Task issuing method and device for dormant driver, electronic equipment and medium

Abstract

The invention provides a task issuing method and device for dormant drivers, electronic equipment and a medium, and the method comprises the steps: predicting the pairing probability of each dormant driver under different reward amounts through employing a trained pairing probability prediction model; obtaining a task reward amount of each dormant driver according to the pairing probability of each dormant driver under different reward amounts, the subsidy cost corresponding to different reward amounts and the subsidy budget; and according to the task reward amount of each dormant driver and a preset task threshold, obtaining the task of each dormant driver and issuing the task. According to the method, the pairing probability of the dormant drivers under different reward amounts is predicted through an algorithm model, the task reward amount of each dormant driver is calculated based on the pairing probability, and an appropriate task is provided for each dormant driver through reward differentiation and task differentiation, so that the task reward amount of each dormant driver is calculated under the effective subsidy budget. And the active degree of the dormant driver is improved as much as possible, so that the optimal task incentive effect is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of online car-hailing, and in particular to a method and device for issuing tasks to dormant drivers, electronic equipment, and media. Background Art

[0002] In the era of mobile Internet, modern travel for users has changed the traditional way of taking taxis. By utilizing the characteristics of mobile Internet and integrating online and offline, the traditional way of drivers waiting for passengers has been changed. Drivers can accept orders based on the passengers' wishes according to their destinations, saving the communication costs between drivers and passengers, reducing the empty driving rate, and maximizing the savings of resources and time for both drivers and passengers.

[0003] In the prior art, platforms often use incentives to increase drivers' enthusiasm for accepting orders. These incentives generally include the following: First, rewards for completing orders, that is, after completing an order, the driver will be given a corresponding reward based on the route and time of the order; second, when a passenger sends an order request, the platform adds reward information to the order request according to certain rules, and then pushes the order request and reward information to the driver's client. These solutions generally only promote active drivers and do not affect inactive drivers. Summary of the invention

[0004] In view of the above defects in the prior art, the present invention provides a method and device for issuing tasks to dormant drivers, an electronic device, and a medium to solve the technical problem of being unable to motivate inactive drivers.

[0005] To achieve the above-mentioned purpose and other related purposes, the present invention provides a method for publishing tasks for dormant drivers, comprising: using a trained pairing probability prediction model to predict the pairing probability of each of the dormant drivers under different reward amounts; obtaining the task reward amount of each of the dormant drivers according to the pairing probability of each of the dormant drivers under different reward amounts, the subsidy cost corresponding to the different reward amounts, and the subsidy budget; obtaining and publishing the task of each of the dormant drivers according to the task reward amount of each of the dormant drivers and a preset task threshold.

[0006] In one embodiment of the present invention, the pairing probability prediction model is a tree model, and the model input features include the characteristics of the dormant driver and the reward amount. The characteristics of the dormant driver include the attribute information of the dormant driver, historical order information, and tracking point information.

[0007] In one embodiment of the present invention, the task reward amount of each dormant driver is obtained according to the pairing probability of each dormant driver under different reward amounts, the subsidy cost corresponding to different reward amounts, and the subsidy budget, including: obtaining the input parameters of the optimization problem according to the pairing probability of each dormant driver under different reward amounts and the subsidy cost corresponding to different reward amounts; obtaining the constraints of the optimization problem according to the subsidy budget and the fact that each dormant driver has only one reward amount; constructing and solving the optimization problem according to the input parameters and constraints of the optimization problem and taking maximizing the number of dormant driver pairings as the objective function to obtain the Boolean variables of each dormant driver under different reward amounts; obtaining the task reward amount of each dormant driver according to the Boolean variables of each dormant driver under different reward amounts.

[0008] In one embodiment of the present invention, after the step of using the trained pairing probability prediction model to predict the pairing probability of each dormant driver under different reward amounts, the step also includes: classifying all dormant drivers to obtain several categories of dormant drivers; according to the subsidy budget, each dormant driver has only one reward amount, and obtaining the constraints of the optimization problem, including: according to the subsidy budget, each dormant driver has only one reward amount, and the reward amounts of dormant drivers belonging to the same category are the same, to obtain the constraints of the optimization problem.

