Shared vehicle scheduling method and device, electronic equipment and storage medium

Abstract

The invention provides a shared vehicle scheduling method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining current vehicle order data of each station in a target area and current environment information of the target area; inputting the current vehicle order data and the current environment information of each station into a pre-trained prediction model to obtain vehicle order prediction data, output by the prediction model, of each station; determining a plurality of associated stations from the stations, and integrating the vehicle order prediction data of the stations to obtain integrated vehicle order prediction data; according to the current vehicle number and the current vehicle reservation data of each target station and the integrated vehicle order prediction data, calculating the vehicle missing number or the vehicle stacking number of each target station; and determining a vehicle scheduling scheme of the target area according to the historical operation and maintenance scheduling data of the target area and the number of missing vehicles or the number of stacked vehicles of each target station. The efficiency of shared vehicle scheduling is improved, and the real-time performance and the flexibility are high.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle dispatching, and in particular to a shared vehicle dispatching method, device, electronic equipment and storage medium. Background Art

[0002] With the development of sharing economy and information technology, shared bicycles and shared electric vehicles are expanding rapidly in major cities. How to reasonably dispatch shared vehicles is a key issue that shared vehicle operators need to solve. At present, the traditional vehicle dispatching method relies on the experience of professionals, focuses on limited stations, has low efficiency, and poor real-time and flexibility. Summary of the invention

[0003] The present invention provides a shared vehicle dispatching method, device, electronic device and storage medium, which are used to solve the defects of the traditional vehicle dispatching mode in the prior art that it relies on the experience of professionals, has low efficiency, poor real-time performance and poor flexibility.

[0004] In a first aspect, the present invention provides a shared vehicle scheduling method, comprising: Obtaining current vehicle order data of each station in the target area and current environmental information of the target area; Inputting the current vehicle order data of each site and the current environmental information into a pre-trained prediction model to obtain the vehicle order prediction data of each site output by the prediction model, wherein the prediction model is trained based on the historical vehicle order data of each site in the target area and the historical environmental information of the target area; Determine a plurality of associated sites from the sites, and integrate the vehicle order forecast data of the sites based on the plurality of associated sites to obtain integrated vehicle order forecast data; Calculate the number of missing vehicles or the number of backlogged vehicles at each target station according to the current number of vehicles and current vehicle reservation data at each target station, as well as the integrated vehicle order forecast data; A vehicle dispatching plan for the target area is determined according to the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station.

[0005] In some embodiments, the determining a plurality of associated sites from the sites comprises: Determining a plurality of associated sites from the sites according to the binding information input by the user; According to the distances between the sites and the vehicle order prediction data of the sites, a plurality of associated sites are determined from the sites.

[0006] In some embodiments, the vehicle order forecast data of each site includes: vehicle order forecast data at the daily level of each site and vehicle order forecast data at the hourly level of each site; the current environmental information includes current date information and current climate information.

[0007] In some embodiments, the calculating of the number of missing vehicles or the number of accumulated vehicles at each target station includes: Determine, based on the integrated vehicle order forecast data, the forecast number of vehicles entering and transferring out of each target station per hour in the future, and the forecast number of vehicles entering and transferring out of each target station in the future day; Calculate the initial number of vehicles missing at each target station based on the current number of vehicles at each target station and the current vehicle reservation data, as well as the predicted number of vehicles entering and transferring out of each target station every hour in the future; According to the predicted number of vehicles entering and transferring out of each target station in the next day, the initial number of vehicles missing at each target station is corrected to obtain the number of vehicles missing at each target station.

[0008] In some embodiments, determining the vehicle dispatching scheme for the target area according to the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station includes: Determine the dispatching route corresponding to each target site according to the historical operation and maintenance dispatching data of the target area and the distance between each target site; Determine the dispatching task volume corresponding to each target station and the dispatching priority corresponding to each target station according to the number of missing vehicles or accumulated vehicles at each target station and the average dispatching task volume of the target area in the previous few days; A vehicle dispatching plan for the target area is determined according to the dispatching routes, dispatching task volumes and dispatching priorities corresponding to the target sites.

[0009] In some embodiments, the method further comprises: According to the vehicle dispatching plan of the target area, multiple shared vehicles in the target area are dispatched, and the vehicle dispatching effect of the target area is evaluated; The parameters of the prediction model are optimized according to the vehicle dispatching effect in the target area.

