Capacity incentive method, device, electronic device and computer storage medium

Abstract

The embodiments of the present application provide a data processing method, device, electronic device and computer storage medium. The data processing method includes: determining whether the first service range corresponding to the target object lacks transportation capacity, and / or determining whether the second service range corresponding to the target object lacks transportation capacity within a set time period after the current moment; if it is determined that there is a lack of transportation capacity, then determining whether the probability of the target object completing at least one order within the set time period does not meet the set threshold based on the historical behavior data and current status data of the target object; if the set threshold is not met, determining the incentive data corresponding to the target object; generating an incentive release message based on the incentive data, and sending the incentive release message to the corresponding target object. This method can improve the response rate.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a capacity incentive method, device, electronic device and computer storage medium. Background Art

[0002] With the development of online ride-hailing platforms and food delivery platforms, people's lives have become much more convenient. In online ride-hailing platforms and food delivery platforms, peak capacity shifting is an urgent problem to be solved. For example, in online ride-hailing platforms or food delivery platforms, there is a tendency for insufficient capacity, long call waiting time, and low response rate during peak call times or hot spots (geographical areas with a large number of demands). In order to solve this problem, how to obtain more capacity during peak hours has become an urgent problem to be solved. Summary of the invention

[0003] In view of this, an embodiment of the present application provides a capacity incentive solution to at least partially solve the above-mentioned problems.

[0004] According to the first aspect of an embodiment of the present application, a capacity incentive method is provided, including: determining whether a first service scope corresponding to a target object lacks capacity, and / or determining whether a second service scope corresponding to the target object lacks capacity within a set time period after a current moment; if it is determined that there is a lack of capacity, determining whether the probability of the target object completing at least one order within the set time period does not meet a set threshold based on the historical behavior data and current status data of the target object; if the set threshold is not met, determining incentive data corresponding to the target object; generating an incentive release message based on the incentive data, and sending the incentive release message to the corresponding target object.

[0005] According to the second aspect of an embodiment of the present application, a capacity incentive device is provided, including: a first determination module, used to determine whether a first service scope corresponding to a target object lacks capacity, and / or, whether a second service scope corresponding to the target object lacks capacity within a set time period after a current moment; a second determination module, used to determine whether the probability of the target object completing at least one order within the set time period does not meet a set threshold based on the historical behavior data and current status data of the target object if it is determined that there is a lack of capacity; a third determination module, used to determine incentive data corresponding to the target object if the set threshold is not met; a sending module, used to generate an incentive release message based on the incentive data, and send the incentive release message to the corresponding target object.

[0006] According to the third aspect of an embodiment of the present application, a capacity incentive method is provided, including: determining whether a first travel platform lacks capacity within a third service scope, the first travel platform being an aggregation platform that aggregates multiple second travel platforms; if it is determined that there is a lack of capacity, determining the probability of the target object completing at least one order within a set time period based on the historical behavior data and current status data of the target object within the third service scope in each of the second travel platforms; if the probability of the target object completing at least one order does not meet a set threshold, determining incentive data for the target object, and sending an incentive message generated based on the incentive data to the target object, so that the target object remains within the third service scope as the capacity of the corresponding second travel platform.

[0007] According to the fourth aspect of an embodiment of the present application, a capacity incentive method is provided, comprising: receiving an incentive release message, the incentive release message carrying incentive data, and the incentive data being determined according to the aforementioned method; displaying the incentive data carried in the incentive release message in a display interface, so that the target object is retained as capacity within the corresponding service scope.

[0008] According to the fifth aspect of the embodiment of the present application, a data processing method is provided, including: determining whether a fourth service scope lacks transportation capacity; if the fourth service scope lacks transportation capacity, obtaining historical behavior data and current status data of target objects within the fourth service scope; determining the probability of each target object completing at least one order within a set time period based on the historical behavior data and the current status data of each target object; generating analysis results based on the probability of each target object completing at least one order and the location information of each target object.

[0009] According to the sixth aspect of an embodiment of the present application, there is provided an electronic device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the aforementioned method.

[0010] According to a seventh aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.

[0011] According to an eighth aspect of an embodiment of the present application, a computer program product is provided, comprising computer instructions, wherein the computer instructions instruct a computing device to perform operations corresponding to the aforementioned method.

