Public vehicle operation management method based on big data analysis and related equipment

Abstract

The application discloses a public vehicle operation management method based on big data analysis and related equipment, and the method comprises the following steps: receiving a battery alarm signal of an electric public vehicle, acquiring battery parameters and vehicle operation data; inputting current environmental data and real-time road condition data into a big data model to obtain a current operation scene of the vehicle; querying a battery parameter interval corresponding to the current operation scene of the vehicle; in the case that the battery parameter is located in the battery parameter interval, acquiring vehicle energy consumption data in a preset mileage interval, and predicting an energy consumption trend of the electric public vehicle in a future preset time period according to the battery parameter, the vehicle energy consumption data and the current operation scene of the vehicle; generating a power output mode of the electric public vehicle according to the energy consumption trend, vehicle operation data and driving behavior data; generating a brake adjustment instruction according to the power output mode; and sending the brake adjustment instruction to a vehicle terminal to enable the vehicle terminal to execute a brake strategy.

Description

Technical Field

[0001] This application relates to the field of electric public vehicles, and more particularly to a public vehicle operation management method and related equipment based on big data analysis. Background Technology

[0002] In modern urban transportation systems, electric public vehicles (such as electric buses) have become an important mode of transport. Electric public vehicles are not only environmentally friendly but also effectively reduce urban air pollution. However, the operation and management of electric public vehicles face many challenges, especially in battery management. The battery is the core component of an electric vehicle, and its performance directly affects the vehicle's range, safety, and operational efficiency. Therefore, how to effectively monitor and manage battery status to ensure stable vehicle operation under various operating conditions has become an urgent problem to be solved.

[0003] Traditional vehicle operation methods rely heavily on manual monitoring and experience-based judgment. In this model, the vehicle's battery status is typically assessed by the driver or operations manager using simple instrument readings. When a battery warning signal appears, the usual practice is to immediately stop the vehicle for inspection or rely on experience to determine if battery replacement is necessary. While this method is simple and straightforward, it presents numerous problems in practical application.

[0004] First, traditional battery monitoring methods lack accuracy. Battery alarm signals are often based on simple parameters such as voltage, current, and temperature, which are easily affected by environmental factors, such as temperature changes and road conditions. Therefore, false alarms sometimes occur, meaning the battery is not actually malfunctioning, but external factors cause the system to misjudge the situation. These false alarms not only increase operating costs but may also lead to unnecessary vehicle downtime, disrupting normal operations.

[0005] Secondly, traditional vehicle operation methods, when battery problems occur, lack comprehensive monitoring and analysis of battery status, making it impossible for operation managers to accurately determine the remaining battery power and the vehicle's driving capacity. This often results in vehicles failing to reach their intended destination after a battery alarm is triggered, and may even be forced to stop en route. This situation not only affects the passenger's travel experience but also causes significant inconvenience for operation management.

[0006] In summary, the current vehicle operation suffers from insufficient accuracy in battery monitoring, which seriously affects the operational efficiency of electric public vehicles. Summary of the Invention

[0007] This application provides a public vehicle operation management method and related equipment based on big data analysis to solve the problem of insufficient accuracy in battery monitoring and improve the operating efficiency of electric public vehicles.

[0008] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0009] Firstly, a public vehicle operation management method based on big data analysis is provided, applied to electronic devices. The electronic devices are equipped with a big data model and are connected to the vehicle terminal of an electric public vehicle. The method includes:

[0010] In response to receiving a battery alarm signal from the electric public vehicle, the system acquires the battery parameters and vehicle operation data of the electric public vehicle, wherein the vehicle operation data includes real-time traffic data, vehicle operation data, and driving behavior data of the electric public vehicle on the current route; and

[0011] Obtain current environmental data;

[0012] The current environmental data and the real-time traffic data are input into the big data model to obtain the current operating scenario of the vehicle. The big data model is constructed based on historical environmental data and historical traffic data.

[0013] The battery parameter range corresponding to the current operating scenario of the vehicle is obtained by querying the preset battery parameter database.

[0014] When the battery parameters are within the specified range, the vehicle energy consumption data of the electric public vehicle within a preset kilometer range is obtained, and based on the battery parameters, the vehicle energy consumption data, and the current operating scenario of the vehicle, the energy consumption trend of the electric public vehicle within a preset future time period is predicted.

[0015] Based on the energy consumption trend, the vehicle operation data, and the driving behavior data, a power output mode for the electric public vehicle on the current driving route is generated, wherein the power output mode is used to control the power distribution of the electric public vehicle.

[0016] A braking adjustment command is generated based on the power output mode, and the braking adjustment command is used to instruct the electric public vehicle to execute a braking strategy.

[0017] The braking adjustment command is sent to the vehicle terminal so that the vehicle terminal executes the braking strategy.

[0018] In one possible implementation of the first aspect, the steps for constructing the big data model include:

[0019] A preset feature extraction algorithm is used to extract features from the historical environmental data and the historical road condition data to obtain n first features, where n is an integer greater than 3;

[0020] Using the first preset clustering algorithm, cluster the n first features to obtain m clustering clusters, where 0 < m < n and m is an integer;

[0021] Using the feature extraction algorithm, extract features from the m clustering clusters to obtain p second features, where 0 < p < m and p is an integer;

[0022] Using the second preset clustering algorithm, cluster the p second features to obtain q clustering results, where each clustering result includes a clustering center, and 0 < q < p and q is an integer;

[0023] Using the preset distance algorithm, for each clustering center, calculate the average distance between all the second features and the clustering center, and take the clustering center corresponding to the smallest average distance as the target clustering center, and take the clustering result corresponding to the target clustering center as the target clustering result;

[0024] According to the preset mapping function, map the target clustering result to the corresponding operation scenario;

[0025] Package the feature extraction algorithm, the first preset clustering algorithm, the second preset clustering algorithm, the distance algorithm and the mapping function to obtain the big data model.

[0026] In another possible implementation manner of the first aspect, the method further includes:

[0027] When the battery parameters are not within the battery parameter range, obtain the current power of the electric bus through the vehicle terminal, and calculate the maximum driving distance of the electric bus according to the current power;

[0028] Obtain the current location of the electric bus;

[0029] According to the current location, determine the remaining driving distance of the electric bus on the current driving route;

[0030] When the remaining driving distance is greater than the maximum driving distance, calculate the straight-line distance between the current location and the end point of the current driving route, and search for an electric bus charging station within the area with the current location as the center and the straight-line distance as the radius;

[0031] When the number of electric bus charging stations is multiple, take the electric bus charging station with the shortest distance to the current location as the target charging station;

[0032] Based on the current location, the target charging station, and the destination of the current driving route, a new driving route is generated and sent to the vehicle terminal.

[0033] In another possible implementation of the first aspect, predicting the energy consumption trend of the electric public vehicle within a future preset time period based on the battery parameters, the vehicle energy consumption data, and the vehicle's current operating scenario includes:

[0034] By inputting the battery parameters, the vehicle energy consumption data, and the vehicle's current operating scenario into a pre-trained prediction model, the energy consumption trend of the electric public vehicle within a preset future time period can be obtained.

[0035] In another possible implementation of the first aspect, generating the power output mode of the electric public vehicle on the current driving route based on the energy consumption trend, the vehicle operation data, and the driving behavior data includes:

[0036] Based on the energy consumption trend, the power supply corresponding to each time step is calculated, and the power supply corresponding to each time step is fitted to generate the power supply curve of the electric public vehicle.

[0037] Based on the vehicle operation data, the driving status of the electric public vehicle is determined, wherein the driving status includes idling status, acceleration status, constant speed status and deceleration status.

[0038] Obtain the energy conversion efficiency curve of the electric public vehicle, and determine the optimal output power of the electric public vehicle in the driving state based on the power supply curve and the energy conversion efficiency curve;

[0039] The curvature of the power supply curve is calculated in real time;

[0040] When the curvature is greater than a preset threshold, the power output mode is determined based on the driving behavior data and the optimal output power of the electric public vehicle in the driving state.

[0041] In another possible implementation of the first aspect, determining the optimal output power of the electric public vehicle in the driving state based on the power supply curve and the energy conversion efficiency curve includes:

[0042] Based on the power supply curve and the energy conversion efficiency curve, obtain the power supply data segment and the corresponding energy conversion efficiency data segment under the driving state;

[0043] For each time point of the power supply data segment and the corresponding energy conversion efficiency data segment, calculate the actual output power at each time point under the driving state, and generate an output power curve based on the actual output power at each time point;

[0044] Based on the output power curve and the energy conversion efficiency curve, the optimal efficiency range is determined, and the average value of the output power corresponding to the optimal efficiency range is calculated. The average value is taken as the optimal output power of the electric public vehicle in the driving state.

[0045] In another possible implementation of the first aspect, determining the power output mode based on the driving behavior data and the optimal output power of the electric public vehicle in the driving state includes:

[0046] Based on the driving behavior data, the driving behavior type is determined, wherein the driving behavior type includes smooth, moderate, and aggressive;

[0047] Obtain the weight coefficients corresponding to the driving behavior type from the preset database;

[0048] The power adjustment coefficient for the actual output power at each time point is calculated based on the weighting coefficient, wherein the product of the optimal output power and the power adjustment coefficient is less than the maximum output power of the electric public vehicle.

[0049] Calculate the product of the actual output power at each time point and the corresponding power adjustment coefficient to obtain multiple adjusted output power values, and generate an optimized power output curve based on all processed output power values;

[0050] The power output mode is determined based on the optimal output power and the optimized power output curve.

[0051] The power output curve includes a low-power range, a medium-power range, and a high-power range. The power output modes include an energy-saving mode, a standard mode, and a power mode. When the optimal output power is located in the low-power range of the power output curve, the power output mode is the energy-saving mode. When the optimal output power is located in the medium-power range of the power output curve, the power output mode is the standard mode. When the optimal output power is located in the high-power range of the power output curve, the power output mode is the power mode.

[0052] In another possible implementation of the first aspect, the driving behavior data includes the frequency of rapid acceleration and braking, vehicle turning angle, vehicle turning speed, and vehicle idling time. Determining the driving behavior type based on the driving behavior data includes:

[0053] Multiple driving behavior features are obtained by extracting features from the frequency of rapid acceleration and braking, the vehicle turning angle, the vehicle turning speed, and the vehicle idling time.