[0010] In some embodiments, the training process of the prediction model includes: Obtaining historical vehicle order data of each site on the i-th day and historical vehicle order data of each site on the i+1-th day, as well as historical environmental information of the target area on the i-th day; Inputting the historical vehicle order data of each site on the i-th day and the historical environmental information of the i-th day into the initial prediction model, obtaining the vehicle order prediction data of each site on the i+1-th day output by the initial prediction model; Calculate the loss function value according to the historical vehicle order data of each site on the i+1th day and the vehicle order forecast data on the i+1th day; According to the loss function value, the parameters of the initial prediction model are iteratively optimized to obtain the prediction model.

[0011] In a second aspect, the present invention further provides a shared vehicle dispatching device, comprising: An acquisition unit, used to acquire current vehicle order data of each station in a target area, and current environment information of the target area; A prediction unit, used for inputting the current vehicle order data of each station and the current environmental information into a pre-trained prediction model to obtain the vehicle order prediction data of each station output by the prediction model, wherein the prediction model is trained based on the historical vehicle order data of each station in the target area and the historical environmental information of the target area; an integration unit, configured to determine a plurality of associated sites from the sites, and integrate the vehicle order forecast data of the sites based on the plurality of associated sites to obtain integrated vehicle order forecast data; A calculation unit, used to calculate the number of missing vehicles or the number of backlogged vehicles at each target station according to the current number of vehicles and current vehicle reservation data at each target station and the integrated vehicle order forecast data; The determination unit is used to determine the vehicle dispatching plan of the target area according to the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station.

[0012] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a shared vehicle scheduling method as described above is implemented.

[0013] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described shared vehicle scheduling methods.

[0014] The shared vehicle scheduling method, device, electronic device and storage medium provided by the present invention obtain the current vehicle order data of each station in the target area and the current environmental information of the target area, input the obtained data into a pre-trained prediction model, obtain the vehicle order prediction data of each station output by the prediction model, integrate the vehicle order prediction data of each station according to multiple associated stations, calculate the number of missing vehicles or the number of accumulated vehicles at each target station according to the current number of vehicles and current vehicle reservation data of each target station, and the integrated vehicle order prediction data, determine the vehicle scheduling plan for the target area according to the historical operation and maintenance scheduling data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station, thereby improving the efficiency of shared vehicle scheduling and having strong real-time performance and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0016] Figure 1 This is one of the flow charts of the shared vehicle scheduling method provided by an embodiment of the present invention; Figure 2 This is the second flow chart of the shared vehicle scheduling method provided by an embodiment of the present invention; Figure 3 It is a flowchart of the training process of the prediction model provided by the embodiment of the present invention; Figure 4 is a schematic diagram of the structure of a shared vehicle dispatching device provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Figure 1 This is a flow chart of a shared vehicle scheduling method provided by an embodiment of the present invention. Figure 1As shown, a shared vehicle dispatching method is provided, comprising the following steps: steps 110 to 150. The steps of the method flow are only a possible implementation of the present invention.

[0019] Step 110: Obtain current vehicle order data of each station in the target area and current environmental information of the target area.

[0020] Optionally, the current vehicle order data includes the order number, vehicle information, order date, order status and other information of the day.

[0021] In some embodiments, the current environmental information includes current date information and current climate information, such as whether the day is a weekday, whether the weather on the day is bad, the morning peak temperature on the day, the evening peak temperature on the day, etc.

[0022] Step 120: input the current vehicle order data and current environmental information of each site into a pre-trained prediction model to obtain the vehicle order prediction data of each site output by the prediction model. The prediction model is trained based on the historical vehicle order data of each site in the target area and the historical environmental information of the target area.

[0023] Optionally, the vehicle order forecast data of each site includes the vehicle order forecast data of each site for the next day and the vehicle order forecast data of each site every hour for the next day.

[0024] In some embodiments, the vehicle order forecast data of each site includes: vehicle order forecast data at the daily level of each site and vehicle order forecast data at the hourly level of each site.

[0025] It can be understood that by inputting the current vehicle order data and current environmental information of each site into the pre-trained prediction model, the vehicle order prediction data of each site is obtained as output by the prediction model, which improves the efficiency and accuracy of vehicle demand prediction and provides a comprehensive data basis for subsequent vehicle scheduling decisions.

[0026] Step 130: determine a plurality of associated sites from each site, and integrate the vehicle order forecast data of each site based on the plurality of associated sites to obtain integrated vehicle order forecast data.

