Method, system and equipment for suggesting fuel-saving driving behavior and medium
By constructing a benchmark vehicle database and using an improved support vector machine algorithm, personalized fuel-saving driving suggestions are generated, solving the problem that existing systems have difficulty assessing driver skill levels and improving the accuracy of fuel economy and fuel-saving potential assessments.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-19
- Publication Date
- 2026-04-10
AI Technical Summary
Existing commercial vehicle driving behavior evaluation and recommendation systems are insufficient to fully reflect driver behavior, and the evaluation criteria fail to take into account complex and ever-changing operating conditions, making it difficult to accurately assess drivers' driving skills and fuel-saving potential.
By constructing multiple benchmark vehicle databases, an improved support vector machine algorithm is used to establish a fuel consumption prediction model. Combined with vehicle network data, the difference between the driving behavior characteristic parameters of the target vehicle and those of the benchmark vehicles is determined, and personalized fuel-saving driving suggestions are generated.
It improves guidance for drivers on fuel-saving driving techniques, reduces energy waste caused by poor driving behavior, and achieves more accurate fuel economy assessment.
Smart Images
Figure CN121834483A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vehicle networking technology, and more specifically to a method, system, device, and medium for suggesting fuel-saving driving behaviors. Background Technology
[0002] Against the backdrop of rising energy costs and increasingly stringent environmental policies, energy-saving and emission-reduction technologies for commercial vehicles have attracted significant attention. When vehicle configuration, performance, cargo, and operating conditions are fixed, the quality of the driver's behavior directly impacts fuel economy. Generally, improving fuel-efficient driving behavior relies primarily on accumulating driving experience and driver training. However, the former requires considerable time and incurs high fuel costs, while the latter only has a short-term impact on driver skills after training and is difficult to maintain over a long period.
[0003] Therefore, with the rapid development of vehicle networking technology, driving behavior evaluation and fuel-saving technology guidance systems have emerged. These systems can evaluate the economic efficiency of a driver's driving behavior during or after a trip, thereby guiding the driver to perform fuel-saving driving maneuvers.
[0004] Current commercial vehicle driving behavior evaluation and suggestion systems mostly perform simple analyses of fixed driving behavior characteristic parameters. The data sources are limited and cannot fully reflect the driver's driving behavior. In addition, the evaluation standards are basically based on setting a single threshold, which does not take into account the complex and variable operating conditions of commercial vehicles, making it difficult to accurately assess the driver's driving level. Therefore, the evaluation system has certain limitations. Summary of the Invention
[0005] The purpose of this invention is to provide a method, system, device, and medium for suggesting fuel-saving driving behaviors. By judging the operating conditions of the target vehicle, comparing the driving behavior data with that of a benchmark vehicle with the same configuration and operating conditions, personalized driving suggestions are generated and the fuel-saving potential after improving driving behavior is calculated, so as to reduce energy waste caused by poor driving behavior and improve the driver's fuel-saving driving skills.
[0006] To achieve the above objectives, embodiments of the present invention provide a method for suggesting fuel-saving driving behaviors, including: Acquire operational data of connected vehicles and build multiple benchmark vehicle databases; Based on each benchmark vehicle database, a corresponding fuel consumption prediction model is constructed and trained; wherein, the fuel consumption prediction model is constructed based on an improved support vector machine algorithm; Obtain the driving behavior characteristic parameters of the target vehicle driver and determine the benchmark vehicle database to which it belongs and the corresponding fuel consumption prediction model. For at least one driving behavior feature parameter of the target vehicle, determine whether the difference between it and the standard value in the corresponding benchmark vehicle database exceeds a preset threshold; if so, replace the driving behavior feature parameter with the standard value, and input all the replaced driving behavior feature parameters into the corresponding fuel consumption prediction model to obtain the predicted fuel consumption. The difference between the actual fuel consumption and the predicted fuel consumption of the target vehicle is calculated to obtain the fuel-saving potential. Based on the fuel-saving potential, fuel-saving driving suggestions are generated for the target vehicle.
[0007] Optionally, the construction of the benchmark vehicle driving behavior database includes: Integrate vehicle operation data from the Internet of Vehicles, including basic vehicle configuration parameters, vehicle operating condition parameters, and driving behavior characteristic parameters; Based on the vehicle's basic configuration parameters and operating condition parameters, the vehicles are classified and multiple benchmark vehicle databases are established, with each database corresponding to vehicles with the same configuration and operating conditions.
