A car rental management system and method

Abstract

An embodiment of this specification provides a car rental management system. The system includes a cloud platform, and the cloud platform includes at least one server, which is configured to be communicatively connected to an in-vehicle communication unit of a vehicle, a service system at a dispatching point, and a mobile terminal of a user. The cloud platform is configured to: obtain vehicle operation information of the vehicle through the in-vehicle communication unit; obtain dispatching point information of the dispatching point through the service system at the dispatching point; read operation data from a database; determine a target dispatching vehicle based on the vehicle operation information and the operation data of the vehicle; generate a dispatching strategy based on the vehicle operation information and the dispatching point information of the target dispatching vehicle; and generate recommended dispatching information for the target dispatching vehicle based on the dispatching strategy, and send the recommended dispatching information to a display device of the vehicle and / or send the recommended dispatching information to the mobile terminal of the user.

Description

Technical Field

[0001] This specification relates to the technical field of vehicle rental, and particularly to a car rental management system and method. Background Art

[0002] With the development of the transportation industry, it has become increasingly common for people to rent vehicles from rental companies, which is also a common way for people to travel. Rental companies have a large number of cars for rent and rental points. The rental companies need to overall manage all cars, including those rented out and those not rented out, in order to keep real-time track of all information of the vehicles and reasonably schedule the vehicles when needed, so as to improve the car-using experience of all car rental users.

[0003] Therefore, it is hoped that a car rental management system and method can be provided to improve the car-using experience of car rental users. Summary of the Invention

[0004] One or more embodiments of this specification provide a car rental management system. The system includes a cloud platform, the cloud platform includes at least one server, and the cloud platform is configured to be communicatively connected to the in-vehicle communication unit of the vehicle, the service system of the dispatching point, and the mobile terminal of the user. The cloud platform is configured to: obtain the vehicle operation information of the vehicle through the in-vehicle communication unit; obtain the dispatching point information of the dispatching point through the service system of the dispatching point; read operation data from the database; determine a target dispatching vehicle based on the vehicle operation information and the operation data of the vehicle; generate a dispatching strategy based on the vehicle operation information and the dispatching point information of the target dispatching vehicle; and generate recommended dispatching information for the target dispatching vehicle based on the dispatching strategy, and send the recommended dispatching information to the display device of the vehicle, and / or send the recommended dispatching information to the mobile terminal of the user.

[0005] One or more embodiments of this specification provide a car rental management method. The method includes: obtaining the vehicle operation information of the vehicle, the dispatching point information of the dispatching point, and operation data; determining a target dispatching vehicle based on the vehicle operation information and the operation data of the vehicle; generating a dispatching strategy based on the vehicle operation information and the dispatching point information of the target dispatching vehicle; and generating recommended dispatching information for the target dispatching vehicle based on the dispatching strategy, and sending the recommended dispatching information to the display device of the vehicle, and / or send the recommended dispatching information to the mobile terminal of the user.

[0006] One or more embodiments of this specification provide a car rental management device, including a processor, and the processor is used to execute the car rental management method.

[0007] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a car rental management method. Description of the Drawings

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail through the accompanying drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0009] Figure 1 is a schematic diagram of the modules of a car rental management system shown in some embodiments of this specification;

[0010] Figure 2 is an exemplary flowchart of a car rental management method shown in some embodiments of this specification;

[0011] Figure 3 is a schematic diagram of determining a scheduling strategy shown in some embodiments of this specification;

[0012] Figure 4 is an exemplary flowchart of determining a scheduling strategy shown in some embodiments of this specification. Detailed Embodiments

[0013] To more clearly illustrate the technical solutions of the embodiments of this specification, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein is a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0015] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 It is a module diagram of a car rental management system according to some embodiments of this specification.

[0018] Car rental companies have a large number of vehicles and rental points for rental. Car rental companies need to coordinate the management of all vehicles, including those that are rented out and those that are not. Car rental companies can obtain the operating status (speed, power, location) and order information of all vehicles in real time, so they can combine the information of all vehicles and dispatch the vehicles. For example, in the same area, there are multiple vehicles that need to be replaced, but the number of battery replacement stations and batteries is limited, and the locations are not the same. Car rental companies need to recommend a suitable battery replacement station for each vehicle, or recommend certain vehicles to go directly to the rental point to replace the vehicle, so as to achieve intelligent scheduling of vehicles and intelligent recommendation of battery replacement stations, thereby ensuring the car experience of all car rental users.

[0019] In some embodiments, the car rental company can implement the above vehicle management based on the car rental management system 100. Figure 1 As mentioned above, in some embodiments, the car rental management system 100 may include a cloud platform 110 .

[0020] The cloud platform 110 may also be referred to as a cloud computing platform, which provides computing, network, and storage capabilities based on services of hardware resources and software resources. Cloud computing platforms may include storage-type cloud platforms that focus on data storage, computing-type cloud platforms that focus on data processing, and comprehensive cloud computing platforms that take both computing and data storage processing into account. In some embodiments, the cloud platform 110 may include at least one server 111. In some embodiments, the cloud platform 110 may also include a database ( Figure 1 Not shown in the figure), used to store operational data in the process of car rental management.

[0021] In some embodiments, the cloud platform 110 may be connected to a number of external systems or modules in a communication manner, and the communication connection may be wireless or wired. For example, the cloud platform 110 may be configured to be connected to a vehicle-mounted communication unit 210, a service system 220 at a dispatch point, and a user's mobile terminal 230 in a communication manner.

[0022] In some embodiments, the cloud platform 110 may be configured to obtain the vehicle operation information of a vehicle through the in-vehicle communication unit 210 of the vehicle, obtain the dispatching point information of a dispatching point through the service system 220 of the dispatching point, read operation data from a database, determine a target dispatching vehicle based on the vehicle operation information and operation data of the vehicle, generate a dispatching strategy based on the vehicle operation information and dispatching point information of the target dispatching vehicle, and generate recommended dispatching information for the target dispatching vehicle based on the dispatching strategy and send the recommended dispatching information to the display device of the vehicle and / or send it to the mobile terminal of the user. Among them, the dispatching strategy may include dispatching parameters for each target dispatching vehicle. For more content about the dispatching strategy, reference can be made to Figure 2 the relevant description.