[0054] The driving behavior features are input into a pre-trained classification model to obtain the driving behavior type.

[0055] Secondly, this application provides an electronic device, comprising:

[0056] The memory is configured to store instructions; and

[0057] The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the aforementioned public vehicle operation management method based on big data analysis.

[0058] Thirdly, this application provides a public vehicle operation management system based on big data analysis, including:

[0059] Electronic devices;

[0060] The vehicle terminal of the electric public vehicle is connected to the electronic device.

[0061] The above technical solution connects electronic devices to the vehicle terminal of electric public vehicles, enabling precise monitoring and intelligent management of battery status, thereby significantly improving the operational efficiency and safety of electric public vehicles. Upon receiving a battery alarm signal, the system acquires the battery parameters and vehicle operation data of the electric public vehicle, along with current environmental data. This data is then input into a big data model built based on historical environmental and road condition data to generate the vehicle's current operating scenario. By querying a preset battery parameter database for the battery parameter range corresponding to the current operating scenario, the system can accurately determine whether the battery status is normal. If the battery parameters are within the normal range, the system further acquires vehicle energy consumption data within a preset kilometer range. Combining the battery parameters, vehicle energy consumption data, and the current operating scenario, the system predicts the energy consumption trend over a preset time period. Based on energy consumption trends, vehicle operation data, and driving behavior data, the system generates power output patterns for electric public vehicles on the current route to optimize power distribution and generates braking adjustment commands to instruct the vehicle terminals to execute braking strategies. This enables intelligent control of electric public vehicles, improving the accuracy of battery monitoring, reducing false alarms, and ensuring stable operation under various operating conditions through intelligent prediction and optimized power distribution. This avoids vehicle downtime due to battery issues, enhancing passenger travel experience and operational management convenience. Furthermore, the analysis of real-time traffic data and driving behavior data optimizes vehicle energy consumption management, further reducing operating costs and providing strong support for the sustainable development of electric public vehicles.

[0062] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0063] Figure 1 A flowchart illustrating a public vehicle operation management method based on big data analysis, provided as an embodiment of this application;

[0064] Figure 2 A schematic diagram of the first clustering provided in an embodiment of this application;

[0065] Figure 3 A schematic diagram of the second clustering provided in an embodiment of this application;

[0066] Figure 4 This is a flowchart illustrating the process after determining the power output mode, as provided in an embodiment of this application.

[0067] Figure 5 This is a structural block diagram of a public vehicle operation management system based on big data analysis, provided as an embodiment of this application. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0069] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0070] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0071] Example 1, Figure 1 This illustration schematically depicts a flowchart of a public vehicle operation management method based on big data analysis according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a public vehicle operation management method based on big data analysis, which is applied to an electronic device. The electronic device is equipped with a big data model and is connected to the vehicle terminal of an electric public vehicle. The method may include the following steps.

[0072] S110. In response to receiving a battery alarm signal from the electric public vehicle, acquire the battery parameters and vehicle operation data of the electric public vehicle, wherein the vehicle operation data includes real-time traffic data, vehicle operation data, and driving behavior data of the electric public vehicle on the current driving route; and

[0073] S120. Obtain current environmental data;

[0074] S130. Input the current environmental data and real-time traffic data into the big data model to obtain the current operating scenario of the vehicle. The big data model is built based on historical environmental data and historical traffic data.

[0075] S140. In the preset battery parameter database, query the battery parameter range corresponding to the current operating scenario of the vehicle.

[0076] S150. When the battery parameters are within the battery parameter range, obtain the vehicle energy consumption data of electric public vehicles within the preset kilometer range, and predict the energy consumption trend of electric public vehicles within the preset time period based on the battery parameters, vehicle energy consumption data and the current operating scenario of the vehicle.

[0077] S160. Based on energy consumption trends, vehicle operation data, and driving behavior data, generate the power output mode of the electric public vehicle on the current driving route, wherein the power output mode is used to control the power distribution of the electric public vehicle.

[0078] S170. Generate a braking adjustment command based on the power output mode. The braking adjustment command is used to instruct the electric public vehicle to execute the braking strategy.

[0079] S180: Send the braking adjustment command to the vehicle terminal so that the vehicle terminal can execute the braking strategy.

[0080] In this embodiment, battery parameters include temperature, voltage, current, etc.; real-time traffic data includes the road type of the current driving route, the traffic density of the current road, etc.; vehicle operation data includes vehicle speed, acceleration, motor power output, etc.; driving behavior data includes the frequency and intensity of rapid acceleration and braking, turning angle and speed, idling time, etc., where idling time refers to the time when the vehicle is stationary but the engine is running.

[0081] The electronic devices first respond to the received battery alarm signal from the electric public vehicle. The battery alarm signal is triggered by the vehicle's Battery Management System (BMS) when it detects an abnormality, such as excessive battery temperature, abnormal voltage, or excessive current. Upon receiving the alarm signal, the system first collects battery parameters, including temperature, voltage, and current. These parameters can be collected in real time by onboard sensors and transmitted to the electronic devices via the vehicle communication network. Next, vehicle operation data is collected, which includes three main aspects: real-time traffic data, vehicle operation data, and driving behavior data. Real-time traffic data covers the road type of the current route (e.g., highway, urban road, or mountain road) and the current traffic density. This data can be obtained through onboard GPS and real-time traffic information services. Vehicle operation data includes vehicle speed, acceleration, and motor power output, which can be read directly from the vehicle's control system. Driving behavior data includes the frequency and intensity of rapid acceleration and braking, turning angle and speed, and idling time. This data can be obtained through the vehicle's terminal.

[0082] Upon receiving a battery alarm signal, the system also acquires current environmental data. Environmental data refers to external factors that affect vehicle performance and battery efficiency. Current environmental data includes, but is not limited to, the following: First, temperature data, including ambient temperature and road surface temperature. Ambient temperature can be measured directly by the vehicle's temperature sensor, while road surface temperature is obtained through weather services. Temperature data directly impacts battery performance because battery chemical reactions and efficiency change with temperature. Second, humidity data, which can be measured by the vehicle's humidity sensor. Humidity affects air density, thus affecting the vehicle's aerodynamic performance and energy consumption. Third, wind speed and direction data, which can be obtained through the vehicle's anemometer or from a local weather station. Wind speed and direction directly affect vehicle drag, thus affecting energy consumption. Additionally, environmental data includes altitude, which can be measured via GPS or a barometer. Altitude affects air density, thus affecting engine efficiency and energy consumption.

[0083] The acquired current environmental data and real-time traffic data are input into a pre-established big data model to determine the vehicle's current operating scenario. In this embodiment, the big data model is built based on a large amount of historical environmental and traffic data. The big data model can employ deep learning algorithms to identify and classify different operating scenarios. Specifically, the inputs to the big data model include current environmental data (such as temperature, humidity, wind speed, altitude, etc.) and real-time traffic data (such as road type, traffic density, etc.). The big data model first preprocesses the input data, including data cleaning, standardization, and feature extraction. Then, the preprocessed data can be input into a multi-layer neural network. The multi-layer neural network analyzes the input data, compares and matches the current situation with historical data, and finally outputs the most matching operating scenario category. For example, the big data model can identify the current situation as a "high temperature and high humidity urban congestion scenario" or a "cold low-speed driving scenario," etc.

[0084] After determining the vehicle's current operating scenario, the system queries a pre-defined battery parameter database for the corresponding battery parameter range. This database records the normal operating parameter ranges for batteries under different operating scenarios. During the query, the current operating scenario is used as the keyword to locate the relevant record in the database. This record includes the normal ranges for battery temperature, voltage, and current under similar scenarios. For example, for a "high-temperature urban congestion scenario," the battery parameter ranges are as follows: battery temperature should be between 35°C and 45°C, voltage between 350V and 380V, and current between -200A and 200A (negative values ​​indicate charging, positive values ​​indicate discharging).

[0085] It's important to note that battery parameter ranges are not fixed and can change depending on the specific scenario. For example, the battery parameter range can be dynamically adjusted based on ambient temperature, driving speed, road gradient, and other factors. By querying the battery parameter range, you can determine whether the current battery operating status is within the normal range. If the actual parameters fall within the range, it indicates that the battery is operating normally under the current scenario; if they exceed the range, further analysis and appropriate measures are required.

[0086] After confirming that the battery parameters are within the normal range, it indicates that the battery may be experiencing false alarms. To more accurately determine the battery's current state, battery energy consumption can be predicted to improve operational efficiency. First, acquire vehicle energy consumption data within a preset kilometer range. This preset kilometer range is typically the most recent distance traveled, such as the most recent 10 or 20 kilometers; the specific length can be set according to actual needs. Energy consumption data includes the average energy consumption rate (kWh / km) and instantaneous energy consumption rate changes within the preset kilometer range. Then, considering the current battery parameters, the acquired energy consumption data, and the vehicle's current operating scenario, a predictive model is used to estimate the energy consumption trend over a future preset time period (e.g., the next 1 or 2 hours).

[0087] Specifically, the prediction model can be a neural network model, and the prediction results include two main indicators: battery consumption rate and remaining range. Battery consumption rate is expressed as the rate of energy loss per hour or per kilometer, while remaining range is an estimated driving distance calculated based on the current battery level and the predicted consumption rate. It should be noted that the prediction is dynamically updated, continuously monitoring actual energy consumption and comparing it with the prediction results. The prediction model is continuously adjusted and optimized based on deviations to improve prediction accuracy.

[0088] Based on predicted energy consumption trends, combined with vehicle operation data and driving behavior data, a power output pattern for electric public vehicles on the current route is generated. This power output pattern is a dynamic strategy used to optimize the vehicle's power allocation to maximize energy efficiency and optimize battery life. The energy consumption trend includes the battery depletion rate and remaining range. If the prediction shows a low remaining range or a rapid battery depletion rate, a more energy-efficient power output pattern is generated. Secondly, vehicle operation data, such as current speed, acceleration, and motor power output, can be analyzed. For example, during high-speed cruising, a stable power output pattern is generated; while in urban areas with frequent acceleration and deceleration, power allocation during acceleration can be optimized to reduce energy loss. Furthermore, if frequent rapid acceleration and braking are detected, a smoother power output curve can be generated to suppress uneconomical driving behaviors.