[0009] In one embodiment of the present invention, all dormant drivers are classified to obtain several categories of dormant drivers, including: obtaining the natural matching rate of dormant drivers according to the matching probability of dormant drivers when the reward amount is 0; obtaining the matching elasticity of dormant drivers according to the matching probability of dormant drivers under different reward amounts; and classifying all dormant drivers according to the vehicle type of dormant drivers, the natural matching rate, and the matching elasticity to obtain several categories of dormant drivers.

[0010] In one embodiment of the present invention, all dormant drivers are classified according to the vehicle type of the dormant drivers, the natural matching rate, and the matching elasticity to obtain several types of dormant drivers, including: grid division is performed according to the vehicle type of all dormant drivers, the natural matching rate, and the matching elasticity to obtain multiple grids; each of the dormant drivers is classified into a corresponding grid, and dormant drivers belonging to the same grid are regarded as the same type of dormant drivers.

[0011] In one embodiment of the present invention, the task of each dormant driver is obtained and published according to the task reward amount of each dormant driver and the preset task threshold, including: obtaining the threshold and reward amount of the first-level subtask according to the task reward amount of each dormant driver and the preset task threshold; obtaining the reward amount of the subsequent subtask according to the parent task reward amount and the reward amount of the first-level subtask, and obtaining the threshold of the subsequent subtask according to the preset subsequent task threshold; obtaining the parent task of each dormant driver according to the threshold and reward amount of the first-level subtask, the threshold and reward amount of the subsequent subtask, and publishing it.

[0012] In one embodiment of the present invention, the subsequent subtasks only include second-level subtasks; the reward amount of the subsequent subtask is obtained based on the reward amount of the parent task and the reward amount of the first-level subtask, and the threshold of the subsequent subtask is obtained based on the preset subsequent task threshold, including: obtaining the reward amount of the second-level subtask based on the reward amount of the parent task and the reward amount of the first-level subtask; obtaining the threshold of the second-level subtask based on the historical average daily pairing number of dormant drivers.

[0013] In one embodiment of the present invention, the reward amount of the second-level sub-task is obtained according to the reward amount of the parent task and the reward amount of the first-level sub-task, including: obtaining the reward amount of the second-level sub-task according to the reward amount of the parent task, the reward amount of the first-level sub-task, whether there is a task dispatch record for the dormant driver at the preset time, whether there is a receipt record for the dormant driver at the preset time, and a preset random increase amount.

[0014] To achieve the above-mentioned purpose and other related purposes, the present invention also provides a task publishing device for dormant drivers, comprising: a first calculation unit, used to predict the pairing probability of each of the dormant drivers under different reward amounts using a trained pairing probability prediction model; a second calculation unit, used to obtain the task reward amount of each of the dormant drivers according to the pairing probability of each of the dormant drivers under different reward amounts, the subsidy cost corresponding to the different reward amounts, and the subsidy budget; a task processing unit, used to obtain and publish the task of each of the dormant drivers according to the task reward amount of each of the dormant drivers and a preset task threshold.

[0015] To achieve the above-mentioned purpose and other related purposes, the present invention also provides an electronic device, including a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement a method provided in any one of the above embodiments.

[0016] To achieve the above-mentioned object and other related objects, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is used to enable a computer to execute the method provided in any one of the above-mentioned embodiments.

[0017] Beneficial effects of the present invention: The present invention proposes a method and device for issuing tasks for dormant drivers, an electronic device, and a medium. The method predicts the pairing probability of dormant drivers under different reward amounts through an algorithm model, and calculates the task reward amount of each dormant driver based on the pairing probability. Through reward differentiation and task differentiation, a suitable task is provided for each dormant driver, thereby increasing the activity level of dormant drivers as much as possible under an effective subsidy budget, thereby achieving the best task incentive effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention 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 of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flowchart of a first task publishing method provided by an embodiment of the present invention;

[0020] Figure 2 A flowchart of calculating the bonus amount for dormant drivers provided by one embodiment of the present invention;

[0021] Figure 3 A flowchart of a second task publishing method provided by an embodiment of the present invention;