[0023] The in-vehicle communication unit 210 can be used for communication between the vehicle and the cloud platform 110. For example, the cloud platform 110 can be communicatively connected to the in-vehicle communication unit 210 to obtain the vehicle operation information of the vehicle.

[0024] The service system 220 of the dispatching point can be a computing device such as a computer at the dispatching point. The cloud platform 110 can be communicatively connected to the service system 220 to obtain the dispatching point information of the dispatching point.

[0025] The mobile terminal 230 may refer to one or more terminal devices or software used by the user. In some embodiments, the mobile terminal 230 may be a mobile device, a tablet computer, a laptop computer, etc. or any combination thereof. In some embodiments, the cloud platform 110 can be communicatively connected to the mobile terminal 230. The cloud platform 110 can send the recommended dispatching information of the target dispatching vehicle to the mobile terminal 230 of the user.

[0026] In some embodiments, the car rental management system 100 may further include a traffic data acquisition module 120.

[0027] In some embodiments, the traffic data acquisition module 120 may be configured to acquire traffic data of a target area. In some embodiments, the traffic data acquisition module 120 can be communicatively connected to the cloud platform 110 to process the traffic data.

[0028] Some embodiments of this specification also provide a car rental management device. In some embodiments, the car rental management device may include at least one processor and at least one memory. The memory can be used to store computer instructions, and at least one processor can be used to execute at least part of the computer instructions to implement the car rental management method.

[0029] Some embodiments of this specification also provide a computer-readable storage medium. In some embodiments, the storage medium may store computer instructions, which can implement the car rental management method when executed by a processor.

[0030] It should be understood that Figure 1 the systems and their modules shown can be implemented in various ways. For example, in some embodiments, Figure 1 the systems and their modules shown can be jointly or independently executed by a computing device using two different CPUs and / or processors.

[0031] It should be noted that the above description of the car rental management system and its modules is only for convenience of description and does not limit this specification to the scope of the examples given. It can be understood that for those skilled in the art, after understanding the principle of the system, they may, without departing from this principle, make any combination of the various modules, or form a subsystem and connect it with other modules. In some embodiments, Figure 1 the cloud platform 110 and the traffic data acquisition module 120 disclosed in may be different modules in a system, or a module may implement the functions of two or more of the above modules. For example, the various modules may share a storage module, or each module may have its own storage module. Such variations are all within the protection scope of this specification.

[0032] Figure 2 is an exemplary flowchart of the car rental management method shown in some embodiments of this specification. As Figure 2 shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by the cloud platform 110.

[0033] Step 210, obtain the vehicle operation information of the vehicle, the dispatching point information of the dispatching point, and the operation data.

[0034] The vehicle operation information may refer to information related to vehicle operation. In some embodiments, the vehicle operation information may include vehicle speed, vehicle location, vehicle load, vehicle battery type, vehicle battery health, vehicle battery information (such as remaining power, battery temperature, etc.), vehicle equipment working status (such as whether devices such as air conditioners and stereos are turned on, and the on position, etc.).

[0035] Among them, the health status of the vehicle battery can usually be obtained through the Battery Management System (BMS) and transmitted to the cloud platform 110 based on the vehicle-mounted communication unit 210. For example, the BMS can monitor the status of the vehicle battery, including but not limited to voltage, current, temperature, State of Charge (SOC), etc., and can estimate the State of Health (SOH) of the battery based on this data. The SOH can be expressed as a percentage based on the capacity of a new battery.

[0036] For the relevant content regarding the working status of vehicle equipment, reference can be made to the relevant description in step 420.

[0037] In some embodiments, the vehicle may refer to vehicles within the target area, which may include electric vehicles, hybrid electric vehicles, etc. The target area can be the entire dispatching area or a partial area within the dispatching area, such as a designated area, etc.

[0038] A dispatching point refers to a location where a user can replace the vehicle battery or the vehicle. For example, the dispatching point can include a battery swapping station or a car rental point, etc.

[0039] Dispatching point information refers to information related to the dispatching point. In some embodiments, the dispatching point information may include battery swapping station information and car rental point information. Among them, the battery swapping station information refers to information related to the battery swapping station, and the car rental point information refers to information related to the car rental point.

[0040] The battery swapping station information can include the location data of the battery swapping station, the number of available batteries, the number of queuing vehicles, the battery type, the consumption duration, the reservation information, etc.; the car rental point information can include the number of available vehicles at the car rental point, the consumption duration, the vehicle type information of the available vehicles (such as the battery level, vehicle type), the reservation information, etc. Among them, the consumption duration refers to the time taken for the target dispatching vehicle to enter and leave the battery swapping station or the car rental point. The reservation information refers to the information that the user reserves on the mobile terminal to replace the battery at the battery swapping station or replace the vehicle at the car rental point.

[0041] The operation data can include user information and order information. In some embodiments, the operation data can be obtained from the database configured on the cloud platform.

[0042] The user information can include the credit rating, car rental frequency, preferred vehicle models, etc.

[0043] The order information can include the status of the car rental order (such as reservation, pick-up, return), the car rental duration, the return location, the order rating, etc.

[0044] In some embodiments, the cloud platform 110 may obtain the vehicle operation information of the vehicle, the dispatching point information of the dispatching point, and the operation data.

[0045] In some embodiments, the cloud platform 110 may obtain the vehicle operation information of the vehicle through the in-vehicle communication unit 210 of the vehicle, obtain the dispatching point information of the dispatching point through the service system 220 of the dispatching point, and obtain the operation data from the database. For more descriptions of the cloud platform 110, the in-vehicle communication unit 210, the service system 220, and the database, reference can be made to Figure 1 the relevant descriptions.

[0046] Step 220, determine the target dispatching vehicle based on the vehicle operation information and operation data of the vehicle.

[0047] The target dispatching vehicle refers to a vehicle that needs to replace the vehicle battery or the vehicle. For example, a vehicle with a battery power less than the power threshold and a remaining return time greater than the time threshold.

[0048] In some embodiments, the cloud platform 110 may determine the target dispatching vehicle based on the vehicle operation information and operation data of the vehicle.