[0089] Specifically, the power output mode can be a time-series power value, such as a maximum power limit or an acceleration slope limit. The power output mode can be dynamically adjusted based on real-time feedback from road conditions and driving behavior. For example, on uphill sections, higher power output can be temporarily permitted; while on downhill sections, the energy recovery rate can be increased. Through this intelligent power output management, energy efficiency can be maximized while ensuring vehicle performance, extending battery life, and improving the overall operational efficiency of the vehicle.

[0090] After generating the power output mode, specific braking adjustment commands can be generated based on this mode. These commands guide electric public vehicles to execute specific braking strategies to achieve optimal energy management and driving safety. Specifically, an ideal deceleration curve is first determined based on the power output mode. This curve must consider not only energy efficiency but also passenger comfort. Then, the optimal braking force distribution is calculated based on the current vehicle speed and the expected deceleration. This optimal braking force distribution includes the force distribution between conventional braking (such as friction braking) and regenerative braking. At low speeds, regenerative braking can be relied upon more to maximize energy recovery; while at high speeds or in emergency situations, conventional braking can be used more to ensure safety.

[0091] In addition, braking adjustment commands need to consider road conditions. For example, on downhill sections, the proportion of regenerative braking can be increased to better control vehicle speed and recover kinetic energy. On slippery surfaces, gentler braking commands can be generated to avoid tire slippage. The final generated braking adjustment command is a data package containing multiple parameters, including braking force magnitude, braking force distribution ratio, braking time curve, and other information. The braking adjustment command is designed to be directly executed by the vehicle's control terminal to ensure precise control and smooth implementation of the braking process.

[0092] Finally, the generated braking adjustment command is sent to the vehicle terminal to execute the corresponding braking strategy. First, the braking adjustment command is transmitted from the electronic device to the vehicle's ECU via the vehicle's communication network (such as CAN bus or Ethernet). Upon receiving the command, the ECU performs rapid verification and processing to ensure its validity and safety. Then, the ECU converts these commands into specific control signals and sends them to various vehicle functions, including braking, power, and energy recovery. In other words, when the vehicle terminal receives the braking adjustment command, it first parses the command and converts it into specific execution commands. These execution commands are then distributed to relevant vehicle functions, such as braking, power, and battery management.

[0093] In this embodiment, by connecting an electronic device to the vehicle terminal of an electric public vehicle, precise monitoring and intelligent management of the battery status are achieved, thereby significantly improving the operation efficiency and safety of the electric public vehicle. After receiving a battery alarm signal, the battery parameters and vehicle operation data of the electric public vehicle are obtained. At the same time, the current environmental data is obtained, and the above data is input into a big data model constructed based on historical environmental data and historical road condition data to generate the current operation scenario of the vehicle. By querying the battery parameter interval corresponding to the current operation scenario in the preset battery parameter database, it is possible to accurately determine whether the battery status is normal. If the battery parameters are within the normal interval, the vehicle energy consumption data within a preset kilometer interval will be further obtained, and combined with the battery parameters, vehicle energy consumption data, and current operation scenario, the energy consumption trend within a preset future time period will be predicted. According to the energy consumption trend, vehicle operation data, and driving behavior data, a power output mode for the electric public vehicle on the current driving route is generated for optimizing power distribution, and a braking adjustment instruction is generated to instruct the vehicle terminal to execute a braking strategy, thereby achieving intelligent control of the electric public vehicle. This not only improves the accuracy of battery monitoring and reduces the occurrence of false alarms, but also ensures the stable operation of the vehicle under various operating conditions through intelligent prediction and optimized power distribution, avoiding vehicle outages caused by battery problems and enhancing the travel experience of passengers and the convenience of operation management. In addition, through the analysis of real-time road condition data and driving behavior data, the energy consumption management of the vehicle is optimized, further reducing the operating cost and providing strong support for the sustainable development of electric public vehicles.

[0094] In one implementation manner of this embodiment, the steps for constructing the big data model include:

[0095] S210. Using a preset feature extraction algorithm, perform feature extraction on the historical environmental data and historical road condition data to obtain n first features, where n is an integer greater than 3;

[0096] S220. Using a first preset clustering algorithm, cluster the n first features to obtain m clustering clusters, where 0 < m < n and m is an integer;

[0097] S230. Using a feature extraction algorithm, perform feature extraction on the m clustering clusters to obtain p second features, where 0 < p < m and p is an integer;

[0098] S240. Using a second preset clustering algorithm, cluster the p second features to obtain q clustering results, where each clustering result includes a clustering center, and 0 < q < p and q is an integer;

[0099] S250. Using a preset distance algorithm, for each cluster center, calculate the average distance between all second features and the cluster center, and take the cluster center corresponding to the smallest average distance as the target cluster center, and take the clustering result corresponding to the target cluster center as the target clustering result.

[0100] S260. Map the target clustering results to the corresponding operational scenarios according to the preset mapping function;

[0101] S270. The feature extraction algorithm, the first preset clustering algorithm, the second preset clustering algorithm, the distance algorithm, and the mapping function are encapsulated to obtain a big data model.

[0102] Feature extraction algorithms are used to extract the most representative and discriminative features from raw, high-dimensional data to reduce data complexity while retaining key information. In this embodiment, Principal Component Analysis (PCA) or Independent Component Analysis (ICA) algorithms can be used to extract features from historical environmental and traffic condition data, ultimately outputting n first features, where n is an integer greater than 3. For example, n is 15, including 5 environmentally relevant features (such as temperature trends and humidity fluctuations) and 10 traffic condition relevant features (such as traffic flow cycles and road slope distribution).

[0103] A first-preset clustering algorithm is used to cluster n first features to group data points with similar features, thereby discovering the inherent structure and patterns in the data. The first-preset clustering algorithm can be K-means, etc. Taking K-means as an example, it iteratively assigns data points to the nearest cluster centers and continuously updates the cluster centers until convergence.

[0104] Figure 2 The diagram illustrates the first clustering method provided in an embodiment of this application. The output of the first clustering is multiple initial clusters based on the original data features. Each cluster represents a set of data points with similar features. Figure 2As shown, in practical implementation, firstly, a suitable number of clusters *m* needs to be determined according to the preset algorithm. Assume the optimal number of clusters is determined to be 10. Then, K-means clustering is performed on the *n* primary features, with *k* = 10. The clustering process divides all data points in the *n* feature space into 10 clusters. Each cluster represents a group of data points with similar features. For example, the clusters could be: 1. High-speed smooth traffic (high speed, low traffic volume, good weather); 2. High-speed congestion (low speed, high traffic volume, good weather); 3. Medium-speed normal traffic (medium speed and traffic volume, good weather); 4. Rainy weather low speed (low speed, medium traffic volume, precipitation); 5. Fog low speed (low speed, low traffic volume, low visibility); 6. Nighttime smooth traffic (high speed, low traffic volume, nighttime); 7. Morning rush hour congestion (low speed, high traffic volume, morning period); 8. Evening rush hour congestion (low speed, high traffic volume, evening period); 9. Weekend shopping area congestion (low speed, high traffic volume, weekend, commercial area); 10. Holiday suburban smooth traffic (high speed, medium traffic volume, holiday, suburbs).

[0105] The final output consists of m clusters, where m is less than n and is a positive integer. Each cluster contains a set of data points with similar characteristics.

[0106] After obtaining m clusters, feature extraction algorithms are used again to extract features from these clusters, thereby further refining and abstracting data features to extract higher-level and more representative features from the clustering results, so as to facilitate subsequent analysis and model building.

[0107] Feature extraction algorithms can use statistical methods (such as mean, variance, skewness, kurtosis, etc.) to describe the distribution characteristics of each cluster.

[0108] Taking statistical methods as an example, for each cluster, the following characteristics can be calculated: 1. Cluster center coordinates: reflecting the average position of the cluster; 2. Cluster radius: reflecting the cluster compactness; 3. Variance of data points within the cluster: reflecting the dispersion of data within the cluster; 4. Distance between clusters: reflecting the degree of separation between clusters.

[0109] Suppose there are 10 clusters (m=10), and 5 features are extracted from each cluster, resulting in a total of 50 features. However, these features may contain redundancies or highly correlated features. Therefore, feature selection is necessary to retain only the most representative and discriminative features.

[0110] By calculating the correlation between features, the p most important secondary features can be selected. For example, the final output will contain 20 features (p = 20), including the center coordinates, main orientation, and density of each cluster. In this embodiment, p secondary features are output, where p is less than m and is a positive integer. The secondary features represent a higher level of abstraction of the original data, capturing key information in the clustering results while reducing the dimensionality of the data.

[0111] To discover the structure and patterns of data at a higher level of abstraction, a second pre-defined clustering algorithm is used to cluster p second features. This groups similar second features together to form more general categories, thereby revealing potential operational scenarios or patterns in the data. The second clustering is performed based on the results of the first clustering, and its output is a higher-level clustering result. In this embodiment, the second pre-defined clustering algorithm can be hierarchical clustering.

[0112] Specifically, taking hierarchical clustering as an example, a tree-like clustering structure can be created, allowing the clustering results to be observed at different levels. The specific steps are as follows: 1. First, treat each second feature as a separate cluster. 2. Calculate the distance between all cluster pairs (Euclidean distance, Manhattan distance, etc. can be used). 3. Find the two closest clusters and merge them into a new cluster. 4. Repeat steps 2 and 3 until a preset number of clusters is reached or a certain stopping condition is met.

[0113] Assuming there are 20 secondary features (p=20), using the second preset clustering algorithm, four high-level clusters (q=4) can be obtained. These four categories represent four different operational scenarios or modes, such as... Figure 3 As shown.

[0114] exist Figure 3 In this model, each clustering result contains a cluster center. For example, the four clustering results represent: 1. Smooth traffic (including first clusters 1, 6, and 10), characterized by high vehicle speeds and low to moderate traffic volume; 2. Moderate congestion (including first clusters 2, 3, 7, 8, and 9), characterized by low to moderate vehicle speeds and moderate to high traffic volume; 3. Weather impact (including first clusters 4 and 5), characterized by low vehicle speeds and significant influence from weather conditions; 4. Special time periods (including first clusters 6, 7, 8, 9, and 10), characterized by significant influence from time and location factors. The first clustering identifies specific traffic conditions, while the second clustering categorizes these conditions into broader scenario types.