[0012] According to the capacity incentive scheme provided in the embodiment of the present application, it is possible to determine whether the first service scope and / or the second service scope corresponding to the target object lacks capacity. If there is a lack of capacity, it is determined whether the probability of the target object completing at least one order within a set time period in the future does not meet the set threshold. If the set threshold is not met, the incentive data corresponding to the target object is determined, and an incentive release message is generated based on the incentive data, and then the incentive release message is sent to the target object so that it can be informed of the incentive release message, thereby increasing its probability of completing at least one order. In this way, when it is determined that there is a lack of capacity, the target object whose probability of completing at least one order does not meet the set threshold can be screened out, and the probability of completing at least one order can be increased by sending an incentive release message to it. This not only increases the available capacity, but also sends the incentive release message in a targeted manner, avoiding the high cost problem of indiscriminate allocation of incentives. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0014] Figure 1A A flowchart of a method for providing a transportation capacity incentive according to Embodiment 1 of the present application;

[0015] Figure 1B It is a schematic diagram of the transport capacity and order quantity of a usage scenario according to the first embodiment of the present application;

[0016] Figure 1C Schematic diagram of the state of the target object at different times according to the first embodiment of the present application;

[0017] Figure 1D Schematic diagram of sub-steps of step S104 according to the first embodiment of the present application;

[0018] Figure 1E Schematic diagram of sub-steps of step S106 according to the first embodiment of the present application;

[0019] Figure 2 This is a flow chart of the steps of a capacity incentive method according to Embodiment 2 of the present application;

[0020] Figure 3 This is a flowchart of a method for capacity incentive according to Embodiment 3 of the present application;

[0021] Figure 4 is a flowchart of a data processing method according to Embodiment 4 of the present application;

[0022] Figure 5 is a structural block diagram of a device according to Embodiment 5 of the present application;

[0023] Figure 6 is a structural block diagram of a device according to Embodiment 6 of the present application;

[0024] Figure 7 is a structural block diagram of a device according to Embodiment 7 of the present application;

[0025] Figure 8 is a structural block diagram of a device according to Embodiment 8 of the present application;

[0026] Fig. 9 This is a schematic diagram of the structure of an electronic device according to Embodiment 9 of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0028] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.

[0029] Embodiment 1

[0030] Reference Figure 1A , showing a step flow chart of the capacity incentive method of embodiment 1 of the present application.

[0031] The method can be applied to scenarios such as online car-hailing scenarios and / or food delivery scenarios, and is used to more accurately estimate whether there is a lack of transportation capacity in the applied scenario, and then when there is a lack of transportation capacity, it can tap available transportation capacity to solve the problem of lack of transportation capacity, thereby improving the response rate. Of course, in other embodiments, the method can also be applied to other appropriate scenarios, without limitation.

[0032] In this embodiment, the method includes the following steps:

[0033] Step S102: Determine whether a first service range corresponding to the target object lacks transportation capacity, and / or determine whether a second service range corresponding to the target object lacks transportation capacity within a set time period after the current moment.

[0034] Since there is a mismatch between supply and demand in the transportation capacity of online ride-hailing platforms and / or food delivery platforms, such as Figure 1B A schematic diagram showing the changes in the number of orders (i.e., demand) and the number of transport capacity (i.e., supply) of an online car-hailing platform over time. During off-peak hours or cold zones (areas with fewer orders), the idle time of transport capacity increases or the idle mileage increases. During peak hours or hot zones (areas with more orders), transport capacity may be insufficient. In order to ensure that there is sufficient transport capacity during peak hours or hot zones, it is necessary to predict hot zones or peak hours.

[0035] The target object can be the transport capacity that meets the screening conditions, such as the driver in the online car-hailing platform, or the rider in the food delivery platform. The screening conditions are used to determine whether the target object is in a state where it can receive messages and will not affect normal driving and riding, so as to ensure that the subsequent incentive release messages sent to the target object will not interfere with its attention and cause dangerous situations. The specific content of the screening conditions can be determined as needed. For example, in order to ensure safety and avoid accidents, the screening conditions include at least one of the following: first time online on the day, in an idle listening state, in a completed order state, etc., but not limited to this.

[0036] For example, Figure 1C A schematic diagram of the target object's activities in the platform is shown. It mainly includes: going online, setting the listening mode, setting the fence (the fence refers to the range of activities), going offline, picking up or picking up food, delivering or delivering food, idle listening, etc. Among them, picking up or picking up food, and delivering or delivering food are states of providing services to the target object, and the target object is usually in a driving or riding state, so it is not appropriate to interfere with the target object's attention in these stages, so these stages are not suitable for triggering push incentive release messages.

[0037] Through the aforementioned screening conditions, suitable target objects can be screened out, thereby ensuring the driving or riding safety of the target objects.

[0038] When it is determined that the target object meets the conditions for the first online access of the day, it means that the target object is not driving or riding and is in a relatively safe state. Therefore, an incentive release message can be sent to it as needed, so as to ensure that the target object's attention will not be disturbed when obtaining information, thereby avoiding dangerous situations.

[0039] Being in an idle order-listening state, in an order-completing state, etc. are similar to meeting the conditions for the first online launch of the day, so they will not be elaborated on.

[0040] In one feasible manner, determining whether the first service scope corresponding to the target object lacks capacity can be achieved by: obtaining a first response rate corresponding to the first service scope in at least one previous time period before the current moment; if the first response rate is less than a response threshold, it is determined that the first service scope lacks capacity, and step S104 is executed; or, if the first response rate is greater than or equal to the response threshold, it is determined that the first service scope does not lack capacity, and no action may be taken, or other appropriate actions may be performed.

[0041] The previous time period is, for example, 15 minutes before the current time or 30 minutes before the current time, and the length of the previous time period can be determined as needed.