[0049] In some embodiments, the cloud platform 110 may determine the candidate dispatching vehicle based on the vehicle operation information and operation data of the vehicle, predict the predicted power consumption rate of the candidate dispatching vehicle based on the historical vehicle operation information and environmental data of the candidate dispatching vehicle, and determine the target dispatching vehicle based on the predicted power consumption rate corresponding to the candidate dispatching vehicle.

[0050] The candidate dispatching vehicle may refer to a vehicle that is preliminarily judged to have a replacement requirement or a battery replacement requirement.

[0051] The historical vehicle operation information of the candidate dispatching vehicle refers to the operation information of the candidate dispatching vehicle at historical times. For example, historical vehicle speed, historical vehicle location, historical vehicle load, historical vehicle battery type, historical vehicle battery health, historical vehicle battery information, historical vehicle equipment working status, etc. The historical time may be a preset time or a preset time length, for example, historical one week or historical 72 hours, etc.

[0052] In some embodiments, the cloud platform 110 may determine the candidate dispatching vehicle based on the vehicle operation information and operation data of the vehicle. For example, a vehicle with a battery power less than the power threshold and a remaining return time greater than the time threshold may be determined as the candidate dispatching vehicle. Among them, the power threshold may be negatively correlated with the load level of the dispatching point in the target area.

[0053] The load level of a dispatching point can be determined based on relevant information of the dispatching point. For example, the load level of a dispatching point is related to the number of available batteries, the number of available vehicles, the number of reserved vehicles, the number of queuing vehicles, etc. within the dispatching point. By way of example only, if the number of available batteries within the dispatching point is less, the number of available vehicles is less, the number of reserved vehicles is less, and the number of queuing vehicles is more (the slower the battery / vehicle replacement speed), it indicates that the load level of the dispatching point is greater. The specific correspondence between the load level of the dispatching point and the relevant information of the dispatching point can be determined by looking up a table.

[0054] In some embodiments, the load level of the dispatching points within the target area can be determined based on the statistical values of the load levels of each dispatching point within the target area. For example, the mean value, extreme value, weighted value, etc. of the load levels of each dispatching point can be used as the load level of the dispatching points within the target area.

[0055] In some embodiments, the cloud platform 110 can determine the power confidence level of the vehicle battery based on the historical charge and discharge records, historical battery temperature, battery health level, and battery type of the vehicle battery; and determine candidate dispatching vehicles based on the power confidence level.

[0056] The historical charge and discharge records refer to the data related to the historical charging and discharging of the vehicle at historical times. For example, the power, voltage, current, and time of each charge / discharge.

[0057] The historical battery temperature refers to the historical data of the battery temperature.

[0058] The battery health level is the data reflecting the health state of the battery.

[0059] The battery type refers to different types of batteries, such as ternary lithium batteries and lithium iron phosphate batteries.

[0060] In some embodiments, the historical charge and discharge records, historical battery temperature, battery health level, and battery type can be stored in a database, and the cloud platform 110 can read these data by reading the battery number.

[0061] The power confidence level can reflect the probability of the battery having false power. For example, if the vehicle shows that the remaining power is 30%, but the actual power of the battery is only 20%, then the battery has false power. When the power confidence level is higher, the probability of the battery having false power is lower, that is, the reliability of the current vehicle power (i.e., the displayed power) is higher. When the battery has false power, the current vehicle power can be corrected based on the power confidence level to obtain the corrected vehicle power, that is, the actual power of the vehicle. For example, the corrected vehicle power = the current vehicle power * the power confidence level.

[0062] The power confidence level can be determined based on historical charge and discharge records, historical battery temperature, battery health condition, and battery type. For example, a virtual power feature vector (a0, b0, c0, t0) can be constructed based on historical charge and discharge records, historical battery temperature, battery health condition, and battery type, and then the power confidence level can be determined through a first vector database based on the virtual power feature vector.

[0063] The first vector database stores a number of historical vectors and the power confidence levels corresponding to each historical vector. The historical vectors can be constructed based on the historical charge and discharge records, historical battery temperature, battery health condition, and battery type of historical vehicles. The power confidence level corresponding to a historical vector refers to the power confidence level of the displayed power of the historical vehicle in the situation corresponding to the historical vector. This power confidence level can be determined based on the actual power of the historical vehicle. For example, the actual power of the historical vehicle can be obtained through multiple power test methods, and the power confidence level of the displayed power can be obtained based on the ratio of the actual power to the displayed power.

[0064] The cloud platform 110 can use the historical vector with the smallest vector distance or a vector distance less than the distance threshold from the virtual power feature vector as a reference vector, and use the power confidence level of the reference vector as the power confidence level of the virtual power feature vector.

[0065] In some embodiments, the cloud platform 110 can determine a corrected vehicle power based on the power confidence level, and then determine the vehicles with a corrected vehicle power less than the power threshold and a distance from the return time greater than the time threshold as candidate dispatching vehicles.

[0066] Environmental data refers to the relevant data of the environment where the candidate dispatching vehicle is located. The environmental data can include data such as temperature and humidity. The environmental data can be determined based on corresponding sensors on the vehicle or by obtaining user input, etc.

[0067] The predicted power consumption rate can be the predicted power consumed by the candidate dispatching vehicle per kilometer of travel.

[0068] In some embodiments, the cloud platform 110 can determine the predicted power consumption rate based on multiple methods. For example, the predicted power consumption rate can be the average historical power consumption rate of the candidate dispatching vehicle.

[0069] In some embodiments, the predicted power consumption rate can also be determined based on historical vehicle operation information, environmental data, and the working state of vehicle devices. In some embodiments, the cloud platform 110 can construct a power consumption feature vector (a1, b1, c1) based on the historical vehicle battery information, environmental data, and the working state of vehicle devices of the candidate dispatching vehicle, and determine the predicted power consumption rate of the candidate dispatching vehicle by querying the second vector database based on the power consumption feature vector. Among them, the working state of vehicle devices can be the working state of devices on the vehicle that consume power, such as in-vehicle air conditioners, in-vehicle monitors, etc. The working state of vehicle devices can include parameters such as on, off, and working power.