[0115] The final output consists of q clustering results, each containing a cluster center, where q is less than p and is a positive integer. Ultimately, the feature set is categorized into several main classes, each representing a typical operational scenario or pattern.

[0116] Then, a preset distance algorithm is used to calculate the average distance between all second features and each cluster center, and the cluster center with the smallest average distance is selected as the target cluster center. In order to select the most representative cluster result from the q cluster results, it serves as the basis for subsequent analysis and application.

[0117] Distance algorithms can include Euclidean distance, cosine similarity, etc. Taking Euclidean distance as an example, the specific steps are as follows: 1. For each cluster center, calculate the Euclidean distances from all p second features to that center. 2. Calculate the average of these distances to obtain the average distance of the cluster center. 3. Repeat steps 1 and 2 to calculate the average distance of all q cluster centers. 4. Compare the q average distances and select the smallest one as the target cluster center.

[0118] The target clustering results represent the most typical and representative patterns or scenarios in the data, reflecting the performance characteristics of electric public vehicles under the most common operating conditions.

[0119] The target clustering results are mapped to the corresponding operational scenarios based on a preset mapping function. Specifically, the preset mapping function establishes a correspondence between the clustering results and specific operational scenarios. The mapping function can be a lookup table or a decision tree. For example, if the target clustering result corresponds to "general congestion" (including clusters 2, 3, 7, 8, and 9 from the first cluster), then the preset mapping function can map it to the following operational scenario: a typical urban congestion scenario (characteristics: low to moderate vehicle speed, moderate to high traffic volume; time: morning and evening rush hours; location: major urban arterial roads, areas surrounding commercial districts, and major roads connecting residential and work areas).

[0120] Finally, the feature extraction algorithm, the first preset clustering algorithm, the second preset clustering algorithm, the distance algorithm, and the mapping function are encapsulated to construct a complete big data model. In implementation, a main control flow can be written that calls each component in a specific order. For example, feature extraction is performed first, followed by the first clustering, the second clustering, and distance calculation, and finally the mapping function is applied. Each component is designed as an independent module with clearly defined input and output interfaces, allowing for optimization or replacement of individual components without affecting the overall model. The result is a complete, end-to-end big data model.

[0121] This implementation employs a two-round clustering process (a first preset clustering algorithm and a second preset clustering algorithm) to group data. This better captures the hierarchical structure and inherent relationships of the data, enabling more accurate identification and classification of different operational scenarios. Furthermore, it maps the optimized clustering results to specific operational scenarios, improving the interpretability and practicality of the model output.

[0122] In one embodiment of this invention, the following steps are also included:

[0123] S310. When the battery parameters are not within the battery parameter range, the current battery level of the electric public vehicle is obtained through the vehicle terminal, and the maximum driving distance of the electric public vehicle is calculated based on the current battery level.

[0124] S320, Obtain the current location of the electric public vehicle;

[0125] S330. Based on the current location, determine the remaining travel distance of the electric public vehicle on the current route;

[0126] S340. If the remaining driving distance is greater than the maximum driving distance, calculate the straight-line distance between the current location and the end point of the current driving route, and search for electric public vehicle charging stations within the area centered on the current location and with the straight-line distance as the radius.

[0127] S350: When there are multiple electric public vehicle charging stations, the electric public vehicle charging station with the shortest distance from the current location will be the target charging station.

[0128] S360 generates a new driving route based on the current location, the target charging station, and the end point of the current driving route, and sends the new driving route to the vehicle terminal.

[0129] In this embodiment, the system first determines whether the battery parameters are within a preset range. If not, the system obtains the current battery level of the electric bus through the vehicle terminal and calculates the maximum driving distance. Specifically, the vehicle terminal reads real-time battery data provided by the Battery Management System (BMS) via the CAN bus or other vehicle networks. This real-time battery data is typically expressed as a percentage. Then, based on the vehicle model's specific energy consumption model, the battery level is converted into an estimated driving range. For example, assuming an electric bus has a full-charge range of 300 kilometers and a current battery level of 60%, considering the influence coefficient of factors such as road conditions and weather (0.9), the maximum driving distance can be estimated as: 300 × 60% × 0.9 ≈ 162 kilometers.

[0130] Subsequently, the current location of the electric public vehicle can be obtained through the onboard GPS module or other positioning systems, such as the BeiDou Navigation Satellite System. In practice, the onboard terminal will periodically (usually every second or every few seconds) update the location information, including data such as longitude, latitude, altitude, speed, and direction. This data is transmitted in real time to the central management system (electronic devices) via mobile communication networks (such as 4G / 5G). For example, the current location could be: longitude 116.3972°E, latitude 39.9075°N, altitude 50 meters, speed 40 km / h, and direction 270° (due west).

[0131] Based on the obtained current location, the remaining travel distance of the electric public vehicle on the current route is determined. In practice, the vehicle's GPS coordinates are first mapped to the nearest road segment on a digital map. Then, a path planning algorithm is used to calculate the shortest path from the current location to the destination. For example, assuming the total length of the current route is 50 kilometers, and map matching determines that the vehicle's current location is 35 kilometers from the starting point, then the remaining travel distance is 15 kilometers.

[0132] If the remaining driving distance is greater than the maximum driving distance, calculate the straight-line distance between the current location and the destination of the current driving route, and locate electric public vehicle charging stations within this range. Specifically, first, the straight-line distance between two points is calculated using the Haversine formula. Assuming the current location is (l at1, lon1) and the destination is (l at2, lon2), the straight-line distance D can be calculated using the following formula:

[0133]

[0134] Where R is the Earth's radius (approximately 6371 kilometers). For example, if the current location is (39.9075°N, 116.3972°E) and the destination is (39.9868°N, 116.4321°E), the calculated straight-line distance is approximately 9.38 kilometers.

[0135] Next, using the current location as the center and the calculated straight-line distance as the radius, perform a spatial query in the GIS database to filter out all charging stations located within the circular area.

[0136] When multiple electric public vehicle charging stations are found, the charging station with the shortest distance from the current location is selected as the target charging station. In this embodiment, the K-Nearest Neighbor (KNN) algorithm can be used, where K=1. Specifically, the distance from the current location to each candidate charging station is first calculated. Euclidean distance can be used. Taking Euclidean distance as an example, for the current location (x0, y0) and the charging station location (x... i ,y i ), distance d i The calculation is as follows:

[0137]

[0138] After calculating all distances, the charging station with the shortest distance is selected as the target. For example, assuming there are three candidate charging stations with distances of 5.2 km, 3.8 km, and 4.5 km from the current location, the charging station with a distance of 3.8 km is selected as the target charging station.

[0139] Based on the current location, the target charging station, and the destination of the current route, a new driving route is generated and sent to the vehicle terminal. Specifically, this can be achieved through interaction between a multi-point path planning algorithm and the in-vehicle navigation system. In practice, a preset path planning algorithm is first used to calculate the optimal route passing through the charging station. This algorithm takes into account factors such as the road network topology, traffic rules, and real-time traffic conditions. For example, assuming the current location is A, the target charging station is B, and the destination is C, the algorithm calculates the optimal path from A to B, and then from B to C, merging the two paths into a single new route. The new route may be represented as a sequence of coordinates of waypoints or a sequence of road segment IDs. The generated route data typically includes information such as total distance, estimated time, and turn instructions. This data is then sent to the vehicle terminal via a wireless communication network (such as 4G / 5G). Upon receiving the new route, the vehicle terminal updates the navigation information and informs the driver of the route change via voice prompts.

[0140] This implementation method, by monitoring the battery status, location information, and driving routes of electric public vehicles in real time, can intelligently determine charging needs and automatically plan the optimal charging route, effectively solving the problem of electric vehicle range limitations and improving the flexibility and reliability of vehicle dispatching. Through precise route planning and charging station selection, it maximizes vehicle operating efficiency while reducing the risk of service interruption due to battery depletion, effectively improving the operational efficiency of electric public vehicles.

[0141] In one embodiment of this invention, the energy consumption trend of electric public vehicles within a preset future time period is predicted based on battery parameters, vehicle energy consumption data, and the current operating scenario of the vehicle, including the following steps:

[0142] S410: Input battery parameters, vehicle energy consumption data and the current operating scenario of the vehicle into a pre-trained prediction model to obtain the energy consumption trend of electric public vehicles within a preset time period in the future.

[0143] In this embodiment, battery parameters, vehicle energy consumption data, and the vehicle's current operating scenario are input into a pre-trained prediction model to obtain the energy consumption trend of electric public vehicles within a preset future time period. Specifically, battery parameters include key indicators such as battery capacity, current charge level, number of charge / discharge cycles, and battery internal resistance. Vehicle energy consumption data includes historical average energy consumption, air conditioning power consumption, and energy consumption during hill climbing. The vehicle's current operating scenario includes environmental factors affecting energy consumption, such as current road conditions, weather conditions, and driving speed.

[0144] Predictive models can employ deep learning models, such as Long Short-Term Memory (LSTM) networks, to process time-series data and capture long-term dependencies. A trained deep learning model can predict energy consumption trends over a future period (e.g., the next 2 or 4 hours) based on the current input state.

[0145] In practical applications, assuming an LSTM model is used, the input vector contains 20 features: 5 battery parameters (e.g., battery capacity, current charge level, battery temperature, internal resistance, cycle count), 5 vehicle energy consumption data (e.g., average energy consumption over the past hour, air conditioning power, motor efficiency, vehicle speed, acceleration), and 10 operational scenario parameters (e.g., ambient temperature, humidity, wind speed, traffic congestion index, gradient, passenger load factor, etc.). The model output is the predicted energy consumption every 15 minutes for the next 4 hours, totaling 16 values.

