An intelligent dispatching system for shared electric two-wheeled vehicles

Abstract

The present invention is applicable to the field of intelligent scheduling technology and provides an intelligent scheduling system for shared electric two-wheeled vehicles, including: an on-board terminal, a cloud computing platform, a scheduling management terminal and a user terminal; the cloud computing platform is connected to the on-board terminal, the scheduling management terminal and the user terminal respectively; the on-board terminal is used to upload the collected multi-source data to the cloud computing platform; the demand forecasting unit in the cloud computing platform generates vehicle demand forecast results for different time periods; the battery management unit generates battery status analysis results; the wireless transmission unit is used to transmit data; the scheduling management terminal is used to generate a scheduling path strategy based on scheduling cost, user waiting cost and battery replacement cost; the user terminal is used to provide multi-dimensional intelligent services. The collaborative work of dynamic perception, accurate prediction and intelligent decision-making in the present invention effectively improves the timeliness and comprehensiveness of electric scheduling.

Description

Technical Field

[0001] The present invention relates to the field of intelligent scheduling technology, and in particular to an intelligent scheduling system for shared electric two-wheeled vehicles. Background Art

[0002] With the popularity of shared travel modes, existing research has made certain progress in the field of intelligent scheduling of shared electric two-wheeled vehicles. At present, the existing scheduling system lacks real-time environmental perception capabilities, resulting in a shortage of vehicles in popular areas during peak hours, while vehicles in unpopular areas are idle. The supply and demand imbalance of vehicles. Secondly, because battery health monitoring is based only on single indicators such as the number of cycles or voltage thresholds, it does not take into account the dynamic impact of hot and humid environments on battery degradation, resulting in large deviations in battery life predictions and users frequently encounter power outages mid-trip. In addition, vehicle tracking through GPS positioning, or dividing high-demand areas based on clustering algorithms, or detecting low-battery vehicles through regular inspections or user feedback, these methods for shared bicycles are difficult to directly adapt to the dynamic charging and swapping needs of electric two-wheeled vehicles and the complex urban road network environment, resulting in poor real-time scheduling and insufficient scheduling.

[0003] In view of this, an intelligent scheduling system for shared electric two-wheeled vehicles is proposed. Summary of the Invention

[0004] The present invention provides an intelligent dispatching system for shared electric two-wheeled vehicles, which is used to solve the problems of poor real-time performance and incomplete dispatching.

[0005] The present invention provides an intelligent dispatching system for shared electric two-wheeled vehicles, comprising:

[0006] On-board terminal, cloud computing platform, dispatching management terminal and user terminal; the cloud computing platform is connected to the on-board terminal, dispatching management terminal and user terminal respectively;

[0007] The vehicle-mounted terminal is used to collect vehicle positioning data, vehicle status data, vehicle environment data and battery status data in real time, and upload them to the cloud computing platform;

[0008] The cloud computing platform includes:

[0009] A demand forecasting unit, which analyzes vehicle usage patterns in various areas based on the vehicle positioning data, vehicle status data, and vehicle environment data, and generates vehicle demand forecast results for different time periods;

[0010] A battery management unit, which generates a battery status analysis result including remaining life, charging circuit, and charging time based on the battery status data;

[0011] A wireless transmission unit, configured to push vehicle positioning data, vehicle status data, and battery status data to the user terminal, and provide the dispatch management terminal with vehicle demand forecast results, battery status analysis results, and vehicle positioning data;

[0012] The dispatch management terminal is used to generate a dispatch path strategy with dispatch cost, user waiting cost and battery replacement cost as targets based on the vehicle demand forecast result, battery status analysis result and vehicle positioning data;

[0013] The user terminal is used to provide real-time vehicle location query, navigation-based vehicle reservation and vehicle usage status feedback services.

[0014] Furthermore, the vehicle-mounted terminal includes:

[0015] Positioning module, used to obtain the vehicle's real-time location coordinates and driving trajectory data;

[0016] Vehicle status sensing module, used to detect the vehicle's operating status, usage status and fault signals;

[0017] Environmental monitoring module, used to collect temperature and humidity data of the vehicle's environment;

[0018] Battery status monitoring module, used to collect battery remaining power and health status data;

[0019] A main controller is connected to the positioning module, battery status monitoring module, vehicle status perception module and environment monitoring module respectively, and is used to integrate and process multi-source data and generate transmission data;

[0020] The data transmission module is used to upload the transmission data to the cloud computing platform.