[0070] The method for determining the predicted power consumption rate based on vector retrieval is similar to the method for determining the power confidence level based on vector retrieval. Among them, the predicted power consumption rate corresponding to the historical vector in the second vector database is the actual power consumption rate of the historical vehicle under the conditions corresponding to the historical vector (i.e., the historical vehicle under the historical vehicle battery information, historical environmental data, and historical vehicle device working state), which can be obtained through various battery performance test methods.

[0071] In some embodiments, the predicted power consumption rate is also related to traffic data. In some embodiments, the cloud platform 110 can adjust the predicted power consumption rate based on traffic data.

[0072] Traffic data can include the current vehicle positions and quantities on each road, the positions and states of traffic lights (e.g., red light / green light), and whether there are traffic obstacles such as construction.

[0073] Traffic data can be obtained by connecting the traffic data module to the real-time traffic information interface provided by the urban traffic management center. For example, the intelligent transportation system (ITS) equipped in the city. Traffic data can also be obtained from a third party, such as a third-party map APP.

[0074] In some embodiments, the cloud platform 110 can determine the power consumption increase amplitude based on traffic data and adjust the predicted power consumption rate based on the power consumption increase amplitude. The power consumption increase amplitude refers to the increase amplitude of the power consumption rate. For example, when the congestion degree in the area where the vehicle is located (e.g., within a radius of 3 km centered on the vehicle) is relatively high (such as greater than the preset congestion level), the vehicle may start and stop frequently, resulting in an increase in power consumption, that is, an increase in the power consumption rate.

[0075] In some embodiments, the power consumption increase amplitude can be predicted through a prediction function / algorithm. Among them, the prediction function / algorithm can be obtained by fitting based on historical data. The historical data can include the historical data of the vehicle itself or the historical data of multiple other vehicles.

[0076] For example, set the power consumption increase prediction function f1: y = a * x1 + b * x2 + c * x3, where a, b, and c are coefficient parameters respectively; x1 is the traffic congestion degree in the area where the candidate dispatching vehicle is located, x2 is the battery health degree, x3 represents the vehicle load, and y is the power consumption increase; use the fitting algorithm to fit the above large amount of historical data to obtain the coefficients a, b, and c, so as to obtain the power consumption increase prediction function; based on the current traffic congestion degree, battery health degree, and vehicle load of the candidate dispatching vehicle, determine the power consumption increase through this function.

[0077] Among them, the traffic congestion degree can be obtained based on traffic data. For example, if the number of vehicles in a certain road / area is larger, the distance between vehicles is closer, the average speed of vehicles is slower, and the number of traffic lights is larger, the traffic congestion degree is greater. The battery health degree and vehicle load can be determined based on obtaining vehicle information.

[0078] In some embodiments, the predicted power consumption rate can be adjusted based on the following method: the adjusted predicted power consumption rate = the predicted power consumption rate + the predicted power consumption rate * the power consumption increase.

[0079] In some embodiments, the cloud platform can determine the target dispatching vehicle in various ways based on the predicted power consumption rate or the adjusted predicted power consumption rate corresponding to the candidate dispatching vehicle. For example, the cloud platform can determine the candidate dispatching vehicle with the predicted power consumption rate or the adjusted predicted power consumption rate greater than the consumption threshold as the target dispatching vehicle.

[0080] Among them, the consumption threshold is positively correlated with the number of dispatching points in the area where the candidate dispatching vehicle is located (for example, within a range of 3 km centered on the vehicle).

[0081] The car rental management method provided by some embodiments of this specification predicts the predicted power consumption rate of the candidate dispatching vehicle based on the historical vehicle operation information and environmental data of the candidate dispatching vehicle, so as to accurately identify the vehicles in need of battery replacement or vehicle replacement, and recommend suitable dispatching points for users, improving the user's car rental experience.

[0082] Step 230, generate a dispatching strategy based on the vehicle operation information and dispatching point information of the target dispatching vehicle.

[0083] The dispatching strategy can be composed of the dispatching parameters of each target dispatching vehicle. The dispatching parameter refers to the dispatching point corresponding to each target dispatching vehicle, that is, the position where each target dispatching vehicle performs battery replacement or vehicle replacement. For example, the dispatching strategy can be expressed as [(target dispatching vehicle 1, dispatching point 3), (target dispatching vehicle 2, dispatching point 5)].

[0084] In some embodiments, the cloud platform 110 may generate a scheduling policy based on the vehicle operation information and scheduling point information of the target scheduling vehicle. For example, for each target scheduling vehicle, the cloud platform 110 may find the scheduling point closest to the target scheduling vehicle among the currently available scheduling points as the scheduling point corresponding to the target scheduling vehicle determined in the scheduling policy. Among them, an available scheduling point refers to a scheduling point where there are available batteries or available vehicles, and the number of queued vehicles + the number of reserved vehicles < the number of vehicles corresponding to the available batteries + the number of available vehicles.

[0085] In some embodiments, the cloud platform 110 may also determine the priority of each target scheduling vehicle when determining the scheduling point based on the ratio of the current vehicle battery level to the battery level confidence of the target scheduling vehicle. For example, for a target scheduling vehicle with a smaller ratio of the current vehicle battery level to the battery level confidence, the cloud platform 110 determines its corresponding scheduling point with higher priority.

[0086] In some embodiments, the cloud platform 110 may determine a candidate scheduling policy based on the scheduling point information and vehicle operation information; determine the user satisfaction and battery loss degree of the candidate scheduling policy based on the candidate scheduling policy; and determine the scheduling policy based on the user satisfaction, battery loss degree, and the candidate scheduling policy. For specific descriptions, see Figure 3 and its related descriptions.

[0087] Step 240, generate recommended scheduling information for the target scheduling vehicle based on the scheduling policy, and send the recommended scheduling information to the display device of the vehicle and / or send it to the mobile terminal of the user.

[0088] The recommended scheduling information refers to the information related to the scheduling policy recommended for the target scheduling vehicle. For example, the scheduling point corresponding to the target scheduling vehicle, etc.

[0089] In some embodiments, the cloud platform 110 may generate recommended scheduling information for the target scheduling vehicle based on the scheduling policy, and send the recommended scheduling information to the display device of the vehicle and / or send it to the user's mobile terminal 230.