[0022] Figure 4 A flowchart of dormant driver classification provided by an embodiment of the present invention;

[0023] Figure 5 A grid method classification flow chart provided for an embodiment of the present invention;

[0024] Figure 6 A multi-layer task configuration flow chart provided for an embodiment of the present invention;

[0025] Figure 7 A flowchart of the second layer subtask configuration provided by an embodiment of the present invention;

[0026] Figure 8 A flowchart for obtaining the threshold and reward amount of the first-level subtask provided by an embodiment of the present invention;

[0027] Fig. 9A flowchart for obtaining the threshold and reward amount of the second-level subtask provided by an embodiment of the present invention;

[0028] Fig.10 A schematic diagram of a task issuing device provided by an embodiment of the present invention;

[0029] Fig.11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0030] Explanation of the reference numerals: 101, first computing unit; 102, second computing unit; 103, task processing unit; 201, processor; 202, memory. DETAILED DESCRIPTION

[0031] The following describes the embodiments of the present invention through specific specific embodiments, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. It should be noted that the following embodiments and the features in the embodiments can be combined with each other without conflict. In addition to the specific methods, equipment, and materials used in the embodiments, according to the technical personnel in this technical field's grasp of the prior art and the records of the present invention, any methods, equipment, and materials of the prior art that are similar or equivalent to the methods, equipment, and materials described in the embodiments of the present invention can also be used to implement the present invention.

[0032] It should be understood that the terms used in the embodiments of the present invention are for describing specific embodiments rather than for limiting the scope of protection of the present invention. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those generally understood by those skilled in the art.

[0033] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In some of the embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0034] The flowchart and block diagram in the accompanying drawings illustrate the system architecture, functions and operations that may be implemented according to the methods and computer program products of various embodiments disclosed in the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, the program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0035] See also Figure 1 , Figure 1 A method for issuing tasks for a dormant driver provided in one embodiment of the present invention includes step S100, step S300 and step S400.

[0036] Step S100, using the trained pairing probability prediction model, predict the pairing probability of each dormant driver under different reward amounts. In this step, the pairing probability is predicted by the trained model. In the subsequent steps, the appropriate task reward amount is calculated for each dormant driver based on the pairing probability of each dormant driver under different reward amounts. Dormant drivers generally refer to drivers who have not accepted orders for more than a certain number of days. The certain number of days can be set according to the actual situation, for example, it can be 10 days, 20 days, 30 days, etc.

[0037] In a specific embodiment of the present invention, the pairing probability prediction model is a tree model. The tree model is a machine learning model with a tree branching structure based on feature space division, which is used for classification and regression tasks. In this embodiment, it is necessary to predict the pairing probability, and the tree model is very suitable. The model input features include the characteristics of the dormant driver and the reward amount. The trained pairing probability prediction model makes decisions on the characteristics of the dormant driver and the reward amount, and finally obtains the pairing probability. In this embodiment, the characteristics of the dormant driver include the attribute information of the dormant driver, the historical order information and the buried point information. Among them, the attribute information of the dormant driver can be, for example, the driver's registered city, the driver's gender, etc.; the historical order information can be, for example, the number of orders received within a certain number of days, and this certain number of days must be longer than the defined number of days for the dormant driver, otherwise the number of orders received is 0 and meaningless; the buried point information can be, for example, the number of orders grabbed by the dormant driver, etc. The label of the model can be, for example, whether the dormant driver is paired on the effective date of the task.

[0038] In the specific implementation, the pairing probability prediction model is first initialized, and then the pairing probability prediction model is trained according to the historical dormant driver task data to obtain a trained pairing probability prediction model. The model only needs to be trained once. Then, the characteristics of each dormant driver and a certain reward amount are input into the trained pairing probability prediction model, and the pairing probability of the dormant driver under the reward amount can be obtained. It should be noted that the pairing probability prediction model can only predict the pairing probability of a dormant driver under a certain reward amount at a time. If you want to obtain the pairing probability of each dormant driver under different reward amounts, multiple predictions are required. Assuming there are N drivers and the reward amount has M levels, for example, the reward amount is 0, 1, 2, ..., M-1 yuan, then after performing N×M predictions in step S100, N×M pairing probabilities can be obtained. The pairing probability of driver i under reward amount j can be recorded as P ij , where i=1,2,…,N and j=0,1,2,…,M-1.