[0008] Optionally, the process of constructing the fuel consumption prediction model includes: Calculate the driving behavior characteristic parameters of benchmark vehicles in each benchmark vehicle database; Principal component analysis was performed on the driving behavior characteristic parameters to obtain the principal component parameter matrix; Using the principal component parameter matrix as input and the average fuel consumption of each benchmark vehicle as output, a fuel consumption prediction model is established using an improved support vector machine algorithm. The improved support vector machine algorithm uses an improved genetic algorithm to optimize the selection of the penalty factor and the variance of the radial basis function kernel function of the support vector machine model. The improved genetic algorithm includes an optimal mutation step added on the basis of the standard mutation operation, so that the combination of the penalty factor and the variance of the radial basis function kernel function explores towards the current optimal solution.
[0009] Optionally, principal component analysis is performed on the driving behavior characteristic parameters to obtain the principal component parameter matrix, including: The driving behavior feature parameters are standardized to obtain a standardized parameter matrix; Calculate the correlation coefficient matrix between various driving behavior characteristic parameters, and solve for the eigenvalues of the correlation coefficient matrix; Based on the magnitude of the eigenvalues, select the top few principal components whose cumulative contribution rate reaches a preset threshold to form a principal component matrix. Then, multiply the standardized parameter matrix with the principal component matrix to obtain the principal component parameter matrix of driving behavior.
[0010] Optionally, the correlation coefficient matrix between each driving behavior characteristic parameter can be calculated using the following formula: ; In the formula, bij represents the j-th feature parameter of the i-th vehicle after standardization. and denoted by , where m represents the average value and m represents the total number of vehicles.
[0011] Optionally, an improved genetic algorithm is used to optimize the selection of the penalty factor and the variance of the radial basis kernel function of the support vector machine model, including: Initialize a population of multiple individuals, where each individual represents a set of parameters including the variance of the penalty factor and the radial basis kernel function; The parameters of each individual are substituted into the support vector machine algorithm for training, and the prediction error of the support vector machine algorithm is calculated. Using the mean absolute error as the fitness function of an individual, the genetic algorithm is used to perform selection and crossover operations on the current population to generate a new intermediate population. Then, the optimal mutation operation is performed on each individual in the new intermediate population to generate the mutated population. Repeat the selection, crossover, and best mutation operations until the preset number of iterations or fitness convergence condition is reached; The individual with the highest fitness is selected from the final population, and its corresponding parameter combination, which includes the penalty factor and the variance of the radial basis kernel function, is used as the setting parameter for the support vector machine algorithm.
[0012] The fitness function is: ; In the formula, m is the number of training samples. For the first The vehicle's actual fuel consumption; For the first The fitted fuel consumption value for the vehicle.
[0013] Optionally, perform a selective mutation operation on each individual in the new intermediate population, including: For individuals in the new intermediate population to be mutated, first follow the formula... The first mutated individual was calculated, where, and These represent the positions of individual i before and after the mutation. For individual movement speed, The optimal individual after performing selection and crossover operations on the population; Will and The input is fed into the support vector machine algorithm, and the minimum prediction error of the support vector machine algorithm is used as the selection objective. Using prediction error to determine the fitness of an individual after mutation, if Its fitness is higher than Then keep Position and perform next-generation operations; like The fitness is lower than Then, random perturbation variation is applied to the individual, according to the formula. Execution, among which, and for The range of values for , Let M be the current iteration number, and M be the maximum iteration number. Given a random number in the interval [0,1], if after random mutation... Its fitness is higher than Then keep Position, otherwise still reserved Location, then execute the next generation operation.
[0014] Secondly, the present invention also provides a fuel-saving driving behavior suggestion system, comprising: The data acquisition unit is used to acquire vehicle operation data of the Internet of Vehicles, build multiple benchmark vehicle databases, and acquire driving behavior characteristic parameters of the drivers of the target analysis vehicles. The model building unit is used to build and train the corresponding fuel consumption prediction model based on each benchmark vehicle database; wherein the fuel consumption prediction model is built based on an improved support vector machine algorithm. The data replacement unit is used to determine whether the difference between at least one driving behavior feature parameter of the target vehicle and the standard value in the corresponding benchmark vehicle database exceeds a preset threshold; if so, the driving behavior feature parameter is replaced with the standard value. The fuel consumption prediction unit is used to input all driving behavior feature parameters after the target analysis vehicle is replaced into the corresponding fuel consumption prediction model to obtain the predicted fuel consumption. The comparison unit is used to calculate the difference between the actual fuel consumption and the predicted fuel consumption of the target vehicle to obtain the fuel-saving potential. The suggestion generation unit is used to generate fuel-saving driving suggestions for the target analysis vehicle based on the fuel-saving space.