[0027] Optionally, based on the vehicle order prediction data of each station, multiple stations involved in the morning peak and evening peak are determined, and based on the distance between these stations and the vehicle order prediction data, a neighbor station group is determined, and the neighbor station group includes multiple associated stations.

[0028] It can be understood that by determining multiple associated sites from each site and integrating the vehicle order forecast data of each site based on the multiple associated sites, it is possible to avoid scheduling vehicles back and forth at adjacent sites, improve scheduling efficiency, and optimize scheduling effects.

[0029] In some embodiments, determining a plurality of associated sites from each site includes: According to the binding information input by the user, a plurality of associated sites are determined from each site; Based on the distance between each station and the vehicle order prediction data of each station, a plurality of associated stations are determined from each station.

[0030] Optionally, determine whether the distance between any two sites is less than a preset distance threshold. If so, continue to determine whether the vehicle order prediction data of the two sites are both greater than a preset prediction value. If so, determine that the two sites are associated sites.

[0031] Step 140: Calculate the number of missing vehicles or backlogged vehicles at each target station based on the current number of vehicles at each target station, the current vehicle reservation data, and the integrated vehicle order forecast data.

[0032] Optionally, a plurality of target stations to be scheduled are determined from all stations in the target area, ie, stations with a shortage of vehicles or an excess of vehicles in the predicted time period.

[0033] In some embodiments, calculating the number of missing vehicles or the number of accumulated vehicles at each target station includes: Based on the integrated vehicle order forecast data, determine the forecast number of vehicles entering and transferring out of each target station every hour in the future, as well as the forecast number of vehicles entering and transferring out of each target station in the future day; Calculate the initial number of vehicles missing at each target station based on the current number of vehicles at each target station, the current vehicle reservation data, and the predicted number of vehicles entering and transferring out of each target station every hour in the future; According to the predicted number of vehicles entering and transferring out of each target station in the next day, the initial number of vehicles missing at each target station is corrected to obtain the number of vehicles missing at each target station.

[0034] Optionally, the calculation formula for the number of missing vehicles or the number of accumulated vehicles at the target station is as follows: The number of missing or accumulated vehicles at the target station = the current number of vehicles at the target station - the number of reserved vehicles at the target station + the predicted number of vehicles entering the target station in the next n hours - the predicted number of vehicles transferring out of the target station in the next n hours; Optionally, if the calculated value of the above formula is a negative value, then the value represents the number of missing vehicles at the target site; if the calculated value of the above formula is a positive value, then the value represents the number of accumulated vehicles at the target site.

[0035] Optionally, the difference between the predicted number of vehicles entering the target site in the next day and the predicted number of vehicles transferring out is calculated, and the number of missing vehicles or the number of accumulated vehicles at the target site is corrected according to the difference.

[0036] Step 150: Determine a vehicle dispatching plan for the target area based on the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or accumulated vehicles at each target station.

[0037] Optionally, the historical operation and maintenance scheduling data includes information such as scheduling time, scheduling task volume, scheduling site, scheduling route, etc.

[0038] Optionally, based on historical operation and maintenance scheduling data, determine the scheduling route from the popular station with vehicle shortage to the nearest unpopular station with vehicle accumulation.

[0039] In some embodiments, a vehicle dispatching scheme for the target area is determined based on historical operation and maintenance dispatching data of the target area and the number of missing vehicles or accumulated vehicles at each target station, including: Determine the dispatching route corresponding to each target site based on the historical operation and maintenance dispatching data of the target area and the distance between each target site; According to the number of missing or accumulated vehicles at each target station and the average dispatch task volume of the target area in the previous few days, determine the dispatch task volume corresponding to each target station and the dispatch priority corresponding to each target station; Determine the vehicle dispatch plan for the target area based on the dispatch routes, dispatch task volumes and dispatch priorities corresponding to each target site.

[0040] Optionally, the priority of a popular station with missing vehicles is determined to be high, so that vehicles are preferentially dispatched to the popular station with missing vehicles.

[0041] It is understandable that by analyzing historical operation and maintenance scheduling data and site requirements, vehicle resources can be effectively allocated to reduce vehicle idleness and shortages; by determining reasonable scheduling routes and task volumes, the response speed and execution efficiency of scheduling can be improved to ensure that vehicles reach the required sites quickly; by optimizing scheduling routes and determining scheduling priorities, it helps to reduce vehicle driving distances, reduce operation and maintenance costs, improve overall operational efficiency, and enhance user experience; determining scheduling plans based on real-time data can quickly respond to changes in market demand, with strong flexibility and adaptability.

