Vehicle driving behavior evaluation method and device, electronic equipment and storage medium

Abstract

The present application relates to the technical field of vehicles, and discloses a vehicle driving behavior evaluation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring vehicle operating parameters under a preset driving condition; identifying vehicle path key points based on a predefined latitude and longitude coordinate sequence, and dividing the preset driving condition into at least one downhill sub-condition based on at least the vehicle path key points; determining the user driving behavior of each downhill sub-condition by using the vehicle operating parameters and a pre-trained driving behavior recognition model; and generating a user evaluation score based on the user driving behavior and a preset weight. The present application can solve the problem that the user driving behavior cannot be effectively quantified and scored under complex roads in mountainous areas, and is beneficial to improving the evaluation system of the user driving behavior, improving the evaluation efficiency, and reducing the labor cost.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, device, electronic device, and storage medium for evaluating vehicle driving behavior. Background Technology

[0002] Currently, vehicle reliability testing generally relies on the Road Assurance System (ROADS) platform for vehicle data collection and transmission. This platform can acquire massive amounts of test samples, significantly reducing data collection costs. However, in complex road conditions such as mountainous areas, the analysis of test vehicle operation data and the identification of driving behavior still depend on manual processing, resulting in insufficient analytical depth, low processing efficiency, and high labor costs. Especially in mountainous regions like Yunnan, where driving behavior characteristics are diverse, road conditions are complex, and the number of test vehicles is large, traditional methods struggle to identify abnormal driving behaviors in a timely and accurate manner, and also fail to provide dynamic assessments of vehicle reliability.

[0003] While some existing driving behavior analysis solutions attempt to address similar pain points, they all suffer from significant functional limitations, as detailed below:

[0004] Patent document CN119398602A discloses a driving behavior scoring method, device, electronic device, and computer-readable storage medium. This scheme collects vehicle network data and builds a general driving behavior evaluation system. Based on this system, it scores the vehicle network data to obtain operational-level indicator scores, and then combines these scores to calculate a comprehensive driving behavior score. However, this patent only establishes a general driving behavior evaluation framework and does not design dynamic condition classification rules for mountainous road conditions (continuous long downhill slopes, sharp bends, etc.), making it difficult to extract the unique driving risk characteristics of mountain roads. Furthermore, the scheme only uses a traditional indicator weighted scoring method and does not introduce a deep learning driving behavior classification model, thus failing to achieve refined driving behavior pattern recognition and risk prediction.

[0005] Patent document CN115880927B discloses a method and supporting system for predicting overtaking in complex mountainous roads based on vehicle-to-everything (V2X) technology. This method can automatically perform a safety pre-assessment of overtaking conditions and provide drivers with a safety reference for overtaking timing based on the calculation results. However, this patent only focuses on predicting overtaking opportunities in a single scenario in mountainous areas, failing to construct a complete comprehensive evaluation system for driving behavior and lacking quantitative analysis of multi-dimensional driving behavior. Furthermore, it does not provide a complete system deployment plan, making it difficult to support large-scale deployment and real-time data feedback. Summary of the Invention

[0006] The purpose of this invention is to provide a method, device, electronic device, and storage medium for evaluating vehicle driving behavior, so as to at least solve the problem that user driving behavior cannot be effectively quantified and scored under complex mountain roads, thereby improving the evaluation system for user driving behavior, increasing evaluation efficiency, and reducing labor costs.

[0007] To address the aforementioned technical problems, in a first aspect, the present invention provides a method for evaluating vehicle driving behavior, comprising at least:

[0008] S1. Obtain vehicle operating parameters under preset driving conditions;

[0009] S2. Identify key points of the vehicle path based on a predefined sequence of latitude and longitude coordinates, and divide the preset driving conditions into at least one downhill sub-condition based on the key points of the vehicle path.

[0010] S3. Determine the user's driving behavior for each downhill sub-condition using the vehicle operating parameters and the pre-trained driving behavior recognition model.

