Charging management method and device based on data analysis and computer equipment

Abstract

The invention discloses a charging management method and device based on data analysis and computer equipment. The method comprises the steps that data from different channels are acquired to obtain multi-source data, an energy consumption model is constructed according to the multi-source data, and the energy consumption model is used for evaluating energy consumption levels of different routes; providing personalized charging suggestions for the user according to the energy consumption model and daily travel habits and personal preferences of the user; the state of the vehicle and the state of the charging pile are monitored in real time, an emergency processing program is started according to the situation that the actual operation situation deviates from the expectation, and an alternative scheme is provided when the selected charging pile becomes unavailable. By implementing the method provided by the invention, the battery consumption can be predicted according to the real-time driving data and the road quality, and the optimal charging scheme can be planned in advance, so that the use efficiency of energy is improved, and the user experience can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to a charging management method, and more specifically to a charging management method, device and computer equipment based on data analysis. Background Art

[0002] With the rapid growth of the electric vehicle (EV) market, the demand for charging management systems has become more urgent. Electric vehicle charging management not only involves the layout of charging piles and the charging status of batteries, but also requires intelligent dynamic adjustments based on the vehicle's driving status, road conditions and user needs to ensure charging efficiency and battery health. However, traditional charging management systems have major limitations in this regard. They cannot respond to the driving conditions of electric vehicles in real time and fail to make full use of vehicle driving data to make intelligent charging decisions.

[0003] Traditional charging management systems mostly rely on the static location of charging stations and the idle state of charging piles, and fail to make corresponding adjustments based on the real-time driving status of the vehicle (such as battery power, road conditions, driving speed, etc.). This makes it difficult for the vehicle to flexibly adjust the charging strategy during driving, which may cause excessive discharge of the battery, increase the battery usage burden, or charge too early during the charging process, wasting energy. Modern electric vehicles are equipped with a large number of sensors that can record driving data in real time, such as battery power, energy consumption, speed, acceleration, etc. However, traditional charging management systems fail to combine these real-time data with charging needs to make intelligent charging decisions, resulting in inaccurate battery power management and reduced energy utilization. Existing road quality detection technologies, such as road roughness detection, can identify and report road conditions, but these technologies are usually not effectively integrated with the charging management system of electric vehicles. In fact, the energy consumption of electric vehicles under different road conditions is different. For example, rough roads will increase the energy consumption of electric vehicles, thereby accelerating the decline of battery power. Therefore, ignoring road conditions will lead to inaccurate charging plans and affect battery health management.

[0004] Therefore, it is necessary to design a new method to predict battery consumption based on real-time driving data and road quality, and plan the optimal charging plan in advance, which not only improves the energy utilization efficiency but also significantly improves the user experience. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and provide a charging management method, device and computer equipment based on data analysis.

[0006] To achieve the above object, the present invention adopts the following technical solution: a charging management method based on data analysis, comprising:

[0007] Acquire data from different channels to obtain multi-source data, wherein the multi-source data includes the vehicle's historical navigation records, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data, and environmental conditions;

[0008] Constructing an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate the energy consumption level of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow, and slope;

[0009] Providing personalized charging recommendations to the user based on the energy consumption model and the user's daily travel habits and personal preferences, including specific arrangements for when and where to charge and tips to help extend driving range;

[0010] Monitor vehicle status and charging pile status in real time, initiate emergency procedures based on actual operating conditions deviating from expectations, and provide alternatives when the selected charging pile becomes unavailable.

[0011] A further technical solution is: constructing an energy consumption model based on the multi-source data includes:

[0012] Preprocessing the multi-source data to obtain a preprocessing result;

[0013] Determine the influence degree of road flatness on energy consumption, the influence degree of traffic flow on energy consumption and the influence degree of slope on energy consumption according to the preprocessing result;

[0014] An energy consumption model is constructed according to the influence of the road flatness on energy consumption, the influence of the traffic flow on energy consumption, and the influence of the slope on energy consumption.

[0015] A further technical solution is: determining the influence of road flatness on energy consumption, the influence of traffic flow on energy consumption and the influence of slope on energy consumption according to the preprocessing unit includes:

[0016] Performing spectrum analysis on the preprocessing results to distinguish high-frequency components from low-frequency components, calculating the road surface fluctuations corresponding to these components in combination with a mathematical model, and evaluating the roughness of different road sections;

[0017] For the separated high-frequency components, calculate their RMS values;

[0018] A mathematical relationship model between vehicle vibration characteristics and energy consumption is established based on the root mean square value combined with the additional loss, and a weight factor related to the roughness is set to determine the degree of influence of road roughness on energy consumption;

[0019] Performing feature engineering processing on the preprocessing result to obtain a feature engineering result;

[0020] Constructing a mathematical relationship model between traffic flow and energy consumption according to the feature engineering structure, and setting a weight factor related to traffic flow to determine the degree of influence of traffic flow on energy consumption;

[0021] Calculating the cumulative value of the low-frequency component of the preprocessing result;

[0022] A mathematical relationship model between the slope and the energy consumption is constructed according to the accumulated value, the vehicle speed and other dynamic characteristics, and a weight factor related to the slope is set to determine the influence of the slope on the energy consumption.

[0023] A further technical solution is: constructing an energy consumption model according to the influence of the road flatness on energy consumption, the influence of traffic flow on energy consumption and the influence of slope on energy consumption, including:

[0024] The influence of the road flatness on energy consumption, the influence of the traffic flow on energy consumption and the influence of the slope on energy consumption are weighted and summed to obtain an energy consumption model.

[0025] A further technical solution is: providing the user with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, the suggestions including specific arrangements for when and where to charge and tips for extending the driving range, including:

[0026] Analyze the multi-source data to establish a detailed user profile, recording the user's driving behavior patterns, frequented locations, and charging habits;

[0027] Using the energy consumption model, combined with the user's travel plan, the energy consumption level of different routes is predicted, and the expected energy consumption is calculated for each possible trip by specifically considering the influence of road flatness, traffic flow, and slope factors;

[0028] Generate customized charging strategies based on the user's daily rhythm and predicted energy consumption;

[0029] Combined with information from user travel pattern profiles, a machine learning algorithm is used to train historical charging behaviors to obtain an adaptive strategy;

[0030] The customized charging strategy is integrated with the adaptive strategy to prioritize the recommendations according to importance and urgency, and generate personalized charging recommendations including specific arrangements for when and where to charge and tips to help extend driving range.