[0090] In some embodiments, after the cloud platform 110 sends the recommended scheduling information to the user's mobile terminal 230, the user can make a reservation according to the recommended scheduling information.

[0091] The car rental management method provided in some embodiments of this specification determines the target scheduling vehicle and combines the vehicle operation information and scheduling point information of the target scheduling vehicle, thereby recommending a suitable scheduling point for the user and ensuring the car - using experience of car - rental users.

[0092] Figure 3 is a schematic diagram of determining a scheduling policy shown in some embodiments of this specification.Figure 4 is an exemplary flowchart for determining a scheduling strategy as shown in some embodiments of this specification. As Figure 4 shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by cloud platform 110.

[0093] Step 410, determine a candidate scheduling strategy based on scheduling point information and vehicle operation information.

[0094] A candidate scheduling strategy refers to a scheduling strategy formed by randomly allocating target scheduling vehicles to each alternative scheduling point. An alternative scheduling point refers to an idle scheduling point. For example, an alternative scheduling point has available batteries or available vehicles, and the number of queuing vehicles at this scheduling point is less than the sum of the number of vehicles corresponding to the available batteries and the number of available vehicles.

[0095] In some embodiments, cloud platform 110 may determine candidate scheduling strategy 303 based on scheduling point information 301 and vehicle operation information 302.

[0096] In some embodiments, a candidate scheduling strategy may be formed by randomly allocating target scheduling vehicles to each alternative scheduling point.

[0097] Among them, the distance between the alternative scheduling point allocated to the target scheduling vehicle and the target scheduling vehicle is less than the maximum driving distance of the target scheduling vehicle. The maximum driving distance refers to the maximum distance that the target scheduling vehicle can still drive, which can be obtained from the remaining power of the target scheduling vehicle / predicted power consumption rate. For example, with the target scheduling vehicle as the center and the maximum driving distance of the target scheduling vehicle as the radius, all alternative scheduling points within the formed circle can participate in the allocation.

[0098] When allocating a target scheduling vehicle to a certain alternative scheduling point, it should also be considered whether the alternative scheduling point is overloaded. If the allocation will not overload the alternative scheduling point, the allocation can continue; if the allocation will overload the alternative scheduling point, other alternative scheduling points need to be found for allocation. An alternative scheduling point is overloaded when the sum of the number of allocated vehicles, the number of queuing vehicles, and the number of reserved vehicles at this alternative scheduling point is greater than the sum of the number of available batteries and the number of available vehicles at this alternative scheduling point.

[0099] When the alternative scheduling point is a battery swapping station or a car rental point, the target scheduling vehicle is preferentially allocated to the alternative scheduling point that is a battery swapping station. If an alternative scheduling point can be used as both a battery swapping point and a car rental point, it is preferentially used as a battery swapping point to participate in the allocation.

[0100] In some embodiments, the cloud platform 110 may predict the predicted load data of a scheduling point at a future time point based on historical scheduling point information, holiday information, traffic data, and future weather data; determine a preliminary scheduling point based on the predicted load data and load threshold parameters; and determine a candidate scheduling strategy based on the preliminary scheduling point, the scheduling point information of the preliminary scheduling point, and vehicle operation information.

[0101] The predicted load data includes the predicted number of queuing vehicles, reserved vehicle data, available battery quantity, and available vehicle data of the scheduling point at multiple future time points. The multiple future time points may be preset. For example, the next 24 hours, the next 3 days, etc.

[0102] In some embodiments, the predicted load data may be obtained through a load prediction model. The load prediction model may be a model for determining the predicted load data of a scheduling point and may be a machine learning model or a custom model.

[0103] In some embodiments, the inputs of the load prediction model may include historical scheduling point information, holiday information, traffic data, and future weather data, and the output of the load prediction model may be the predicted load data of the scheduling point.

[0104] The future weather data refers to the weather data at a future time point. For example, future temperature, future humidity, precipitation, weather type (such as foggy day, thunderstorm), etc.

[0105] The holiday information includes whether the current time point belongs to a holiday and the type of holiday.

[0106] The parameters of the load prediction model may be obtained through training. In some embodiments, the load prediction model may be trained based on multiple first training samples with first labels. For example, multiple first training samples with first labels may be input into an initial load prediction model, a loss function may be constructed through the first labels and the prediction results of the initial load prediction model, the parameters of the initial load prediction model may be iteratively updated based on the loss function, and when the loss function of the initial load prediction model meets a preset condition, the model training is completed. The preset condition may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0107] In some embodiments, the first training sample may include sample historical scheduling point information, sample holiday information, sample traffic data at a first historical time point, and sample weather data at a second historical time point, and the first label may be the scheduling point load data actually collected at the second historical time point of the scheduling point. In some embodiments, the first training sample may be obtained based on historical data, and the first label may be obtained based on manual annotation. The first historical time point is before the second historical time point.

[0108] The load threshold parameter refers to the maximum number of target scheduling vehicles that a scheduling point can receive in a future period of time. It can be determined by presetting. The load threshold parameter may include a first load threshold and a second load threshold. The first load threshold is greater than the second load threshold.

[0109] In some embodiments, the load threshold parameter may also be related to the degree of traffic congestion. For example, the greater the degree of traffic congestion, the smaller the load threshold parameter (the first threshold parameter, the second threshold parameter). The load threshold parameter can be obtained by looking up a table. For more information on calculating the degree of traffic congestion, reference can be made to Figure 2 the relevant description.

[0110] A preliminary scheduling point refers to a scheduling point where there is an available battery or a replaceable vehicle when the target scheduling vehicle arrives in the future. For example, based on the predicted load data of the scheduling point, the scheduling points can be classified, such as busy scheduling points, general scheduling points, and idle scheduling points. Among them, the general scheduling points and the idle scheduling points are determined as preliminary scheduling points.

