Vehicle Scheduling Method, Device, Electronic Device and Storage Medium

Abstract

The present invention provides a vehicle scheduling method, device, electronic device and storage medium. The vehicle scheduling method includes: obtaining user pick-up and return behavior data, and based on the user pick-up and return behavior data, obtaining a pick-up and return behavior feature vector; determining pick-up and return information based on the pick-up and return behavior feature vector; wherein the pick-up and return information includes the user's next pick-up and return time, pick-up and return location, user identity information, usage scenario information, and periodic pick-up and return rule information; obtaining a vehicle scheduling strategy based on the pick-up and return information, and performing vehicle scheduling based on the vehicle scheduling strategy. The vehicle scheduling method, device, electronic device and storage medium provided by the present invention can solve the defect in the prior art that personalized scheduling cannot be performed for users, and realize personalized scheduling for users, thereby improving the user's pick-up and return experience and pick-up and return efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and particularly to a vehicle scheduling method, device, electronic device, and storage medium. Background Art

[0002] Currently, there are more and more shared electric vehicles on the market. In order to make reasonable use of the shared electric bicycles put on the market, it is necessary to perform scheduling according to the actual utilization situation of the shared electric bicycles to improve the utilization efficiency of the shared electric bicycles.

[0003] The current general vehicle scheduling method is to perform scheduling according to the hot regions and hot times of users' borrowing and returning vehicles, which meets the general hot scheduling requirements. However, this scheduling method cannot perform personalized scheduling for users and cannot further improve the user experience and the borrowing and returning efficiency. Summary of the Invention

[0004] The present invention provides a vehicle scheduling method, device, electronic device, and storage medium to solve the defect in the prior art that personalized scheduling cannot be performed for users, and to achieve personalized scheduling for users, and improve the user experience and borrowing and returning efficiency of users.

[0005] The present invention provides a vehicle scheduling method, including:

[0006] Obtain the user's borrowing and returning behavior data, and based on the user's borrowing and returning behavior data, obtain a borrowing and returning behavior feature vector;

[0007] Based on the borrowing and returning behavior feature vector, determine the borrowing and returning information; wherein, the borrowing and returning information includes the user's next borrowing and returning time, borrowing and returning location, user identity information, usage scenario information, and periodic borrowing and returning rule information;

[0008] Based on the borrowing and returning information, obtain a vehicle scheduling strategy, and perform vehicle scheduling based on the vehicle scheduling strategy.

[0009] According to the vehicle scheduling method provided by the present invention, the obtaining of the borrowing and returning behavior feature vector based on the user's borrowing and returning behavior data includes:

[0010] Input the user's borrowing and returning behavior data into a trained feature modeling algorithm model to obtain the borrowing and returning behavior feature vector.

[0011] According to the vehicle scheduling method provided by the present invention, the feature modeling algorithm model is an algorithm model obtained by modeling based on a high-dimensional vector space;

[0012] The borrowing and returning behavior feature vector includes: feature vectors corresponding to borrowing information and returning information.

[0013] According to the vehicle scheduling method provided by the present invention, determining the vehicle pick-up and return information based on the vehicle pick-up and return behavior feature vector includes:

[0014] Classifying the vehicle pick-up and return behavior feature vector based on a classification algorithm to determine the feature vector category corresponding to the vehicle pick-up and return behavior feature vector;

[0015] Performing pattern recognition on the feature vector category based on a classification threshold judgment algorithm to obtain the corresponding vehicle pick-up and return pattern;

[0016] Based on the vehicle pick-up and return pattern and the preset pick-up and return station information, obtaining the vehicle pick-up and return information.

[0017] According to the vehicle scheduling method provided by the present invention, obtaining the vehicle scheduling strategy based on the vehicle pick-up and return information includes:

[0018] Optimizing the vehicle pick-up and return information based on a nested loop join algorithm and in combination with the vehicle dispatching requirements to obtain the vehicle scheduling strategy.