[0031] A further technical solution is: providing the user with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, wherein the suggestions include specific arrangements for when and where to charge and tips for extending the driving range, and also includes:

[0032] By integrating energy consumption models, real-time traffic data and charging station information to evaluate and optimize the energy consumption of each candidate route, it will capture instantaneous power fluctuations to adjust the score, and ultimately select the optimal route that ensures sufficient power throughout the journey and provides personalized charging recommendations.

[0033] The further technical solution is: the energy consumption of each candidate route is evaluated and optimized by integrating energy consumption models, real-time traffic data and charging pile information, capturing instantaneous power fluctuations to adjust the score, and finally selecting an optimal route that ensures sufficient power throughout the journey and provides personalized charging suggestions, including:

[0034] When planning multiple candidate routes from a starting point to a destination, the energy consumption model is used to score the energy consumption of each route, and energy-aware path selection is implemented in combination with real-time traffic conditions and location information of available charging piles along the route;

[0035] Capture instantaneous power fluctuations and optimize the energy consumption score of each candidate route, taking into account the power required to reach the target charging station and other charging opportunities that may be encountered along the way;

[0036] Ultimately, an optimal route is determined to ensure that the vehicle maintains sufficient power throughout the journey, and personalized charging reminders are pushed to users through mobile applications or in-vehicle systems.

[0037] The present invention also provides a charging management device based on data analysis, comprising:

[0038] A multi-source data acquisition unit, used to acquire data from different channels to obtain multi-source data, wherein the multi-source data includes historical navigation records of the vehicle, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data and environmental conditions;

[0039] An energy consumption model building unit, used to build an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate the energy consumption level of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow, and slope;

[0040] a charging suggestion generating unit, configured to provide a user with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, wherein the suggestions include specific arrangements for when and where to charge and tips for extending the driving range;

[0041] A real-time monitoring unit is used to monitor the vehicle status and charging pile status in real time, initiate emergency handling procedures according to the deviation of actual operating conditions from expectations, and provide alternative solutions when the selected charging pile becomes unavailable.

[0042] The present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0043] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention monitors vehicle and road conditions in real time by integrating multi-source data from vehicle historical navigation records, GPS positioning information, road sensors, traffic flow data, vehicle operation data and environmental conditions; constructs an energy consumption model based on multi-source data, comprehensively considers multi-dimensional factors such as road flatness, traffic flow, slope, etc., and evaluates the energy consumption of different routes; provides personalized charging suggestions based on the energy consumption model in combination with the user's travel habits and personal preferences, plans the best charging time and place in advance, and improves the cruising range; monitors the status of charging piles and vehicles in real time, and if any abnormality occurs, initiates emergency processing and provides alternative charging solutions when the charging piles are unavailable, ensuring a smooth and efficient charging experience, predicting battery consumption based on real-time driving data and road quality, and planning the optimal charging solution in advance, which not only improves the energy utilization efficiency, but also significantly improves the user experience.

[0045] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0047] Figure 1 A schematic diagram of an application scenario of a charging management method based on data analysis provided by an embodiment of the present invention;

[0048] Figure 2 A schematic diagram of a charging management method based on data analysis provided by an embodiment of the present invention;

[0049] Figure 3A schematic block diagram of a charging management device based on data analysis provided by an embodiment of the present invention;

[0050] Figure 4 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0053] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0054] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0055] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of an application scenario of a charging management method based on data analysis provided in an embodiment of the present invention. Figure 2A schematic flow chart of a charging management method based on data analysis provided in an embodiment of the present invention. The charging management method based on data analysis is applied to a server. The monitored server 20 may be a server in a distributed service platform, which interacts with terminals and sensors for data, and monitors vehicle and road conditions in real time by integrating multi-source data from vehicle historical navigation records, GPS positioning information, road sensors, traffic flow data, vehicle operation data, and environmental conditions. Based on multi-source data, an energy consumption model is constructed, and multi-dimensional factors such as road flatness, traffic flow, and slope are comprehensively considered to evaluate the energy consumption of different routes. Based on the user's travel habits and personal preferences, personalized charging suggestions are provided based on the energy consumption model, and the best charging time and location are planned in advance to improve the driving range. The charging pile and vehicle status are monitored in real time. If an abnormality occurs, emergency processing is initiated and an alternative charging solution is provided when the charging pile is unavailable to ensure a smooth and efficient charging experience.

[0056] Figure 2 FIG. 1 is a flow chart of a charging management method based on data analysis provided by an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S140.

[0057] S110. Acquire data from different channels to obtain multi-source data, wherein the multi-source data includes historical navigation records of the vehicle, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data, and environmental conditions.

[0058] In this embodiment, the vehicle's historical navigation records: By analyzing the user's travel paths over a period of time, the user's daily travel patterns and habits can be understood. For example, some users may have a fixed commuting route, while other users may prefer irregular long-distance travel. This information is crucial for predicting future driving behavior and charging needs.

[0059] Current GPS location information: Real-time access to the vehicle's specific location is important for determining available charging stations near the vehicle's location, assessing the distance to the destination, and selecting the optimal route. In addition, it enables the system to provide instant charging recommendations based on the current location.

[0060] Road conditions collected by sensors: Modern electric vehicles are equipped with various sensors (such as cameras, lidar, etc.) that can detect road surface conditions, including but not limited to road surface flatness, slope changes, the presence of obstacles, etc. These data not only help build energy consumption models, but also provide support for safe driving.

[0061] Traffic flow data: Real-time traffic speed and density information obtained from public or private traffic information service providers can help optimize journey planning, avoid congested sections, thereby reducing unnecessary energy consumption and ensuring that there are enough idle charging piles when the charging station arrives.

[0062] Vehicle operation data: Data read directly from the vehicle's internal systems, such as remaining battery power, instantaneous power output, average energy consumption rate, acceleration / deceleration characteristics, etc., are critical for accurately estimating remaining range and formulating reasonable charging strategies.

[0063] Environmental conditions: Temperature, humidity, wind speed and other information provided by weather forecasts and other related meteorological services will affect the performance and energy efficiency of electric vehicles. Cold weather may reduce battery efficiency, while extreme high temperature conditions require consideration of the additional load caused by air conditioning use.

[0064] By fusing the above multi-source data, the method of this embodiment can create a more comprehensive and dynamic energy consumption model that can not only reflect static factors (such as fixed road attributes) but also adapt to real-time changing factors (such as instant traffic conditions and weather conditions). The resulting personalized charging suggestions and route planning will greatly improve the energy efficiency of electric vehicles, while improving user experience and protecting battery health.

[0065] S120. Constructing an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate energy consumption levels of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow, and slope.

[0066] In one embodiment, the above-mentioned step S120 may include steps S121 - S123 .