[0111] The classification method of scheduling points includes: calculating the load degree of each scheduling point at multiple future time points based on the predicted load data; if the future average load degree of a certain scheduling point (i.e., the mean value of the load degrees at multiple future time points) is greater than the first load threshold, then it is considered that the scheduling point is a busy scheduling point; if the future average load degree of a certain scheduling point is lower than the second load threshold, then it is considered that the scheduling point is an idle scheduling point; if the future average load degree of a certain scheduling point is between the first load threshold and the second load threshold, then it is considered that the scheduling point is a general scheduling point. For more information on calculating the load degree, reference can be made to Figure 2 the relevant description.

[0112] In some embodiments, the candidate scheduling strategy can be generated by randomly allocating the target scheduling vehicles to each preliminary scheduling point.

[0113] The car rental management method provided in some embodiments of this specification considers the predicted load data of the scheduling point at the future time point when determining the candidate scheduling strategy, avoiding the situation that there is no available battery / vehicle for use when the target scheduling vehicle arrives at the scheduling point at the future time point, thereby recommending a suitable scheduling point for the target scheduling vehicle.

[0114] Step 420, based on the candidate scheduling strategy, determine the user satisfaction and battery loss degree of the candidate scheduling strategy.

[0115] User satisfaction refers to the degree of satisfaction of each user of the target scheduling vehicle with the candidate scheduling strategy. For example, if the estimated arrival time at the scheduling point is shorter and the driving distance is shorter, the user satisfaction is higher. User satisfaction can be determined in various ways, such as by looking up a table or obtaining user feedback, etc.

[0116] The battery loss degree refers to the additional loss of the battery caused by the operation of the target scheduling vehicle under non-healthy battery levels. The non-healthy battery level can be a preset value such as 20% of the total battery level.

[0117] In some embodiments, the cloud platform 110 can determine the user satisfaction and battery loss degree of the candidate scheduling strategy based on the candidate scheduling strategy.

[0118] In some embodiments, the cloud platform 110 can, based on the candidate scheduling strategy 303, the target area map information 304, the current environmental data 305, the future weather data 306, and the vehicle equipment working status 307, reach the prediction layer 308-1 of the prediction model 308 to determine the predicted arrival time series 309 and the predicted vehicle battery information series 311; based on the driving distance series 312 corresponding to the candidate scheduling strategy, the predicted arrival time series 309, the predicted vehicle battery information series 311, and the current battery health level 313, pass through the health prediction layer 308-2 of the prediction model 308 to determine the vehicle battery loss degree series 314.

[0119] The target area map information refers to the map of the target area obtained in real time. For example, the electronic map of the target area obtained in real time.

[0120] The current environmental data refers to the relevant information of the environment where the target scheduling vehicle is currently located.

[0121] The future weather data refers to the weather data at future time points.

[0122] The vehicle equipment working status refers to the working status of the equipment inside the target scheduling vehicle. For example, whether the air conditioner is turned on, whether the audio is turned on, and the corresponding equipment gear (i.e., the equipment power) when turned on.

[0123] The prediction model 308 can be a machine learning model for determining information such as the predicted arrival time series, the predicted vehicle battery information series, and the vehicle battery loss degree series, or other custom models.

[0124] In some embodiments, the prediction model can include a reach prediction layer 308-1 and a health prediction layer 308-2.

[0125] The reach prediction layer 308-1 can be a model for extracting the predicted arrival time series and the predicted vehicle battery information series. For example, the reach prediction layer can be a recurrent neural network (RNN) model.

[0126] The health prediction layer 308-2 can be a model for extracting the vehicle battery loss degree series. For example, the health prediction layer can be a deep neural network (DNN) model.

[0127] In some embodiments, the inputs to the arrival prediction layer 308-1 may include the candidate scheduling policy 303, the target area map information 304, the current environmental data 305, the future weather data 306, and the vehicle equipment working status 307. The outputs of the arrival prediction layer 308-1 may be the predicted arrival time series 309 and the predicted vehicle battery information series 311.

[0128] The predicted arrival time series refers to the series formed by the predicted arrival times of each target scheduling vehicle under the candidate scheduling policy 303. The arrival time refers to the time when the target scheduling vehicle arrives at its corresponding scheduling point.

[0129] The predicted vehicle battery information series refers to the series formed by the predicted vehicle battery information of each target scheduling vehicle at future time points. The vehicle battery information may include the remaining power, battery temperature, etc.

[0130] In some embodiments, the inputs to the health prediction layer 308-2 may include the driving distance series 312 corresponding to the candidate scheduling policy, the predicted arrival time series 309, the predicted vehicle battery information series 311, and the current battery health level 313. The output of the health prediction layer 308-2 may be the vehicle battery degradation degree series 314.

[0131] The driving distance series refers to the series formed by the driving distances between each target scheduling vehicle and its corresponding scheduling point.

[0132] Regarding the content of the battery health level, reference can be made to Figure 2 and its related descriptions.

[0133] The vehicle battery degradation degree series refers to the series formed by the predicted vehicle battery degradation degrees of each target scheduling vehicle after driving (such as after vehicle replacement or return). The vehicle battery degradation degree can be obtained by subtracting the battery health level collected after driving from the sample battery health level. The sample battery health level can be the average value or the initial preset value of the vehicle's battery health level, etc.

[0134] The prediction model 308 can be obtained by separately training the arrival prediction layer 308-1 and the health prediction layer 308-2.

[0135] The parameters of the arrival prediction layer 308-1 can be obtained through training. In some embodiments, the arrival prediction layer 308-1 can be trained based on the second training samples and the second labels. The specific content of the training method can be referred to the training of the load prediction model. In some embodiments, the second training samples may include the sample scheduling policy, the sample target area map information, the sample environmental data at the first historical time point, and the sample weather data at the second historical time point. The second labels may be the actually recorded arrival time series and the vehicle battery information series.

[0136] The parameters of the health prediction layer 308-2 can be obtained through training. In some embodiments, the health prediction layer 308-1 can be obtained by training based on the third training sample and the third label. For the specific content of the training method, reference can be made to the training of the load prediction model. In some embodiments, the third sample may include a sample driving distance sequence, a sample arrival time sequence, a sample vehicle battery information sequence, and a sample battery health level, and the third label may be the vehicle battery loss degree collected after driving ends.

[0137] In some embodiments, the time when the target scheduling vehicle arrives at the scheduling point and the power consumption rate of the target scheduling vehicle may also be related to traffic data.