[0011] S4. Generate a user evaluation score based on the user's driving behavior and preset weights.

[0012] Optionally, step S1 specifically includes:

[0013] S11. Real-time acquisition of vehicle driving data stream under the preset driving conditions;

[0014] S12. Extract the vehicle operating parameters of the preset number of channels from the driving data stream.

[0015] Optionally, the user's driving behavior includes at least standard driving behavior and non-standard driving behavior;

[0016] Step S4 specifically includes:

[0017] S41. Obtain the percentage of non-standard driving behaviors in each downhill sub-condition;

[0018] S42. Generate a user evaluation score based on the behavior percentage and the preset weight.

[0019] Optionally, after step S4, the method further includes:

[0020] S5. Construct vehicle operation curves based on vehicle operating parameters;

[0021] S6. Determine the abnormal points in the user's driving behavior based on a preset abnormal threshold;

[0022] S7. Upload the user evaluation score, the vehicle operation curve, the identification results on the downhill sub-condition, and the anomaly points to the information control platform.

[0023] Optionally, the pre-training process of the driving behavior recognition model specifically includes:

[0024] S81. Collect vehicle operation data;

[0025] S82. Preprocess the vehicle operation data to obtain standard vehicle data;

[0026] S83. Construct a structured dataset based on the standard vehicle data, and divide the structured dataset into a training set, a validation set, and a test set at least according to a preset ratio;

[0027] S84. Train an initial recognition model based on the training set, the validation set, and the test set, and output the recognition accuracy and F1 score of the initial recognition model;

[0028] S85. When both the recognition accuracy and the F1 score meet the preset requirements, the initial recognition model is determined as the driving behavior recognition model.

[0029] Secondly, the present invention also provides a vehicle driving behavior evaluation device, comprising at least:

[0030] The parameter acquisition module is used to acquire vehicle operating parameters under preset driving conditions;

[0031] The working condition division module is used to identify key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, so as to divide the preset driving working condition into at least one downhill sub-working condition based on the vehicle path key points.

[0032] The behavior determination module is used to determine the user's driving behavior for each of the downhill sub-conditions using the vehicle operating parameters and a pre-trained driving behavior recognition model.

[0033] The score evaluation module is used to generate a user evaluation score based on the user's driving behavior and preset weights.

[0034] Optionally, the parameter acquisition module is specifically used for:

[0035] The vehicle's driving data stream under the preset driving conditions is acquired in real time; and the vehicle's operating parameters are extracted from the driving data stream for a preset number of channels.

[0036] Optionally, the user's driving behavior includes at least standard driving behavior and non-standard driving behavior;

[0037] The score evaluation module is specifically used for:

[0038] Obtain the percentage of non-standard driving behaviors in each downhill sub-condition; and generate a user evaluation score based on the percentage of behaviors and the preset weights.

[0039] Thirdly, the present invention also provides an electronic device, including a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the program to implement the steps in the vehicle driving behavior evaluation method of any one of the first aspects.

[0040] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps in the vehicle driving behavior evaluation method of any one of the first aspects.

[0041] The technical solution provided by this invention firstly obtains vehicle operating parameters under preset driving conditions; secondly, identifies key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, and divides the preset driving conditions into at least one downhill sub-condition based on the key points of the vehicle path; then, uses the vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition; finally, generates a user evaluation score based on the user's driving behavior and preset weights.

[0042] Therefore, this invention, on the one hand, identifies key points of the vehicle path based on latitude and longitude coordinate sequences, and can automatically segment and distinguish various downhill sub-conditions. It can effectively isolate high-risk sub-sections such as continuous long downhill slopes and sharp bends in mountainous areas, solving the problem that traditional general evaluation systems cannot specifically isolate downhill conditions in mountainous areas and the interference of mixed road conditions in the analysis results. On the other hand, this invention uses the vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition, and can automatically complete the classification of driving behavior under downhill conditions, which helps to reduce labor and time costs. Attached Figure Description