[0019] The vehicle scheduling method provided by the present invention further includes:

[0020] Obtaining the confidence level of the vehicle scheduling strategy;

[0021] When the confidence level is greater than a preset value, sending a reminder message to the user terminal corresponding to the vehicle scheduling strategy.

[0022] The present invention further provides a vehicle scheduling device, including:

[0023] A feature extraction module, configured to obtain user vehicle pick-up and return behavior data, and based on the user vehicle pick-up and return behavior data, obtain a vehicle pick-up and return behavior feature vector;

[0024] A feature processing module, configured to determine vehicle pick-up and return information based on the vehicle pick-up and return behavior feature vector; wherein, the vehicle pick-up and return information includes the user's next vehicle pick-up and return time, pick-up and return location, user identity information, usage scenario information, and periodic vehicle pick-up and return pattern information;

[0025] A strategy generation module, configured to obtain a vehicle scheduling strategy based on the vehicle pick-up and return information, and perform vehicle scheduling based on the vehicle scheduling strategy.

[0026] The present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of any one of the above vehicle scheduling methods are implemented.

[0027] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above-mentioned vehicle scheduling methods are implemented.

[0028] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of any one of the above-mentioned vehicle scheduling methods are implemented.

[0029] For the vehicle scheduling method, device, electronic device and storage medium provided by the present invention, by using the user's vehicle return behavior data, a vehicle return behavior feature vector is obtained, and further vehicle return information is obtained. Then, based on the vehicle return information, a vehicle scheduling strategy is obtained. In the vehicle scheduling strategy obtained by the present invention, it is obtained based on the user's vehicle return behavior data. Based on the user's vehicle return behavior data, personalized scheduling of vehicles can be performed, improving the user's vehicle return experience and vehicle return efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is one of the flow diagrams of the vehicle scheduling method provided by the present invention;

[0032] Figure 2 It is another flow diagram of the vehicle scheduling method provided by the present invention;

[0033] Figure 3 It is the structural diagram of the vehicle scheduling device provided by the present invention;

[0034] Figure 4 It is the structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0036] The following will describe Figures 1 - 4 the vehicle scheduling method, device, electronic device and storage medium of the present invention.

[0037] As Figure 1 shown, the vehicle scheduling method provided by the present invention includes:

[0038] Step 110: Obtain the user's vehicle usage and return behavior data, and based on the user's vehicle usage and return behavior data, obtain a vehicle usage and return behavior feature vector.

[0039] It can be understood that the vehicle usage and return in the present invention include vehicle usage and vehicle return. The user's vehicle usage and return behavior data includes user information and the user's vehicle usage habit data within a preset time period.

[0040] A central control module is provided on the vehicle. The central control module can record the user's vehicle usage behavior data, and upload the vehicle usage data and user information to the background server for processing and analysis by the background server.

[0041] By abstracting and extracting the user's vehicle usage and return behavior data, a vehicle usage and return behavior feature vector can be obtained.

[0042] The vehicle in this embodiment can be an electric vehicle, such as a shared two-wheeled electric vehicle or a shared electric vehicle.

[0043] Step 120: Determine the vehicle usage and return information based on the vehicle usage and return behavior feature vector; wherein, the vehicle usage and return information includes the user's next vehicle usage and return time, vehicle usage and return location, user identity information, usage scenario information, and periodic vehicle usage and return rule information.

[0044] It can be understood that the vehicle usage and return behavior feature vector is a feature vector obtained based on the user's historical vehicle usage and return behavior data. Based on the user's vehicle usage and return behavior feature vector, the user's next vehicle usage and return time and vehicle usage and return location can be predicted.

[0045] The user identity information may include the user's age and gender; the usage scenario may be in which specific life scenarios the vehicle is used; the periodic vehicle usage and return rule information may be the vehicle usage and return rule information of the user within a set period, such as within a week or a month.

[0046] Step 130: Obtain a vehicle scheduling strategy based on the vehicle usage and return information, and perform vehicle scheduling based on the vehicle scheduling strategy.