[0042] Figure 2 The second flow chart of the shared vehicle dispatching method provided by the embodiment of the present invention. Figure 2 As shown, in some embodiments, the above method also includes: According to the vehicle dispatching plan of the target area, multiple shared vehicles in the target area are dispatched, and the vehicle dispatching effect in the target area is evaluated; According to the vehicle dispatch effect in the target area, the parameters of the prediction model are optimized.

[0043] It can be understood that by evaluating the vehicle dispatch effect in the target area and optimizing the parameters of the prediction model according to the vehicle dispatch effect in the target area, it helps to improve the accuracy and reliability of the prediction model, so that it can better predict future demand.

[0044] In an embodiment of the present invention, by acquiring current vehicle order data of each station in the target area and current environmental information of the target area, the acquired data is input into a pre-trained prediction model to obtain vehicle order prediction data of each station output by the prediction model, and the vehicle order prediction data of each station is integrated according to multiple associated stations. The number of missing vehicles or the number of backlogged vehicles at each target station is calculated according to the current number of vehicles and the current vehicle reservation data of each target station, as well as the integrated vehicle order prediction data. The vehicle scheduling plan for the target area is determined according to the historical operation and maintenance scheduling data of the target area and the number of missing vehicles or the number of backlogged vehicles at each target station, thereby improving the efficiency of shared vehicle scheduling and enhancing real-time performance and flexibility.

[0045] Figure 3 The flowchart of the training process of the prediction model provided by the embodiment of the present invention is as follows. Figure 3 As shown, in some embodiments, the training process of the prediction model includes: Step 310: Obtain historical vehicle order data of each station on the i-th day and historical vehicle order data of each station on the i+1-th day, as well as historical environmental information of the target area on the i-th day; Step 320: input the historical vehicle order data of each station on the i-th day and the historical environmental information of the i-th day into the initial prediction model to obtain the vehicle order prediction data of each station on the i+1th day output by the initial prediction model; Step 330: Calculate the loss function value based on the historical vehicle order data of each station on the i+1th day and the vehicle order forecast data on the i+1th day; Step 340: Iteratively optimize the parameters of the initial prediction model according to the loss function value to obtain a prediction model.

[0046] Optionally, the vehicle order forecast data for each site on the i+1th day includes: vehicle order forecast data at the daily level for each site and vehicle order forecast data at the hourly level for each site; the historical environmental information includes historical date information and historical climate information.

[0047] It can be understood that training the initial prediction model based on the historical vehicle order data and historical environmental information of each site to obtain the prediction model can improve the robustness of the prediction model and the accuracy of the prediction.

[0048] The following is a description of a shared vehicle scheduling device provided by an embodiment of the present invention. The shared vehicle scheduling device described below and the shared vehicle scheduling method described above can be referenced to each other.

[0049] Figure 4 A schematic diagram of the structure of a shared vehicle dispatching device provided by an embodiment of the present invention, such as Figure 4 As shown, the shared vehicle dispatching device 400 includes: An acquisition unit 410 is used to acquire current vehicle order data of each station in the target area and current environment information of the target area; A prediction unit 420, configured to input the current vehicle order data and current environmental information of each station into a pre-trained prediction model to obtain the vehicle order prediction data of each station output by the prediction model, wherein the prediction model is trained based on the historical vehicle order data of each station in the target area and the historical environmental information of the target area; An integration unit 430 is used to determine a plurality of associated sites from each site, and integrate the vehicle order prediction data of each site based on the plurality of associated sites to obtain integrated vehicle order prediction data; The calculation unit 440 is used to calculate the number of missing vehicles or the number of accumulated vehicles at each target station according to the current number of vehicles and current vehicle reservation data at each target station and the integrated vehicle order prediction data; The determination unit 450 is used to determine the vehicle dispatching plan for the target area according to the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station.

[0050] Optionally, a plurality of associated sites are determined from each site, including: According to the binding information input by the user, a plurality of associated sites are determined from each site; Based on the distance between each station and the vehicle order prediction data of each station, a plurality of associated stations are determined from each station.

[0051] Optionally, the vehicle order forecast data of each site includes: vehicle order forecast data at the daily level of each site and vehicle order forecast data at the hourly level of each site; the current environmental information includes current date information and current climate information.