[0043] Figure 1 This is a flowchart of a vehicle driving behavior evaluation method provided by the present invention;

[0044] Figure 2 This is a schematic diagram of another vehicle driving behavior evaluation method provided by the present invention;

[0045] Figure 3 This is a schematic diagram of the structure of a vehicle driving behavior evaluation device provided by the present invention;

[0046] Figure 4 This is a schematic diagram of the structure of an electronic device provided by the present invention;

[0047] Figure 5 This invention provides a user evaluation result image;

[0048] Figure 6 This is an architecture diagram of a vehicle driving behavior evaluation system provided by the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0050] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0051] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0052] Figure 1 This is a flowchart of a vehicle driving behavior evaluation method provided by the present invention. The present invention is applicable to at least various vehicle driving behavior evaluation scenarios, especially suitable for vehicle driving behavior evaluation scenarios in mountainous environments. This vehicle driving behavior evaluation method can be, but is not limited to, executed by the vehicle driving behavior evaluation device of the present invention as the execution subject, which can be implemented in software and / or hardware. Figure 1 As shown, the vehicle driving behavior evaluation method includes at least the following steps:

[0053] S1. Obtain vehicle operating parameters under preset driving conditions.

[0054] The preset driving conditions can be the test road conditions specified by the test personnel. The test road conditions can be mountain roads, such as mountain roads in Yunnan. The vehicle operating parameters can be at least one of the following: time, odometer reading, ECU speed, longitude, latitude, GPS altitude, engine speed, actual engine torque percentage, engine torque demand percentage, final set torque, accelerator pedal opening, brake pedal opening, retarder engagement, target gear, actual gear, and cruise control switch.

[0055] S2. Identify key points of the vehicle path based on a predefined sequence of latitude and longitude coordinates, and divide the preset driving conditions into at least one downhill sub-condition based on the key points of the vehicle path.

[0056] The latitude and longitude coordinate sequence is used to determine the vehicle's key point path. When the vehicle travels to a coordinate in the latitude and longitude coordinate sequence, and passes that coordinate (e.g., a typical curve or slope in a mountainous area), the traveled path is marked as a key point of the vehicle path. Users can adaptively set the latitude and longitude coordinate sequence according to actual test road conditions. The travel segment between two key points of the vehicle path constitutes a downhill sub-condition. In one scenario, a round trip between location A and location B constitutes one lap. The single lap travel segment is divided into multiple downhill sub-conditions to be identified, and each lap's travel data is automatically divided into at least four downhill sub-conditions for analysis.

[0057] S3. Use vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition.

[0058] The driving behavior recognition model can be a Long Short-Term Memory (LSTM) machine learning model. User driving behavior can include typical driving behaviors such as rapid acceleration, rapid deceleration, frequent braking, speeding, and improper steering on consecutive curves. User driving behavior can be further divided into standard driving behavior and non-standard driving behavior.

[0059] S4. Generate user evaluation scores based on user driving behavior and preset weights.

[0060] The preset weights correspond to preset driving conditions. When a user selects a preset driving condition, the preset weights will be automatically configured. Alternatively, users can manually set or modify the preset weights.

[0061] The technical solution provided by this invention firstly obtains vehicle operating parameters under preset driving conditions; secondly, identifies key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, and divides the preset driving conditions into at least one downhill sub-condition based on the key points of the vehicle path; then, uses the vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition; finally, generates a user evaluation score based on the user's driving behavior and preset weights.

[0062] Therefore, this invention, on the one hand, identifies key points of the vehicle path based on latitude and longitude coordinate sequences, and can automatically segment and distinguish various downhill sub-conditions. It can effectively isolate high-risk sub-sections such as continuous long downhill slopes and sharp bends in mountainous areas, solving the problem that traditional general evaluation systems cannot specifically isolate downhill conditions in mountainous areas and the interference of mixed road conditions in the analysis results. On the other hand, this invention uses vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition, and can automatically complete the classification of driving behavior under downhill conditions, which helps to reduce labor and time costs.