[0067] S121. Preprocess the multi-source data to obtain a preprocessing result.

[0068] In this embodiment, the vehicle sensor data includes an accelerometer (for measuring vertical acceleration), a gyroscope (for monitoring changes in vehicle posture), a GPS (for obtaining geographic location information), and the like.

[0069] Traffic flow data: derived from traffic monitoring systems or historical data, providing real-time or predicted traffic conditions at the road segment level.

[0070] Environmental conditions: information such as weather conditions, road type and quality, slope, etc. that may affect driving behavior.

[0071] Clean multi-source data to remove outliers and fill in missing values.

[0072] Use filtering techniques (such as low-pass filters) to separate high-frequency components (small bumps) from low-frequency components (long-term elevation changes). Synchronize timestamps to ensure temporal consistency between different data sources. Standardize or normalize numerical variables for subsequent analysis.

[0073] S122. Determine the influence degree of road flatness on energy consumption, the influence degree of traffic flow on energy consumption, and the influence degree of slope on energy consumption according to the preprocessing result.

[0074] In this embodiment, the degree of influence of road flatness on energy consumption is an indicator that measures the additional energy consumption caused by uneven road surfaces (such as potholes, cracks, etc.). When a vehicle travels on an uneven road, the movement of the suspension system will increase and more frequent acceleration and deceleration operations may be caused, which will cause additional energy loss.

[0075] The vertical acceleration data collected by the sensor is used for spectrum analysis to separate the high-frequency components (representing small bumps), and the root mean square value (RMS) is calculated to quantify the vibration amplitude caused by the uneven road surface. A mathematical relationship model between vehicle vibration characteristics and energy consumption is established, and a weight factor W related to the unevenness is introduced. uneven This weight factor reflects the specific impact of the roughness on a specific road section on the total energy consumption.

[0076] The degree to which traffic flow affects energy consumption refers to how traffic conditions (e.g., congestion levels) change the vehicle's operating mode (e.g., frequent start-stop, following distance adjustment, increased acceleration and deceleration frequency, etc.), thereby affecting overall energy consumption. Heavy traffic flow usually means more start-stop operations, which significantly increases energy consumption.

[0077] Analyze the pre-processed real-time or historical traffic data and extract key features, such as the number of starts and stops, average following distance, acceleration and deceleration patterns, etc. Construct a mathematical relationship model between traffic flow and energy consumption, and set a weight factor W related to traffic density traffic , which can dynamically reflect the impact of traffic flow changes on the total expected energy consumption.

[0078] The degree of slope effect on energy consumption shows the impact of terrain changes (i.e. uphill or downhill) on the vehicle's energy needs. When going uphill, the vehicle needs additional power to overcome gravity; while when going downhill, there is an opportunity to store some energy through the kinetic energy recovery system. The greater the slope, the more significant this effect.

[0079] The GPS data and terrain database are used to determine the altitude difference of each section of the journey and calculate the slope angle θ of each section of the journey.

[0080] A mathematical model is used to describe the relationship between vertical acceleration and various factors (including the vehicle's horizontal attitude angle θ(t), speed v(t) and its rate of change), with special attention paid to the cumulative value A corresponding to the low-frequency component. ccumulationlow , to evaluate the effect of slope on energy consumption.

[0081] Add a slope-related weight factor W to the model slope , directly reflects the impact of slope on energy demand. For uphill sections, W slope A positive value indicates that more energy is needed; for downhill sections, W slope It can be a negative value, indicating that energy consumption can be reduced by kinetic energy recovery.

[0082] In summary, these three levels of influence describe from different perspectives how road conditions, traffic environment and terrain characteristics work together to affect the energy consumption process of vehicles. By quantitatively analyzing these factors, we can build a more accurate energy consumption prediction model, thereby optimizing driving route selection and promoting energy conservation and emission reduction.

[0083] In one embodiment, the above-mentioned step S122 may include steps S1221 - S1227 .

[0084] S1221. Perform spectrum analysis on the preprocessing results to distinguish high-frequency components from low-frequency components, calculate the road surface fluctuations corresponding to these components using a mathematical model, and evaluate the roughness of different road sections.

[0085] S1222. For the separated high-frequency components, calculate the root mean square value thereof;

[0086] S1223. A mathematical relationship model between vehicle vibration characteristics and energy consumption is established based on the RMS value combined with the additional loss, and a weight factor related to the roughness is set to determine the degree of influence of road roughness on energy consumption.

[0087] In this embodiment, the vehicle vertical acceleration information is analyzed in the frequency domain, the time domain data is converted to the frequency domain through Fourier transform, and the high-frequency component and the low-frequency component are identified. The high-frequency component reflects the slight bumps and vibrations of the road surface.

[0088] Next, the weight coefficients corresponding to the high-frequency and low-frequency components were determined. For the high-frequency component, it is associated with small bumps on the road, which cause the vehicle suspension system to work more, thus increasing additional energy consumption.

[0089] The root mean square value (RMShigh) of the frequency data corresponding to the high-frequency components was calculated. This step helped quantify the degree of increased energy consumption due to the uneven road surface. The larger the RMShigh, the more uneven the road surface, and the more energy the vehicle needs to consume to overcome these bumps when driving.

[0090] Therefore, the impact of road roughness on energy consumption can be measured by the weight coefficient of the high-frequency component and its root mean square value. Specifically, more severe road roughness will increase RMShigh, thereby increasing the energy consumption of the vehicle during driving.

[0091] Specifically, a mathematical relationship model between vehicle vibration characteristics (such as RMS value) and energy consumption is established using statistical regression analysis or other machine learning techniques. For example, a linear or nonlinear regression model can be constructed, in which energy consumption is used as the dependent variable, and RMS value and other related factors are used as independent variables. In addition to direct vibration, a series of secondary effects caused by uneven road surface need to be considered, such as increased tire rolling resistance, increased suspension system operation, etc., which are additional sources of energy loss. By inputting the actual measured road flatness index (such as RMS) into the model established above, the energy consumption increment caused by the uneven road surface can be estimated. If you want to evaluate the total energy consumption impact over a longer journey, you need to further consider the cumulative effect, that is, the accumulation of energy consumption in multiple short-distance trips.

[0092] In this embodiment, on the basis of the traditional energy consumption model based on vibration characteristics, additional variables are added to represent the secondary effects. For example, in addition to the RMS value, other factors can be added as independent variables, such as:

[0093] Tire rolling resistance coefficient: estimated based on road conditions and tire type.

[0094] Suspension system activity frequency or travel length: measured directly by sensors or obtained from the vehicle control unit.

[0095] Vehicle speed: Because the vehicle may respond differently to the same road irregularities at different speeds.