[0015] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the proposed method for the above-described fuel-saving driving behavior.
[0016] Fourthly, the present invention also provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the proposed method for the above-described fuel-saving driving behavior.
[0017] The above technical solution analyzes the operating conditions of the target vehicle and compares the driving behavior data with that of a benchmark vehicle with the same configuration and operating conditions. It then generates personalized driving suggestions and calculates the fuel-saving potential after improving driving behavior, thereby reducing energy waste caused by poor driving behavior and improving the driver's fuel-saving driving skills.
[0018] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0019] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a method for suggesting fuel-saving driving behaviors provided by an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the construction process of a fuel consumption prediction model provided in an embodiment of the present invention; Figure 3 This is an embodiment of a fuel-saving driving behavior suggestion system architecture provided by the present invention; Figure 4 This is a schematic diagram of the structure of a fuel-saving driving behavior suggestion system provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0020] Various embodiments of this disclosure will be described more fully in the following detailed description. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.
[0021] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions or operations and do not limit the addition of one or more functions or operations. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a specific feature, number, step, operation, or combination of the foregoing and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, or combinations of the foregoing, or the possibility of adding one or more features, numbers, steps, operations, or combinations of the foregoing.
[0022] In various embodiments of this disclosure, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.
[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0024] See Figure 1 The diagram shows a flowchart of a method for suggesting fuel-saving driving behavior in a specific embodiment, including the following execution steps: Step 100: Obtain vehicle operation data for connected vehicles and build multiple benchmark vehicle databases.
[0025] Specifically, the construction process of the benchmark vehicle driving behavior database is as follows: Integrate vehicle operation data from the Internet of Vehicles, wherein the vehicle operation data includes basic vehicle configuration parameters, vehicle operating condition parameters, and driving behavior characteristic parameters; classify vehicles according to the basic vehicle configuration parameters and the vehicle operating condition parameters, and establish multiple benchmark vehicle databases, wherein each database corresponds to vehicles with the same configuration and operating conditions.
[0026] For example, the multiple benchmark vehicle databases consist of vehicles driven by experienced drivers or with good fuel economy. The databases cover vehicles with various configurations and operating conditions, and each benchmark vehicle database consists of vehicles with the same configuration and operating conditions. Vehicles with the same configuration refer to vehicles with the same basic configuration parameters, and vehicles with the same operating conditions refer to vehicles with the same operating condition parameters.
[0027] By utilizing the massive amounts of data in the database, we can establish evaluation criteria for vehicle driving behavior under different configurations and operating conditions.
[0028] Step 101: Based on the database of each benchmark vehicle, construct and train the corresponding fuel consumption prediction model. The fuel consumption prediction model is constructed based on an improved support vector machine algorithm.
[0029] For details, see Figure 2 As shown, the process of constructing the fuel consumption prediction model includes the following steps: S1: Calculate the driving behavior characteristic parameters of benchmark vehicles in each benchmark vehicle database.
[0030] S2: Perform principal component analysis on the driving behavior characteristic parameters to obtain the principal component parameter matrix.
[0031] Specifically, step S2 can be executed in the following ways: S20: Standardize the driving behavior feature parameters to obtain a standardized parameter matrix.
[0032] Specifically, a benchmark vehicle database contains m vehicles. Each vehicle has n driving behavior characteristic parameters calculated, forming an m x n feature parameter matrix. Using the formula... The m x n eigenparameter matrix is standardized to obtain the standardized parameter matrix, where... and The first and second parts before and after standardization, respectively. The first car In this embodiment, there are several characteristic parameters. , ; and The first The mean and standard deviation of each characteristic parameter.
[0033] S21: Calculate the correlation coefficient matrix between various driving behavior characteristic parameters, and solve for the eigenvalues of the correlation coefficient matrix.
[0034] Specifically, the correlation coefficient matrix between various driving behavior characteristic parameters is calculated using the following formula: ; In the formula, bij represents the j-th feature parameter of the i-th vehicle after standardization. and denoted by , where m represents the average value and m represents the total number of vehicles.
[0035] S22: Select the top several principal components whose cumulative contribution rate reaches a preset threshold based on the size of the eigenvalues, form a principal component matrix, and multiply the standardized parameter matrix with the principal component matrix to obtain the driving behavior principal component parameter matrix.