[0021] Furthermore, the vehicle usage patterns in each area are analyzed based on the vehicle positioning data, vehicle status data, and vehicle environment data to generate vehicle demand forecast results for different time periods, including:

[0022] extracting the vehicle distribution thermal characteristics of each area based on the real-time position coordinates and driving trajectory data of the vehicles, calculating the vehicle idle rate, failure rate and real-time usage frequency based on the operating status, usage status and fault signals of the vehicles, and generating an environmental correction coefficient based on the temperature data and humidity data of the environment in which the vehicles are located;

[0023] The vehicle distribution thermal characteristics, idle rate, failure rate and real-time usage frequency are input as input features into the improved LSTM model, wherein the environmental correction coefficient is embedded in the gating unit of the improved LSTM model to adjust the memory weight of the improved LSTM model for temperature and humidity sensitive periods;

[0024] Output the vehicle demand forecast results for each area within the preset time.

[0025] Furthermore, the environmental correction coefficient is embedded in the gating unit of the improved LSTM model to adjust the memory weight of the improved LSTM model for the temperature and humidity sensitive periods, including:

[0026] Mapping the temperature data and humidity data into a temperature influencing factor and a humidity influencing factor respectively, and generating an environmental correction coefficient through linear weighting;

[0027] Concatenating the environmental correction coefficient with the historical hidden state corresponding to the gating unit to generate a temperature and humidity sensitive gating weight;

[0028] During a preset high temperature and high humidity sensitive period, the forgetting rate of the gating weight is reduced to a preset percentage range to enhance the memory strength of the improved LSTM model for the vehicle usage pattern during the same period in history.

[0029] Furthermore, generating a battery status analysis result including remaining life, charging circuit, and charging time based on the battery status data includes:

[0030] Acquire a battery internal resistance change rate, a capacity attenuation rate, and an ambient temperature deviation value based on the battery status data, wherein the ambient temperature deviation value is the absolute difference between the ambient temperature of the battery and a preset reference temperature;

[0031] Establishing a battery health state decay rate model by analyzing the correlation between the battery internal resistance change rate, capacity decay rate and temperature deviation value;

[0032] Calculate the remaining cycle life based on the difference between the cumulative number of battery cycles and a preset cycle life threshold; calculate the remaining capacity life based on the difference between the current health status index and a preset capacity decay threshold, combined with the decay rate model;

[0033] The remaining time of the cycle life and the remaining time of the capacity life are compared, and the time with the smaller value is selected as the target prediction result of the remaining life.

[0034] Furthermore, the generating of a battery status analysis result including remaining life, charging line and charging time based on the battery status data further includes:

[0035] Divide the charging priority levels according to the vehicle's remaining power and battery health status;

[0036] Based on the vehicle's real-time location, charging station distribution, and real-time traffic data obtained through a third-party map interface, the system uses a linear weighting method to assign weights to multiple objectives, with the optimization goals of minimizing travel time, maximizing charging efficiency, and minimizing battery health loss, to generate the optimal charging path.

[0037] The charging path is updated in real time according to traffic status changes and charging pile availability analysis, and the updated charging path is pushed to the scheduling management terminal.

[0038] Furthermore, the generating of a battery status analysis result including remaining life, charging line and charging time based on the battery status data further includes:

[0039] Dynamically calculate the basic charging time based on the required charging amount, charging pile power and battery health status, and compensate and correct the charging time based on ambient temperature data;

[0040] Based on the regional vehicle usage peak period output by the demand forecasting unit and the time-of-use electricity price data obtained through the power grid server interface, selecting a period with low demand and low electricity price as a recommended charging window;

[0041] When abnormal battery temperature or health status is detected below a safe threshold, a cooling interval is automatically inserted and the charging time is extended.

[0042] Furthermore, the generation of a dispatch path strategy targeting dispatch cost, user waiting cost, and battery replacement cost includes:

[0043] The expression of the objective function is:

[0044]

[0045] in: is the vehicle number, is the total number of shared electric two-wheeled vehicles, is the area number, is the total number of regions, Number the backup battery. is the total number of available batteries, is the unit distance scheduling cost, For vehicles Dispatched to distance, is the congestion cost per unit time, For vehicles Dispatched to The real-time traffic congestion time is obtained through the Amap API. is a binary variable. If the vehicle Dispatch to region ,but ,otherwise , The unit cost of waiting for the user, For the region The forecast demand, For the region The initial number of vehicles, is the cost of a single battery replacement, This is the correction factor for hot and humid climates. The battery loses power faster in high temperature and high humidity environments. is a binary variable. If the vehicle Using a backup battery ,but ,otherwise .

[0046] Furthermore, the constraints of the scheduling path strategy include vehicle allocation constraints, regional capacity constraints, battery health constraints, time window constraints, high-demand area service constraints and charging pile competition constraints.