[0063] Based on the above embodiments or implementation methods Figure 2This is a flowchart of another vehicle driving behavior evaluation method provided by the present invention, which is based on the above embodiments and includes additions. Figure 2 As shown, the vehicle driving behavior evaluation method includes at least the following steps:

[0064] S11. Real-time acquisition of vehicle driving data stream under preset driving conditions.

[0065] Among them, the driving data stream can be all driving data of the vehicle under preset driving conditions.

[0066] S12. Extract vehicle operating parameters from the preset number of channels in the driving data stream.

[0067] The preset number of channels can be 16. Each channel is used to extract one type of vehicle operating parameter.

[0068] S2. Identify key points of the vehicle path based on a predefined sequence of latitude and longitude coordinates, and divide the preset driving conditions into at least one downhill sub-condition based on the key points of the vehicle path.

[0069] S3. Use vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition.

[0070] In one specific implementation, the pre-training of the driving behavior recognition model may optionally be:

[0071] S81. Collect vehicle operation data.

[0072] Among them, vehicle operation data can be obtained through the vehicle-mounted remote terminal, which consists of the following modules: the OBD module is used to collect the streaming data generated during vehicle operation and temporarily store it in the storage module; the storage module is used to temporarily store the data collected by the OBD module; the communication module is used to establish a communication protocol with the cloud platform and complete the functions of data sending and command receiving; the control module is used to manage the above processes in an overall manner to ensure the smooth operation of data collection, storage and transmission.

[0073] S82. Preprocess the vehicle operation data to obtain standard vehicle data.

[0074] Preprocessing can include filtering, missing value imputation, outlier removal, and smoothing of time series data using a sliding window method.

[0075] S83. Construct a structured dataset based on standard vehicle data, and divide the structured dataset into a training set, a validation set, and a test set at least according to a preset ratio.

[0076] The preset ratio can be 80% for the training set, 15% for the validation set, and 5% for the test set.

[0077] S84. Train the initial recognition model based on the training set, validation set, and test set, and output the recognition accuracy and F1 score of the initial recognition model.

[0078] The training process employs cross-validation to optimize network parameters and suppress overfitting. The initial recognition model can be a Long Short-Term Memory (LSTM) network built on the TensorFlow deep learning framework. The input layer of the initial recognition model has 16 feature channels and contains three LSTM hidden layers. The output layer adopts a four-class classification structure, corresponding to the outputs of normal driving behavior, mild abnormal driving behavior, moderate abnormal driving behavior, and severe abnormal driving behavior. The F1 score can be the harmonic mean of precision (how accurately the prediction is made) and recall (how few false negatives are detected). It is known that the F1 score is directly output during model training.

[0079] S85. When both the recognition accuracy and F1 score meet the preset requirements, the initial recognition model is determined as the driving behavior recognition model.

[0080] The preset requirements include an accuracy rate of no less than 90% and an F1 score of no less than 0.85. Once the driving behavior recognition model is determined, it can be packaged into a Docker container and deployed to the ROADS platform server. An API interface is used to connect to the email system, automatically generating a PDF report (including a scoring table, operational curves, and condition recognition results). After receiving the email, engineers can click a link to view an interactive GUI interface, supporting anomaly backtracking and operation suggestion generation.

[0081] S41. Obtain the percentage of non-standard driving behaviors in each downhill sub-condition.

[0082] Among these, the behavior percentage can be the proportion of irregular driving behavior in a user's driving behavior.

[0083] S42. Generate user evaluation scores based on the proportion of behaviors and preset weights.

[0084] The method for determining user rating scores can be:

[0085] ;

[0086] In the formula, S represents the user rating score, n1 represents the number of first-type irregular driving behaviors in the downhill sub-condition, such as sudden braking, n2 represents the number of second-type irregular driving behaviors in the downhill sub-condition, such as speeding, N represents the total number of driving behaviors in the downhill sub-condition, W1 represents the preset weight of the first-type irregular driving behavior, and W2 represents the preset weight of the second-type irregular driving behavior. There can be multiple categories of irregular driving behavior. Furthermore, if there are multiple downhill sub-conditions, the user rating scores for each downhill sub-condition are calculated separately.