[0036] For example, the eigenvalues and eigenvectors of the correlation coefficient matrix are obtained. The eigenvalues are sorted from largest to smallest, and their cumulative contribution rates are calculated. The eigenvectors of the top five principal components with a cumulative contribution rate of 90% are taken as the principal component matrix. The product of the standardized parameter matrix and the principal component matrix is taken as the principal component parameter matrix, represented as follows: .
[0037] Principal component analysis is used to extract key driving behavior factors, solving the problem that with numerous driving behavior characteristic parameters, it is difficult to determine the main factors affecting fuel economy.
[0038] S3: Using the principal component parameter matrix as input and the average fuel consumption of each benchmark vehicle as output, a fuel consumption prediction model is established using an improved support vector machine algorithm.
[0039] The improved support vector machine algorithm uses an improved genetic algorithm to optimize the selection of the penalty factor and the variance of the radial basis function kernel function of the support vector machine model. The improved genetic algorithm includes an optimal mutation step added on the basis of the standard mutation operation, so that the combination of the penalty factor and the variance of the radial basis function kernel function explores towards the current optimal solution.
[0040] Specifically, an improved genetic algorithm is used to optimize the selection of the penalty factor and the variance of the radial basis kernel function in the support vector machine model, including the following execution steps: SA: Initializes a population of multiple individuals, where each individual represents a set of parameters including the variance of the penalty factor and the radial basis kernel function.
[0041] SB: Substitute the parameters of the individual into the support vector machine algorithm for training, and calculate the prediction error of the support vector machine algorithm.
[0042] Specifically, an improved genetic algorithm is used to refine the selection of the penalty factor c and the variance g of the radial basis function kernel in the support vector machine (SVM) model. This yields the parameter combination with the highest training accuracy, which is then used as the model's parameters. The improved SVM model is then used to establish a fuel consumption prediction model. The parameter combination c and g with the highest training accuracy refers to the combination that minimizes the prediction error of the SVM model, i.e., minimizes the fitness function.
[0043] SC: Using the mean absolute error as the fitness function of an individual, perform selection and crossover operations on the current population using a genetic algorithm to generate a new intermediate population, and perform a selective mutation operation on each individual in the new intermediate population to generate the mutated population.
[0044] The fitness function is: ; In the formula, m is the number of training samples. For the first The vehicle's actual fuel consumption; For the first The fitted fuel consumption value of the vehicle is, in this embodiment, the regression fuel consumption value of the improved support vector machine model.
[0045] It should be understood that the principle of the support vector machine model is: to combine m n-dimensional vectors (i.e., ... By nonlinearly mapping to a high-dimensional space, an optimal plane is established in the high-dimensional space, minimizing the distance of all training samples from this plane, i.e., minimizing the error. This includes: ; Where c represents the penalty factor, indicating the degree of penalty for samples with excessive errors. As slack variables, Indicates the insensitive loss coefficient, fitting the fuel consumption value. For linear functions established in high-dimensional space, To be Nonlinear functions mapped to high-dimensional space. Introducing radial basis function kernel. Solving the above equation yields the support vector machine regression model, where g is the variance of the kernel function.
[0046] In one specific implementation, the selective mutation operation performed on each individual in the new intermediate population in step SC can specifically be performed using the following sub-steps: SC0: For individuals in the new intermediate population to be mutated, first follow the formula... The first mutated individual was calculated, where, and These represent the positions of individual i before and after the mutation (i.e., the values of the combination parameters c and g). For individual movement speed, The optimal individual after performing selection and crossover operations on the population.
[0047] SC1: Will and The input is fed into the support vector machine algorithm, and the minimum prediction error of the support vector machine algorithm is used as the selection objective.
[0048] The smaller the error value, the higher the individual fitness.
[0049] SC2: Use prediction error to determine the fitness of individuals after mutation. Its fitness is higher than Then keep Position and perform next-generation operations.
[0050] SC3: If The fitness is lower than Then, random perturbation variation is applied to the individual, according to the formula. Execution, among which, and for The range of values for , Let M be the current iteration number, and M be the maximum iteration number. Given a random number in the interval [0,1], if after random mutation... Its fitness is higher than Then keep Position, otherwise still reserved Location, then execute the next generation operation.
[0051] SD: Repeated selection, crossover, and selective mutation operations until the preset number of iterations or fitness convergence condition is reached.