[0047] Furthermore, the user terminal includes:

[0048] Positioning query module, used to send real-time vehicle location query requests to the cloud computing platform, and receive and display the positioning data of the target vehicle;

[0049] The navigation reservation module is used to initiate a vehicle locking request to the cloud computing platform based on the reservation instruction input by the user and the navigation route planning result, and receive the reservation confirmation information and vehicle status information returned by the cloud computing platform;

[0050] A status feedback module is used to collect user feedback data on the vehicle usage status and upload the feedback data to the cloud computing platform;

[0051] The navigation reservation module generates a navigation path from the user's current location to the target vehicle by calling a third-party map service interface, and the vehicle locking request includes the vehicle number, reservation time and user identity verification information.

[0052] It can be seen from the above technical solutions that the present invention has the following advantages:

[0053] The demand forecasting unit of the present invention alleviates the problem of uneven vehicle distribution, reducing vehicle shortages in popular areas and idleness in unpopular areas; the battery management unit improves the accuracy of remaining life and charging paths through embedded humid and hot environment correction factors and multi-dimensional health status assessments, reducing the risk of power outages caused by battery problems for users; the scheduling management terminal generates a global optimal scheduling strategy, reducing operating costs while improving vehicle turnover; the user terminal enhances the system's response speed and resource allocation rationality through real-time data interaction. Through the synergy of dynamic perception, accurate prediction, and intelligent decision-making, this system solves the problems of scheduling lag, extensive battery management, and large demand forecast deviations in existing technologies, providing efficient and reliable technical support for the operation of shared electric two-wheeled vehicles in high-density cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of the structure of an embodiment of an intelligent dispatching system for shared electric two-wheeled vehicles in the present invention;

[0055] Figure 2 This is a schematic structural diagram corresponding to the vehicle-mounted terminal in the present invention;

[0056] Figure 3 This is a schematic diagram of an embodiment flow chart corresponding to the demand forecasting unit in the present invention;

[0057] Figure 4a This is a flow chart of an embodiment of a battery management unit in the present invention;

[0058] Figure 4b This is a flow chart of another embodiment of the battery management unit in the present invention;

[0059] Figure 4c FIG. 2 is a flow chart of another embodiment of a battery management unit in the present invention. DETAILED DESCRIPTION

[0060] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "corresponding to" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0061] Example 1

[0062] See also Figure 1 The intelligent dispatching system for shared electric two-wheeled vehicles in the present invention comprises: an on-board terminal 1, a cloud computing platform 2, a dispatching management terminal 3 and a user terminal 4; the cloud computing platform 2 is connected to the on-board terminal 1, the dispatching management terminal 3 and the user terminal 4 respectively; the on-board terminal 1 is used to collect vehicle positioning data, vehicle status data, vehicle environment data and battery status data in real time, and upload them to the cloud computing platform 2; the cloud computing platform 2 includes a demand forecasting unit 201, which analyzes the vehicle usage pattern in each area based on the vehicle positioning data, vehicle status data and vehicle environment data, and generates vehicle demand forecast results in different time periods; the battery management unit 202 is based on the battery The status data generates a battery status analysis result including the remaining life, charging route and charging time; the wireless transmission unit 203 is used to push the vehicle positioning data, vehicle status data and battery status data to the user terminal 4, and provide the vehicle demand prediction results, battery status analysis results and vehicle positioning data to the scheduling management terminal 3; the scheduling management terminal 3 is used to generate a scheduling path strategy with scheduling cost, user waiting cost and battery replacement cost as the target based on the vehicle demand prediction results, battery status analysis results and vehicle positioning data; the user terminal 4 is used to provide real-time vehicle location query, navigation-based vehicle reservation and vehicle usage status feedback services.

[0063] The vehicle-mounted terminal 1 of the present invention collects multi-source vehicle data in real time and uploads it to the cloud computing platform 2. The platform generates a scheduling basis through analysis by the demand forecasting unit and the battery management unit; the scheduling management terminal 3 formulates a multi-objective optimization strategy based on the forecast results and real-time positioning data provided by the platform, and the user terminal 4 obtains vehicle information through the platform and realizes navigation reservation and status feedback. Through data interconnection and functional complementarity, a scheduling system with dynamic perception and intelligent decision-making is formed, which effectively improves the timeliness and comprehensiveness of scheduling.

[0064] Example 2

[0065] See also Figure 2 , the vehicle-mounted terminal 1 in the present invention includes:

[0066] The positioning module 101 is used to obtain the vehicle's real-time position coordinates and driving trajectory data; the vehicle status perception module 102 is used to detect the vehicle's operating status, usage status and fault signals; the environmental monitoring module 103 is used to collect temperature data and humidity data of the vehicle's environment; the battery status monitoring module 104 is used to collect battery remaining power and health status data; the main controller 105 is connected to the positioning module, battery status monitoring module, vehicle status perception module and environmental monitoring module respectively, and is used to integrate and process multi-source data and generate transmission data; the 106 data transmission module is used to upload the transmission data to the cloud computing platform.