[0047] It can be understood that after predicting the next vehicle usage and return time and vehicle usage and return location based on the vehicle usage and return behavior feature vector, it is possible to determine which area and which moment there are users who need to use or return the vehicle. After determining the number of vehicles that need to be used or returned in the target area and target moment, combined with the actual demand data of the target area, vehicle scheduling is performed so that there are corresponding numbers of vehicles in the target area and target moment for users to use.

[0048] In some embodiments, obtaining the vehicle borrowing and returning behavior feature vector based on the vehicle borrowing and returning behavior data of the user includes:

[0049] Inputting the vehicle borrowing and returning behavior data of the user into a trained feature modeling algorithm model to obtain the vehicle borrowing and returning behavior feature vector.

[0050] It can be understood that the feature modeling algorithm model can be trained and completed on a cloud server. The feature modeling algorithm model can be trained using the historical vehicle borrowing and returning behavior data of users collected as training samples, and the corresponding vehicle borrowing and returning behavior feature vectors of the historical vehicle borrowing and returning behavior data of users as sample labels.

[0051] The cloud server distributes the trained feature modeling algorithm model to the servers in each scheduling area. The servers in each scheduling area process the vehicle borrowing and returning behavior data of the users in that scheduling area to obtain the corresponding vehicle borrowing and returning behavior feature vectors.

[0052] In some embodiments, the feature modeling algorithm model is an algorithm model obtained based on high-dimensional vector space modeling.

[0053] The vehicle borrowing and returning behavior feature vector includes: the feature vectors corresponding to the vehicle borrowing information and the vehicle returning information.

[0054] It can be understood that the vehicle borrowing information may include information such as the vehicle borrowing time and the vehicle borrowing location; the vehicle returning information may include information such as the vehicle returning time and the vehicle returning location. The vehicle borrowing and returning behavior feature vector may further include statistical feature information on vehicle borrowing and returning within a target time period, such as statistical feature information on vehicle borrowing and returning within a week. Further, it may be the number of vehicle borrowings and returns, and the vehicle borrowing time and returning time within a week in a target area.

[0055] In some embodiments, determining the vehicle borrowing and returning information based on the vehicle borrowing and returning behavior feature vector includes:

[0056] Classifying the vehicle borrowing and returning behavior feature vector based on a classification algorithm to determine the feature vector category corresponding to the vehicle borrowing and returning behavior feature vector;

[0057] Performing pattern recognition on the feature vector category based on a classification threshold judgment algorithm to obtain the corresponding vehicle borrowing and returning pattern;

[0058] Based on the vehicle borrowing and returning pattern and the preset vehicle borrowing and returning station information, obtaining the vehicle borrowing and returning information.

[0059] It can be understood that the vehicle rental and return mode may include a user borrowing a vehicle and a user returning a vehicle. The classification algorithm may be the LVM (Las Vegas Wrapper) algorithm, and the LVM algorithm is a typical wrapper feature selection method.

[0060] The classification threshold judgment algorithm is also to perform pattern recognition and judgment on the feature vector type based on a preset classification threshold. Further, the classification threshold judgment algorithm may be an arithmetic mean algorithm. That is, calculate the arithmetic mean of the feature vectors under the same category, perform pattern recognition based on the arithmetic mean of the feature vectors under the same category, and match the arithmetic mean of the feature vectors under the same category with different feature vector values corresponding to a plurality of preset vehicle rental and return modes respectively to determine the corresponding vehicle rental and return mode.

[0061] Based on the vehicle rental and return mode determined according to the feature vector category, adsorb according to the station information near the vehicle borrowing and returning points, and calculate the most suitable vehicle rental and return station and time point.

[0062] In some embodiments, obtaining a vehicle scheduling strategy based on the vehicle rental and return information includes:

[0063] Based on the nested loop join algorithm and combined with the vehicle dispatching demand, optimize the vehicle rental and return information to obtain the vehicle scheduling strategy.