[0039] It should be noted that the reward amounts do not necessarily have to be continuous or at equal intervals. The reward amounts can also be 0, 5, 10, 15 yuan, or 0, 1, 5, 10 yuan. The specific reward amounts can be set according to the actual activity circumstances.

[0040] Step S300: According to the matching probability of each dormant driver under different reward amounts, the subsidy cost corresponding to different reward amounts, and the subsidy budget, the task reward amount of each dormant driver is obtained. In this step, the specific amount of the subsidy cost corresponding to different reward amounts has nothing to do with the driver, and is generally only related to the reward amount. For a certain taxi-hailing platform, it is a known value and can be recorded as w j The subsidy budget corresponds to the total amount of the proposed reward, which can be recorded as C. This step is based on p ij 、w j And C assigns different task reward amounts to each dormant driver to achieve the best incentive effect.

[0041] See also Figure 2 In a specific embodiment of the present invention, step S300 includes steps S301 to S304.

[0042] Step S301: According to the pairing probability of each dormant driver under different reward amounts and the subsidy cost corresponding to different reward amounts, the input parameters of the optimization problem are obtained. ij 、w j As input parameters of the optimization problem, they are all known quantities.

[0043] Step S302: According to the subsidy budget, each dormant driver has only one reward amount, and the constraints of the optimization problem are obtained. In order to better define the optimization problem and solve it, the decision variables of the optimization problem can be defined as: the task reward amount of driver i is a Boolean variable j, denoted as x ij , where x ij Either 0 or 1, this is what the optimization problem needs to solve. With the definition of decision variables, these two constraints can be expressed by mathematical formulas. The sum of subsidies for all dormant drivers must be less than or equal to the subsidy budget, that is, ∑ ij (P ij *x ij *w j )≤C, each dormant driver has only one reward amount, that is, ∑ j x ij =1.

[0044] Step S303: Based on the input parameters and constraints of the optimization problem, the optimization problem is constructed and solved with the objective function of maximizing the number of dormant driver pairings, and the Boolean variables of each dormant driver under different reward amounts are obtained. The objective function is to maximize the number of paired drivers, which is expressed in mathematical language as maximizing the sum of the pairing probabilities of the drivers, which can be expressed as: max[∑ ij (P ij *x ij )]. For any dormant driver, after solving the optimization problem, M Boolean variables can be obtained, and only one Boolean variable corresponding to the reward amount is 1, and the Boolean variables corresponding to the rest of the reward amounts are 0. For example, for the first dormant driver, the solution of the decision variable is: x 10 =0,x 11 =0,x 12 =1,x 13 =0, ... The result is the Boolean variable of the first dormant driver under different reward amounts.

[0045] Step S304: Obtain the task reward amount for each dormant driver based on the Boolean variables of each dormant driver under different reward amounts. 12 is 1, and the others are 0, indicating that the task reward amount of the first dormant driver corresponds to the third-tier reward, for example, 2 yuan.

[0046] See also Figure 3In a specific embodiment of the present invention, in the above steps S301 to S304, when the optimization problem is defined and solved, it is necessary to solve the Boolean variables of each dormant driver under different reward amounts, that is, it is necessary to solve N×M decision variables. A large number of decision variables will affect the speed of solving. In this embodiment, in order to speed up the solution, step S100 also includes step S200: classify all dormant drivers to obtain several categories of dormant drivers; and when constructing constraints, let the reward amount of dormant drivers belonging to the same category be the same. For example, there are 10,000 dormant drivers and 5 types of reward amounts. Through classification, the 10,000 dormant drivers are divided into 48 categories, so the decision variables change from the initial 10,000×5 to 48×5, which greatly reduces the amount of calculation.

[0047] See also Figure 4 In a specific embodiment of the present invention, step S200 includes steps S210 to S230.