[0067] Specifically, the positioning module 101 integrates a GPS / Beidou dual-mode positioning chip, receives satellite signals in real time and analyzes longitude and latitude coordinates, combines inertial measurement unit data to compensate for positioning drift during signal obstruction, and generates vehicle position coordinates and driving trajectory data.

[0068] Vehicle state sensing module 102 includes an inertial sensor and a vehicle control bus decoder. The inertial sensor detects the vehicle's three-axis acceleration and angular velocity to determine the vehicle's driving state. The vehicle control bus decoder connects to the vehicle's motor controller and decodes CAN bus signals to obtain motor speed, fault diagnostic codes, and brake signals. The operating state refers to the vehicle's physical motion, including speed, acceleration, and steering angle. The usage state refers to whether the vehicle is occupied by a user (determined by the connection status of the vehicle's Bluetooth lock / user terminal). Fault signals include motor failures and brake system abnormalities.

[0069] Environmental monitoring module 103 uses a digital temperature and humidity sensor installed in the vehicle's waterproof cavity to collect real-time ambient temperature and humidity. The detected temperature and humidity data is used to modify the battery health model (for example, high temperature accelerates capacity decay) and trigger overheat protection mechanisms.

[0070] The battery status monitoring module 104 is implemented through a battery management system chip, and mainly collects the following remaining power and health status. The remaining power is calculated in real time based on the coulomb counting method, and the health status is comprehensively evaluated through internal resistance detection and capacity decay rate (comparison of the number of cycles with the initial capacity).

[0071] The main controller 105 uses a low-power microcontroller and runs an embedded real-time operating system to implement the following functions: receiving raw data from each module, aligning timestamps, and filtering data; encapsulating the data in JSON format, adding vehicle ID, timestamp, and CRC checksum, and generating a transmission data packet; and triggering a local alarm and marking the data priority when a fault signal is detected.

[0072] The data transmission module 106 adopts a low-power wide area network communication module, supports the TCP / IP protocol stack, establishes a long connection with the cloud computing platform through the operator network, and transmits data by event triggering or periodic reporting, supporting breakpoint resumption and encrypted transmission.

[0073] The above embodiment uses the on-board terminal to collaboratively collect vehicle location, operating status, ambient temperature and humidity, and battery health data in real time through multiple modules, providing high-precision multi-dimensional data for subsequent scheduling; at the same time, it effectively reduces operation and maintenance costs and extends battery life, ensuring user riding safety and experience.

[0074] Example 3

[0075] See also Figure 3The demand forecasting unit of the present invention analyzes the vehicle usage patterns in each area based on vehicle positioning data, vehicle status data, and vehicle environment data, and generates vehicle demand forecast results for different time periods, including the following steps:

[0076] S31. Extract the thermal characteristics of vehicle distribution in each area based on the real-time vehicle position coordinates and driving trajectory data, calculate the vehicle's idle rate, failure rate and real-time usage frequency based on the vehicle's operating status, usage status and fault signals, and generate an environmental correction coefficient based on the temperature and humidity data of the vehicle's environment;

[0077] 1. Vehicle Distribution Thermal Feature Extraction: Divide the city into gridded areas and count the dwell time and frequency of vehicles in each area. Use a kernel density estimation algorithm to generate a thermal distribution map. The thermal value (0–1) of each area reflects the degree of vehicle concentration.

[0078] 2. The idle rate is the proportion of unoccupied and undispatched vehicles in the area; the failure rate is the proportion of vehicles reporting failure signals in the area; and the real-time usage frequency is the number of times a vehicle is used per unit time.

[0079] 3. Normalize the detected temperature data to the temperature impact factor, and normalize the humidity data to the humidity impact factor. After linear weighting, obtain the environmental correction coefficient. The linear weighting weight coefficient is set according to the local climate characteristics. For example, at 2:00 PM on a summer day in Nanning, Guangxi, the temperature is 38°C and the humidity is 90%. The corresponding weights of the temperature and humidity impact factors are 0.6 and 0.4. The calculated temperature and humidity impact factors are 0.76 and 0.9, respectively. The correction coefficient at this time is 0.816.

[0080] S32. The vehicle distribution thermal characteristics, idle rate, failure rate, and real-time usage frequency are input as input features into the improved LSTM model, wherein the environmental correction coefficient is embedded in the gating unit of the improved LSTM model to adjust the memory weight of the improved LSTM model for temperature and humidity sensitive periods;

[0081] The above-determined vehicle distribution thermal characteristics, idle rate, failure rate, and real-time usage frequency are used as input features. Based on the standard LSTM, the environmental correction coefficient is embedded in the forget gate to dynamically adjust the historical memory weight. The specific implementation is as follows:

[0082] S321. Mapping the temperature data and humidity data into temperature influence factors and humidity influence factors, respectively, and generating an environmental correction coefficient by linear weighting;

[0083] S322. Concatenate the environmental correction coefficient with the historical hidden state corresponding to the gating unit to generate a temperature and humidity sensitive gating weight;

[0084] S323. During the preset high temperature and high humidity sensitive period, the forgetting rate of the gated weights is reduced to a preset percentage range to enhance the memory strength of the improved LSTM model on the historical vehicle usage patterns during the same period.