[0096] Load weight: affects the response of the suspension system and the contact pressure of the tires.

[0097] Among them, the mathematical relationship model between vehicle vibration characteristics and energy consumption is E=α·RMS2+β1·RRC+β2·HSF+β3·V+β4·W+∈; among them, E is the total energy consumption; RMS is the root mean square acceleration value; RRC is the tire rolling resistance coefficient; HSF is the suspension system activity frequency or stroke length; V is the vehicle speed; W is the load; Α, βi are parameters to be estimated; ∈ is the error term.

[0098] For more complex nonlinear relationships, you can consider using machine learning methods, such as support vector machines (SVM), random forests, neural networks, etc. These models can automatically capture the complex interactions between input features and do not require pre-setting specific function expressions.

[0099] Collect a large amount of actual driving data, including but not limited to RMS value, tire status, suspension system working condition, vehicle speed, load, etc. Correspondingly record the fuel consumption or battery power change under each test as the target output.

[0100] The collected data is used to train a machine learning model, which learns how to predict energy consumption based on input features. During this process, the model automatically learns and adjusts the weights to reflect the impact of each factor on energy consumption.

[0101] No matter which method is chosen to build the model, experimental verification and necessary calibration work must be carried out. This involves field testing under different conditions to ensure that the model prediction results are consistent with the actual situation. If a large deviation is found, it is necessary to review the model structure, adjust the parameter settings or introduce new influencing factors.

[0102] Considering that factors such as vehicle aging and environmental changes may cause model performance to deteriorate, it is recommended to update the model regularly and retrain it using the latest driving data to maintain the effectiveness and accuracy of the model.

[0103] In summary, by introducing more variables describing secondary effects and combining appropriate statistical or machine learning techniques, additional losses can be effectively reflected in the mathematical relationship model between vehicle vibration characteristics (such as RMS value) and energy consumption. This method not only improves the accuracy of the model, but also provides a powerful tool for understanding and optimizing the energy efficiency of vehicles under real road conditions.

[0104] S1224, performing feature engineering processing on the preprocessing result to obtain a feature engineering result;

[0105] S1225. Construct a mathematical relationship model between traffic flow and energy consumption according to the feature engineering structure, and set a weight factor related to traffic flow to determine the degree of influence of traffic flow on energy consumption.

[0106] In this embodiment, although the flowchart provided does not mention how to process the traffic flow data, in actual applications, the traffic flow will also affect the energy consumption of the vehicle. The traffic flow usually affects the start-stop frequency, following distance, acceleration and deceleration behavior of the vehicle, etc.

[0107] Start-stop loss: Frequent start-stop operations will lead to more energy consumption, especially in urban congestion environments.

[0108] Following effect: In high-density traffic flow, vehicles may be forced to maintain a close following distance, reducing the chance of sliding and increasing energy consumption.

[0109] Acceleration and deceleration patterns: Changes in traffic flow will cause vehicles to constantly adjust their speed, and this speed change will also significantly affect energy consumption.

[0110] Therefore, the impact of traffic flow on energy consumption can be represented by factors such as the number of vehicle starts and stops, the average following distance, and the acceleration and deceleration patterns. When building the model, these parameters should be taken into account to accurately evaluate their impact on total energy consumption.

[0111] Specifically, obtain real-time or historical traffic flow information at the road segment level from the traffic management department or a third-party service provider.

[0112] Vehicle operation data: The vehicle's start and stop times, average speed, acceleration and deceleration patterns, and other dynamic driving behaviors are recorded through the on-board diagnostic system (OBD) or other sensor devices.

[0113] Environmental conditions: including weather conditions, road type and quality, grade, and other factors that may affect vehicle performance.

[0114] Remove outliers and fill in missing values ​​to ensure data consistency and accuracy. Ensure that the timestamps of all data sources are consistent to facilitate subsequent analysis. Standardize or normalize numerical variables so that data of different magnitudes can be compared on the same scale.

[0115] According to the influencing factors mentioned above (such as the number of starts and stops, following distance, acceleration and deceleration mode), new features are extracted from the original data.

[0116] Start-stop loss: Calculate the number of starts and stops of the vehicle per unit time.

[0117] Following effect: Measures the minimum following distance to the vehicle in front and its frequency distribution.

[0118] Acceleration and deceleration mode: Count the frequency and intensity of acceleration and deceleration events, and take into account the rate of change of acceleration.

[0119] Interactive features: Explore the interactions between different features, such as the relationship between traffic flow and vehicle speed, or the association between start-stop loss and following effect.

[0120] Choose a suitable algorithm to build an energy consumption prediction model. It can be linear regression, decision tree, random forest, gradient boosting machine (GBM), support vector machine (SVM) or deep learning model, depending on the data characteristics and problem complexity.

[0121] The mathematical relationship model between traffic flow and energy consumption is E=α·RMS2+β1·TFC+β2·STP+β3·FWD+β4·ACD+∈, where E is the total energy consumption; TFC is the traffic flow characteristic; STP is the start-stop loss; FWD is the following effect; ACD is the acceleration and deceleration mode; Α, βi are parameters to be estimated; ∈ is the error term.

[0122] Use cross-validation to evaluate model performance and adjust hyperparameters to improve prediction accuracy. If you are using a machine learning model, you can find the optimal parameter combination through grid search or random search.

[0123] Check the model's performance on an independent test set to ensure that it generalizes well.

[0124] Analyze the difference between the predicted results and the actual energy consumption, and return to the above two steps to further improve the model if necessary.

[0125] Apply the finalized model to real-world scenarios and monitor its long-term performance. Continuously update and improve the model based on user feedback and technological developments.

[0126] Through the above steps, the impact of traffic flow on energy consumption can be quantified more accurately, thus providing a scientific basis for intelligent traffic management and new energy vehicle design.

[0127] S1226, calculating the cumulative value of the low-frequency component of the preprocessing result;

[0128] S1227. Construct a mathematical relationship model between the slope and energy consumption based on the accumulated value, vehicle speed and other dynamic characteristics, and set a weight factor related to the slope to determine the influence of the slope on the energy consumption.

[0129] In this embodiment, the accumulation value of the frequency data corresponding to the low-frequency component is calculated. low ), this part of the data reflects the overall elevation change of the road surface, that is, the long-term slope and curvature.

[0130] Mathematical model application: Use the mathematical model a(t) = f(x(t), θ(t)) + b·v(t) + c·(dv(t)) / dt, where x(t) is the elevation of the road surface at time t, θ(t) is the horizontal attitude angle of the vehicle, and v(t) is the speed of the vehicle at time t. This model can help understand how the slope affects the vertical acceleration of the vehicle, thereby affecting energy consumption.