[0048] Step S210: Obtain the natural matching rate of the dormant driver based on the matching probability of the dormant driver when the reward amount is 0. According to the matching probability of each dormant driver at different reward amounts predicted in step S100, find the matching probability when the reward amount is 0, and then obtain the natural matching rate of each dormant driver. The natural matching rate reflects the matching probability of the dormant driver when there is no reward, which can be used as a consideration for classifying dormant drivers.

[0049] Step S220, according to the pairing probability of dormant drivers under different reward amounts, obtain the pairing elasticity of dormant drivers. Pairing elasticity indicates the sensitivity of the pairing probability to changes in the reward amount. According to the pairing probability of dormant drivers under different reward amounts, several points in a two-dimensional plane can be obtained. In the two-dimensional plane, the X-axis represents the reward amount and the Y-axis represents the pairing probability. Then, according to these data points, the pairing elasticity is calculated using the least squares method. If the pairing elasticity is greater than 1, it means that the pairing probability is very sensitive to changes in the reward amount, that is, a small increase in the reward amount will lead to a significant increase in the pairing probability; if the pairing elasticity is less than 1, it means that the pairing probability is not very sensitive to changes in the reward amount, that is, the increase in the reward amount has little effect on the pairing probability; if the pairing elasticity is close to 0, it means that the pairing probability is almost unaffected by the reward amount. Pairing elasticity can also be used as a consideration for classifying dormant drivers.

[0050] Step S230, classify all dormant drivers according to their vehicle types, natural matching rates, and matching elasticity, and obtain several types of dormant drivers. The vehicle types of dormant drivers may be, for example, economy type, ordinary type, luxury type, or other vehicle types. In this step, the dormant drivers may be conveniently classified (also referred to as grouping) based on vehicle types, natural matching rates, and matching elasticity. In addition, other classification considerations may also be added.

[0051] See also Figure 5 In a specific embodiment of the present invention, step S230 includes: S231, gridding according to the vehicle type, natural matching rate, and matching elasticity of all dormant drivers to obtain multiple grids; S232, each dormant driver is classified into a corresponding grid, and dormant drivers belonging to the same grid are regarded as the same type of dormant drivers. Different dormant drivers have different sensitivities to the reward amount, so a reward amount can be set for each dormant driver, but in fact, the number of dormant drivers is very large, and many groups of drivers are similar. By gridding dormant drivers according to characteristics such as vehicle type, natural matching rate, and matching elasticity, the dormant driver group can be divided into subsets with similar characteristics. The purpose of this is to make the driver's behavior and response to the reward more consistent in each subset, so that the solution to the optimization problem is more effective and accurate.

[0052] For example, in a specific embodiment of the present invention, the natural matching rate and matching elasticity are divided into 4 buckets (bucketing is a method of data binning or segmentation, which is a common data preprocessing technology for dividing the values ​​of continuous variables into a finite number of discrete intervals or "buckets". The purpose of this is to simplify the complexity of the model and improve the interpretability of the model), and taking the above-mentioned economy, ordinary, and luxury models as examples, all dormant drivers can be divided into 3×4×4 types, a total of 48 combinations (or categories).

[0053] Step S400: Obtain and publish the task of each dormant driver according to the task reward amount of each dormant driver and the preset task threshold. The preset task threshold can be, for example, completing a certain number of orders, that is, the number of completed orders is greater than or equal to a set value, or it can be a certain number of grabbed orders. For dormant drivers, the preset task threshold can be set to, for example, the number of completed orders is equal to 1, or the number of completed orders is equal to 2, or the number of grabbed orders is equal to 10, etc., which can be set according to actual conditions.

[0054] The reward amount for each dormant driver in step S300 is generally the average reward amount per order, for example, the average reward amount per completed order or the average reward amount per grabbed order. Since the above optimization problem is mainly solved for each order, the task reward amount in step S300 can be the average reward amount per order multiplied by the number of orders.

[0055] Assuming that the task threshold of a dormant driver is: the number of completed orders is 1, and the task reward amount is: 10 yuan, then a task can be issued to the dormant driver: 10 yuan reward for completing 1 order. After the above steps, the task reward amount of each driver (each type of driver) is customized, so the task issuance effect is more reasonable and efficient.