[0085] S33. Output the vehicle demand forecast results for each area within the preset time.

[0086] The environmental correction coefficient is concatenated with the historical hidden state of the forget gate, and the forget gate output is calculated using the weight matrix and bias. The preset high temperature and high humidity sensitive period is set as when the temperature is greater than 35% and the humidity is greater than 80%. During the sensitive period, the forget gate output is multiplied by the attenuation factor to reduce the forgetting rate of the gated weight to a preset percentage range, which can be set to 50%. After reducing the forgetting rate, the model retains more historical data for the same period (such as the vehicle usage patterns of the same period last year), enhancing its adaptability to demand fluctuations in hot and humid environments. The final hidden state of the improved LSTM is input into the fully connected layer, and the demand forecast value for each region in the next T (24) hours is output, that is, the predicted demand for each region is output.

[0087] The above embodiment improves the LSTM model through environmental correction, so that the improved model is more adaptable to scenarios with large fluctuations in temperature and humidity, and effectively improves the accuracy of the demand forecasting model.

[0088] Example 4

[0089] In the present invention, the battery management unit generates a battery status analysis result including the remaining life, charging circuit and charging time based on the battery status data, which includes the following steps:

[0090] S411. Obtain the battery internal resistance change rate, capacity attenuation rate, and ambient temperature deviation value based on the battery status data, where the ambient temperature deviation value is the absolute difference between the ambient temperature of the battery and the preset reference temperature;

[0091] S412. Establish a battery health state decay rate model by analyzing the correlation between the battery internal resistance change rate, capacity decay rate and temperature deviation value;

[0092] S413. Calculate the remaining cycle life based on the difference between the cumulative number of battery cycles and the preset cycle life threshold; calculate the remaining capacity life based on the difference between the current health status index and the preset capacity decay threshold, combined with the decay rate model;

[0093] S414. Compare the remaining cycle life time and the remaining capacity life time, and select the smaller time as the target prediction result of the remaining life.

[0094] Specifically, the battery's internal resistance change rate is determined by periodically measuring the battery's AC impedance through the BMS chip, thereby calculating the resistance growth rate per unit time. The capacity decay rate is calculated based on charge and discharge cycle data, with the capacity decay percentage calculated (e.g., a 2% capacity drop per 100 cycles). The ambient temperature deviation value is the absolute difference between the real-time temperature collected by the ambient temperature sensor and the reference temperature (25°C) (e.g., a 10°C deviation at 35°C). Using multiple linear regression analysis, an equation is established to establish the relationship between the internal resistance change rate, capacity decay rate, and temperature deviation value, and the decay rate is calculated.

[0095] The preset cycle life threshold is set based on the battery type. The preset capacity decay threshold follows the industry standard. For example, a battery is considered failed when the capacity drops to 80% of its initial value. The final remaining life is the smaller of the cycle life and capacity life, ensuring a conservative forecast.

[0096] S421. Divide the charging priority level according to the vehicle's remaining power and battery health status;

[0097] S422. Based on the vehicle's real-time location, charging station distribution, and real-time traffic data obtained through a third-party map interface, the optimal charging path is generated by weighting multiple objectives using a linear weighting method, with the optimization objectives of minimizing travel time, maximizing charging efficiency, and minimizing battery health loss.

[0098] S423. Update the charging path in real time based on traffic status changes and charging pile availability analysis, and push the updated charging path to the dispatch management terminal.

[0099] Specifically, vehicles are categorized into three levels based on their remaining battery life (low battery prioritized) and battery health (low capacity prioritized): emergency charging (battery level <20%), regular charging (20%-50%), and delayed charging (>50%). The dispatch management terminal accesses the AutoNavi Map API to obtain real-time traffic data. Combined with the distribution of charging stations, the system uses a linear weighting method to assign weights and generate a globally optimal route, aiming for the shortest travel time, highest charging station efficiency, and minimum battery health loss. Traffic status changes and charging station availability are monitored every five minutes, and the route is automatically replanned and pushed to the dispatch terminal to ensure timely dispatch.

[0100] S431. Dynamically calculate the basic charging time based on the required charging amount, charging pile power and battery health status, and compensate and correct the charging time in combination with the ambient temperature data;

[0101] S432. Based on the regional vehicle peak period output by the demand forecasting unit and the time-of-use electricity price data obtained through the grid server interface, select the period with low demand and low electricity price as the recommended charging window;

[0102] S433. When it is detected that the battery temperature is abnormal or the health status is below the safety threshold, a cooling interval is automatically inserted and the charging time is extended.