[0087] S5. Construct vehicle operation curves based on vehicle operation parameters.

[0088] The vehicle operating curves can include vehicle speed curves, torque curves, engine speed curves, etc., and can be drawn based on changes in vehicle operating parameters.

[0089] S6. Determine abnormal points in the user's driving behavior based on preset abnormal thresholds.

[0090] The preset anomaly threshold can be a calibration value. For example, an anomaly is determined by the vehicle speed being greater than 80 km / h, which is considered a speeding anomaly, and that moment is recorded as the anomaly point. Figure 5 This invention provides a user evaluation result image, such as... Figure 5 As shown.

[0091] S7. Upload user evaluation scores, vehicle operation curves, identification results and anomalies on downhill conditions to the information control platform.

[0092] The technical solution provided by this invention firstly acquires the vehicle's driving data stream under preset driving conditions in real time. Further, it extracts vehicle operating parameters for a preset number of channels from the driving data stream. Further, it identifies key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, dividing the preset driving conditions into at least one downhill sub-condition based on these key points. Further, it uses the vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition. Further, it obtains the proportion of non-standard driving behaviors in each downhill sub-condition. Further, it generates a user evaluation score based on the behavior proportion and a preset weight. Further, it constructs a vehicle operating curve based on the vehicle operating parameters. Further, it identifies anomalies in the user's driving behavior based on a preset anomaly threshold. Finally, it uploads the user evaluation score, the vehicle operating curve, the recognition results for the downhill sub-conditions, and the anomalies to an information control platform.

[0093] Therefore, this invention, on the one hand, identifies key points of vehicle paths based on latitude and longitude coordinate sequences, automatically segmenting and distinguishing various downhill sub-conditions. It effectively isolates high-risk sub-sections such as continuous long downhill slopes and sharp bends in mountainous areas, solving the problem that traditional general evaluation systems cannot specifically isolate downhill conditions in mountainous areas and address the interference of mixed road conditions in the analysis results. On the other hand, this invention utilizes vehicle operating parameters and a pre-trained driving behavior recognition model to determine user driving behavior for each downhill sub-condition, automatically classifying driving behavior under downhill conditions, thus reducing manpower and time costs. Furthermore, this invention provides a new user data mining paradigm for companies in vertical industries such as automotive. During product development, it can accurately capture potential user needs, providing data support for product design optimization and functional iteration; during market operation and after-sales service, it can respond to user feedback in real time, shortening service response cycles and improving user satisfaction. Meanwhile, its highly scalable and secure design supports cross-platform and cross-industry scenario adaptation, helping enterprises break down data silos, deeply mine the value of unstructured data, promote the transformation of business models from "passive response" to "proactive prediction", and inject continuous momentum into the enhancement of enterprises' core competitiveness.

[0094] Figure 6 This is an architecture diagram of a vehicle driving behavior evaluation system provided by the present invention, such as... Figure 6 As shown, the evaluation system includes:

[0095] The user layer is used to provide the user interface.

[0096] The cloud layer is used to facilitate data interaction between the user layer and the data layer.

[0097] The data layer is used to store driving data streams.

[0098] The algorithm layer includes a feature extraction module and a behavior recognition module. The feature extraction module extracts vehicle operating parameters. The behavior recognition module calls the driving behavior recognition model to identify user driving behavior.

[0099] The application layer includes a scoring and output module, a platform deployment module, and an output display module. The scoring and output module calculates user evaluation scores. The platform deployment module deploys the driving behavior recognition model. The output display module displays vehicle trajectory curves, recognition results on downhill slopes, and anomaly alerts.