[0138] In some embodiments, the input to the prediction layer may further include current traffic data and historical traffic data. The historical traffic data may be traffic data at a preset historical time point or time period. For more content about traffic data, reference can be made to the relevant description in step 220.

[0139] In some embodiments, the cloud platform 110 may also determine or adjust the user satisfaction based on the user's historical order information and the scheduling point information. For example, the user may determine a satisfaction correction value by looking up a table based on the average historical order score and the consumption duration at the scheduling point. Among them, the historical order score can be obtained from the historical order information. If the lower the average historical order score of the user and the longer the consumption duration at the scheduling point, the greater the satisfaction correction value.

[0140] In some embodiments, the user satisfaction can be adjusted based on the satisfaction correction value. For example, the adjusted user satisfaction = user satisfaction - satisfaction correction value.

[0141] Step 430, determine a scheduling strategy based on the user satisfaction, the battery loss degree, and the candidate scheduling strategies.

[0142] In some embodiments, the cloud platform 110 may determine the scheduling strategy 316 based on the user satisfaction 315, the battery loss degree, and the candidate scheduling strategies 303.

[0143] In some embodiments, the cloud platform 110 may determine the scheduling strategy of the target scheduling vehicle by calculating the scheduling effect score of each candidate scheduling strategy. For example, select a candidate scheduling strategy with the highest scheduling effect score as the scheduling strategy.

[0144] The scheduling effect score can also be referred to as the comprehensive score and can be determined in various ways. For example, the cloud platform can obtain the scheduling effect score of the candidate scheduling policy by performing a weighted sum of the mean of the user satisfaction corresponding to the candidate scheduling policy and the mean of the battery loss degree. By way of example only, the scheduling effect score of the candidate scheduling policy = α * mean of user satisfaction - β * mean of battery loss degree, where α and β respectively represent the weight coefficients of the importance of user satisfaction and battery loss degree.

[0145] In some embodiments, the determination of the scheduling policy may also be related to the adaptation value between the scheduling point and the target scheduling vehicle.

[0146] In some embodiments, the adaptation value can be determined based on the available battery quality of the scheduling point and the predicted power consumption rate of the target scheduling vehicle.

[0147] In some embodiments, when considering the adaptation value between the scheduling point and the target scheduling vehicle, the scheduling effect score of the candidate scheduling policy can be calculated by the following formula: scheduling effect score = α * mean of user satisfaction - β * mean of loss degree + δ * total adaptation value; where δ is the weight coefficient of the importance of the total adaptation value.

[0148] The available battery quality of the scheduling point can be determined by the battery charge confidence. For example, the higher the battery charge confidence, the higher the available battery quality. The average available battery quality of the scheduling point is obtained by averaging the available battery quality of all batteries at the scheduling point.

[0149] In some embodiments, the adaptation value can be determined based on the average available battery quality of the scheduling point and the predicted power consumption rate of the target scheduling vehicle. For example, the higher the predicted power consumption rate of the target scheduling vehicle, the higher the adaptation value to the scheduling point with high average available battery quality; conversely, the higher the adaptation value to the scheduling point with low average available battery quality. The adaptation value can be determined by looking up a table.

[0150] The total adaptation value can be obtained by taking the mean of the adaptation values of each target scheduling vehicle and its corresponding scheduling point.

[0151] In some embodiments, the determination of the scheduling policy may also be related to the usage ratio of idle scheduling points in the candidate scheduling policy. For example, the larger the usage ratio of idle scheduling points in the candidate scheduling policy, the lower the probability that the available batteries or replaceable vehicles at the scheduling point are insufficient, and the shorter the queuing time of the target scheduling vehicle. Therefore, when other conditions are the same, the target scheduling vehicle is preferentially assigned to the idle scheduling point.

[0152] The usage ratio of idle scheduling points refers to the ratio of the idle scheduling points used by the target scheduling vehicles in the candidate scheduling strategies to the total scheduling points in the candidate scheduling strategies. For example, the usage ratio of idle scheduling points = the number of vehicles assigned to idle scheduling points / the number of all target scheduling vehicles.

[0153] In some embodiments, when considering the usage ratio of idle scheduling points in the candidate scheduling strategies, the scheduling effect score of the candidate scheduling strategies can be calculated by the following formula: Scheduling effect score = α * the average value of user satisfaction - β * the average value of loss degree + γ * the usage ratio of idle scheduling points; where γ is the weight coefficient of the importance of the usage ratio of idle scheduling points.

[0154] The car rental management method provided by some embodiments of this specification can recommend a better scheduling strategy for the target scheduling vehicles more accurately by determining the user satisfaction degree of the candidate scheduling strategies and the battery loss degree of the target scheduling vehicles. At the same time, it also considers the user satisfaction degree, which can further improve the user car rental experience.

[0155] It should be noted that the above description of process 400 is only for illustration and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 400 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0156] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0157] At the same time, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be combined appropriately.

[0158] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numerical and alphabetical characters, or the use of other names described in this specification are not used to limit the order of the processes and methods in this specification. Although some currently useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details are only for illustrative purposes. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0159] Similarly, it should be noted that, in order to simplify the presentation of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, sometimes multiple features are grouped into one embodiment, drawing, or description thereof. However, this method of disclosure does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0160] In some embodiments, numbers are used to describe components and attribute quantities. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximate", or "substantially" in some examples. Unless otherwise stated, "about", "approximate", or "substantially" indicate that the stated number allows a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and these approximate values may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0161] For each patent, patent application, patent application publication, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification as references. Except for the application history documents that are inconsistent with or conflict with the content of this specification, and except for the documents that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0162] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly presented and described in this specification.