[0052] SE: Select the individual with the highest fitness from the final population, and use the corresponding parameter combination, which includes the penalty factor and the variance of the radial basis kernel function, as the setting parameters for the support vector machine algorithm.
[0053] The positions of the combined parameters c and g are updated using an improved genetic algorithm. Based on the prediction error of the trained support vector machine model, the values of the combined parameters c and g with the smallest prediction error are determined, and the trained support vector machine model is used as the fuel consumption prediction model for the benchmark vehicle database.
[0054] In this embodiment, a benchmark vehicle library with the same configuration and type as the target analysis vehicle is selected, and the benchmark vehicle driving behavior characteristic parameter standard is determined based on the mean and distribution of the driving behavior characteristic parameters of each vehicle in the benchmark vehicle library.
[0055] Step 102: Obtain the driving behavior characteristic parameters of the target analysis vehicle driver, and determine the benchmark vehicle database to which it belongs and the corresponding fuel consumption prediction model.
[0056] Specifically, the system integrates vehicle operation data from the Internet of Vehicles (IoV) database with driver behavior data from target analysis vehicles. The IoV operation data originates from raw signals from vehicle GPS, onboard sensors, and vehicle ECU signals, or from processed parameter data, including basic vehicle configuration parameters, vehicle operating condition parameters, and vehicle driving behavior characteristic parameters. Basic vehicle configuration parameters include, but are not limited to, vehicle model, fuel type, drive type, engine, transmission, rear axle ratio, and tire type. Vehicle operating condition parameters include, but are not limited to, market segment, operating scenario, cargo type, operating area, percentage of highway use, and percentage of national highway use. Driving behavior characteristic parameters include, but are not limited to, average vehicle speed, speed standard deviation, speed fluctuation coefficient, percentage of high-speed use, average throttle, throttle standard deviation, throttle fluctuation coefficient, percentage of high-throttle use, number of braking operations per 100 km / h, braking duration per 100 km / h, average braking depth, shift frequency, average upshift speed, average downshift speed, percentage of high-gear use, percentage of idling time, percentage of coasting in gear, percentage of coasting in neutral, and proportion of assisted braking application.
[0057] In this embodiment, vehicle network data from tens of thousands of vehicles is obtained. This data originates from the onboard terminal acquisition devices of each vehicle and is transmitted to the data storage system via a cloud network. The parameters collected by the onboard terminal acquisition devices include GPS, onboard sensor, and ECU signals, encompassing vehicle operation signals such as time, location, mileage, fuel consumption, vehicle speed, engine speed, throttle position, gear position, braking, torque, friction torque, load, altitude, gradient, and road type. Basic vehicle configuration parameters and vehicle operating condition parameters are obtained from the order system. This system records the vehicle configuration parameters and operating condition parameters for each vehicle. Vehicle configuration parameters include vehicle model, fuel type, drive type, engine, transmission, rear axle ratio, and tire model; operating condition parameters include market segment, operating scenario, and cargo type.
[0058] By preprocessing vehicle operation signals, removing abnormal data, and performing data filtering, the driving behavior characteristic parameters are obtained, including average vehicle speed (unit, km / h), vehicle speed standard deviation (unit, km / h), vehicle speed fluctuation coefficient (unit, none), high speed percentage (unit, %), average throttle (unit, %), throttle standard deviation (unit, %), throttle fluctuation coefficient (unit, none), high throttle percentage (unit, %), number of braking operations per 100 km / h (unit, times / 100 km), braking duration per 100 km / h (unit, min / 100 km), and average braking depth (unit, %). The data includes shift frequency (times / 100 km), average upshift speed (r / min), average downshift speed (r / min), percentage of high gears (%), percentage of idling time (%), percentage of coasting time (%), and percentage of auxiliary braking application (%). Simultaneously, vehicle operating condition parameters are obtained, including operating area, percentage of highways (%), and percentage of national highways (%). Operating areas include the northern plains, southeastern hills, Loess Plateau, Northwest China, Southwest Plateau, Southwest mountainous areas, plains and hills, and mountainous areas.
[0059] In this embodiment, vehicle configuration parameters, operating condition parameters, and driving behavior characteristic parameters of tens of thousands of vehicles are integrated. The vehicles are classified according to the vehicle configuration parameters and operating condition parameters, and the top 80% of vehicles in terms of fuel consumption in each benchmark vehicle database are selected to obtain a benchmark vehicle database with different configurations and operating conditions.