[0064] It can be understood that the vehicle dispatching demand is also the number of vehicles that need to be borrowed and returned within a target time period in a target area. In different regions, the vehicle dispatching demand may be different and can be adjusted according to the actual situation.

[0065] The nested loop join algorithm is also the Join algorithm. Based on the big data batch processing function of the nested loop join algorithm, superimpose the vehicle dispatching demand into the dispatching demand pool, correct the features of the user's next vehicle rental and return location and time point, and use the superimposed result to match the vehicles to be dispatched, and perform dispatching operations on the matched vehicles to be dispatched.

[0066] In some embodiments, the vehicle scheduling method further includes:

[0067] Obtain the confidence level of the vehicle scheduling strategy;

[0068] When the confidence level is greater than a preset value, send a reminder message to the user terminal corresponding to the vehicle scheduling strategy.

[0069] It can be understood that after obtaining the vehicle scheduling strategy, the vehicle scheduling strategy can be sent to the scheduling control terminal for display, so that the scheduling personnel can confirm it. After the scheduling personnel confirm and input the corresponding confidence level, the confidence level is also the accuracy rate of the vehicle scheduling strategy. The server system determines whether the scheduling strategy will be executed based on the input confidence level. The higher the confidence level, the higher the possibility that the vehicle scheduling strategy will be executed.

[0070] When the confidence level is greater than the preset value, it is determined that the scheduling strategy will be executed. Therefore, a reminder message is sent to the user terminal corresponding to the vehicle scheduling strategy, such as a mobile phone, to remind the corresponding user of the pick-up time and pick-up location, or to remind the user of the return time and return location.

[0071] In some other embodiments, the flowchart of the vehicle scheduling method provided by the present invention is as Figure 2 shown. The user's pick-up and return behavior data is input into the feature modeling algorithm model to obtain the pick-up and return behavior feature vector. Then, the pick-up and return behavior vector is input into the pattern fitting algorithm model to obtain the predicted next pick-up and return time and location of the user. Then, the obtained next pick-up and return time and location of the user are input into the nested loop connection algorithm model, and combined with the vehicle dispatching requirements, data correction is performed to obtain the final vehicle scheduling strategy.

[0072] In summary, the vehicle scheduling method provided by the present invention includes: obtaining the user's pick-up and return behavior data, and based on the user's pick-up and return behavior data, obtaining the pick-up and return behavior feature vector; determining the pick-up and return information based on the pick-up and return behavior feature vector; wherein, the pick-up and return information includes the user's next pick-up and return time, pick-up and return location, user identity information, usage scenario information, and periodic pick-up and return rule information; obtaining the vehicle scheduling strategy based on the pick-up and return information, so as to perform vehicle scheduling based on the vehicle scheduling strategy.

[0073] In the vehicle scheduling method provided by the present invention, first, based on the user's pick-up and return behavior data, the pick-up and return behavior feature vector is obtained, and further the pick-up and return information is obtained. Then, the vehicle scheduling strategy is obtained based on the pick-up and return information. The vehicle scheduling strategy obtained in the present invention is obtained based on the user's pick-up and return behavior data. Based on the user's pick-up and return behavior data, personalized scheduling of the vehicle can be performed, improving the user's pick-up and return experience and efficiency.

[0074] Next, the vehicle scheduling device provided by the present invention will be described. The vehicle scheduling device described below can be mutually corresponding and referred to the vehicle scheduling method described above.

[0075] As Figure 3As shown in the figure, the vehicle scheduling device 300 provided by the present invention includes: a feature extraction module 310, a feature processing module 320, and a policy generation module 330.

[0076] The feature extraction module 310 is used to obtain the user's pick-up and return behavior data, and based on the user's pick-up and return behavior data, obtain a pick-up and return behavior feature vector.