[0131] When going uphill, the vehicle needs extra power to overcome gravity, while when going downhill, there is an opportunity to store some energy through the kinetic energy recovery system. The greater the slope, the more obvious this effect is.

[0132] Therefore, the influence of slope on energy consumption can be measured by the accumulation value of low-frequency components. low Larger or more variable slopes result in higher energy demands, especially when driving on roads in mountainous or hilly areas.

[0133] S123: construct an energy consumption model according to the influence of the road flatness on energy consumption, the influence of the traffic flow on energy consumption, and the influence of the slope on energy consumption.

[0134] In this embodiment, the influence of the road flatness on energy consumption, the influence of the traffic flow on energy consumption, and the influence of the slope on energy consumption are weighted and summed to obtain an energy consumption model.

[0135] Finally, when all these factors are quantified, a comprehensive energy consumption model E can be constructed, which takes into account the high-frequency component impact caused by road flatness, the time loss caused by traffic flow, the energy consumption caused by start-stop operation, and the energy consumption caused by slope changes. In this way, not only can the energy consumption under different conditions be accurately predicted, but also strong support can be provided for optimizing driving routes.

[0136] A comprehensive energy consumption function EE is constructed, which combines the high-frequency component impact caused by road flatness, the time loss caused by traffic flow, the energy consumption caused by start-stop operation, and the energy consumption caused by slope change. The specific form is as follows:

[0137] E=∑(W uneven ×RMShigh+W traffic ×T+W slope ×S), where RMS high It is the root mean square value of the high-frequency frequency data, representing slight bumps on the road; T represents the time loss caused by traffic flow and the energy consumption caused by start-stop operations; S represents the energy consumption caused by slope changes.

[0138] Use cross-validation to evaluate model performance and adjust hyperparameters to improve prediction accuracy. Test the model's performance on an independent test set to ensure good generalization. Continuously update and improve the model based on user feedback and technological developments.

[0139] Ultimately, this comprehensive energy consumption model can help users choose the best driving route that meets time and distance requirements while saving energy, and provide a scientific basis for intelligent traffic management and new energy vehicle design. In addition, it also supports road maintenance decisions by understanding which road sections are most likely to cause energy waste and making targeted improvements.

[0140] S130: providing the user with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, wherein the suggestions include specific arrangements for when and where to charge and tips for extending the driving range.

[0141] In one embodiment, the above-mentioned step S130 may include steps S131 - S135 .

[0142] S131, analyzing the multi-source data, establishing a detailed user profile, and recording the user's driving behavior pattern, frequently visited locations, and charging habit information.

[0143] In this embodiment, the user's driving data, including but not limited to driving time, speed, route selection, parking location and frequency, is continuously collected through vehicle built-in sensors and other sources (such as mobile phone applications). These data are analyzed to identify the user's typical travel pattern, such as commuting route, weekend activity range, etc., and record the user's charging time and location preferences.

[0144] Specifically, it integrates data from multiple channels, including but not limited to the vehicle's historical navigation records, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data, and environmental conditions. By analyzing the above multi-source data, it builds a detailed user profile that records the user's driving behavior patterns (such as acceleration habits, average speed), frequented locations, charging habits, and other information.

[0145] S132. Utilize the energy consumption model and combine it with the user's travel plan to predict energy consumption levels on different routes, specifically taking into account the impact of road flatness, traffic flow, and slope factors, and calculate the expected energy consumption for each possible trip.

[0146] In this embodiment, the energy consumption model constructed above is applied to each potential route planned by the user, taking into account the impact of factors such as road flatness, traffic flow, slope, etc. on energy consumption. Specific energy consumption estimates for each route are generated to help users understand the energy requirements under different options.

[0147] Specifically, the energy consumption model constructed previously is combined with the user's travel plan (for example, through a calendar application or manually entered destinations) to predict energy consumption levels under different routes. Taking into account the influence of factors such as road flatness, traffic flow, slope, etc., the expected energy consumption is calculated for each possible trip.

[0148] S133: Generate a customized charging strategy based on the user's daily life rhythm and predicted energy consumption.

[0149] In this embodiment, the best time to charge is determined in combination with the user's schedule (such as work schedule or social activities), ensuring that the battery is fully charged but not overcharged. The location of nearby charging piles is recommended to optimize the choice of charging points and reduce unnecessary detour distances.

[0150] Specifically, the historical charging behavior is trained using machine learning algorithms combined with information from the user's travel pattern profile. This includes not only analyzing the user's charging choices at different times and locations, but also understanding the user's behavioral patterns in response to different types of notifications and prompts, as well as changes in charging needs in the face of different weather conditions or special events. Based on this, the system can dynamically adjust and optimize charging recommendations to generate a personalized adaptive charging strategy for each user. This process takes into account the user's daily activity patterns, preference settings, and any temporary changes to provide a charging solution that best meets the user's actual needs.

[0151] S134. Combine the information in the user travel pattern file and use the machine learning algorithm to train the historical charging behavior to obtain an adaptive strategy.

[0152] In this embodiment, key features are extracted from the user's historical charging records, such as charging frequency, average charging amount, common charging stations, etc. The model is trained using a supervised learning method so that it learns to automatically adjust charging recommendations based on input conditions (such as weather, traffic conditions, etc.), thereby improving the accuracy and practicality of the recommendations.

[0153] S135. Integrate the customized charging strategy with the adaptive strategy, set priorities for each suggestion according to importance and urgency, and generate personalized charging suggestions, which include specific arrangements for when and where to charge and tips that help extend the driving range.

[0154] In this embodiment, the advantages of the two strategies are compared, and the optimal combination is selected to form a charging plan that is both in line with the user's long-term habits and flexible to short-term changes. Weights are assigned to each suggestion, such as emergency charging needs taking precedence over regular maintenance charging; practical tips are also added, such as how to save power by changing the driving style. Users are allowed to evaluate each charging experience, and feedback is collected to further improve the algorithm and service quality.

[0155] Specifically, the vehicle status and the status of charging piles along the way are continuously monitored. Once the actual situation is found to deviate from the initial plan (such as charging pile failure), an updated charging plan is immediately provided to ensure that users will not fall into the dilemma of insufficient power.

[0156] Tips for extending your driving range include:

[0157] Driving behavior optimization guidance: Encourage users to adopt more energy-saving driving methods, such as smooth acceleration and deceleration, predictive driving (releasing the accelerator in advance and gliding to the red light to stop), etc., to reduce unnecessary energy waste.