[0056] When issuing tasks, a single task reward may not be able to attract the interest of dormant drivers, or dormant drivers continue to dormant only for the reward of completing the task. In this case, a more complex task system can be introduced. For example, a ladder task can be used. The main form of a ladder task is: the outer layer is the parent task, and the inner layer is composed of multiple subtasks. The subtasks need to set thresholds and reward amounts respectively. There is a sequence between subtasks. After completing the previous subtask, you can enter the next subtask. The reward amounts between subtasks are issued independently. This will achieve a better incentive effect.

[0057] See also Figure 6 In a specific embodiment of the present invention, step S400 includes steps S410 to S430.

[0058] Step S410: According to the task reward amount of each dormant driver and the preset task threshold, the threshold and reward amount of the first-level subtask are obtained. The reward amount of the first-level subtask is calculated through the previous steps.

[0059] Step S420: According to the parent task reward amount and the first-level subtask reward amount, the subsequent subtask reward amount is obtained, and according to the preset subsequent task threshold, the subsequent subtask threshold is obtained. The subsequent subtask can have multiple layers and be set as needed. The reward amount of the subsequent subtask can be a fixed value, or an overall parent task reward amount can be preset for each dormant driver, and then the reward amount of the subsequent subtask is calculated based on the parent task reward amount and the first-level subtask reward amount.

[0060] See also Figure 7 In a specific embodiment of the present invention, the subsequent subtasks only include the second-level subtasks; in this case, step S420 may include: S421, obtaining the reward amount of the second-level subtask according to the reward amount of the parent task and the reward amount of the first-level subtask; S422, obtaining the threshold of the second-level subtask according to the historical average daily matching number of dormant drivers. For example, the reward amount of the second-level subtask may be directly equal to the reward amount of the parent task minus the reward amount of the first-level subtask, and the threshold of the second-level subtask is equal to the historical average daily matching number of dormant drivers plus 1.

[0061] In a specific embodiment of the present invention, step S421 includes: obtaining the reward amount of the second-level sub-task based on the reward amount of the parent task, the reward amount of the first-level sub-task, whether the dormant driver has a task dispatch record at the preset time, whether the dormant driver has a receipt record at the preset time, and a preset random increase amount.

[0062] For example, the reward amount of the parent task minus the reward amount of the first-level subtask can be used as the default value of the reward amount of the second-level subtask.

[0063] If the dormant driver has no dispatch record on T-1 (the day before the task is released) (the task has not been dispatched to the dormant driver), then when the task is released on T, the actual payment value of the second-level subtask reward amount will be equal to the default value of the second-level subtask reward amount.

[0064] If the dormant driver has a distribution record on T-1 day, but no collection record, it means that the dormant driver has seen the task but has not received it. In this case, the reward amount can be increased, and the actual distribution value of the second-level subtask reward amount is equal to the default value of the second-level subtask reward amount plus a to b yuan (0 < a < b). This can further increase the enthusiasm of dormant drivers to receive tasks.

[0065] It can be understood that in addition to the reward amount of the second-level sub-tasks being adjustable according to certain rules, the reward amount of the first-level sub-tasks can also be fine-tuned according to certain rules, and the threshold of the sub-tasks can also be fine-tuned according to certain rules to increase the enthusiasm of dormant drivers to claim task rewards.

[0066] Step S430: According to the threshold and reward amount of the first-level subtasks, the threshold and reward amount of the subsequent subtasks, the parent task of each dormant driver is obtained and published. The threshold and reward amount of all subtasks are combined to obtain the parent task.

[0067] It should be noted that when there are subsequent subtasks, the reward amount of the first-level subtask is calculated based on the proportion when calculating the optimization problem. Assuming that the total subsidy budget is C, and the reward amount of the first-level subtask accounts for 70% of the total subsidy budget, then the formula ∑ ij (P ij *x ij *w j )≤C should be adjusted to ∑ ij (P oj *x ij *w j )≤0.7C. In addition, when fine-tuning the reward amount of a subtask, the fine-tuning amount also needs to be considered to avoid exceeding the total budget.