[0052] Optionally, the number of missing vehicles or the number of accumulated vehicles at each target station is calculated, including: Based on the integrated vehicle order forecast data, determine the forecast number of vehicles entering and transferring out of each target station every hour in the future, as well as the forecast number of vehicles entering and transferring out of each target station in the future day; Calculate the initial number of vehicles missing at each target station based on the current number of vehicles at each target station, the current vehicle reservation data, and the predicted number of vehicles entering and transferring out of each target station every hour in the future; According to the predicted number of vehicles entering and transferring out of each target station in the next day, the initial number of vehicles missing at each target station is corrected to obtain the number of vehicles missing at each target station.

[0053] Optionally, according to the historical operation and maintenance scheduling data of the target area and the number of missing vehicles or accumulated vehicles at each target station, a vehicle scheduling plan for the target area is determined, including: Determine the dispatching route corresponding to each target site based on the historical operation and maintenance dispatching data of the target area and the distance between each target site; According to the number of missing or accumulated vehicles at each target station and the average dispatch task volume of the target area in the previous few days, determine the dispatch task volume corresponding to each target station and the dispatch priority corresponding to each target station; Determine the vehicle dispatch plan for the target area based on the dispatch routes, dispatch task volumes and dispatch priorities corresponding to each target site.

[0054] Optionally, the shared vehicle dispatching device 400 further includes: An evaluation unit, configured to dispatch a plurality of shared vehicles in a target area according to a vehicle dispatching plan of the target area, and evaluate a vehicle dispatching effect in the target area; The model optimization unit is used to optimize the parameters of the prediction model according to the vehicle scheduling effect in the target area.

[0055] Optionally, the training process of the prediction model includes: Obtain the historical vehicle order data of each station on the i-th day and the historical vehicle order data of each station on the i+1th day, as well as the historical environmental information of the target area on the i-th day; Input the historical vehicle order data of each station on the i-th day and the historical environmental information of the i-th day into the initial prediction model, and obtain the vehicle order prediction data of each station on the i+1th day output by the initial prediction model; Calculate the loss function value based on the historical vehicle order data of each station on the i+1th day and the vehicle order forecast data on the i+1th day; According to the loss function value, the parameters of the initial prediction model are iteratively optimized to obtain the prediction model.

[0056] It should be noted here that the shared vehicle scheduling device provided in the embodiment of the present invention can implement all the method steps implemented in the above-mentioned shared vehicle scheduling method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0057] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the shared vehicle scheduling method, which includes: obtaining the current vehicle order data of each station in the target area and the current environmental information of the target area; inputting the current vehicle order data and the current environmental information of each station into a pre-trained prediction model to obtain the vehicle order prediction data of each station output by the prediction model, and the prediction model is trained based on the historical vehicle order data of each station in the target area and the historical environmental information of the target area; determining multiple associated stations from each station, and integrating the vehicle order prediction data of each station based on the multiple associated stations to obtain integrated vehicle order prediction data; calculating the number of missing vehicles or the number of backlogged vehicles at each target station based on the current number of vehicles and the current vehicle reservation data of each target station, as well as the integrated vehicle order prediction data; determining the vehicle scheduling plan for the target area based on the historical operation and maintenance scheduling data of the target area and the number of missing vehicles or the number of backlogged vehicles at each target station.

[0058] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0059] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the shared vehicle scheduling method provided by the above-mentioned methods, the method comprising: obtaining current vehicle order data of each station in the target area, and current environmental information of the target area; inputting the current vehicle order data and current environmental information of each station into a pre-trained prediction model to obtain vehicle order prediction data of each station output by the prediction model, wherein the prediction model is trained based on historical vehicle order data of each station in the target area and historical environmental information of the target area; determining multiple associated stations from each station, and integrating the vehicle order prediction data of each station based on the multiple associated stations to obtain integrated vehicle order prediction data; calculating the number of missing vehicles or the number of backlogged vehicles at each target station based on the current number of vehicles and the current vehicle reservation data of each target station, and the integrated vehicle order prediction data; determining a vehicle scheduling plan for the target area based on the historical operation and maintenance scheduling data of the target area and the number of missing vehicles or the number of backlogged vehicles at each target station.