[0158] Environmental adaptability recommendations: It is recommended to use the air conditioning system reasonably and avoid extreme temperature settings, as this will significantly affect battery efficiency. At the same time, it is recommended to choose flat roads with smooth traffic and avoid high-energy consumption sections (such as steep mountain roads) to reduce energy consumption.

[0159] Maintenance Tips: remind users to keep tire pressure normal, ensure smooth wheel rotation, and pay attention to other components that may affect efficiency (such as the brake system). In addition, it is recommended to remove unnecessary heavy objects in the car to reduce the vehicle load and save electricity.

[0160] Through the above steps, the system can not only provide users with accurate charging guidance, but also encourage users to develop more energy-saving driving habits, thereby effectively improving the use efficiency and user experience of electric vehicles.

[0161] The customized charging strategy is integrated with the results of the adaptive strategy to prioritize the recommendations according to importance and urgency. For example, for an upcoming important trip, ensuring that the battery is fully charged may be the highest priority task; while for regular daytime short trips, charging time can be flexibly arranged without affecting the overall rhythm of life.

[0162] Based on the user's current location, remaining power, information about nearby available charging stations, and other factors, the system will provide the most suitable charging location and timing recommendations. In addition, it will also consider the impact of external factors (such as weather changes and temporary traffic control) and update the recommendations in a timely manner.

[0163] All recommendations will be carefully designed to ensure that the information is clear and easy to understand, and the operation is simple and fast. At the same time, users are encouraged to provide feedback to help the system continuously improve and perfect its recommendation mechanism.

[0164] In summary, by combining customized charging strategies with adaptive strategies, it is not only possible to provide a reasonable charging plan based on the user's daily life rhythm and predicted energy consumption, but also to use machine learning technology to achieve more accurate dynamic adjustments that meet personal needs. Such a comprehensive solution aims to maximize the convenience and economic benefits of electric vehicle use while improving user satisfaction.

[0165] In addition, between step S120 and step S130, the following steps are also included:

[0166] By integrating energy consumption models, real-time traffic data and charging station information to evaluate and optimize the energy consumption of each candidate route, it will capture instantaneous power fluctuations to adjust the score, and ultimately select the optimal route that ensures sufficient power throughout the journey and provides personalized charging recommendations.

[0167] Specifically, when planning multiple candidate routes from a starting point to a destination, the energy consumption model is used to score the energy consumption of each route, and energy-aware path selection is implemented in combination with real-time traffic conditions and location information of available charging piles along the route;

[0168] Capture instantaneous power fluctuations and optimize the energy consumption score of each candidate route, taking into account the power required to reach the target charging station and other charging opportunities that may be encountered along the way;

[0169] Ultimately, an optimal route is determined to ensure that the vehicle maintains sufficient power throughout the journey, and personalized charging reminders are pushed to users through mobile applications or in-vehicle systems.

[0170] In this embodiment, the energy consumption of each candidate route is evaluated and optimized by integrating the energy consumption model, real-time traffic data and charging pile information, and finally an optimal route is selected that ensures sufficient power throughout the journey and provides personalized charging suggestions.

[0171] The energy consumption of multiple candidate routes from the starting point to the destination is scored using a pre-built energy consumption model. Dynamic path score adjustment is implemented based on real-time traffic conditions (such as traffic congestion, road construction information, etc.) and the location and status information of available charging piles along the way.

[0172] Real-time monitoring of instantaneous power changes during vehicle operation, including fluctuations in power consumption caused by acceleration, deceleration, and climbing. Based on the above fluctuation information, the energy consumption score of each candidate route is further optimized, taking into account the power required to reach the next target charging station and other charging opportunities that may be encountered along the way.

[0173] After comprehensively considering all factors, choose the best route that meets the current power requirements and maximizes the use of existing charging pile resources. Make sure that the selected route can maintain sufficient power throughout the entire journey to avoid the situation of being stranded midway due to insufficient power.

[0174] Through mobile applications or in-vehicle information systems, users are informed of the best charging time and location, as well as tips to extend the driving range. Algorithms and services are continuously improved based on user feedback to better adapt to the usage habits and personal preferences of different users.

[0175] By introducing this series of energy-aware path selection and optimization measures, it can not only help electric vehicle users plan their travel routes more reasonably, but also effectively improve the vehicle's energy efficiency and reduce unnecessary charging times, thereby reducing overall travel costs and improving users' driving experience.

[0176] S140, monitor the vehicle status and charging pile status in real time, initiate emergency procedures according to the deviation of actual operating conditions from expectations, and provide alternative solutions when the selected charging pile becomes unavailable.

[0177] In this embodiment, the following contents are monitored in real time:

[0178] Battery Capacity Monitoring: Continuously track the remaining battery capacity (SOC) to assess battery life.

[0179] Health Check: Regularly check the health of batteries and other key components to provide early warning of potential problems.

[0180] Driving behavior analysis: Collect and analyze data such as acceleration, deceleration, and average speed to adjust energy consumption predictions.

[0181] Availability detection: Connect to the charging station server through the network to obtain information on whether the charging pile is idle.

[0182] Compatibility verification: Confirm that the target charging station matches the vehicle interface and technical specifications.

[0183] Service quality evaluation: Based on historical records or user feedback, the service quality of each charging point is scored.

[0184] When the actual operation of the vehicle deviates from expectations (for example, the battery is consumed too quickly or the selected charging station suddenly becomes unavailable), the system will automatically trigger the emergency handling process:

[0185] If a charger on the current route becomes unavailable, a search is immediately conducted for nearby alternative options and a new optimal route is calculated.

[0186] Adjust the amount and timing of planned charging to ensure the vehicle always has enough charge to reach the next reliable charging point.

[0187] Send timely warning information to the driver, including recommended actions (such as changing the destination, finding an alternative charging station, etc.).

[0188] Provide users with additional help resources, such as navigation to the nearest open charging station or contacting customer service for further guidance.

[0189] Once a selected charger is marked as unavailable, the system should quickly provide one or more viable alternatives:

[0190] Intelligently recommend the best alternative location based on the vehicle’s current location, remaining battery power, and the status of surrounding charging stations.

[0191] Considering factors such as distance, waiting time, and cost, provide users with a ranked list of choices.

[0192] With the continuous influx of new information (such as usage feedback from other users), the recommendation results are kept real-time and accurate.

[0193] In order to ensure the effective operation of all the above functions, it is necessary to establish a strong back-end support platform, integrate data streams from different sources, and use advanced algorithms for efficient data processing and decision making. In addition, it is also necessary to ensure that the system's security and privacy protection measures are in place to prevent the leakage of sensitive information.