[0042] The first service range is an area of ​​N kilometers adjacent to the location of the target object, where N is a positive number and can be determined as needed. N can be adjusted as needed, for example, 3, 3.5, 5, etc. N depends on the supply and demand situation. If the current time is an off-peak period, the value of N is relatively large. During peak periods, the value of N can be reduced to improve transportation efficiency.

[0043] By obtaining the call volume and answer volume within a range of N kilometers around the target object's location (i.e., the first service range) within 15 minutes before the current moment, and determining the first answer rate based on the call volume and answer volume, if the first answer rate is less than a set threshold (which can be determined as needed, such as 75%), it is determined that there is a lack of capacity within the first service range; otherwise, it can be determined that there is no lack of capacity within the first service range.

[0044] In one feasible method, determining whether the second service scope corresponding to the target object lacks transportation capacity within a set time period after the current moment can be achieved by: determining the second response rate of the second service scope in a historical time period corresponding to the set time period in a cycle before the set time period, and the third response rate of the second service scope in the current day; based on the second response rate and the third response rate, determining whether the second service scope lacks transportation capacity in the subsequent set time period.

[0045] The length of the set time period can be determined as needed, for example, 30 minutes after the current moment. Due to the regularity of daily life, the number of orders issued has the characteristics of periodic fluctuations. For example, the number of orders issued and the number of responses in a certain time period on the first day of the previous cycle may be similar to the number of orders issued and the number of responses in the time period corresponding to the first day of the current cycle. Therefore, when predicting whether there will be a lack of transportation capacity in the future set time period, the second response rate of the second service range (for example, the city where the target object is located) in the previous cycle and the third response rate in the second service range of the elapsed time period on the current day can be combined to predict whether there will be a lack of transportation capacity in the future set time period based on the second response rate and the third response rate.

[0046] For example, if the current time is 10:00 on Monday, the second response rate may be the second response rate within the second service range corresponding to 10:00-10:30 on Monday of the previous week. The third response rate may be the third response rate within the second service range corresponding to 0:00-10:00 on Monday of this week.

[0047] The second service range may be the same as or different from the first service range. For example, the second service range may be the district where the target object is located.

[0048] An input feature is constructed based on the second response rate and the third response rate, and the input feature is input into a trained machine learning model (e.g., a DNN model) to obtain a prediction result output by the machine learning model, which is used to indicate whether there is a lack of capacity in a future set time period. The machine learning model can be a pre-trained model for predicting whether there is a lack of capacity in a future set time period. In order to improve the accuracy of the screening, the threshold can be adjusted by the PID algorithm, and the real-time response rate is used as the error value in the PID algorithm during the adjustment.

[0049] Step S104: If it is determined that there is a lack of transportation capacity, then based on the historical behavior data and current status data of the target object, determine whether the probability of the target object completing at least one order within the set time period does not meet a set threshold.

[0050] The historical behavior data includes at least one of the following: the total number of completed orders of the target object, the historical daily resource acquisition information of the target object, the offline time corresponding to the current time slice, etc., but is not limited thereto. Among them, the historical daily resource acquisition information of the target object is used to indicate the resource acquisition situation of the target object on each single day.

[0051] According to the needs, a day can be divided into multiple time slices, such as morning, afternoon, evening, etc., or multiple slices such as (7:00-9:00], (9:00-12:00], (12:00-17:00], (17:00-19:00], etc. By slicing a single day and obtaining the latest offline time of the target object in each time slice, the offline habits and working hours of the target object can be more accurately reflected. Therefore, the probability of the target object completing at least one order in the future set time period can be accurately estimated.

[0052] The current status data includes at least one of the following: online time for the day, resource information of the target object acquired on the day, number of completed orders of the target object on the day, idle time of the target object on the day and current location, but is not limited thereto.

[0053] In one possible approach, Figure 1D As shown, step S104 includes the following sub-steps:

[0054] Sub-step S1041: If it is determined that there is a lack of transportation capacity, construct input features based on the historical behavior data and current status data of the target object.

[0055] For example, historical behavior data and current state data are concatenated as input features, or historical behavior data and current state data are processed in an appropriate manner, and the processing results are concatenated as input features.

[0056] Sub-step S1042: Input the input features into a machine learning model for predicting the probability of completing at least one order, so as to obtain the probability of the target object completing at least one order within the set time period output by the machine learning model.

[0057] The machine learning model used to predict the probability of completing at least one order is, for example, an XGboost model, which is trained by training samples. Based on the input features of the target object, the machine learning model can predict the corresponding probability of completing at least one order.

[0058] Sub-step S1043: Based on the probability of completing at least one order and the obtained set threshold, determine whether the probability of completing at least one order does not meet the set threshold.

[0059] If the probability of completing at least one order does not meet the set threshold, for example, the probability of completing at least one order is less than or equal to the set threshold, it means that the target object is more likely to be unable to provide services within the set time period, and additional incentives are needed to increase the probability of the target object providing services within the set time period. Therefore, step S106 can be executed.