[0103] Specifically, the base charging time is calculated based on the required charge amount, charging station power, and battery health status. For example, slow charging takes 2 hours and fast charging takes 1 hour. When the ambient temperature is above 25°C, the charging time increases by 10% for every 5°C increase; when it is below 10°C, the charging time increases by 5%.

[0104] Here, low-demand periods are defined as those outside of the regional peak vehicle usage hours (e.g., 7:00 AM to 9:00 AM and 5:00 PM to 7:00 PM) output by the demand forecasting unit (e.g., 1:00 PM to 3:00 PM and 11:00 AM to 1:00 PM). Low-price periods are defined as those when the electricity price falls below a preset threshold (e.g., 0.5 yuan / kWh) by obtaining time-of-use electricity price data from the grid interface (e.g., off-peak hours, 00:00 AM to 8:00 AM). Finally, select the period that meets both low demand and low prices (e.g., 1:00 AM to 3:00 AM).

[0105] The temperature safety threshold here sets the battery temperature to ≥50℃ (triggering forced cooling) or ≤0℃ (triggering preheating); the health status safety threshold is set to 70%. If it is less than 70%, the battery will be immediately deactivated and replaced. When the temperature or capacity exceeds the limit, a 15-minute cooling interval will be automatically inserted, the charging time will be extended, and an alarm will be pushed to the dispatch terminal.

[0106] The above embodiment improves the accuracy of prediction results by quantifying the combined impact of internal resistance, capacity, and temperature on the attenuation rate, combining cycle and capacity life thresholds; dynamically optimizes paths based on real-time data, balancing time, efficiency, and battery health, and adapting to areas with more complex road networks; combines demand forecasting with time-of-use electricity prices to complete charging during periods of low operating costs, and ensures battery reliability through safety thresholds.

[0107] Example 5

[0108] The dispatch management terminal of the present invention is used to generate a dispatch routing strategy based on the vehicle demand forecast results, battery status analysis results, and vehicle positioning data, with dispatch cost, user waiting cost, and battery replacement cost as targets, including the following:

[0109] The objective function of the scheduling path strategy is as follows:

[0110] The expression of the objective function is:

[0111]

[0112] in: is the vehicle number, is the total number of shared electric two-wheeled vehicles, is the area number, is the total number of regions, Number the backup battery. is the total number of available batteries, is the unit distance scheduling cost, For vehicles Dispatched to distance, is the congestion cost per unit time, For vehicles Dispatched to The real-time traffic congestion time is obtained through the Amap API. is a binary variable. If the vehicle Dispatch to region ,but ,otherwise , The unit cost of waiting for the user, For the region The forecast demand, For the region The initial number of vehicles, is the cost of a single battery replacement, This is the correction factor for hot and humid climates. The battery loses power faster in high temperature and high humidity environments. is a binary variable. If the vehicle Using a backup battery ,but ,otherwise .

[0113] Constraints include vehicle allocation constraints, regional capacity constraints, battery health constraints, time window constraints, high-demand area service constraints, and charging pile competition constraints. The expressions are as follows:

[0114] Vehicle assignment constraints:

[0115]

[0116] in: For vehicles Whether it is dispatched or not, each vehicle is assigned to only one area to avoid duplicate dispatch;

[0117] Regional capacity constraints:

[0118]

[0119] in: For the region Maximum parking capacity to prevent vehicle accumulation in the area;

[0120] Battery health constraints:

[0121]

[0122] in: For vehicles Battery health index, For health thresholds, forced replacement of low-health batteries to avoid mid-flight failures;

[0123] Time window constraints:

[0124]

[0125] in: For vehicles Dispatching to a region The estimated time, To maximize the allowed scheduling time, ensure scheduling timeliness and avoid delays;

[0126] Service constraints in high-demand areas:

[0127]

[0128] in: is the demand threshold, The lowest service rate ensures that more than 80% of the demand in popular areas is met;

[0129]

[0130] in: The maximum number of vehicles that can be served by a single charging station is set to avoid overcrowding at the same charging station and causing queuing delays.

[0131] The high-complexity constraints such as the regional capacity constraint and charging pile competition constraint are relaxed into the objective function through Lagrange multipliers. The original problem is decomposed into two independent sub-problems: vehicle scheduling and battery replacement, which are solved separately. The solution is gradually approached to the optimal solution through sub-gradient updating. The algorithm terminates when the rate of change of the objective function is less than a threshold or the maximum number of iterations is reached.

[0132] The above embodiment effectively reduces computational complexity and is suitable for large-scale vehicle dispatching scenarios such as those in Nanning, Guangxi. By dynamically adjusting the multiplier weights, it can flexibly respond to emergencies such as traffic congestion. This enables low-cost, highly responsive intelligent dispatching, significantly improving vehicle utilization and user experience.