[0060] Step 103: For at least one driving behavior feature parameter of the target vehicle, determine whether the difference between it and the standard value in the corresponding benchmark vehicle database exceeds a preset threshold; if so, replace the driving behavior feature parameter with the standard value, and input all the replaced driving behavior feature parameters into the corresponding fuel consumption prediction model to obtain the predicted fuel quantity.
[0061] Step 104: Calculate the difference between the actual fuel consumption and the predicted fuel consumption of the target vehicle to obtain the fuel-saving potential.
[0062] For example, taking average vehicle speed as an example, the difference between the average speed of the target vehicle and the average speed standard of the benchmark vehicle database is calculated. When the difference exceeds the set average speed difference limit (2 km / h in this embodiment), the average speed of the target vehicle is replaced with the average speed standard of the benchmark vehicle database. Then, the driving behavior characteristic parameters of the target vehicle are input into the fuel consumption prediction model to obtain the fuel-saving space prediction when the average speed is optimized to the average speed standard of the benchmark vehicle database. The above steps are repeated to obtain the fuel-saving space when each driving characteristic parameter is optimized to the driving behavior characteristic parameter standard of the benchmark vehicle database.
[0063] An improved support vector machine is used to establish a fuel-saving space prediction model to solve the problem of difficulty in predicting fuel-saving space and to explore the fuel-saving potential of different vehicle drivers.
[0064] Step 105: Based on the fuel-saving space, generate fuel-saving driving suggestions for the target vehicle.
[0065] In one specific implementation, customized driving suggestions for the target vehicle are generated based on various driving behavior characteristic parameters and fuel-saving potential. Taking speed-related driving behavior characteristic parameters as an example, when the fuel-saving potential calculated based on driving behavior characteristic parameters such as average speed and speed fluctuation coefficient is 0.5L / 100km, if the average speed and speed fluctuation coefficient exceed the set difference limit, the driving behavior suggestion can be expressed as: Your average speed is too high, and your speed control is relatively volatile. It is recommended that you choose a reasonable speed during driving and try to keep the speed stable while ensuring driving safety.
[0066] In this embodiment, the driving behavior score is obtained by analyzing the fuel consumption ranking of the target vehicle among vehicles with the same configuration and operating conditions.
[0067] For drivers of different skill levels, customized fuel-saving driving suggestions are generated based on driving style, solving the problem of a single evaluation standard.
[0068] In one specific implementation, see Figure 3 As shown, this is an embodiment of the fuel-saving driving behavior suggestion system architecture provided by the present invention. The cloud network collects corresponding data through the target analysis vehicle and its data acquisition terminal and the benchmark vehicle database and its data acquisition terminal. The driving behavior data is compared with the operating data of vehicles with the same configuration and operating conditions in the benchmark vehicle driving behavior database. The comparison results are stored in the data storage terminal. The comparison results are input into a pre-built fuel consumption prediction model to predict the fuel-saving potential of the target analysis vehicle. Based on the comparison results and the fuel-saving potential, fuel-saving driving suggestions are generated for the target analysis vehicle.
[0069] In this embodiment, by judging the operating conditions of the target vehicle, comparing the driving behavior data with that of a benchmark vehicle with the same configuration and operating conditions, personalized driving suggestions are generated and the fuel-saving potential after improving driving behavior is calculated, so as to reduce energy waste caused by poor driving behavior and improve the driver's fuel-saving driving skills.
[0070] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0071] like Figure 4As shown, the following are embodiments of the fuel-saving driving behavior suggestion system provided in this disclosure. It belongs to the same inventive concept as the fuel-saving driving behavior suggestion method in the above embodiments. For details not described in detail in the embodiments of the fuel-saving driving behavior suggestion system, please refer to the embodiments of the above fuel-saving driving behavior suggestion method.
[0072] A system of recommendations for fuel-efficient driving behaviors includes: The data acquisition unit is used to acquire vehicle operation data of the Internet of Vehicles, build multiple benchmark vehicle databases, and acquire driving behavior characteristic parameters of the drivers of the target analysis vehicles. The model building unit is used to build and train the corresponding fuel consumption prediction model based on each benchmark vehicle database; wherein the fuel consumption prediction model is built based on an improved support vector machine algorithm. The data replacement unit is used to determine whether the difference between at least one driving behavior feature parameter of the target vehicle and the standard value in the corresponding benchmark vehicle database exceeds a preset threshold; if so, the driving behavior feature parameter is replaced with the standard value. The fuel consumption prediction unit is used to input all driving behavior feature parameters after the target analysis vehicle is replaced into the corresponding fuel consumption prediction model to obtain the predicted fuel consumption. The comparison unit is used to calculate the difference between the actual fuel consumption and the predicted fuel consumption of the target vehicle to obtain the fuel-saving potential. The suggestion generation unit is used to generate fuel-saving driving suggestions for the target analysis vehicle based on the fuel-saving space.