[0060] Alternatively, if the probability of completing at least one order meets the set threshold, for example, the probability of completing at least one order is greater than the set threshold, it means that the target object is more likely to be able to provide services within the set time period, and there is no need to issue additional incentives to the target object, so no action can be taken, or other appropriate operations can be performed.

[0061] The set threshold may be a pre-set fixed value. Alternatively, in this embodiment, in order to improve intelligence and adaptability and prevent the inability to accurately screen out target objects with a low probability of completing at least one order, the set threshold may also be determined based on the real-time response rate. For example, in one feasible manner, the following process may be performed at an appropriate time: the set threshold is adjusted using a PID algorithm based on the real-time response rate of the second service scope.

[0062] The PID algorithm can effectively realize closed-loop control of the set threshold, wherein the real-time response rate within the second service range is used as the error value to perform PID control on the set threshold, which can ensure real-time performance and adaptively adjust the set threshold according to actual conditions.

[0063] Step S106: If the set threshold is not met, determining the excitation data corresponding to the target object.

[0064] The incentive data of the target object may be virtual resources sent to the target object, or other physical items or virtual items that can be used as incentives.

[0065] In one possible approach, Figure 1E As shown, step S106 may include the following sub-steps:

[0066] Sub-step S1061: If the set threshold is not met, the trained causal model is used to predict the probability of the target object corresponding to the incentive data with different values ​​completing at least one order.

[0067] The causal model is trained based on the historical feedback data of the target object. The historical incentive feedback data includes but is not limited to the values ​​of the incentive data obtained historically by the target object and the corresponding number of completed orders. The causal model trained with the historical incentive feedback data can predict the probability of completing at least one order corresponding to different values ​​of the incentive data.

[0068] When in use, feature data is determined based on the historical behavior data of the target object, the number of orders and responses at the location of the target object, the predicted number of orders and responses within a set time period, and the values ​​of different incentive data, and the feature data is input into the causal model to obtain the probability of completing at least one order corresponding to the value of the incentive data output by the causal model. The probability of completing at least one order is used to indicate the probability of completing a shipping order within a set time period when the incentive data with the value is issued to the target object.

[0069] For example, if the value of the incentive data is M1, M2, M3, etc., the causal model can predict the probability of completing at least one order when the value of the incentive data is M1, M2, and M3, etc., and the value of the incentive data can be the incentive data corresponding to completing an order. In this way, corresponding incentive data can be provided for each single waybill, which can reduce the difficulty for the target object to obtain the incentive data, thereby increasing the probability of completing at least one order, and avoiding the problem that the existing incentive data acquisition conditions require the completion of multiple waybills, making the acquisition too difficult, and the target object will choose to give up, thereby failing to increase the probability of completing the order.

[0070] Sub-step S1062: Determine a target value of the incentive data according to incentive data with different values ​​and the corresponding probability of completing at least one order, and determine the incentive data of the target object according to the value.

[0071] Optimization is performed based on incentive data with different values ​​and their corresponding probabilities of completing at least one order to obtain a more optimal incentive data value corresponding to the target object.

[0072] Step S108: Generate an incentive publishing message according to the incentive data, and send the incentive publishing message to the corresponding target object.

[0073] In one feasible manner, an incentive release message can be generated according to a preset template and incentive data, and the incentive release message can be sent to a terminal device corresponding to the target object, so that the target object can be informed of the incentive message through the terminal device, so as to increase the probability of the target object completing at least one order within a set time period. The incentive data is the incentive that can be obtained by completing a single waybill. This can reduce the difficulty of obtaining the incentive, thereby increasing the enthusiasm of the target object, and can also achieve the splitting of the waybill task.

[0074] The causal model is used to predict the probability of completing at least one order when the target object obtains incentive data with different values, and the better value of the incentive data is optimized based on the prediction results. The incentive data can be accurately determined without causing excessive costs.

[0075] Through this embodiment, it is possible to determine whether the first service scope and / or the second service scope corresponding to the target object lacks transportation capacity. If there is a lack of transportation capacity, it is determined whether the probability of the target object completing at least one order within a set time period in the future does not meet the set threshold. If the set threshold is not met, the incentive data corresponding to the target object is determined, and an incentive release message is generated based on the incentive data, and then the incentive release message is sent to the target object so that it can be informed of the incentive release message, thereby increasing its probability of completing at least one order. In this way, when it is determined that there is a lack of transportation capacity, the target object whose probability of completing at least one order does not meet the set threshold can be screened out, and the probability of completing at least one order can be increased by sending an incentive release message to it. This not only increases the available transportation capacity, but also sends the incentive release message in a targeted manner, avoiding the high cost problem of indiscriminate allocation of incentives.

[0076] The capacity incentive method of this embodiment can be executed by any appropriate electronic device with capacity incentive capabilities, including but not limited to: servers, mobile terminals (such as mobile phones, PADs, etc.) and PCs, etc.