[0133] Example 6

[0134] In this embodiment, the user terminal 4 includes a positioning query module 401, which is used to send a vehicle real-time location query request to the cloud computing platform, receive and display the positioning data of the target vehicle; a navigation reservation module 402, which is used to initiate a vehicle locking request to the cloud computing platform based on the reservation instruction input by the user and the navigation path planning result, and receive the reservation confirmation information and vehicle status information returned by the cloud computing platform; a status feedback module 403, which is used to collect user feedback data on the vehicle usage status and upload the feedback data to the cloud computing platform; wherein, the navigation reservation module generates a navigation path from the user's current location to the target vehicle by calling a third-party map service interface, and the vehicle locking request includes the vehicle number, reservation time and user identity authentication information.

[0135] The user sends a real-time location query request to the cloud computing platform through the positioning query module. After receiving the request, the platform obtains the GPS coordinates and status information of the target vehicle from the on-board terminal and returns it. After the user terminal parses the data, it dynamically displays the vehicle location on the map interface; the navigation reservation module calls the AutoNavi Map API to generate the optimal path from the user's current location to the target vehicle. After the user confirms the reservation, the terminal encapsulates the encrypted vehicle number, reservation timestamp and user identity token into a lock request and sends it to the cloud platform. After verifying the legitimacy of the token, the cloud platform locks the vehicle and returns the reservation success status and remaining power; after use, the status feedback module collects the text or image data submitted by the user through a preset form, uploads it to the cloud platform database after compression and encryption, and triggers the battery management unit or scheduling decision unit for subsequent processing, thereby forming a closed-loop service link.

[0136] It is understandable that those skilled in the art can, under the guidance of the above embodiments, combine various implementation methods in the above embodiments to obtain technical solutions of multiple implementation methods.

[0137] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent dispatching system for shared electric two-wheeled vehicles, characterized in that: include: On-board terminal, cloud computing platform, dispatching management terminal and user terminal; the cloud computing platform is connected to the on-board terminal, dispatching management terminal and user terminal respectively; The vehicle-mounted terminal is used to collect vehicle positioning data, vehicle status data, vehicle environment data and battery status data in real time, and upload them to the cloud computing platform; The cloud computing platform includes: A demand forecasting unit, which analyzes vehicle usage patterns in various areas based on the vehicle positioning data, vehicle status data, and vehicle environment data, and generates vehicle demand forecast results for different time periods; A battery management unit, which generates a battery status analysis result including remaining life, charging circuit, and charging time based on the battery status data; A wireless transmission unit, configured to push vehicle positioning data, vehicle status data, and battery status data to the user terminal, and provide the dispatch management terminal with vehicle demand forecast results, battery status analysis results, and vehicle positioning data; The dispatch management terminal is used to generate a dispatch path strategy with dispatch cost, user waiting cost and battery replacement cost as targets based on the vehicle demand forecast result, battery status analysis result and vehicle positioning data; the generation of the dispatch path strategy with dispatch cost, user waiting cost and battery replacement cost as targets includes: The expression of the objective function is: in: is the vehicle number, is the total number of shared electric two-wheeled vehicles, is the area number, is the total number of regions, Number the backup battery. is the total number of available batteries, is the unit distance scheduling cost, For vehicles Dispatching to a region distance, is the congestion cost per unit time, For vehicles Dispatching to a region The real-time traffic congestion time is obtained through the Amap API. is a binary variable. If the vehicle Dispatch to region ,but ,otherwise , Waiting cost for users, For the region The forecast demand, For the region The initial number of vehicles, is the cost of a single battery replacement, This is the correction factor for hot and humid climates. The battery loses power faster in high temperature and high humidity environments. is a binary variable. If the vehicle Using a backup battery ,but ,otherwise ; The constraints of the scheduling path strategy include vehicle allocation constraints, regional capacity constraints, battery health constraints, time window constraints, high-demand area service constraints, and charging pile competition constraints; The user terminal is used to provide real-time vehicle location query, navigation-based vehicle reservation and vehicle usage status feedback services.

2. The intelligent dispatching system for shared electric two-wheeled vehicles according to claim 1, characterized in that: The vehicle-mounted terminal includes: Positioning module, used to obtain the vehicle's real-time location coordinates and driving trajectory data; Vehicle status sensing module, used to detect the vehicle's operating status, usage status and fault signals; Environmental monitoring module, used to collect temperature and humidity data of the vehicle's environment; Battery status monitoring module, used to collect battery remaining power and health status data; A main controller is connected to the positioning module, battery status monitoring module, vehicle status perception module and environment monitoring module respectively, and is used to integrate and process multi-source data and generate transmission data; The data transmission module is used to upload the transmission data to the cloud computing platform.