[0194] The above-mentioned charging management method based on data analysis monitors vehicle and road conditions in real time by integrating multi-source data from vehicle historical navigation records, GPS positioning information, road sensors, traffic flow data, vehicle operation data and environmental conditions; constructs an energy consumption model based on multi-source data, comprehensively considers multi-dimensional factors such as road flatness, traffic flow, slope, etc., and evaluates the energy consumption of different routes; provides personalized charging suggestions based on the energy consumption model in combination with the user's travel habits and personal preferences, plans the best charging time and location in advance, and improves the cruising range; monitors the status of charging piles and vehicles in real time, and if any abnormality occurs, initiates emergency processing and provides alternative charging solutions when the charging piles are unavailable, ensuring a smooth and efficient charging experience, predicting battery consumption based on real-time driving data and road quality, and planning the optimal charging solution in advance, which not only improves the energy utilization efficiency, but also significantly improves the user experience.

[0195] Figure 3 is a schematic block diagram of a charging management device 300 based on data analysis provided by an embodiment of the present invention. Figure 3As shown, corresponding to the above charging management method based on data analysis, the present invention also provides a charging management device 300 based on data analysis. The charging management device 300 based on data analysis includes a unit for executing the above charging management method based on data analysis, and the device can be configured in a desktop computer, tablet computer, laptop computer, etc. For details, please refer to Figure 3 The charging management device 300 based on data analysis includes a multi-source data acquisition unit 301, an energy consumption model construction unit 302, a charging suggestion generation unit 303 and a real-time monitoring unit 304.

[0196] A multi-source data acquisition unit 301 is used to acquire data from different channels to obtain multi-source data, wherein the multi-source data includes the vehicle's historical navigation records, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data and environmental conditions; an energy consumption model construction unit 302 is used to construct an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate the energy consumption level of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow, and slope; a charging suggestion generation unit 303 is used to provide users with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, and the suggestions include specific arrangements for when and where to charge and tips that help extend the driving range; a real-time monitoring unit 304 is used to monitor the vehicle status and charging pile status in real time, initiate emergency handling procedures based on the deviation of actual operating conditions from expectations, and provide alternative solutions when the selected charging pile becomes unavailable.

[0197] In one embodiment, the energy consumption model building unit 302 is used to:

[0198] Preprocessing the multi-source data to obtain preprocessing results; determining the influence of road flatness on energy consumption, the influence of traffic flow on energy consumption, and the influence of slope on energy consumption according to the preprocessing results; and constructing an energy consumption model according to the influence of road flatness on energy consumption, the influence of traffic flow on energy consumption, and the influence of slope on energy consumption.

[0199] In one embodiment, the energy consumption model building unit 302 is further used to:

[0200] Performing spectrum analysis on the preprocessing results to distinguish high-frequency components and low-frequency components, calculating the road surface fluctuations corresponding to these components in combination with mathematical models, and evaluating the roughness of different road sections; calculating the root mean square value of the separated high-frequency components; establishing a mathematical relationship model between vehicle vibration characteristics and energy consumption based on the root mean square value combined with additional losses, and setting a weight factor related to roughness to determine the degree of influence of road roughness on energy consumption; performing feature engineering on the preprocessing results to obtain feature engineering results; constructing a mathematical relationship model between traffic flow and energy consumption based on the feature engineering structure, and setting a weight factor related to traffic flow to determine the degree of influence of traffic flow on energy consumption; calculating the cumulative value of low-frequency components on the preprocessing results; constructing a mathematical relationship model between slope and energy consumption based on the cumulative value, vehicle speed and other dynamic characteristics, and setting a weight factor related to slope to determine the degree of influence of slope on energy consumption.

[0201] In one embodiment, the energy consumption model construction unit 302 is further used to: perform weighted summation of the influence of the road flatness on energy consumption, the influence of traffic flow on energy consumption, and the influence of slope on energy consumption to obtain an energy consumption model.

[0202] In one embodiment, the charging suggestion subunit is used to:

[0203] Analyze the multi-source data, establish a detailed user profile, and record the user's driving behavior pattern, frequented places, and charging habit information; use the energy consumption model, combined with the user's travel plan, to predict the energy consumption level under different routes, specifically taking into account the influence of road flatness, traffic flow, and slope factors, and calculate the expected energy consumption for each possible journey; generate a customized charging strategy based on the user's daily life rhythm and predicted energy consumption; combine the information in the user's travel pattern profile, use a machine learning algorithm to train historical charging behavior to obtain an adaptive strategy; integrate the customized charging strategy with the adaptive strategy, set priorities for each suggestion according to importance and urgency, and generate personalized charging suggestions, the suggestions include specific arrangements for when and where to charge and tips that help extend the driving range.

[0204] In one embodiment, the device further comprises:

[0205] The path determination unit is used to evaluate and optimize the energy consumption of each candidate route by integrating energy consumption models, real-time traffic data and charging pile information. It will capture instantaneous power fluctuations to adjust the score and ultimately select the optimal path that ensures sufficient power throughout the journey and provides personalized charging recommendations.

[0206] In one embodiment, the path determination unit is used to:

[0207] When planning multiple candidate routes from a starting point to a destination, the energy consumption model is used to score the energy consumption of each route, and energy-aware path selection is implemented by combining real-time traffic conditions and location information of available charging piles along the way; instantaneous power fluctuations are captured to optimize the energy consumption score of each candidate route, while considering the amount of power required to reach the target charging pile and other charging opportunities that may be encountered along the way; and finally an optimal route is determined to ensure that the vehicle maintains sufficient power throughout the journey, and personalized charging reminders are pushed to users through mobile applications or vehicle systems.

[0208] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned charging management device 300 based on data analysis and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0209] The charging management device 300 based on data analysis can be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.

[0210] See also Figure 4 , Figure 4 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0211] See also Figure 4 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0212] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a charging management method based on data analysis.

[0213] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0214] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a charging management method based on data analysis.

[0215] The network interface 505 is used to communicate with other devices over the network. Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0216] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps:

[0217] Acquire data from different channels to obtain multi-source data, wherein the multi-source data includes the vehicle's historical navigation records, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data and environmental conditions; construct an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate the energy consumption level of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow and slope; provide users with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, and the suggestions include specific arrangements for when and where to charge and tips that help extend the driving range; monitor the vehicle status and charging pile status in real time, initiate emergency handling procedures based on the deviation of actual operating conditions from expectations, and provide alternative solutions when the selected charging pile becomes unavailable.