[0077] Embodiment 2

[0078] Reference Figure 2 , showing a schematic diagram of the step flow of the method of embodiment 2 of the present application.

[0079] The method comprises the following steps:

[0080] Step S202: Determine whether the first travel platform lacks transportation capacity within the third service scope.

[0081] The first travel platform is an aggregation platform that aggregates multiple second travel platforms. For example, the first travel platform may be an aggregation online car-hailing platform, and the second travel platform may be a platform that provides online car-hailing services. Passengers can place orders through the first travel platform, and the first travel platform can publish the order to one or more second travel platforms, so that the transport capacity providing travel services in each second travel platform can receive the order and provide services for the order.

[0082] The third service scope may be a pre-defined area, or may be a certain geographical object (such as a map station) as the center and a certain range around it, and there is no restriction on this.

[0083] Whether there is a lack of transport capacity within the third service scope can be determined based on the response rate and average response time within a period of time within the third service scope. The response rate can be the ratio of the number of orders issued within a period of time to the number of responses, and the average response time can be the sum of the waiting time of each responded order within the period of time divided by the number of responses.

[0084] If the response rate of the third service range is lower than a set threshold (which can be determined as needed), or the average response time is greater than or equal to a set time threshold (which can be determined as needed), it is determined that the third service range lacks capacity and step S204 is executed; otherwise, no action is taken.

[0085] Step S204: If it is determined that there is a lack of transportation capacity, the probability of the target object completing at least one order within a set time period is determined based on the historical behavior data and current status data of the target object within the third service scope in each of the second travel platforms.

[0086] When it is determined that there is a lack of capacity within the third service scope, in order to retain the capacity on the travel platform to provide services, target objects with a low probability of providing services (i.e., the probability of completing at least one order) within a future period of time (i.e., a set time period) can be determined for each second travel platform, and then these target objects can be incentivized so that they can actively provide services within the future period of time, thereby increasing available capacity.

[0087] The implementation method of determining the probability of the target object completing at least one order based on the historical behavior data and the current status data can be as described in the above-mentioned embodiment, so it is not repeated here.

[0088] If the probability of the target object completing at least one order does not meet the set threshold, it means that it may not provide services in a certain period of time in the future. In order to increase the available transportation capacity, step S206 can be executed to increase the probability of the target object providing services to increase the available transportation capacity.

[0089] If the probability of the target object completing at least one order meets the set threshold, it means that it may provide services in a certain period of time in the future, so no action can be taken for such a target.

[0090] The threshold value may be set as required, or PID adjustment may be performed based on the response rate, etc., and there is no limitation on this.

[0091] Step S206: If the probability of the target object completing at least one order does not meet the set threshold, the incentive data of the target object is determined, and an incentive message generated based on the incentive data is sent to the target object, so that the target object is retained within the third service scope as the corresponding second travel platform's capacity.

[0092] The method of determining the incentive data of the target object can be as described in the above embodiment, so it is not repeated here. Based on the incentive data, an incentive message can be generated and sent to the target object to encourage the target object to provide services within a set time period, thereby improving the transportation capacity of the second travel platform.

[0093] Through this method, when it is determined that there is a lack of transportation capacity, the target objects whose probability of completing at least one order does not meet the set threshold can be screened out, and their probability of completing at least one order can be increased by sending them incentive release messages. This not only increases the available transportation capacity, but also sends incentive release messages in a targeted manner, avoiding the high cost problem of indiscriminate allocation of incentives.

[0094] Embodiment 3

[0095] Reference Figure 3 , showing a step flow chart of the method of embodiment 3 of the present application.

[0096] In this embodiment, the method can be applied to a driver's client, which includes the following steps:

[0097] Step S302: receiving an incentive release message, wherein the incentive release message carries incentive data.

[0098] The excitation data is determined by the method of the aforementioned embodiment, so it will not be described in detail.

[0099] Step S304: displaying the incentive data carried in the incentive release message in a display interface, so that the target object is retained as transportation capacity within the corresponding service scope.

[0100] In order to enhance the perception of incentive release messages and not interfere with the normal driving of drivers, the incentive release messages are displayed to drivers through voice broadcasts on terminal devices, scrolling on the homepage, etc. The form of voice broadcasts is such as "Congratulations on winning an exclusive surprise reward. Please complete another order within xx:xx:00-xx:xx:00 to receive a reward of y yuan."

[0101] In this way, it is possible to dig out appropriate objects (i.e., target objects that may not be able to provide services) at appropriate times (i.e., areas and times where there is a lack of transportation capacity), and send them incentive data with appropriate values ​​to increase the amount of transportation capacity that can be provided. In this way, when the budget is limited, it is possible to avoid the waste caused by sending incentive data to all target objects. The value of the incentive data for the target object can be optimized with the set total incentive upper limit as a constraint to avoid extreme cases from becoming universal issuance. In addition, since the number of target objects to which incentive data is sent for retention is affected by the difference between supply and demand, the PID algorithm is used to adjust the size of the set threshold using the change in the difference between supply and demand to avoid the waste of supply exceeding demand caused by over-issuance of incentive data.

