here.

[0110] The embodiment of the present disclosure also provides an electronic device, referring to Figure 6 , including: a processor 301, a memory 302, and a computer program 3021 stored in the memory 302 and executable on the processor, wherein when the processor 301 executes the program, the method for determining task incentive parameters of the aforementioned embodiment is implemented.

[0111] An embodiment of the present disclosure further provides a readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining task incentive parameters of the aforementioned embodiment.

[0112] As for the device 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.

[0113] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems may also be used together with the teachings based thereon. According to the above description, it is apparent that the structure required for constructing such systems is. In addition, the embodiments of the present disclosure are not directed to any particular programming language either. It should be understood that the contents of the embodiments of the present disclosure described herein may be realized using various programming languages, and the description of the specific languages ​​above is intended to disclose the best mode of implementation of the embodiments of the present disclosure.

[0114] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the embodiments of the present disclosure can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0115] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present disclosure, the various features of the embodiments of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: that the claimed embodiments of the present disclosure require more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself as a separate embodiment of the embodiments of the present disclosure.

[0116] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0117] The various component embodiments of the embodiments of the present disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the service evaluation device according to the embodiments of the present disclosure. The embodiments of the present disclosure may also be implemented as a device or apparatus program for executing part or all of the methods described herein. Such a program implementing the embodiments of the present disclosure may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0118] It should be noted that the above embodiments illustrate rather than limit the embodiments of the present disclosure, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The embodiments of the present disclosure may be implemented by means of hardware including several different elements and by means of appropriately programmed computers. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0120] The above description is only a preferred embodiment of the embodiments of the present disclosure and is not intended to limit the embodiments of the present disclosure. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the embodiments of the present disclosure should be included in the protection scope of the embodiments of the present disclosure.

[0121] The above is only a specific implementation of the embodiment of the present disclosure, but the protection scope of the embodiment of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed by the embodiment of the present disclosure, which should be included in the protection scope of the embodiment of the present disclosure. Therefore, the protection scope of the embodiment of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for determining task incentive parameters, It is characterized in that The method comprises: Predicting the task execution parameters of each time slice in the target area within a preset time period after the current time, and obtaining the future task execution parameters of the time slice, wherein the task execution parameters are used to indicate the abnormality degree of task execution, and the larger the task execution parameters, the higher the abnormality degree; Counting the task execution parameters of each time slice in the target area during the historical time to obtain the historical task execution parameters of each time slice; For each time slice, determining a task execution parameter threshold of the time slice according to the historical task execution parameters of the time slice; Determine, according to the future task execution parameter of each time slice and the task execution parameter threshold, a task incentive parameter corresponding to the task executed at the current time, wherein the task incentive parameter is the additional benefit obtained by executing the task; The step of determining the task incentive parameter corresponding to the task executed at the current time according to the future task execution parameter and the task execution parameter threshold of each time slice includes: If the task execution parameter difference of each target time slice is greater than or equal to 0, and the task execution parameter difference of the second time slice is greater than the task execution parameter difference of the first time slice, and the future task execution parameter of the second time slice is greater than the future task execution parameter of the first time slice, then the task incentive parameter corresponding to the task executed at the current time is increased, the target time slice includes: a preset number of target time slices after the current time, the target time slice includes the first time slice and the second time slice after the first time slice, and the task execution parameter difference is obtained by subtracting the task execution parameter threshold of the target time slice from the future task execution parameter of the target time slice; The method further comprises: If the task execution parameter difference of each target time slice is less than 0, and the task execution parameter difference of the second time slice is smaller than the task execution parameter difference of the first time slice, and the future task execution parameter of the second time slice is smaller than the future task execution parameter of the first time slice, then the task incentive parameter corresponding to the task executed at the current time is reduced.

2. The method according to claim 1, It is characterized in that The historical time is divided into one or more historical periods, the historical period is divided into one or more time slices, and the step of determining the task execution parameter threshold of the time slice according to the historical task execution parameter of the time slice includes: Taking the historical task execution parameters of the time slice in each of the historical cycles as variables, calculating the mean value and standard deviation of the variables; Determining a fluctuation extreme value corresponding to the task execution parameter within the time slice according to a preset fluctuation coefficient and the standard deviation; The sum of the average value and the fluctuation extreme value is calculated to obtain the task execution parameter threshold of the time slice.

3. The method according to claim 1, It is characterized in that The step of increasing the task incentive parameter corresponding to the task executed at the current time includes: Setting the task incentive parameter corresponding to the task executed at the current time to the maximum task incentive parameter, or increasing the task incentive parameter corresponding to the task executed at the current time by a preset adjustment step; The step of reducing the task incentive parameter corresponding to the task executed at the current time includes: The task incentive parameter corresponding to the task executed at the current time is set to the minimum task incentive parameter, or the task incentive parameter corresponding to the task executed at the current time is reduced by a preset adjustment step.

4. The method according to claim 1, It is characterized in that The first time slice is the time slice to which the current time belongs or the first time slice after it, and the second time slice is the last time slice after the current time.

5. The method according to claim 1, It is characterized in that The step of predicting the task execution parameters of each time slice in the target area within a preset time period after the current time includes: Obtaining the task characteristics of the target area within a preset time period after the current time; The task characteristics are input into a pre-trained task indicator prediction model to predict the task execution parameters within a preset time period after the current time. The task indicator prediction model is trained by task samples including task execution parameter sample values ​​and task feature sample values.

6. An electronic device, It is characterized in that include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for determining task incentive parameters as described in one or more of claims 1 to 5 is implemented.

7. A readable storage medium, It is characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining task incentive parameters as described in one or more of method claims 1-5.

Images