3. The intelligent dispatching system for shared electric two-wheeled vehicles according to claim 2, characterized in that: The analyzing of vehicle usage patterns in each area based on the vehicle positioning data, vehicle status data, and vehicle environment data to generate vehicle demand forecast results for different time periods includes: extracting the vehicle distribution thermal characteristics of each area based on the real-time position coordinates and driving trajectory data of the vehicles, calculating the vehicle idle rate, failure rate and real-time usage frequency based on the operating status, usage status and fault signals of the vehicles, and generating an environmental correction coefficient based on the temperature data and humidity data of the environment in which the vehicles are located; The vehicle distribution thermal characteristics, idle rate, failure rate and real-time usage frequency are input as input features into the improved LSTM model, wherein the environmental correction coefficient is embedded in the gating unit of the improved LSTM model to adjust the memory weight of the improved LSTM model for temperature and humidity sensitive periods; Output the vehicle demand forecast results for each area within the preset time.

4. The intelligent dispatching system for shared electric two-wheeled vehicles according to claim 3 is characterized in that: The environmental correction coefficient is embedded in the gating unit of the improved LSTM model to adjust the memory weight of the improved LSTM model for temperature and humidity sensitive periods, including: Mapping the temperature data and humidity data into a temperature influencing factor and a humidity influencing factor respectively, and generating an environmental correction coefficient through linear weighting; Concatenating the environmental correction coefficient with the historical hidden state corresponding to the gating unit to generate a temperature and humidity sensitive gating weight; During a preset high temperature and high humidity sensitive period, the forgetting rate of the gating weight is reduced to a preset percentage range to enhance the memory strength of the improved LSTM model for the vehicle usage pattern during the same period in history.

5. The intelligent dispatching system for shared electric two-wheeled vehicles according to claim 2, characterized in that: Generating a battery status analysis result including remaining life, charging circuit, and charging time based on the battery status data includes: Acquire a battery internal resistance change rate, a capacity attenuation rate, and an ambient temperature deviation value based on the battery status data, wherein the ambient temperature deviation value is the absolute difference between the ambient temperature of the battery and a preset reference temperature; Establishing a battery health state decay rate model by analyzing the correlation between the battery internal resistance change rate, capacity decay rate and temperature deviation value; Calculate the remaining cycle life based on the difference between the cumulative number of battery cycles and a preset cycle life threshold; calculate the remaining capacity life based on the difference between the current health status index and a preset capacity decay threshold, combined with the decay rate model; The remaining time of the cycle life and the remaining time of the capacity life are compared, and the time with the smaller value is selected as the target prediction result of the remaining life.

6. The intelligent dispatching system for shared electric two-wheeled vehicles according to claim 5, characterized in that: The generating of a battery status analysis result including a remaining life, a charging line, and a charging time based on the battery status data further includes: Divide the charging priority levels according to the vehicle's remaining power and battery health status; Based on the vehicle's real-time location, charging station distribution, and real-time traffic data obtained through a third-party map interface, the system uses a linear weighting method to assign weights to multiple objectives, with the optimization goals of minimizing travel time, maximizing charging efficiency, and minimizing battery health loss, to generate the optimal charging path. The charging path is updated in real time according to traffic status changes and charging pile availability analysis, and the updated charging path is pushed to the scheduling management terminal.

7. The intelligent dispatching system for shared electric two-wheeled vehicles according to claim 6, characterized in that: The generating of a battery status analysis result including a remaining life, a charging line, and a charging time based on the battery status data further includes: Dynamically calculate the basic charging time based on the required charging amount, charging pile power and battery health status, and compensate and correct the charging time based on ambient temperature data; Based on the regional vehicle usage peak period output by the demand forecasting unit and the time-of-use electricity price data obtained through the power grid server interface, selecting a period with low demand and low electricity price as a recommended charging window; When abnormal battery temperature or health status is detected below a safe threshold, a cooling interval is automatically inserted and the charging time is extended.

8. The intelligent dispatching system for shared electric two-wheeled vehicles according to claim 1, characterized in that: The user terminal includes: Positioning query module, used to send real-time vehicle location query requests to the cloud computing platform, and receive and display the positioning data of the target vehicle; The navigation reservation module is used to initiate a vehicle locking request to the cloud computing platform based on the reservation instruction input by the user and the navigation route planning result, and receive the reservation confirmation information and vehicle status information returned by the cloud computing platform; A status feedback module is used to collect user feedback data on the vehicle usage status and upload the feedback data to the cloud computing platform; The navigation reservation module generates a navigation path from the user's current location to the target vehicle by calling a third-party map service interface, and the vehicle locking request includes the vehicle number, reservation time and user identity verification information.

Images