Claims

1. A car rental management system, comprising: The cloud platform includes at least one server configured to be communicatively connected with the vehicle-mounted communication unit of the vehicle, the service system of the dispatching point, and the mobile terminal of the user; A traffic data acquisition module is configured to acquire traffic data of a target area; The cloud platform is configured as follows: Obtaining vehicle operation information of the vehicle through the vehicle-mounted communication unit; the vehicle operation information includes vehicle speed, vehicle position, vehicle load, vehicle battery type, vehicle battery health, vehicle battery information and vehicle equipment working status; Obtaining dispatch point information of the dispatch point through a service system of the dispatch point; Reading operational data from a database; the operational data includes user information and order information, the user information includes credit rating, rental frequency, and preferred car model, and the order information includes the status of the rental order, rental duration, return location, and order score; Determining a target dispatch vehicle based on the vehicle operation information and the operation data of the vehicle; wherein determining a target dispatch vehicle based on the vehicle operation information and the operation data of the vehicle comprises: Determine the battery power confidence of the vehicle battery based on the historical charge and discharge records of the vehicle battery, the historical battery temperature, the health of the vehicle battery and the type of the vehicle battery; and determine the corrected vehicle power based on the power confidence, and determine the vehicle whose corrected vehicle power is less than the power threshold and whose time to return is greater than the time threshold as a candidate dispatch vehicle; Based on the historical vehicle operation information and environmental data of the candidate dispatch vehicle, the predicted power consumption rate of the candidate dispatch vehicle is predicted; and based on the traffic data, the power consumption increase is generated by the power consumption increase prediction function, and the power consumption increase prediction function is: y=a*x1+b*x2+c*x3; wherein a, b, and c are coefficient parameters respectively; x1 is the degree of traffic congestion in the area where the candidate dispatch vehicle is located, x2 represents the battery health of the vehicle, x3 represents the vehicle load, and y represents the power consumption increase; The adjusted predicted power consumption rate is generated based on the power consumption increase using the following algorithm: Adjusted predicted power consumption rate = predicted power consumption rate + predicted power consumption rate * power consumption increase rate; Determining the target dispatch vehicle based on the adjusted predicted power consumption rate corresponding to the candidate dispatch vehicle; Determining a candidate scheduling strategy based on the scheduling point information and the vehicle operation information; Based on the candidate scheduling strategy, determine the user satisfaction and battery loss corresponding to the candidate scheduling strategy; the battery loss refers to the additional loss of the battery caused by the target scheduling vehicle running at an unhealthy power level, and the unhealthy power level is 20% of the total power level; Determine a scheduling strategy based on the user satisfaction, the battery depletion, the candidate scheduling strategies and an adaptation value, wherein the adaptation value is determined based on the available battery quality of the scheduling point and the predicted power consumption rate of the target scheduling vehicle; and Based on the scheduling strategy, recommended scheduling information of the target scheduling vehicle is generated, and the recommended scheduling information is sent to a display device of the vehicle and / or to a mobile terminal of the user.

2. The system according to claim 1, characterized in that The cloud platform is further configured as follows: Based on the historical dispatch point information, holiday information and the traffic data, predict the predicted load data of the dispatch point at a future time point; Determining a preliminary dispatching point based on the predicted load data and the load threshold parameter; The candidate scheduling strategy is determined based on the preliminary scheduling point, the scheduling point information of the preliminary scheduling point and the vehicle operation information.

3. A car rental management method, comprising: Obtain traffic data for the target area; Obtain vehicle operation information of the vehicle and dispatch point information and operation data of the dispatch point; The vehicle operation information includes vehicle speed, vehicle location, vehicle load, vehicle battery type, vehicle battery health, vehicle battery information, and vehicle equipment working status; the operation data includes user information and order information, the user information includes credit rating, rental frequency, and preferred car model, and the order information includes the status of the rental order, rental duration, return location, and order score; Determining a target dispatch vehicle based on the vehicle operation information and the operation data of the vehicle; wherein determining a target dispatch vehicle based on the vehicle operation information and the operation data of the vehicle comprises: Determine the battery power confidence of the vehicle battery based on the historical charge and discharge records of the vehicle battery, the historical battery temperature, the health of the vehicle battery and the type of the vehicle battery; and determine the corrected vehicle power based on the power confidence, and determine the vehicle whose corrected vehicle power is less than the power threshold and whose time to return is greater than the time threshold as a candidate dispatch vehicle; Based on the historical vehicle operation information and environmental data of the candidate dispatch vehicle, the predicted power consumption rate of the candidate dispatch vehicle is predicted; and based on the traffic data, the power consumption increase is generated by the power consumption increase prediction function, and the power consumption increase prediction function is: y=a*x1+b*x2+c*x3; wherein a, b, and c are coefficient parameters respectively; x1 is the degree of traffic congestion in the area where the candidate dispatch vehicle is located, x2 represents the battery health of the vehicle, x3 represents the vehicle load, and y represents the power consumption increase; The adjusted predicted power consumption rate is generated based on the power consumption increase using the following algorithm: Adjusted predicted power consumption rate = predicted power consumption rate + predicted power consumption rate * power consumption increase rate; Determining the target dispatch vehicle based on the adjusted predicted power consumption rate corresponding to the candidate dispatch vehicle; Determining a candidate scheduling strategy based on the scheduling point information and the vehicle operation information; Based on the candidate scheduling strategy, determine the user satisfaction and battery loss corresponding to the candidate scheduling strategy; the battery loss refers to the additional loss of the battery caused by the target scheduling vehicle running at an unhealthy power level, and the unhealthy power level is 20% of the total power level; Determine a scheduling strategy based on the user satisfaction, the battery depletion, the candidate scheduling strategies and an adaptation value, wherein the adaptation value is determined based on the available battery quality of the scheduling point and the predicted power consumption rate of the target scheduling vehicle; and Based on the scheduling strategy, recommended scheduling information of the target scheduling vehicle is generated, and the recommended scheduling information is sent to a display device of the vehicle and / or to a mobile terminal of a user.

4. The method according to claim 3, wherein determining a candidate scheduling strategy based on the scheduling point information and the vehicle operation information comprises: Based on the historical dispatch point information, holiday information and the traffic data, predict the predicted load data of the dispatch point at a future time point; Determining a preliminary dispatching point based on the predicted load data and the load threshold parameter; The candidate scheduling strategy is determined based on the preliminary scheduling point, the scheduling point information of the preliminary scheduling point and the vehicle operation information.

5. A car rental management device, comprising a processor, characterized in that: The processor is used to execute the car rental management method as described in any one of claims 3-4.

6. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the car rental management method according to any one of claims 3 to 4.

Images