[0102] In order to ensure higher incentive efficiency, a causal model is used to predict the probability of a driver completing at least one order when incentive data with different values ​​are issued. Then, an optimization algorithm is used to ensure a higher incentive efficiency under a certain probability of completing at least one order, thereby achieving capacity adjustment in areas and time periods where there is a shortage of capacity, improving the response rate, and providing real-time incentives to drivers, which has a better incentive effect.

[0103] Embodiment 4

[0104] Reference Figure 4 , showing a schematic diagram of the step flow of the method of embodiment 4 of the present application.

[0105] The method can be applied to a data analysis platform, and the method includes:

[0106] Step S402: Determine whether the fourth service range lacks transportation capacity.

[0107] The fourth service scope may be any appropriate scope, such as the area where a certain designated geographical object is located, or an area defined by a user, etc., without limitation.

[0108] Based on the answer rate, average answer waiting time, etc. within the fourth service range, it can be determined whether there is a lack of transportation capacity within the fourth service range.

[0109] In the case of lack of transport capacity, step S404 may be performed to mine target objects with a low probability of providing services. If there is no lack of transport capacity, no action may be taken.

[0110] Step S404: If the fourth service range lacks transportation capacity, historical behavior data and current status data of the target object within the fourth service range are obtained.

[0111] The historical behavior data and the current status data may be the same or similar to the historical behavior data and the current status data in the aforementioned embodiment 1, so they will not be described in detail. For example, the historical behavior data may be the total number of completed orders of the target object, the historical daily resource information acquired by the target object, the offline time corresponding to the current time slice, etc. The current status data includes at least one of the following: the online time of the day, the resource information acquired by the target object on the day, the number of completed orders of the target object on the day, the idle time of the target object on the day and the current location, etc., but is not limited to this.

[0112] Step S406: Determine the probability of each target object completing at least one order within a set time period based on the historical behavior data and the current status data of each target object.

[0113] For example, in one feasible manner, the historical behavior data and the current state data may be spliced ​​as input features. Alternatively, the historical behavior data and the current state data may be processed in an appropriate manner, and the processing results may be spliced ​​as input features. The input features are input into a machine learning model for predicting the probability of completing at least one order, so as to obtain the probability of the target object completing at least one order within the set time period output by the machine learning model.

[0114] The probability of completing at least one order within a set time period represents the probability that the target object can provide services within a set time period in the future.

[0115] Step S408: Generate analysis results based on the probability of each target object completing at least one order and the location information of each target object. By analyzing the probability of a target object completing at least one order in the future, it is possible to effectively mine idle target objects with a low probability of providing services in the future. Then, combined with their location information, it is possible to analyze which locations have more idle target objects. Subsequently, the target objects can be scheduled as needed, and these analysis results can be used to balance resources, thereby improving efficiency and increasing the amount of transportation capacity, avoiding or reducing the problem of lack of transportation capacity.

[0116] Optionally, in a feasible manner, a display interface can be generated based on the analysis result, in which the target objects are distributed according to the location information, and the corresponding probability of completing at least one order is displayed. The probability can be visualized in any appropriate manner, such as directly displaying a numerical value, using a bar graph, using different colors, etc., without limitation. In this way, the display interface makes it possible to more intuitively observe the probability of completing at least one order corresponding to different target objects, thereby achieving a convenient viewing effect.

[0117] Embodiment 5

[0118] Reference Figure 5 , showing the structural block diagram of the capacity incentive device of Example 5 of the present application.

[0119] In this embodiment, the capacity incentive device includes:

[0120] A first determination module 502 is used to determine whether a first service range corresponding to a target object lacks transportation capacity, and / or to determine whether a second service range corresponding to the target object lacks transportation capacity within a set time period after a current moment;

[0121] The second determination module 504 is used to determine whether the probability of the target object completing at least one order within the set time period does not meet a set threshold based on the historical behavior data and current status data of the target object if it is determined that there is a lack of transportation capacity;

[0122] A third determination module 506, configured to determine the stimulus data corresponding to the target object if the set threshold is not met;

[0123] The sending module 508 is used to generate an incentive release message according to the incentive data, and send the incentive release message to the corresponding target object, so that the target object is retained as transportation capacity within the first service range or the second service range.

[0124] Optionally, the first determination module 502 is used to obtain a first response rate corresponding to the first service range in at least one previous time period before the current moment when determining whether the first service range corresponding to the target object lacks capacity, the first service range being an area range of N kilometers adjacent to the location of the target object, where N is a positive number; if the first response rate is less than a response threshold, it is determined that the first service range lacks capacity.

[0125] Optionally, the first determination module 502 is used to determine the second response rate of the second service scope in a historical time period corresponding to the set time period in a cycle before the set time period, and the third response rate of the second service scope in the current day when determining whether the second service scope corresponding to the target object lacks capacity within a set time period after the current moment; based on the second response rate and the third response rate, determine whether the second service scope lacks capacity in the subsequent set time period.