[0068] It should be noted that the steps of the above methods are divided only for the purpose of clear description. When implementing, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they contain the same logical relationship, they are all within the protection scope of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but not changing the core design of the algorithm and process, are all within the protection scope of this patent. For example, Figure 8 It shows a flowchart of obtaining the threshold and reward amount of the first-level subtask in another execution order. Fig. 9 It shows a flowchart of obtaining the threshold and reward amount of the second-level subtask in another execution order.

[0069] See also Fig.10 , Fig.10 A task publishing device for dormant drivers provided in one embodiment of the present invention includes a first calculation unit 101, a second calculation unit 102, and a task processing unit 103. The first calculation unit 101 is used to predict the pairing probability of each dormant driver under different reward amounts using a trained pairing probability prediction model; the second calculation unit 102 is used to obtain the task reward amount of each dormant driver according to the pairing probability of each dormant driver under different reward amounts, the subsidy cost corresponding to different reward amounts, and the subsidy budget; the task processing unit 103 is used to obtain and publish the task of each dormant driver according to the task reward amount of each dormant driver and a preset task threshold.

[0070] It should be noted that the above-mentioned functional modules can be fully or partially integrated into one physical entity during actual implementation, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, some or all of the steps of the above method, or the above functional modules can be completed by hardware integrated logic circuits in the processor element or instructions in software form.

[0071] It should be noted that the task issuing device of this embodiment is a device corresponding to the above-mentioned task issuing method, and the functional modules in the task issuing device may correspond to the corresponding steps in the task issuing method. The task issuing device of this embodiment can be implemented in conjunction with the task issuing method, that is, in the absence of conflict, the relevant technical details mentioned in the task issuing method of the above-mentioned embodiment can also be applied to the task issuing device of this embodiment.

[0072] See also Fig.11 , Fig.11 An electronic device provided for one embodiment of the present invention includes a processor 201, a memory 202 and a communication bus; the communication bus is used to connect the processor 201 and the memory 202; the processor 201 is used to execute a computer program stored in the memory 202 to implement the above-mentioned dormant driver task publishing method.

[0073] The above-mentioned processor can be, for example, a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components; the above-mentioned memory may include random access memory (RAM), and may also include non-volatile memory (Non-volatile Memory), such as at least one disk storage.

[0074] The above-mentioned electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0075] The electronic device mentioned above can be any electronic product that can perform human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0076] The electronic device may also include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0077] The network where the above electronic devices are located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

[0078] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. The computer program is used to enable a computer to execute the above-mentioned dormant driver task issuance method.

[0079] In general, the present invention utilizes algorithmic capabilities to identify the willingness of dormant drivers to accept orders, generates personalized driver tasks, and maximizes the number of recalled dormant drivers; and utilizes algorithmic capabilities to control and predict budgets to prevent events such as over-budgeting, thereby improving controllability and stability; and also utilizes algorithmic capabilities to automatically publish tasks based on online traffic, thereby reducing labor costs.

[0080] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for issuing tasks to dormant drivers, characterized in that: include: Using the trained pairing probability prediction model, predict the pairing probability of each dormant driver under different reward amounts; Obtaining a task reward amount for each dormant driver based on the pairing probability of each dormant driver under different reward amounts, the subsidy cost corresponding to the different reward amounts, and the subsidy budget; According to the task reward amount of each dormant driver and the preset task threshold, the task of each dormant driver is obtained and published.

2. The method for issuing tasks to dormant drivers according to claim 1, characterized in that: The pairing probability prediction model is a tree model, and the model input features include the characteristics of the dormant driver and the reward amount. The characteristics of the dormant driver include the dormant driver's attribute information, historical order information and tracking point information.

3. The task issuing method for dormant drivers according to claim 1, characterized in that: The task reward amount for each dormant driver is obtained based on the pairing probability of each dormant driver under different reward amounts, the subsidy cost corresponding to different reward amounts, and the subsidy budget, including: Obtaining input parameters for the optimization problem based on the pairing probability of each dormant driver under different reward amounts and the subsidy costs corresponding to different reward amounts; According to the subsidy budget and each dormant driver having only one reward amount, the constraints of the optimization problem are obtained; Based on the input parameters and constraints of the optimization problem, and with maximizing the number of dormant driver pairings as the objective function, an optimization problem is constructed and solved to obtain Boolean variables for each dormant driver under different reward amounts; The task reward amount of each dormant driver is obtained according to the Boolean variables of each dormant driver under different reward amounts.