[0146] For example, consider the following current status of an electric bus: Battery parameters: 100kWh capacity, current charge 80%, battery temperature 25℃, internal resistance 0.1Ω, cycle life 500 times; Energy consumption data: average energy consumption of 1.2kWh / km over the past hour, air conditioning power 3kW, motor efficiency 90%, current speed 40km / h, acceleration 0.5m / s². 2 Operating scenario: ambient temperature 30℃, humidity 60%, wind speed 2m / s, road congestion index 0.3, average slope 1%, passenger load factor 70%, etc. After standardizing the above data, it is input into the pre-trained LSTM model, and the following prediction results are output: the estimated energy consumption (kWh) every 15 minutes in the next 4 hours: [1.8, 1.7, 1.9, 2.0, 2.1, 2.0, 1.8, 1.7, 1.6, 1.5, 1.4, 1.3, 1.2, 1.1, 1.0, 0.9].

[0147] The results indicate that energy consumption may increase slightly in the next hour (due to entering congested or uphill sections), and then gradually decrease (due to entering flat sections).

[0148] This implementation method can accurately predict future energy consumption trends, plan charging strategies in advance, avoid service interruptions caused by power depletion, and thus significantly improve the operational efficiency and reliability of electric public vehicles.

[0149] In one embodiment of this invention, the power output mode of the electric public vehicle on the current route is generated based on energy consumption trends, vehicle operation data, and driving behavior data, including the following steps:

[0150] S510. Based on the energy consumption trend, calculate the power supply corresponding to each time step, and fit the power supply corresponding to each time step to generate the power supply curve of the electric public vehicle.

[0151] S520. Based on vehicle operation data, determine the driving status of the electric public vehicle, including idling, acceleration, constant speed, and deceleration.

[0152] S530. Obtain the energy conversion efficiency curve of the electric public vehicle, and determine the optimal output power of the electric public vehicle in the driving state based on the power supply curve and the energy conversion efficiency curve.

[0153] S540, calculates the curvature of the power supply curve in real time;

[0154] S550: When the curvature is greater than a preset threshold, the power output mode is determined based on driving behavior data and the optimal output power of the electric public vehicle in driving state.

[0155] First, the power supply for each time step is calculated based on the energy consumption trend, and the power supply for each time step is fitted to generate a power supply curve for the electric public transport vehicle. Specifically, the required power supply for each time step (e.g., every 15 minutes) is calculated based on the energy consumption trend. The calculation method is to divide the energy consumption of each time interval by the time interval to obtain the average power. For example, if 3 kWh of energy is expected to be consumed within 15 minutes, the average power supply for that time step is 12 kW (3 kWh / 0.25 h).

[0156] Next, curve fitting is performed on the discrete power points. Fitting methods include polynomial fitting, spline interpolation, or Fourier series fitting. In this embodiment, cubic spline interpolation is used to ensure the smoothness and continuity of the curve. Assume the following power data points: (0, 10kW), (15, 12kW), (30, 15kW), (45, 13kW), (60, 11kW), where the first number represents time (minutes) and the second number represents power. After using cubic spline interpolation, a continuous function P(t) is obtained, representing the power supplied at any time t.

[0157] The driving status of electric public vehicles is determined based on vehicle operation data, including idling, acceleration, constant speed, and deceleration. First, onboard sensors (such as speed sensors and accelerometers) acquire real-time speed and acceleration data. The rules for determining the driving status of electric public vehicles are as follows: 1. Idle: Vehicle speed is close to 0 (e.g., less than 1 km / h), and acceleration is close to 0. 2. Acceleration: Acceleration is greater than a certain positive threshold (e.g., 0.1 m / s²). 2 3. Uniform speed state: The vehicle speed is greater than a certain threshold (e.g., 5 km / h), and the acceleration is close to 0 (e.g., the absolute value is less than 0.05 m / s²). 2 4. Deceleration state: Acceleration is less than a certain negative threshold (e.g., -0.1 m / s²). 2 ).

[0158] Then, the energy conversion efficiency curve of the electric public vehicle is obtained, and the optimal output power of the electric public vehicle under each driving state is determined based on the power supply curve and the energy conversion efficiency curve.

[0159] First, the energy conversion efficiency curve of the motor is obtained through a pre-set energy conversion efficiency curve database. The energy conversion efficiency curve represents the relationship between the motor's output power and efficiency. For example, a typical motor efficiency curve may show the highest efficiency (e.g., 90-95%) within the range of 20-80% of rated power, while the efficiency is lower at extremely low or extremely high power.

[0160] Next, the power supply curve is combined with the energy conversion efficiency curve to determine the optimal output power for each driving state. A lookup table method can be used in this specific implementation. For example, suppose that at a certain moment, the power supply curve gives a power of 50kW, and the efficiency curve shows that the efficiency is highest at 48kW (reaching 94%). Therefore, 48kW is taken as the optimal output power at that moment.

[0161] The selection criteria for optimal power may differ depending on the driving conditions: 1. Idle: Select the lowest power that can maintain basic system operation. 2. Acceleration: Select the power point with the highest efficiency while meeting acceleration requirements. 3. Constant speed: Select the power point that can maintain the current speed with the highest efficiency. 4. Deceleration: Prioritize energy recovery and select the power point that maximizes recovery efficiency.

[0162] The curvature of the power supply curve is calculated in real time. Curvature is an important indicator describing the degree of curvature of the curve, reflecting the extent to which the curve deviates from a straight line near a certain point.

[0163] For a parameterized planar curve, such as the power supply curve P(t), where t represents time, the curvature K can be calculated using the following formula:

[0164] K = |P″(t)| / (1+(P′(t))) 2 ) (3 / 2) ;

[0165] Where P'(t) and P'(t) are the first and second derivatives of P(t), respectively.

[0166] In practical applications, since power supply curves are typically discrete data points, numerical methods are needed to approximate the derivatives and curvature. The central difference method can be used.

[0167] P′(t)≈(P(t+h)-P(th)) / (2h);

[0168] P″(t)≈(P(t+h)-2P(t)+P(th) / h2 ;

[0169] Where h is the time step. For example, suppose at time point t = 30 minutes, P(29) = 48 kW, P(30) = 50 kW, P(31) = 53 kW, and the time step h = 1 minute. Then:

[0170] P'(30)≈(53-48) / 2=2.5kW / min;

[0171] P”(30)≈(53-2×50+48)=1kW / min 2 ;

[0172] Substituting into the curvature formula, the curvature at t = 30 minutes can be calculated.

[0173] Curvature allows for real-time monitoring of the drastic changes in power supply. High curvature signifies rapid changes in power demand. By monitoring curvature, sudden shifts in power demand can be predicted, thereby improving the flexibility and responsiveness of energy management.

[0174] When the curvature exceeds a preset threshold, the power output mode is determined based on driving behavior data and the optimal output power of the electric public vehicle in the current driving state. First, a curvature threshold is set, which can be twice the average curvature. When the curvature is detected to exceed the threshold, the power management strategy is triggered.

[0175] Next, we analyze driving behavior data. This data includes the driver's accelerator pedal position, braking frequency, and steering angle. For example, if the driver frequently depresses the accelerator pedal, it can be predicted that the electric bus is about to enter a section of road requiring frequent acceleration.

[0176] Based on driving behavior data and the previously determined optimal output power, the power output mode is determined. Power output modes can include: 1. Energy-saving mode: Limiting power output to a low level while ensuring basic performance to maximize energy efficiency. 2. Dynamic response mode: Allowing rapid power changes to adapt to frequent acceleration and deceleration demands. 3. Smooth mode: Smoothing the energy consumption curve through gradual changes in power output to reduce peak load. 4. Performance mode: Allowing higher power output for short periods to meet instantaneous high-performance demands.

[0177] For example, suppose the current curvature is 0.5, exceeding the preset threshold of 0.3. Driving behavior data shows that the driver is frequently accelerating, while the optimal output power for the current driving state is 60kW. In this case, the dynamic response mode is selected, setting the power output range to 50-70kW to quickly respond to the driver's actions while maintaining fluctuations near the optimal power.

[0178] This implementation method, by considering the changing trend (curvature) of the power supply, driving behavior, and optimal power, can more flexibly adjust the power output to meet driving needs while optimizing energy utilization within the possible range. It can improve the vehicle's dynamic performance while maximizing energy efficiency, thus achieving a better balance between performance and efficiency, and realizing intelligent and personalized power output management.

[0179] In one embodiment of this invention, the optimal output power of the electric public vehicle in operation is determined based on the power supply curve and the energy conversion efficiency curve, including the following steps:

[0180] S610. Based on the power supply curve and energy conversion efficiency curve, obtain the power supply data segment and the corresponding energy conversion efficiency data segment under driving conditions;

[0181] S620. For each time point of the power supply data segment and the corresponding energy conversion efficiency data segment, calculate the actual output power at each time point under driving conditions, and generate an output power curve based on the actual output power at each time point.

[0182] S630. Based on the output power curve and the energy conversion efficiency curve, determine the optimal efficiency range and calculate the average value of the output power corresponding to the optimal efficiency range. Use the average value as the optimal output power of the electric public vehicle in the driving state.

[0183] First, based on the power supply curve and energy conversion efficiency curve, obtain the power supply data segment and the corresponding energy conversion efficiency data segment for a specific driving state. Specifically, it is necessary to locate the corresponding time period in the entire power supply curve according to the driving state (such as idling, acceleration, constant speed, or deceleration). This can be achieved by finding the time points when the driving state changes. For example, if the time point when the vehicle changes from idling to acceleration is t1, and the time point when it changes back to constant speed is t2, then the power supply data in the time interval [t1, t2] corresponds to the acceleration state.

[0184] Next, data for that time interval is extracted from the power supply curve to form the power supply data segment for that driving state. Simultaneously, the efficiency data corresponding to these power supply values ​​is found in the energy conversion efficiency curve. Since the energy conversion efficiency curve is a function of power as the independent variable, the corresponding efficiency values ​​can be obtained directly through table lookup or interpolation. For example, assuming the power supply is 40kW at time t1 and 60kW at time t2 during acceleration, the efficiency values ​​corresponding to all power points within the range of 40kW to 60kW are found in the energy conversion efficiency curve.