[0218] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0219] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0220] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps:

[0221] Acquire data from different channels to obtain multi-source data, wherein the multi-source data includes the vehicle's historical navigation records, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data and environmental conditions; construct an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate the energy consumption level of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow and slope; provide users with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, and the suggestions include specific arrangements for when and where to charge and tips that help extend the driving range; monitor the vehicle status and charging pile status in real time, initiate emergency handling procedures based on the deviation of actual operating conditions from expectations, and provide alternative solutions when the selected charging pile becomes unavailable.

[0222] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0223] It should be noted that the functions or steps that can be implemented by the above storage medium or computer device can be correspondingly referred to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.

[0224] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0225] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0226] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0227] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0228] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A charging management method based on data analysis, characterized in that: include: Acquire data from different channels to obtain multi-source data, wherein the multi-source data includes the vehicle's historical navigation records, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data, and environmental conditions; Constructing an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate the energy consumption level of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow, and slope; Providing personalized charging recommendations to the user based on the energy consumption model and the user's daily travel habits and personal preferences, including specific arrangements for when and where to charge and tips to help extend driving range; Monitor vehicle status and charging pile status in real time, initiate emergency procedures based on actual operating conditions deviating from expectations, and provide alternatives when the selected charging pile becomes unavailable.

2. The charging management method based on data analysis according to claim 1, characterized in that: The step of constructing an energy consumption model according to the multi-source data comprises: Preprocessing the multi-source data to obtain a preprocessing result; Determine the influence degree of road flatness on energy consumption, the influence degree of traffic flow on energy consumption and the influence degree of slope on energy consumption according to the preprocessing result; An energy consumption model is constructed according to the influence of the road flatness on energy consumption, the influence of the traffic flow on energy consumption, and the influence of the slope on energy consumption.

3. The charging management method based on data analysis according to claim 2, characterized in that: The determining, according to the preprocessing unit, the influence degree of road flatness on energy consumption, the influence degree of traffic flow on energy consumption, and the influence degree of slope on energy consumption comprises: Performing spectrum analysis on the preprocessing results to distinguish high-frequency components from low-frequency components, calculating the road surface fluctuations corresponding to these components in combination with a mathematical model, and evaluating the roughness of different road sections; For the separated high-frequency components, calculate their RMS values; A mathematical relationship model between vehicle vibration characteristics and energy consumption is established based on the root mean square value combined with the additional loss, and a weight factor related to the roughness is set to determine the influence of the road roughness on the energy consumption; Performing feature engineering processing on the preprocessing result to obtain a feature engineering result; Constructing a mathematical relationship model between traffic flow and energy consumption according to the feature engineering structure, and setting a weight factor related to traffic flow to determine the degree of influence of traffic flow on energy consumption; Calculating the cumulative value of the low-frequency component of the preprocessing result; A mathematical relationship model between the slope and the energy consumption is constructed according to the accumulated value, the vehicle speed and other dynamic characteristics, and a weight factor related to the slope is set to determine the influence of the slope on the energy consumption.

4. The charging management method based on data analysis according to claim 3, characterized in that: The energy consumption model is constructed according to the influence degree of the road flatness on the energy consumption, the influence degree of the traffic flow on the energy consumption and the influence degree of the slope on the energy consumption, including: The influence of the road flatness on energy consumption, the influence of the traffic flow on energy consumption and the influence of the slope on energy consumption are weighted and summed to obtain an energy consumption model.

5. The charging management method based on data analysis according to claim 1, characterized in that: According to the energy consumption model and the user's daily travel habits and personal preferences, the user is provided with personalized charging suggestions, the suggestions including specific arrangements for when and where to charge and tips for extending the driving range, including: Analyze the multi-source data to establish a detailed user profile, recording the user's driving behavior pattern, frequented locations, and charging habits; Using the energy consumption model, combined with the user's travel plan, the energy consumption level of different routes is predicted, and the expected energy consumption is calculated for each possible trip by specifically considering the influence of road flatness, traffic flow, and slope factors; Generate customized charging strategies based on the user's daily rhythm and predicted energy consumption; Combined with information from user travel pattern profiles, a machine learning algorithm is used to train historical charging behaviors to obtain an adaptive strategy; The customized charging strategy is integrated with the adaptive strategy to prioritize the recommendations according to importance and urgency, and generate personalized charging recommendations including specific arrangements for when and where to charge and tips to help extend driving range.

6. The charging management method based on data analysis according to claim 1, characterized in that: The providing of personalized charging suggestions to the user based on the energy consumption model and the user's daily travel habits and personal preferences, wherein the suggestions include specific arrangements for when and where to charge and tips for extending the driving range, further includes: By integrating energy consumption models, real-time traffic data and charging station information to evaluate and optimize the energy consumption of each candidate route, it will capture instantaneous power fluctuations to adjust the score, and ultimately select the optimal route that ensures sufficient power throughout the journey and provides personalized charging recommendations.

7. The charging management method based on data analysis according to claim 6, characterized in that: The energy consumption of each candidate route is evaluated and optimized by integrating energy consumption models, real-time traffic data and charging pile information. Instantaneous power fluctuations are captured to adjust the score, and finally an optimal route is selected to ensure sufficient power throughout the journey and provide personalized charging suggestions, including: When planning multiple candidate routes from a starting point to a destination, the energy consumption model is used to score the energy consumption of each route, and energy-aware path selection is implemented in combination with real-time traffic conditions and location information of available charging piles along the route; Capture instantaneous power fluctuations and optimize the energy consumption score of each candidate route, taking into account the power required to reach the target charging station and other charging opportunities that may be encountered along the way; Ultimately, an optimal route is determined to ensure that the vehicle maintains sufficient power throughout the journey, and personalized charging reminders are pushed to users through mobile applications or in-vehicle systems.

8. A charging management device based on data analysis, characterized in that: include: A multi-source data acquisition unit, used to acquire data from different channels to obtain multi-source data, wherein the multi-source data includes historical navigation records of the vehicle, current GPS positioning information, road conditions collected by sensors, traffic flow data, vehicle operation data and environmental conditions; An energy consumption model building unit, used to build an energy consumption model based on the multi-source data, wherein the energy consumption model is used to evaluate the energy consumption level of different routes, and the model comprehensively considers multi-dimensional influencing factors such as road flatness, traffic flow, and slope; a charging suggestion generating unit, configured to provide a user with personalized charging suggestions based on the energy consumption model and the user's daily travel habits and personal preferences, wherein the suggestions include specific arrangements for when and where to charge and tips for extending the driving range; A real-time monitoring unit is used to monitor the vehicle status and charging pile status in real time, initiate emergency handling procedures according to the deviation of actual operating conditions from expectations, and provide alternative solutions when the selected charging pile becomes unavailable.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images