[0126] Optionally, the second determination module 504 is used to construct input features based on the historical behavior data and current status data of the target object if it is determined that there is a lack of transportation capacity; input the input features into a machine learning model for predicting the probability of completing at least one order to obtain the probability of the target object completing at least one order within the set time period output by the machine learning model; and determine whether the probability of completing at least one order does not meet the set threshold based on the probability of completing at least one order and the obtained set threshold.

[0127] Optionally, the device further includes: an adjustment module 510, configured to use a PID algorithm to determine, according to the real-time response rate of the second service range, whether to adjust the set threshold.

[0128] Optionally, the historical behavior data includes at least one of the following: the total number of completed orders of the target object, the historical daily resource acquisition information of the target object, and the offline time corresponding to the current time slice; and / or, the current status data includes at least one of the following: the online time on that day, the resource information acquired by the target object on that day, the number of completed orders of the target object on that day, the idle time of the target object on that day and the current location.

[0129] Optionally, the third determination module 506 is used to use a trained causal model to predict the probability of a target object corresponding to incentive data with different values ​​completing at least one order if the set threshold is not met, and the causal model is trained based on historical record feedback data of the target object; determine the target value of the incentive data based on the incentive data with different values ​​and the corresponding probability of completing at least one order, and determine the incentive data of the target object based on the value.

[0130] The capacity incentive device of this embodiment is used to implement the corresponding capacity incentive methods in the aforementioned multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here. In addition, the functional implementation of each module in the capacity incentive device of this embodiment can refer to the description of the corresponding parts in the aforementioned method embodiments, which will not be repeated here.

[0131] Embodiment 6

[0132] Reference Figure 6 , shows a structural block diagram of the device of embodiment 6 of the present application.

[0133] The device includes:

[0134] A fourth determination module 602 is used to determine whether the first travel platform lacks transportation capacity within the third service range, wherein the first travel platform is an aggregation platform that aggregates multiple second travel platforms;

[0135] A fifth determination module 604 is configured to determine, if it is determined that there is a lack of transport capacity, a probability that the target object completes at least one order within a set time period based on the historical behavior data and current status data of the target object within the third service range in each of the second travel platforms;

[0136] The sixth determination module 606 is used to determine the incentive data of the target object if the probability of the target object completing at least one order does not meet the set threshold, and send an incentive message generated based on the incentive data to the target object, so that the target object is retained within the third service scope as the corresponding second travel platform's transportation capacity.

[0137] The capacity incentive device of this embodiment is used to implement the corresponding capacity incentive methods in the aforementioned multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0138] Embodiment 7

[0139] Reference Figure 7 , shows a structural block diagram of the device of embodiment 7 of the present application.

[0140] The device includes:

[0141] A receiving module 702 is used to receive an incentive release message, wherein the incentive release message carries incentive data, and the incentive data is determined according to the above-mentioned device;

[0142] The display module 704 is used to display the incentive data carried in the incentive release message in a display interface, so that the target object is retained as transportation capacity within the corresponding service scope.

[0143] The device of this embodiment is used to implement the corresponding methods in the aforementioned multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be described in detail here.

[0144] Embodiment 8

[0145] Reference Figure 8 , shows a structural block diagram of the device of Example 8 of the present application.

[0146] The device includes:

[0147] A seventh determination module 802 is used to determine whether the fourth service range lacks transportation capacity;

[0148] An acquisition module 804 is configured to acquire historical behavior data and current status data of a target object within the fourth service range if the fourth service range lacks transportation capacity;

[0149] An eighth determination module 806, configured to determine the probability of each of the target objects completing at least one order within a set time period according to the historical behavior data and the current state data of each of the target objects;

[0150] The generating module 808 is used to generate an analysis result according to the probability of each target object completing at least one order and the location information of each target object.

[0151] The device of this embodiment is used to implement the corresponding methods in the aforementioned multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be described in detail here.

[0152] Embodiment 9

[0153] Reference Fig. 9 , shows a schematic diagram of the structure of an electronic device according to Embodiment 9 of the present application. The specific embodiments of the present application do not limit the specific implementation of the electronic device.

[0154] like Fig. 9 As shown, the electronic device may include: a processor (processor) 902 , a communication interface (Communications Interface) 904 , a memory (memory) 906 , and a communication bus 908 .

[0155] in:

[0156] The processor 902 , the communication interface 904 , and the memory 906 communicate with each other via a communication bus 908 .

[0157] The communication interface 904 is used to communicate with other electronic devices or servers.

[0158] The processor 902 is used to execute the program 910, and specifically can execute the relevant steps in the above method embodiment.

[0159] Specifically, the program 910 may include program codes, which include computer operation instructions.

[0160] The processor 902 may be a processor CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0161] The memory 906 is used to store the program 910. The memory 906 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0162] The program 910 can be specifically used to enable the processor 902 to perform operations corresponding to the aforementioned method.