[0185] Next, for each time point in the power supply data segment and the corresponding energy conversion efficiency data segment, the actual output power at each time point under driving conditions is calculated, and an output power curve is generated based on these actual output powers. First, the actual output power is the result of the power supply power after energy conversion, and its calculation formula is:

[0186] Actual output power = power supplied × energy conversion efficiency;

[0187] The above calculations are required for each time point. For example, assuming that at a certain time point t, the power supply is 50kW and the corresponding energy conversion efficiency is 0.9 (i.e., 90%), then the actual output power at that time point is: 50kW × 0.9 = 45kW.

[0188] Assume the following data: t1: power supply 40kW, efficiency 0.88; t2: power supply 45kW, efficiency 0.90; t3: power supply 50kW, efficiency 0.92; the calculated actual output power is: t1: 40kW × 0.88 = 35.2kW; t2: 45kW × 0.90 = 40.5kW; t3: 50kW × 0.92 = 46.0kW.

[0189] Based on the calculation results above, a new data sequence can be generated, which represents the change of actual output power over time. Connecting these data points will form the output power curve.

[0190] Based on the output power curve and the energy conversion efficiency curve, the optimal efficiency range is determined, and the average output power corresponding to this range is calculated. This average value is taken as the optimal output power for the electric public vehicle under specific driving conditions. First, the output power curve and the energy conversion efficiency curve need to be compared and analyzed. Typically, the energy conversion efficiency curve will show one or more high-efficiency regions; the task is to find the part within these regions that best matches the actual output power.

[0191] The optimal efficiency range can be determined using the following steps: 1. Set an efficiency threshold on the energy conversion efficiency curve, for example, 90%. 2. Identify all power ranges with efficiencies higher than this threshold. 3. Check the overlap between these high-efficiency ranges and the actual output power curve. 4. Select the range with the highest overlap as the optimal efficiency range. For example, suppose the energy conversion efficiency curve shows an efficiency exceeding 90% in the 35-50kW range, while the actual output power curve falls within the 30-55kW range for most of the time. Then, 35-50kW can be determined as the optimal efficiency range.

[0192] Next, calculate the average output power within the optimal efficiency range. Assume the sampled output power values ​​within this range are as follows: 37kW, 40kW, 43kW, 46kW, 49kW; the average value is calculated as: (37+40+43+46+49) / 5 = 43kW. Therefore, 43kW is determined as the optimal output power for this driving condition.

[0193] This implementation method allows for a clear view of the vehicle's actual power output capability at different times through the output power curve, and obtains an optimal output power value that meets actual power requirements while ensuring high efficiency. By controlling the actual operation around this power, energy utilization efficiency can be maximized and unnecessary energy loss can be reduced.

[0194] In one embodiment of this invention, the power output mode is determined based on driving behavior data and the optimal output power of the electric public vehicle in driving mode, including the following steps:

[0195] S710. Based on driving behavior data, determine the driving behavior type, which includes smooth, moderate, and aggressive driving behavior types;

[0196] S720. Obtain the weight coefficients corresponding to the driving behavior type from the preset database;

[0197] S730. Calculate the power adjustment coefficient of the actual output power at each time point according to the weighting coefficient. The product of the optimal output power and the power adjustment coefficient is less than the maximum output power of the electric public vehicle.

[0198] S740. Calculate the product of the actual output power at each time point and the corresponding power adjustment coefficient to obtain multiple adjusted output power values, and generate an optimized power output curve based on all processed output power values.

[0199] S750: Determine the power output mode based on the optimal output power and the optimized power output curve;

[0200] The power output curve includes a low power range, a medium power range, and a high power range. The power output modes include energy-saving mode, standard mode, and power mode. When the optimal output power is located in the low power range of the power output curve, the power output mode is energy-saving mode. When the optimal output power is located in the medium power range of the power output curve, the power output mode is standard mode. When the optimal output power is located in the high power range of the power output curve, the power output mode is power mode.

[0201] Determine the driving behavior type based on driving behavior data, including three types: smooth, medium, and aggressive. First, extract key features from the driving behavior data. The key features include the acceleration change rate, braking frequency, steering angle change, etc. For example, indicators such as the average acceleration, maximum acceleration, and acceleration standard deviation within a certain period of time can be calculated. Then, compare these feature values with predefined thresholds to determine the driving behavior type.

[0202] In specific implementation, the following method can be adopted: Set the acceleration change rate thresholds a1 and a2, where a1 < a2. Calculate the average acceleration change rate a within a certain period of time (such as 5 minutes). If a < a1, it is determined as smooth driving; if a1 ≤ a < a2, it is determined as medium driving; if a ≥ a2, it is determined as aggressive driving. For example, assume that a1 = 2m / s 3 , a2 = 4m / s 3 , and the average acceleration change rate calculated within a certain period of time is 3.5m / s 3 , the number of hard brakes is 2 times, and the number of rapid lane changes is 1 time. Judging from the acceleration change rate, it belongs to medium driving.

[0203] Smooth driving means lower energy consumption and higher energy efficiency, while aggressive driving may lead to increased energy consumption and reduced efficiency.

[0204] After that, obtain the weight coefficient corresponding to the driving behavior type in the preset database. The preset database contains different driving behavior types and their corresponding weight coefficients, which reflect the influence degree of different driving behaviors on the power output demand.

[0205] In specific implementation, the following method can be adopted: Store a mapping table in the database, and map the three driving behavior types of smooth, medium, and aggressive to different weight coefficient ranges respectively. For example: Smooth driving: weight coefficient range 0.8 - 1.0; Medium driving: weight coefficient range 1.0 - 1.2; Aggressive driving: weight coefficient range 1.2 - 1.5.

[0206] When the driving behavior type is determined, the corresponding weight coefficient range can be queried from the database. In order to more accurately reflect the continuous change of driving behavior, interpolation calculation can be performed within each range. For example, if it is determined as medium driving but偏向平稳 (biased towards smooth), 1.05 can be selected as the weight coefficient; if it is偏向激进 (biased towards aggressive), 1.15 can be selected as the weight coefficient.

[0207] The power adjustment coefficient is calculated based on the weighted coefficients to determine the actual output power at each time point, while ensuring that the product of the optimal output power and the power adjustment coefficient is less than the maximum output power of the electric public vehicle. Specifically, the power adjustment coefficient is used to fine-tune the actual output power based on driving behavior to better suit the driver's driving style. In practice, the following method can be used: 1. First, use the weighted coefficients obtained in step S720 as the base adjustment coefficients. 2. Calculate the power adjustment coefficient based on the vehicle's maximum output power and the base adjustment coefficients.

[0208] The power adjustment factor can be calculated using the following formula:

[0209] Power adjustment coefficient = min(weighting coefficient, maximum output power / optimal output power);

[0210] The min function ensures that the adjusted power does not exceed the vehicle's maximum output power. For example, assuming the maximum output power of an electric public vehicle is 200kW, the optimal output power at a certain moment is 150kW, and the weighting coefficient is 1.2 (corresponding to aggressive driving), then: Power adjustment coefficient = min(1.2, 200kW / 150kW) = min(1.2, 1.33) = 1.2.

[0211] In the example above, even with aggressive driving, the adjusted power (150kW × 1.2 = 180kW) will not exceed the maximum output power of 200kW.

[0212] The product of the actual output power and the corresponding power adjustment coefficient at each time point is calculated to obtain multiple adjusted output power values. Based on all processed output power values, an optimized power output curve is generated. Specifically, the actual output power at each time point is first adjusted, and then the adjusted data points are connected to form a new power output curve. The specific implementation method is as follows: 1. For each time point, the actual output power is multiplied by the power adjustment coefficient calculated in step S730. 2. All adjusted power values ​​are arranged in chronological order to form a new data sequence. 3. A preset interpolation algorithm is used to connect the discrete data points into a continuous curve. For example, suppose the following data is available: Time point 1: Actual output power 100kW, power adjustment coefficient 1.1; Time point 2: Actual output power 120kW, power adjustment coefficient 1.15; Time point 3: Actual output power 110kW, power adjustment coefficient 1.05.

[0213] Calculate the adjusted output power: Time point 1: 100kW * 1.1 = 110kW; Time point 2: 120kW * 1.15 = 138kW; Time point 3: 110kW * 1.05 = 115.5kW.

[0214] The adjusted power values ​​form a new data sequence: [110kW, 138kW, 115.5kW]. Next, methods such as cubic spline interpolation or Bézier curves can be used to connect the discrete points into a smooth curve, thereby obtaining the optimized power output curve.

[0215] Finally, the power output mode is determined based on the optimal output power and the optimized power output curve. First, the optimized power output curve is divided into low-power, medium-power, and high-power ranges. Then, the corresponding power output mode is determined based on the range where the optimal output power falls. In practice, the threshold for dividing the power ranges is first determined. For example, 0-40% of the maximum power can be defined as the low-power range, 40-70% as the medium-power range, and 70-100% as the high-power range. Second, the optimized power output curve is analyzed to determine the range of each range. Finally, the range where the optimal output power falls is determined, and the corresponding power output mode is selected accordingly. For example, assuming the maximum output power of an electric public vehicle is 200kW, the power ranges are divided as follows: low-power range: 0-80kW; medium-power range: 80-140kW; high-power range: 140-200kW. If the calculated optimal output power is 110kW, then the optimal output power falls within the medium-power range. According to the rules, the standard mode should be selected as the power output mode in this case.

[0216] The optimized power output curve of this implementation better reflects the driver's driving style and needs than the original actual power output curve. It also effectively ensures that the power output does not exceed the vehicle's physical limitations, thus allowing for more precise control of the vehicle's power output. This satisfies the driver's operational needs while optimizing energy efficiency. Furthermore, based on the vehicle's current optimal operating point and overall power distribution characteristics, the most suitable power output mode can be selected. The energy-saving mode is suitable for low-load conditions, maximizing energy efficiency; the standard mode balances performance and efficiency, suitable for daily driving; and the power mode is activated when high-performance output is required, meeting special driving needs. This allows for dynamic adjustment of the vehicle's operating state according to actual conditions, satisfying performance requirements in different scenarios while maximizing energy efficiency where possible. This not only improves the vehicle's adaptability but also provides the driver with a better driving experience.