[0060] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0061] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for 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.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A shared vehicle dispatching method, characterized in that: include: Obtaining current vehicle order data of each station in the target area and current environmental information of the target area; Inputting the current vehicle order data of each site and the current environmental information into a pre-trained prediction model to obtain the vehicle order prediction data of each site output by the prediction model, wherein the prediction model is trained based on the historical vehicle order data of each site in the target area and the historical environmental information of the target area; Determine a plurality of associated sites from the sites, and integrate the vehicle order forecast data of the sites based on the plurality of associated sites to obtain integrated vehicle order forecast data; Calculate the number of missing vehicles or the number of backlogged vehicles at each target station according to the current number of vehicles and current vehicle reservation data at each target station, as well as the integrated vehicle order forecast data; A vehicle dispatching plan for the target area is determined according to the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station.

2. The shared vehicle dispatching method according to claim 1, characterized in that: The determining of a plurality of associated sites from the sites includes: Determining a plurality of associated sites from the sites according to the binding information input by the user; According to the distances between the sites and the vehicle order prediction data of the sites, a plurality of associated sites are determined from the sites.

3. The shared vehicle dispatching method according to claim 1, characterized in that: The vehicle order forecast data of each site includes: the vehicle order forecast data of each site at the daily level and the vehicle order forecast data of each site at the hourly level; the current environmental information includes the current date information and the current climate information.

4. The shared vehicle dispatching method according to claim 1, characterized in that: The calculation of the number of missing vehicles or the number of accumulated vehicles at each target station includes: Determine, based on the integrated vehicle order forecast data, the forecast number of vehicles entering and transferring out of each target station per hour in the future, and the forecast number of vehicles entering and transferring out of each target station in the future day; Calculate the initial number of vehicles missing at each target station based on the current number of vehicles at each target station and the current vehicle reservation data, as well as the predicted number of vehicles entering and transferring out of each target station every hour in the future; According to the predicted number of vehicles entering and transferring out of each target station in the next day, the initial number of vehicles missing at each target station is corrected to obtain the number of vehicles missing at each target station.

5. The shared vehicle dispatching method according to claim 1, characterized in that: Determining the vehicle dispatching scheme for the target area according to the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station includes: Determine the dispatching route corresponding to each target site according to the historical operation and maintenance dispatching data of the target area and the distance between each target site; Determine the dispatching task volume corresponding to each target station and the dispatching priority corresponding to each target station according to the number of missing vehicles or accumulated vehicles at each target station and the average dispatching task volume of the target area in the previous few days; A vehicle dispatching plan for the target area is determined according to the dispatching routes, dispatching task volumes and dispatching priorities corresponding to the target sites.

6. The shared vehicle dispatching method according to any one of claims 2 to 5, characterized in that: The method further comprises: According to the vehicle dispatching plan of the target area, multiple shared vehicles in the target area are dispatched, and the vehicle dispatching effect of the target area is evaluated; The parameters of the prediction model are optimized according to the vehicle dispatching effect in the target area.

7. The shared vehicle dispatching method according to claim 1, characterized in that: The training process of the prediction model includes: Obtaining historical vehicle order data of each site on the i-th day and historical vehicle order data of each site on the i+1-th day, as well as historical environmental information of the target area on the i-th day; Inputting the historical vehicle order data of each site on the i-th day and the historical environmental information of the i-th day into the initial prediction model, obtaining the vehicle order prediction data of each site on the i+1-th day output by the initial prediction model; Calculate the loss function value according to the historical vehicle order data of each site on the i+1th day and the vehicle order forecast data on the i+1th day; According to the loss function value, the parameters of the initial prediction model are iteratively optimized to obtain the prediction model.

8. A shared vehicle dispatching device, characterized in that: include: An acquisition unit, used to acquire current vehicle order data of each station in a target area, and current environment information of the target area; A prediction unit, used for inputting the current vehicle order data of each station and the current environmental information into a pre-trained prediction model to obtain the vehicle order prediction data of each station output by the prediction model, wherein the prediction model is trained based on the historical vehicle order data of each station in the target area and the historical environmental information of the target area; an integration unit, configured to determine a plurality of associated sites from the sites, and integrate the vehicle order forecast data of the sites based on the plurality of associated sites to obtain integrated vehicle order forecast data; A calculation unit, used to calculate the number of missing vehicles or the number of backlogged vehicles at each target station according to the current number of vehicles and current vehicle reservation data at each target station and the integrated vehicle order forecast data; The determination unit is used to determine the vehicle dispatching plan of the target area according to the historical operation and maintenance dispatching data of the target area and the number of missing vehicles or the number of accumulated vehicles at each target station.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the shared vehicle scheduling method as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the shared vehicle scheduling method as described in any one of claims 1 to 7 is implemented.

Images