[0163] The specific implementation of each step in program 910 can refer to the corresponding description of the corresponding steps and units in the above method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above method embodiment, which will not be repeated here.

[0164] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0165] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the method shown here.

[0166] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.

[0167] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.

Claims

1. A capacity incentive method, comprising: Determine whether a first service range corresponding to the target object lacks transportation capacity, and / or determine whether a second service range corresponding to the target object lacks transportation capacity within a first set time period after the current moment; If it is determined that there is a lack of transportation capacity, determining whether the probability of the target object completing at least one order within the second set time period does not meet a set threshold based on the historical behavior data and current status data of the target object; If the set threshold is not met, determining the incentive data corresponding to the target object; An incentive release message is generated according to the incentive data, and the incentive release message is sent to the corresponding target object, so that the target object is retained as transportation capacity within the first service scope or the second service scope.

2. The method according to claim 1, wherein: The determining whether the first service range corresponding to the target object lacks transportation capacity includes: Obtaining a first response rate corresponding to the first service range in at least one previous time period before the current moment, where the first service range is an area of ​​N kilometers adjacent to the location of the target object, where N is a positive number; If the first response rate is less than a response threshold, it is determined that the first service range lacks transportation capacity.

3. The method according to claim 1, wherein: The determining whether the second service range corresponding to the target object lacks transportation capacity within a first set time period after the current moment includes: Determine a second response rate of the second service range in a historical time period corresponding to the first set time period in a cycle before the first set time period, and a third response rate of the second service range in the current day; It is determined whether the second service range lacks transportation capacity within a subsequent first set time period according to the second response rate and the third response rate.

4. The method according to claim 1, wherein: If it is determined that there is a lack of transportation capacity, determining whether the probability of the target object completing at least one order within the second set time period does not meet a set threshold based on the historical behavior data and current status data of the target object includes: If it is determined that there is a lack of transport capacity, constructing input features based on the historical behavior data and current state data of the target object; Inputting the input features into a machine learning model for predicting the probability of completing at least one order, so as to obtain the probability of the target object completing at least one order within the second set time period output by the machine learning model; According to the probability of completing at least one order and the obtained set threshold, it is determined whether the probability of completing at least one order does not meet the set threshold.

5. The method according to claim 4, wherein: The method further comprises: The set threshold is adjusted using a PID algorithm according to the real-time response rate of the second service range.

6. The method according to claim 4, wherein: The historical behavior data includes at least one of the following: the total number of completed orders of the target object, the historical daily resource acquisition information of the target object, and the offline time corresponding to the current time slice; and / or, the current status data includes at least one of the following: the online time on that day, the resource information acquired by the target object on that day, the number of completed orders of the target object on that day, the idle time of the target object on that day and the current location.

7. The method according to claim 1, wherein: If the set threshold is not met, determining the incentive data corresponding to the target object includes: If the set threshold is not met, a trained causal model is used to predict the probability of the target object corresponding to the incentive data with different values ​​completing at least one order, wherein the causal model is trained based on the historical record feedback data of the target object; According to the incentive data with different values ​​and the corresponding probability of completing at least one order, a target value of the incentive data is determined, and the incentive data of the target object is determined according to the value.

8. A capacity incentive method, comprising: Determining whether a first travel platform lacks transportation capacity within a third service scope, where the first travel platform is an aggregation platform that aggregates multiple second travel platforms; If it is determined that there is a lack of transport capacity, determining the probability that the target object completes at least one order within a set time period based on the historical behavior data and current status data of the target object within the third service scope in each of the second travel platforms; If the probability of the target object completing at least one order does not meet the set threshold, the incentive data of the target object is determined, and an incentive message generated based on the incentive data is sent to the target object, so that the target object is retained within the third service scope as the corresponding second travel platform's transportation capacity.

9. A capacity incentive method, comprising: Receiving an incentive release message, wherein the incentive release message carries incentive data, and the incentive data is determined according to the method according to any one of claims 1 to 7 or the method according to claim 8; The incentive data carried in the incentive release message is displayed in a display interface so that the target object is retained as transportation capacity within the corresponding service scope.

10. A data processing method, comprising: Determine whether there is a lack of capacity in the fourth service area; If the fourth service scope lacks transportation capacity, obtaining historical behavior data and current status data of the target object within the fourth service scope; Determining the probability of each of the target objects completing at least one order within a set time period based on the historical behavior data and the current status data of each of the target objects; An analysis result is generated according to the probability of completing at least one order of each target object and the location information of each target object.

11. An electronic device, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the method according to any one of claims 1 to 7, or an operation corresponding to the method according to claim 8, or an operation corresponding to the method according to claim 9, or an operation corresponding to the method according to claim 10.

12. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 7, or the method according to claim 8, or the method according to claim 9, or the method according to claim 10 is implemented.

13. A computer program product, comprising computer instructions, wherein the computer instructions instruct a computing device to perform operations corresponding to the method of any one of claims 1 to 7, or operations corresponding to the method of claim 8, or operations corresponding to the method of claim 9, or operations corresponding to the method of claim 10.

Images