[0217] In one embodiment of this invention, the driving behavior data includes the frequency of rapid acceleration and braking, vehicle turning angle, vehicle turning speed, and vehicle idling time. Determining the driving behavior type based on this data includes the following steps:

[0218] S810 extracts features from the frequency of rapid acceleration and braking, vehicle turning angle, vehicle turning speed, and vehicle idling time to obtain multiple driving behavior features.

[0219] S820. Input the driving behavior features into the pre-trained classification model to obtain the driving behavior type.

[0220] First, several key features are extracted from the raw driving behavior data. For the frequency of rapid acceleration and braking, an acceleration threshold (e.g., positive acceleration greater than 3 m / s²) can be set. 2 For rapid acceleration, the negative acceleration is less than -3 m / s². 2 For emergency braking, the system counts the number of times a threshold is exceeded within a unit of time (e.g., per hour). For vehicle turning angle, steering wheel angle sensor data can be used to calculate the maximum angle value for each turn. Vehicle turning speed can be obtained through an angular velocity sensor, recording the maximum angular velocity during each turn. Vehicle idling time can be statistically analyzed by determining the duration of engine operation but vehicle speed at zero. After obtaining key features, a sliding window method can be used to calculate time-series features. For example, a 7-day moving average of the number of rapid accelerations per hour can be calculated to reflect the long-term trend of driving behavior. Finally, a set of feature vectors that comprehensively reflects the characteristics of driving behavior is obtained, providing input for subsequent classification models.

[0221] Next, the extracted driving behavior features are input into a pre-trained classification model to obtain the driving behavior type. This pre-trained classification model can employ machine learning algorithms, such as deep learning models. During the training phase, a large amount of labeled driving behavior data needs to be prepared, including feature vectors and corresponding behavior type labels (e.g., aggressive, moderate, energy-efficient, etc.). The model is trained using this data to learn the mapping relationship between features and behavior types.

[0222] During the prediction phase, new feature vectors are input into the model, which can then predict the type of driving behavior based on the learned rules. For example, if a feature vector shows frequent rapid acceleration, sudden braking, large turning angles, and high speeds, the model classifies it as "aggressive" driving behavior.

[0223] This implementation method achieves accurate quantification and intelligent recognition of driving behavior by extracting and classifying features from driving behavior data.

[0224] Example 2, Figure 4 This application provides a schematic flowchart illustrating the process after determining the power output mode, as illustrated in an embodiment of this application. Figure 4 After determining the power output mode based on driving behavior data and the optimal output power of the electric public vehicle in operation, the following steps are also included:

[0225] S910. Obtain the current location and current time of the electric public vehicle, and determine the remaining mileage of the electric public vehicle on the current driving route based on the current location.

[0226] S920. Input the remaining mileage into the pre-trained prediction model to obtain the destination time when the electric public vehicle reaches the end of the current route.

[0227] S930. Based on the optimized power output curve and power output mode, calculate the first energy consumption value of the electric public vehicle from the current time point to the destination time point.

[0228] S940. Determine the second energy consumption value for the remaining mileage based on the energy consumption trend;

[0229] S950: The value of subtracting the first energy consumption value from the second energy consumption value is used as the energy saving for the electric public vehicle on the remaining mileage of the current route and is displayed.

[0230] Based on the optimized power output curve and power output mode, calculate the first energy consumption value of the electric public vehicle from the current time point to the destination time point, including:

[0231] S931. Map the remaining mileage to the time dimension of the power output curve, and on the power output curve, determine the target curve segment from the current time point to the end time point, and divide the target curve segment into low power range, medium power range and high power range.

[0232] S932. Calculate the first power average value of the low power range of the target curve segment, and obtain the first time period of the low power range;

[0233] S933. Calculate the second average power value of the medium power range of the target curve segment, and obtain the second time period of the medium power range;

[0234] S934. Calculate the third power average value of the high power range of the target curve segment, and obtain the third time period of the high power range;

[0235] S935. Based on the preset power output mode database, obtain the first energy conversion efficiency corresponding to the energy-saving mode, the second energy conversion efficiency corresponding to the standard mode, and the third energy conversion efficiency of the power mode.

[0236] S936. The product of the first average power and the first time period is taken as the first energy consumption, the product of the second average power and the second time period is taken as the second energy consumption, and the product of the third average power and the third time period is taken as the third energy consumption.

[0237] S937. Calculate the first value of the first energy consumption and the first energy conversion efficiency, calculate the second value of the second energy consumption and the second energy conversion efficiency, and calculate the third value of the third energy consumption and the third energy conversion efficiency;

[0238] S938. The sum of the first, second, and third values ​​is used as the energy saving of the electric public vehicle for the remaining mileage of the current route, and is displayed.

[0239] First, the current location and time of the electric bus are obtained, and the remaining driving distance is calculated. This can be achieved through the Global Positioning System (GPS) and the onboard computer system. The GPS receiver accurately locates the vehicle's latitude and longitude coordinates, while the onboard computer records the current timestamp. After obtaining this data, the current location is compared with the preset driving route to calculate the remaining driving distance. For example, if the total route length of an electric bus is 20 kilometers, and the GPS currently shows that the vehicle has traveled 12 kilometers, then the remaining distance is 8 kilometers.

[0240] Next, a pre-trained prediction model is used to estimate the vehicle's arrival time at its destination. This prediction model can be a machine learning algorithm, such as a Long Short-Term Memory (LSTM) network, which considers various factors affecting travel time. Input data includes not only remaining mileage but also current time, weather conditions, traffic flow, and other relevant data. The prediction model is trained on a large amount of historical driving data, learning the complex relationships between these factors and actual travel time. For example, if the remaining mileage is 8 kilometers and the current time is 5 PM on a weekday, the model might predict a 30-minute journey, taking into account potential traffic congestion. During the prediction process, the model estimates travel time based on the input remaining mileage and other relevant factors, using learned patterns.

[0241] Based on the optimized power output curve and power output mode, the first energy consumption value of the electric public vehicle from the current time point to the destination time point is calculated. The power output curve describes the expected power output at each time point from the current time to the expected arrival time at the destination.

[0242] Next, the second energy consumption value for the remaining distance is determined based on the energy consumption trend. The second energy consumption value for the remaining distance is obtained by adding up all the energy consumption between the current time point and the destination time point.

[0243] The energy savings for the electric bus on its current route are calculated by subtracting the first energy consumption value, calculated based on optimized power output, from the second energy consumption value predicted based on energy consumption trends. For example, if the second energy consumption value is 6.4 kWh, and the optimized expected first energy consumption value is 5.8 kWh, then the energy savings are 6.4 kWh - 5.8 kWh = 0.6 kWh. The energy savings reflect the energy efficiency of the optimization strategy. After calculation, the energy savings are displayed numerically. They can be displayed directly as a value (e.g., "Expected energy saving 0.6 kWh"), or converted to a percentage ("Expected energy saving 9.4%") or equivalent mileage ("Equivalent to an additional 1.5 km of driving range").

[0244] Specifically, based on the optimized power output curve and power output mode, the first energy consumption value of the electric public vehicle from the current time point to the destination time point is calculated, including the following steps:

[0245] First, map the remaining mileage to the time dimension of the power output curve and divide the power ranges. First, convert the spatial dimension (remaining mileage) to the time dimension. For example, if the remaining mileage is 10 kilometers and the expected average speed is 30 kilometers per hour, then the corresponding time dimension is 20 minutes. Next, determine the target curve segment on the power output curve from the current time point to the endpoint time point. The target curve segment reflects the expected change in power output. Then, divide this target curve segment into three power ranges: low, medium, and high. The division criteria can be based on a percentage of the power value; for example, define 0-40% of the maximum power as the low power range, 40-70% as the medium power range, and 70-100% as the high power range.

[0246] Next, the average power of the low-power interval of the target curve segment is calculated, and the time period is obtained. First, all power data points are collected within the previously defined low-power interval. Assuming the low-power interval contains 100 data points with power values ​​of 5kW, 7kW, 6kW, etc., the average value is calculated by adding these power values ​​together and dividing by the number of data points. For example, if the total power value of these 100 points is 800kW, then the average power is 8kW. Simultaneously, the duration of this low-power interval is recorded. If each data point represents 1 second, then the time period of this low-power interval is 100 seconds, or 1 minute and 40 seconds.

[0247] For the medium power range, similar to S932, first determine all data points for the medium power range. Assume the medium power range contains 150 data points with power values ​​of 25kW, 28kW, 30kW, etc. When calculating the average, add these power values ​​together and divide by the number of data points. For example, if the sum of the power values ​​of the 150 points is 4500kW, then the average power is 30kW. Simultaneously, record the duration of this medium power range. If each data point represents 1 second, then the time period of the medium power range is 150 seconds, or 2 minutes and 30 seconds.

[0248] For the high-power range, similar to S932 and S933, it's first necessary to determine all data points within that range. Assume the high-power range contains 50 data points with power values ​​of 70kW, 75kW, 80kW, etc. To calculate the average, these power values ​​are summed and then divided by the number of data points. For example, if the sum of the power values ​​from the 50 points is 3750kW, then the average power is 75kW. Simultaneously, the duration of this high-power range is recorded. If each data point represents 1 second, then the high-power range lasts for 50 seconds. The high-power range typically corresponds to vehicle acceleration or hill-climbing, which, although short in duration, consumes more energy and significantly impacts total energy consumption.

[0249] The energy conversion efficiency under different modes is obtained by querying a preset power output mode database. This database stores energy conversion efficiency data for various power output modes. Typically, electric vehicles have multiple driving modes, such as Eco mode, Standard mode, and Power mode. The energy conversion efficiency differs in each mode. For example, Eco mode might have a 90% energy conversion efficiency, Standard mode 85%, and Power mode 80%, reflecting the vehicle's energy utilization efficiency under different operating conditions.

[0250] Multiply the previously calculated average power value by the corresponding time period to obtain the energy consumption for each power range. Specifically, for the low power range, if the average power is 8kW and the time period is 100 seconds (approximately 1.67 minutes), the energy consumption is calculated as: 8kW × (100 / 3600)h = 0.22kWh. Similarly, for the medium power range, if the average power is 30kW and the time period is 150 seconds (2.5 minutes), the energy consumption is calculated as: 30kW × (150 / 3600)h = 1.25kWh. For the high power range, if the average power is 75kW and the time period is 50 seconds (approximately 0.83 minutes), the energy consumption is calculated as: 75kW × (50 / 3600)h = 1.04kWh.