[0073] Figure 5 This is a schematic diagram of the hardware structure of an electronic device that implements various embodiments of the present invention.
[0074] The fuel-saving driving behavior recommendations provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structures involved in the embodiments of this invention do not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.
[0075] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.
[0076] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
[0077] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.
[0078] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.
[0079] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.
[0080] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.
[0081] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.
[0082] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.
[0083] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.
[0084] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.
[0085] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.
[0086] Electronic devices can achieve display functions through GPUs, displays, and application processors.
[0087] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.
[0088] A display screen is used to display images, videos, etc. A display screen includes a display panel.
[0089] The storage medium provided in this application stores a program product containing suggested methods for achieving fuel-efficient driving behavior.
[0090] The method for suggesting fuel-saving driving behaviors includes: acquiring vehicle operation data from the Internet of Vehicles (IoV) and constructing multiple benchmark vehicle databases; constructing and training a corresponding fuel consumption prediction model based on each benchmark vehicle database; wherein the fuel consumption prediction model is constructed based on an improved support vector machine algorithm; acquiring driving behavior feature parameters of the driver of the target analysis vehicle and determining its corresponding benchmark vehicle database and fuel consumption prediction model; for at least one driving behavior feature parameter of the target analysis vehicle, determining whether the difference between it and the standard value in the corresponding benchmark vehicle database exceeds a preset threshold; if so, replacing the driving behavior feature parameter with the standard value, and inputting all the replaced driving behavior feature parameters into the corresponding fuel consumption prediction model to obtain the predicted fuel consumption; calculating the difference between the actual fuel consumption and the predicted fuel consumption of the target analysis vehicle to obtain the fuel-saving space; and generating fuel-saving driving suggestions for the target analysis vehicle based on the fuel-saving space.
[0091] In some possible implementations, the subject matter of this disclosure, namely the method and system for recommending fuel-saving driving behavior, can be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.
[0092] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.
[0093] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for suggesting fuel-saving driving behaviors, characterized in that, include: Acquire operational data of connected vehicles and build multiple benchmark vehicle databases; Based on each benchmark vehicle database, a corresponding fuel consumption prediction model is constructed and trained; wherein, the fuel consumption prediction model is constructed based on an improved support vector machine algorithm; Obtain the driving behavior characteristic parameters of the target vehicle driver and determine the benchmark vehicle database to which it belongs and the corresponding fuel consumption prediction model. For at least one driving behavior feature parameter of the target vehicle, determine whether the difference between it and the standard value in the corresponding benchmark vehicle database exceeds a preset threshold; if so, replace the driving behavior feature parameter with the standard value, and input all the replaced driving behavior feature parameters into the corresponding fuel consumption prediction model to obtain the predicted fuel consumption. The difference between the actual fuel consumption and the predicted fuel consumption of the target vehicle is calculated to obtain the fuel-saving potential. Based on the fuel-saving potential, fuel-saving driving suggestions are generated for the target vehicle.
2. The method for suggesting fuel-saving driving behavior according to claim 1, characterized in that, The construction of the benchmark vehicle driving behavior database includes: Integrate vehicle operation data from the Internet of Vehicles, including basic vehicle configuration parameters, vehicle operating condition parameters, and driving behavior characteristic parameters; Based on the vehicle's basic configuration parameters and operating condition parameters, the vehicles are classified and multiple benchmark vehicle databases are established, with each database corresponding to vehicles with the same configuration and operating conditions.
3. The method for suggesting fuel-saving driving behavior according to claim 2, characterized in that, The process of constructing the fuel consumption prediction model includes: Calculate the driving behavior characteristic parameters of benchmark vehicles in each benchmark vehicle database; Principal component analysis was performed on the driving behavior characteristic parameters to obtain the principal component parameter matrix; Using the principal component parameter matrix as input and the average fuel consumption of each benchmark vehicle as output, a fuel consumption prediction model is established using an improved support vector machine algorithm. The improved support vector machine algorithm uses an improved genetic algorithm to optimize the selection of the penalty factor and the variance of the radial basis function kernel function of the support vector machine model. The improved genetic algorithm includes an optimal mutation step added on the basis of the standard mutation operation, so that the combination of the penalty factor and the variance of the radial basis function kernel function explores towards the current optimal solution.