[0100] Figure 3 This is a schematic diagram of a vehicle driving behavior evaluation device provided by the present invention. The present invention is applicable to at least various vehicle driving behavior evaluation scenarios, especially suitable for mountain driving behavior evaluation scenarios. This vehicle driving behavior evaluation device can be implemented using software and / or hardware. Figure 3As shown, the vehicle driving behavior evaluation device includes at least:

[0101] The parameter acquisition module 110 is used to acquire vehicle operating parameters under preset driving conditions.

[0102] The working condition division module 120 is used to identify key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, so as to divide the preset driving working condition into at least one downhill sub-working condition based on at least the key points of the vehicle path.

[0103] The behavior determination module 130 is used to determine the user's driving behavior for each downhill sub-condition using vehicle operating parameters and a pre-trained driving behavior recognition model.

[0104] The score evaluation module 140 is used to generate user evaluation scores based on user driving behavior and preset weights.

[0105] Optionally, the parameter acquisition module 110 is specifically used for:

[0106] Real-time acquisition of vehicle driving data stream under preset driving conditions; and extraction of vehicle operating parameters from the driving data stream for a preset number of channels.

[0107] Optionally, user driving behavior includes at least standard driving behavior and non-standard driving behavior;

[0108] The score evaluation module 140 is specifically used for:

[0109] Obtain the percentage of non-standard driving behaviors in each downhill sub-condition; and generate user evaluation scores based on the percentage of behaviors and preset weights.

[0110] Optionally, it also includes:

[0111] Display module 150 is used to construct a vehicle operation curve based on vehicle operation parameters; and to determine abnormal points in user driving behavior based on preset abnormal thresholds; and to display user evaluation scores, vehicle operation curves, and downhill sub-conditions.

[0112] Optionally, the pre-training process of the driving behavior recognition model specifically includes:

[0113] S81. Collect vehicle operation data.

[0114] S82. Preprocess the vehicle operation data to obtain standard vehicle data.

[0115] S83. Construct a structured dataset based on standard vehicle data, and divide the structured dataset into a training set, a validation set, and a test set at least according to a preset ratio.

[0116] S84. Train the initial recognition model based on the training set, validation set, and test set, and output the recognition accuracy and F1 score of the initial recognition model.

[0117] S85. When both the recognition accuracy and F1 score meet the preset requirements, the initial recognition model is determined as the driving behavior recognition model.

[0118] The technical solution provided by this invention firstly acquires vehicle operating parameters under preset driving conditions through a parameter acquisition module; secondly, it identifies key points of the vehicle path based on a predefined latitude and longitude coordinate sequence through a condition division module, thereby dividing the preset driving conditions into at least one downhill sub-condition based on the key points of the vehicle path; then, it determines the user's driving behavior for each downhill sub-condition using the vehicle operating parameters and a pre-trained driving behavior recognition model through a behavior determination module; and finally, it generates a user evaluation score based on the user's driving behavior and preset weights through a score evaluation module.

[0119] Therefore, this invention, on the one hand, identifies key points of the vehicle path based on latitude and longitude coordinate sequences, and can automatically segment and distinguish various downhill sub-conditions. It can effectively isolate high-risk sub-sections such as continuous long downhill slopes and sharp bends in mountainous areas, solving the problem that traditional general evaluation systems cannot specifically isolate downhill conditions in mountainous areas and the interference of mixed road conditions in the analysis results. On the other hand, this invention uses the vehicle operating parameters and a pre-trained driving behavior recognition model to determine the user's driving behavior for each downhill sub-condition, and can automatically complete the classification of driving behavior under downhill conditions, which helps to reduce labor and time costs.