[0251] By combining the previously calculated energy consumption for each power range with the corresponding energy conversion efficiency, a more accurate energy consumption value is obtained. Specifically, for the low power range (corresponding to energy-saving mode), if the energy consumption is 0.22 kWh and the energy conversion efficiency is 90%, then the actual energy consumption is calculated as: 0.22 kWh / 0.9 = 0.244 kWh. For the medium power range (corresponding to standard mode), if the energy consumption is 1.25 kWh and the energy conversion efficiency is 85%, the actual energy consumption is calculated as: 1.25 kWh / 0.85 = 1.47 kWh. For the high power range (corresponding to power mode), if the energy consumption is 1.04 kWh and the energy conversion efficiency is 80%, the actual energy consumption is calculated as: 1.04 kWh / 0.8 = 1.3 kWh. By considering the energy conversion losses under different operating conditions, the energy consumption estimate is closer to the actual situation.

[0252] The system calculates and displays the total energy consumption and energy savings of the electric public vehicle over the remaining mileage of its current route. First, the actual energy consumption values ​​for the three power ranges calculated earlier are added together to obtain the total energy consumption. For example, if the energy consumption in the low-power range is 0.244 kWh, the medium-power range is 1.47 kWh, and the high-power range is 1.3 kWh, then the total energy consumption is 0.244 + 1.47 + 1.3 = 3.014 kWh. Total energy consumption represents the total electricity the vehicle is expected to consume over the remaining mileage. Next, the optimized energy consumption value is compared with the previously predicted energy consumption value based on energy consumption trends to calculate the energy savings. Assuming the trend-predicted energy consumption value is 3.5 kWh, then the energy savings are 3.5 kWh - 3.014 kWh = 0.486 kWh. Finally, the energy savings are displayed.

[0253] This implementation method achieves high-precision estimation of the energy consumption of electric public vehicles by considering the energy conversion efficiency under different driving modes. It not only considers the energy consumption characteristics of the vehicle under different driving conditions but also introduces energy conversion efficiency, making the energy consumption prediction closer to reality. By comparing the optimized energy consumption with the trend-predicted energy consumption, the energy-saving effect is intuitively demonstrated, effectively improving vehicle operating efficiency.

[0254] This application also provides an electronic device, including:

[0255] The memory is configured to store instructions; and

[0256] The processor is configured to retrieve instructions from memory and, when executing those instructions, to implement the aforementioned public vehicle operation management method based on big data analytics.

[0257] Figure 5 This paper illustrates a structural block diagram of a public vehicle operation and management system based on big data analysis, as provided in an embodiment of this application. Figure 5As shown in the illustration, this application also provides a public vehicle operation management system based on big data analysis, including:

[0258] 10 electronic devices;

[0259] The vehicle terminal 20 of the electric public vehicle is connected to the electronic device 10.

[0260] This application also provides a machine-readable storage medium storing instructions that cause a machine to execute the above-described public vehicle operation management method based on big data analysis.

[0261] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0262] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0263] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0264] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0265] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0266] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0267] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0268] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0269] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A public vehicle operation management method based on big data analysis, characterized by, Applied to an electronic device, the electronic device is deployed with a big data model, and the electronic device is connected to a vehicle terminal of an electric public vehicle. The method includes: In response to receiving a battery alarm signal of the electric public vehicle, obtaining battery parameters and vehicle operation data of the electric public vehicle. Among them, the vehicle operation data includes real-time road condition data, vehicle operation data, and driving behavior data of the electric public vehicle on the current driving route; and Obtaining current environmental data; Inputting the current environmental data and the real-time road condition data into the big data model to obtain the current vehicle operation scenario, where the big data model is constructed based on historical environmental data and historical road condition data; In a preset battery parameter database, querying to obtain a battery parameter interval corresponding to the current vehicle operation scenario; When the battery parameters are within the battery parameter interval, obtaining vehicle energy consumption data of the electric public vehicle within a preset kilometer interval, and predicting the energy consumption trend of the electric public vehicle within a future preset time period according to the battery parameters, the vehicle energy consumption data, and the current vehicle operation scenario; Generating a power output mode of the electric public vehicle on the current driving route according to the energy consumption trend, the vehicle operation data, and the driving behavior data, where the power output mode is used to control the power distribution of the electric public vehicle; Generating a braking adjustment instruction according to the power output mode, where the braking adjustment instruction is used to instruct the electric public vehicle to execute a braking strategy; Sending the braking adjustment instruction to the vehicle terminal so that the vehicle terminal executes the braking strategy; Among them, the generating a power output mode of the electric public vehicle on the current driving route according to the energy consumption trend, the vehicle operation data, and the driving behavior data includes: Calculating the power supply corresponding to each time step according to the energy consumption trend, and fitting the power supply corresponding to each time step to generate a power supply curve of the electric public vehicle; Determining the driving state of the electric public vehicle according to the vehicle operation data, where the driving state includes an idle state, an accelerating state, a constant speed state, and a decelerating state; Obtaining an energy conversion efficiency curve of the electric public vehicle, and determining the optimal output power of the electric public vehicle in the driving state according to the power supply curve and the energy conversion efficiency curve; Calculating the curvature of the power supply curve in real time; When the curvature is greater than a preset threshold, determining a power output mode according to the driving behavior data and the optimal output power of the electric public vehicle in the driving state.

2. The method of claim 1, wherein, The construction steps of the big data model include: Using a preset feature extraction algorithm to extract features from the historical environmental data and the historical road condition data to obtain n first features, where n is an integer greater than 3; Using a first preset clustering algorithm to cluster the n first features to obtain m clustering clusters, where 0 < m < n and m is an integer; Using the feature extraction algorithm, extract features from m clustering clusters to obtain p second features, where 0 < p < m and p is an integer; Using a second preset clustering algorithm, cluster the p second features to obtain q clustering results, where each clustering result includes a clustering center, and 0 < q < p and q is an integer; Using a preset distance algorithm, for each clustering center, calculate the average distance between all the second features and the clustering center, and use the clustering center corresponding to the smallest average distance as the target clustering center, and use the clustering result corresponding to the target clustering center as the target clustering result; According to a preset mapping function, map the target clustering result to the corresponding operation scenario; Package the feature extraction algorithm, the first preset clustering algorithm, the second preset clustering algorithm, the distance algorithm and the mapping function to obtain the big data model.

3. The method of claim 1, wherein, The method further includes: In the case where the battery parameters are not within the battery parameter range, obtain the current battery level of the electric bus through the vehicle terminal, and calculate the maximum driving distance of the electric bus according to the current battery level; Obtain the current location of the electric bus; According to the current location, determine the remaining driving distance of the electric bus on the current driving route; In the case where the remaining driving distance is greater than the maximum driving distance, calculate the straight-line distance between the current location and the end point of the current driving route, and search for an electric bus charging station within the area centered on the current location with the straight-line distance as the radius; In the case where there are multiple electric bus charging stations, use the electric bus charging station with the shortest distance from the current location as the target charging station; Generate a new driving route according to the current location, the target charging station and the end point of the current driving route, and send the new driving route to the vehicle terminal.

4. The method according to claim 1, characterized in that, The predicting the energy consumption trend of the electric bus within a preset future time period according to the battery parameters, the vehicle energy consumption data and the current operation scenario of the vehicle includes: Input the battery parameters, the vehicle energy consumption data and the current operation scenario of the vehicle into a pre-trained prediction model to obtain the energy consumption trend of the electric bus within a preset future time period.

5. The method according to claim 1, characterized in that, The determining the optimal output power of the electric bus in the driving state according to the power supply power curve and the energy conversion efficiency curve includes: According to the power supply power curve and the energy conversion efficiency curve, obtain the power supply power data segment and the corresponding energy conversion efficiency data segment in the driving state; For each time point of the power supply power data segment and the corresponding energy conversion efficiency data segment, calculate the actual output power at each time point in the driving state, and generate an output power curve according to the actual output power at each time point; Based on the output power curve and the energy conversion efficiency curve, the optimal efficiency range is determined, and the average value of the output power corresponding to the optimal efficiency range is calculated. The average value is taken as the optimal output power of the electric public vehicle in the driving state.

6. The method according to claim 5, characterized in that, The step of determining the power output mode based on the driving behavior data and the optimal output power of the electric public vehicle in the driving state includes: Based on the driving behavior data, the driving behavior type is determined, wherein the driving behavior type includes smooth, moderate, and aggressive; Obtain the weight coefficients corresponding to the driving behavior type from the preset database; The power adjustment coefficient for the actual output power at each time point is calculated based on the weighting coefficient, wherein the product of the optimal output power and the power adjustment coefficient is less than the maximum output power of the electric public vehicle. Calculate the product of the actual output power at each time point and the corresponding power adjustment coefficient to obtain multiple adjusted output power values, and generate an optimized power output curve based on all processed output power values; The power output mode is determined based on the optimal output power and the optimized power output curve. The power output curve includes a low-power range, a medium-power range, and a high-power range. The power output modes include an energy-saving mode, a standard mode, and a power mode. When the optimal output power is located in the low-power range of the power output curve, the power output mode is the energy-saving mode. When the optimal output power is located in the medium-power range of the power output curve, the power output mode is the standard mode. When the optimal output power is located in the high-power range of the power output curve, the power output mode is the power mode.

7. The method according to claim 6, characterized in that, The driving behavior data includes the frequency of rapid acceleration and braking, vehicle turning angle, vehicle turning speed, and vehicle idling time. Determining the driving behavior type based on the driving behavior data includes: Multiple driving behavior features are obtained by extracting features from the frequency of rapid acceleration and braking, the vehicle turning angle, the vehicle turning speed, and the vehicle idling time. The driving behavior features are input into a pre-trained classification model to obtain the driving behavior type.

8. An electronic device, characterized in that, include: The memory is configured to store instructions; as well as The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the public vehicle operation management method based on big data analysis according to any one of claims 1 to 7.

9. A public vehicle operation management system based on big data analysis, characterized in that, include: The electronic device according to claim 8; The vehicle terminal of the electric public vehicle is connected to the electronic device.

Images