4. The method for suggesting fuel-saving driving behavior according to claim 3, characterized in that, Principal component analysis was performed on the driving behavior characteristic parameters to obtain the principal component parameter matrix, including: The driving behavior feature parameters are standardized to obtain a standardized parameter matrix; Calculate the correlation coefficient matrix between various driving behavior characteristic parameters, and solve for the eigenvalues of the correlation coefficient matrix; Based on the magnitude of the eigenvalues, select the top few principal components whose cumulative contribution rate reaches a preset threshold to form a principal component matrix. Then, multiply the standardized parameter matrix with the principal component matrix to obtain the principal component parameter matrix of driving behavior.
5. The method for suggesting fuel-saving driving behavior according to claim 4, characterized in that, The correlation coefficient matrix among the various driving behavior characteristic parameters is calculated using the following formula: ； In the formula, bij represents the j-th feature parameter of the i-th vehicle after standardization. and denoted by , where m represents the average value and m represents the total number of vehicles.
6. The method for suggesting fuel-saving driving behavior according to claim 3, characterized in that, An improved genetic algorithm is used to optimize the selection of the penalty factor and the variance of the radial basis kernel function in the support vector machine model, including: Initialize a population of multiple individuals, where each individual represents a set of parameters including the variance of the penalty factor and the radial basis kernel function; The parameters of each individual are substituted into the support vector machine algorithm for training, and the prediction error of the support vector machine algorithm is calculated. Using the mean absolute error as the fitness function of an individual, the genetic algorithm is used to perform selection and crossover operations on the current population to generate a new intermediate population. Then, the optimal mutation operation is performed on each individual in the new intermediate population to generate the mutated population. Repeat the selection, crossover, and best mutation operations until the preset number of iterations or fitness convergence condition is reached; The individual with the highest fitness is selected from the final population, and the corresponding parameter combination, which includes the penalty factor and the variance of the radial basis kernel function, is used as the setting parameter for the support vector machine algorithm. The fitness function is: ； In the formula, m is the number of training samples. For the first The vehicle's actual fuel consumption; For the first The fitted fuel consumption value for the vehicle.
7. The method for suggesting fuel-saving driving behavior according to claim 6, characterized in that, Perform selective mutation operations on each individual in the new intermediate population, including: For individuals in the new intermediate population to be mutated, first follow the formula... The first mutated individual was calculated, where, and These represent the positions of individual i before and after the mutation. For individual movement speed, The optimal individual after performing selection and crossover operations on the population; Will and The input is fed into the support vector machine algorithm, and the minimum prediction error of the support vector machine algorithm is used as the selection objective. Using prediction error to determine the fitness of an individual after mutation, if Its fitness is higher than Then keep Position and perform next-generation operations; like The fitness is lower than Then, random perturbation variation is applied to the individual, according to the formula. Execution, among which, and for The range of values for , Let M be the current iteration number, and M be the maximum iteration number. Given a random number in the interval [0,1], if after random mutation... Its fitness is higher than Then keep Position, otherwise still reserved Location, then execute the next generation operation.
8. A fuel-saving driving behavior suggestion system, characterized in that, include: The data acquisition unit is used to acquire vehicle operation data of the Internet of Vehicles, build multiple benchmark vehicle databases, and acquire driving behavior characteristic parameters of the drivers of the target analysis vehicles. The model building unit is used to build and train the corresponding fuel consumption prediction model based on each benchmark vehicle database; wherein the fuel consumption prediction model is built based on an improved support vector machine algorithm. The data replacement unit is used to determine whether the difference between at least one driving behavior feature parameter of the target vehicle and the standard value in the corresponding benchmark vehicle database exceeds a preset threshold; if so, the driving behavior feature parameter is replaced with the standard value. The fuel consumption prediction unit is used to input all driving behavior feature parameters after the target analysis vehicle is replaced into the corresponding fuel consumption prediction model to obtain the predicted fuel consumption. The comparison unit is used to calculate the difference between the actual fuel consumption and the predicted fuel consumption of the target vehicle to obtain the fuel-saving potential. The suggestion generation unit is used to generate fuel-saving driving suggestions for the target analysis vehicle based on the fuel-saving space.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the proposed method for fuel-saving driving behavior as described in any one of claims 1 to 7.
10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the proposed method for fuel-saving driving behavior as described in any one of claims 1 to 7.