4. The method for issuing tasks to dormant drivers according to claim 3, characterized in that: After the step of using the trained pairing probability prediction model to predict the pairing probability of each dormant driver under different reward amounts, the following step further comprises: Classify all dormant drivers and obtain several categories of dormant drivers; According to the subsidy budget and each dormant driver having only one reward amount, the constraints of the optimization problem are obtained, including: According to the subsidy budget, each dormant driver has only one reward amount, and dormant drivers belonging to the same category have the same reward amount, thereby obtaining the constraint conditions of the optimization problem.

5. The method for issuing tasks to dormant drivers according to claim 4, characterized in that: All dormant drivers are classified into several categories, including: According to the matching probability of dormant drivers when the reward amount is 0, the natural matching rate of dormant drivers is obtained; According to the pairing probability of dormant drivers under different reward amounts, the pairing elasticity of dormant drivers is obtained; All dormant drivers are classified according to their vehicle models, the natural matching rate, and the matching elasticity to obtain several categories of dormant drivers.

6. The method for issuing tasks to dormant drivers according to claim 5, characterized in that: According to the dormant driver's vehicle model, the natural matching rate, and the matching elasticity, all dormant drivers are classified into several categories, including: Performing grid division according to the vehicle types of all dormant drivers, the natural pairing rate, and the pairing elasticity to obtain a plurality of grids; Each of the dormant drivers is classified into a corresponding grid, and dormant drivers belonging to the same grid are regarded as the same type of dormant drivers.

7. The method for issuing tasks to dormant drivers according to claim 1, characterized in that: According to the task reward amount of each dormant driver and the preset task threshold, the task of each dormant driver is obtained and published, including: According to the task reward amount of each dormant driver and the preset task threshold, the threshold and reward amount of the first-level subtask are obtained; Based on the parent task reward amount and the first-level subtask reward amount, the subsequent subtask reward amount is obtained, and based on the preset subsequent task threshold, the subsequent subtask threshold is obtained; According to the threshold and reward amount of the first-level subtasks and the threshold and reward amount of the subsequent subtasks, the parent task of each dormant driver is obtained and published.

8. The method for issuing tasks to dormant drivers according to claim 7, characterized in that: The subsequent subtasks only include second-level subtasks; Based on the parent task reward amount and the first-level subtask reward amount, the subsequent subtask reward amount is obtained. Based on the preset subsequent task threshold, the subsequent subtask threshold is obtained, including: The reward amount of the second-level subtask is obtained based on the reward amount of the parent task and the reward amount of the first-level subtask; The threshold for the second-level subtask is obtained based on the historical average daily pairing number of dormant drivers.

9. The method for issuing tasks to dormant drivers according to claim 8, characterized in that: The reward amount for the second-level subtask is obtained based on the parent task reward amount and the first-level subtask reward amount, including: The reward amount of the second-level subtask is obtained based on the parent task reward amount, the first-level subtask reward amount, whether the dormant driver has a task dispatch record at the preset time, whether the dormant driver has a collection record at the preset time, and the preset random increase amount.

10. A task issuing device for dormant drivers, characterized in that: include: The first calculation unit is configured to use a trained pairing probability prediction model to predict the pairing probability of each dormant driver under different reward amounts; A second calculation unit is configured to obtain a task reward amount for each dormant driver based on a pairing probability of each dormant driver under different reward amounts, a subsidy cost corresponding to different reward amounts, and a subsidy budget; The task processing unit is used to obtain and publish the task of each dormant driver according to the task reward amount of each dormant driver and a preset task threshold.

11. An electronic device, characterized in that: The system comprises a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute the computer program stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that A computer program is stored thereon, and the computer program is used to make a computer execute the method according to any one of claims 1 to 9.

Images