[0077] The feature processing module 320 is used to determine pick-up and return information based on the pick-up and return behavior feature vector; wherein, the pick-up and return information includes the user's next pick-up and return time, pick-up and return location, user identity information, usage scenario information, and periodic pick-up and return rule information.

[0078] The policy generation module 330 is used to obtain a vehicle scheduling policy based on the pick-up and return information, and perform vehicle scheduling based on the vehicle scheduling policy.

[0079] In some embodiments, the feature extraction module 310 is further used to input the user's pick-up and return behavior data into a trained feature modeling algorithm model to obtain the pick-up and return behavior feature vector.

[0080] In some embodiments, the feature modeling algorithm model is an algorithm model obtained by modeling based on a high-dimensional vector space.

[0081] The pick-up and return behavior feature vector includes: a feature vector corresponding to pick-up information and return information.

[0082] In some embodiments, the feature processing module 320 includes: a feature classification unit, a feature recognition unit, and an information extraction unit.

[0083] The feature classification unit is used to classify the pick-up and return behavior feature vector based on a classification algorithm to determine the feature vector category corresponding to the pick-up and return behavior feature vector.

[0084] The feature recognition unit is used to perform pattern recognition on the feature vector category based on a classification threshold judgment algorithm to obtain a corresponding pick-up and return pattern.

[0085] The information extraction unit is used to obtain the pick-up and return information based on the pick-up and return pattern and preset pick-up and return station information.

[0086] In some embodiments, the policy generation module 330 is further used to optimize the pick-up and return information based on a nested loop connection algorithm and in combination with vehicle dispatching requirements to obtain the vehicle scheduling policy.

[0087] In some embodiments, the vehicle scheduling device 300 further includes: a confidence level acquisition module and a message reminder module.

[0088] The confidence level acquisition module is used to acquire the confidence level of the vehicle scheduling strategy.

[0089] The message reminder module is used to send a reminder message to the user terminal corresponding to the vehicle scheduling strategy when the confidence level is greater than a preset value.

[0090] The electronic device, computer program product, and storage medium provided by the present invention will be described below. The electronic device, computer program product, and storage medium described below can be mutually corresponding and referenced with the vehicle scheduling method described above.

[0091] Figure 4 The schematic diagram of the physical structure of an electronic device is exemplified, as Figure 4 shown. The electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440. Among them, the processor 410, the communication interface 420, and the memory 430 complete mutual communication through the communication bus 440. The processor 410 can call the logical instructions in the memory 430 to execute the vehicle scheduling method, and the method includes:

[0092] Step 110: Obtain the user's pick-up and return behavior data, and based on the user's pick-up and return behavior data, obtain the pick-up and return behavior feature vector;

[0093] Step 120: Determine the pick-up and return information based on the pick-up and return behavior feature vector; wherein, the pick-up and return information includes the user's next pick-up and return time, pick-up and return location, user identity information, usage scenario information, and periodic pick-up and return rule information;

[0094] Step 130: Obtain a vehicle scheduling strategy based on the pick-up and return information, and perform vehicle scheduling based on the vehicle scheduling strategy.

[0095] In addition, when the logical instructions in the above-mentioned memory 430 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0096] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle scheduling method provided by the above-mentioned various methods. The method includes:

[0097] Step 110, obtaining user pick-up and return behavior data, and obtaining a pick-up and return behavior feature vector based on the user pick-up and return behavior data;

[0098] Step 120, determining pick-up and return information based on the pick-up and return behavior feature vector; wherein the pick-up and return information includes the user's next pick-up and return time, pick-up and return location, user identity information, usage scenario information, and periodic pick-up and return rule information;

[0099] Step 130, obtaining a vehicle scheduling strategy based on the pick-up and return information, and performing vehicle scheduling based on the vehicle scheduling strategy.

[0100] In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the vehicle scheduling method provided by the above-mentioned various methods. The method includes:

[0101] Step 110, obtaining user pick-up and return behavior data, and obtaining a pick-up and return behavior feature vector based on the user pick-up and return behavior data;

[0102] Step 120, determining pick-up and return information based on the pick-up and return behavior feature vector; wherein the pick-up and return information includes the user's next pick-up and return time, pick-up and return location, user identity information, usage scenario information, and periodic pick-up and return rule information;

[0103] Step 130: Obtain a vehicle scheduling strategy based on the vehicle return information, and perform vehicle scheduling based on the vehicle scheduling strategy.

[0104] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0105] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solutions, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle scheduling method, characterized in that, Including: Obtain the user's vehicle pick-up and return behavior data, and based on the user's vehicle pick-up and return behavior data, obtain a vehicle pick-up and return behavior feature vector; Based on the vehicle pick-up and return behavior feature vector, determine vehicle pick-up and return information; wherein, the vehicle pick-up and return information includes the user's next vehicle pick-up and return time, vehicle pick-up and return location, user identity information, usage scenario information, and periodic vehicle pick-up and return pattern information; Based on the vehicle pick-up and return information, obtain a vehicle scheduling strategy, and perform vehicle scheduling based on the vehicle scheduling strategy. The vehicle includes a shared two-wheeled electric vehicle; The determining the vehicle pick-up and return information based on the vehicle pick-up and return behavior feature vector includes: Based on a classification algorithm, classify the vehicle pick-up and return behavior feature vector to determine the feature vector category corresponding to the vehicle pick-up and return behavior feature vector; Perform pattern recognition on the feature vector category based on a classification threshold judgment algorithm to obtain a corresponding vehicle pick-up and return pattern. The vehicle pick-up and return pattern includes the user borrowing a vehicle and the user returning a vehicle; Based on the vehicle pick-up and return pattern and the preset pick-up and return station information, obtain the vehicle pick-up and return information; Specifically including: Based on the vehicle pick-up and return pattern, adsorb according to the station information near the pick-up and return point, and calculate the most suitable vehicle pick-up and return station and time point.

2. The vehicle scheduling method according to claim 1, wherein The obtaining the vehicle pick-up and return behavior feature vector based on the user's vehicle pick-up and return behavior data includes: Input the user's vehicle pick-up and return behavior data into a trained feature modeling algorithm model to obtain the vehicle pick-up and return behavior feature vector.

3. The vehicle scheduling method according to claim 2, wherein The feature modeling algorithm model is an algorithm model obtained based on high-dimensional vector space modeling; The vehicle pick-up and return behavior feature vector includes: feature vectors corresponding to vehicle borrowing information and vehicle returning information.

4. The vehicle scheduling method according to claim 1, wherein, The obtaining the vehicle scheduling strategy based on the vehicle pick-up and return information includes: Based on a nested loop join algorithm and combined with vehicle dispatching requirements, optimize the vehicle pick-up and return information to obtain the vehicle scheduling strategy.

5. The vehicle scheduling method according to any one of claims 1-4, characterized in that Also including: Obtain the confidence level of the vehicle scheduling strategy; When the confidence level is greater than a preset value, send a reminder message to the user terminal corresponding to the vehicle scheduling strategy.

6. A vehicle scheduling device, applying the vehicle scheduling method as described in claim 1, characterized in that, Including: A feature extraction module, configured to obtain the user's vehicle pick-up and return behavior data, and based on the user's vehicle pick-up and return behavior data, obtain a vehicle pick-up and return behavior feature vector; A feature processing module, configured to determine vehicle pick-up and return information based on the vehicle pick-up and return behavior feature vector; wherein, the vehicle pick-up and return information includes the user's next vehicle pick-up and return time, vehicle pick-up and return location, user identity information, usage scenario information, and periodic vehicle pick-up and return pattern information; A strategy generation module, configured to obtain a vehicle scheduling strategy based on the vehicle pick-up and return information, and perform vehicle scheduling based on the vehicle scheduling strategy.

7. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the vehicle scheduling method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the vehicle scheduling method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the vehicle scheduling method according to any one of claims 1 to 5.

Images