[0120] This invention provides an electronic device, Figure 4 This is a schematic diagram of the structure of an electronic device provided by the present invention. See also: Figure 4The electronic device 1000 includes a processor 1001 and a memory 1002. The memory 1002 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1001, the steps in any of the above-described vehicle driving behavior evaluation methods are performed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other via a communication bus and / or other forms of connection mechanisms (not shown). The memory 1002 stores a processor-executable computer program. When the electronic device 1000 is running, the processor 1001 executes the computer program to perform the vehicle driving behavior evaluation method in any optional implementation of the above embodiments, to at least achieve the following functions: obtaining vehicle operating parameters under preset driving conditions; identifying key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, to divide the preset driving conditions into at least one downhill sub-condition based at least on the vehicle path key points; determining the user driving behavior for each downhill sub-condition using the vehicle operating parameters and a pre-trained driving behavior recognition model; and generating a user evaluation score based on the user driving behavior and preset weights.

[0121] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle driving behavior evaluation method provided in all embodiments of this invention: acquiring vehicle operating parameters under preset driving conditions; identifying key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, dividing the preset driving conditions into at least one downhill sub-condition based at least on the vehicle path key points; determining the user driving behavior for each downhill sub-condition using the vehicle operating parameters and a pre-trained driving behavior recognition model; and generating a user evaluation score based on the user driving behavior and preset weights.

[0122] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can 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 computer-readable storage media include: an electrical connection having one or more wires, a portable computer 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. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0123] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0124] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0125] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating vehicle driving behavior, characterized in that, At least including: S1. Obtain vehicle operating parameters under preset driving conditions; S2. Identify key points of the vehicle path based on a predefined sequence of latitude and longitude coordinates, and divide the preset driving conditions into at least one downhill sub-condition based on the key points of the vehicle path. S3. Determine the user's driving behavior for each downhill sub-condition using the vehicle operating parameters and the pre-trained driving behavior recognition model. S4. Generate a user evaluation score based on the user's driving behavior and preset weights.

2. The vehicle driving behavior evaluation method according to claim 1, characterized in that, Step S1 specifically includes: S11. Real-time acquisition of vehicle driving data stream under the preset driving conditions; S12. Extract the vehicle operating parameters of the preset number of channels from the driving data stream.

3. The vehicle driving behavior evaluation method according to claim 1, characterized in that, The user's driving behavior includes at least standard driving behavior and non-standard driving behavior; Step S4 specifically includes: S41. Obtain the percentage of non-standard driving behaviors in each downhill sub-condition; S42. Generate a user evaluation score based on the behavior percentage and the preset weight.

4. The vehicle driving behavior evaluation method according to claim 1, characterized in that, Following step S4, the following is also included: S5. Construct vehicle operation curves based on vehicle operating parameters; S6. Determine the abnormal points in the user's driving behavior based on a preset abnormal threshold; S7. Upload the user evaluation score, the vehicle operation curve, the identification results on the downhill sub-condition, and the anomaly points to the information control platform.

5. The vehicle driving behavior evaluation method according to claim 1, characterized in that, The pre-training process of the driving behavior recognition model specifically includes: S81. Collect vehicle operation data; S82. Preprocess the vehicle operation data to obtain standard vehicle data; S83. Construct a structured dataset based on the standard vehicle data, and divide the structured dataset into a training set, a validation set, and a test set at least according to a preset ratio; S84. Train an initial recognition model based on the training set, the validation set, and the test set, and output the recognition accuracy and F1 score of the initial recognition model; S85. When both the recognition accuracy and the F1 score meet the preset requirements, the initial recognition model is determined as the driving behavior recognition model.

6. A vehicle driving behavior evaluation device, characterized in that, The device is used to perform the vehicle driving behavior evaluation method as described in any one of claims 1-5; The device includes at least: The parameter acquisition module is used to acquire vehicle operating parameters under preset driving conditions; The working condition division module is used to identify key points of the vehicle path based on a predefined latitude and longitude coordinate sequence, so as to divide the preset driving working condition into at least one downhill sub-working condition based on the vehicle path key points. The behavior determination module is used to determine the user's driving behavior for each of the downhill sub-conditions using the vehicle operating parameters and a pre-trained driving behavior recognition model. The score evaluation module is used to generate a user evaluation score based on the user's driving behavior and preset weights.

7. The vehicle driving behavior evaluation device according to claim 6, characterized in that, The parameter acquisition module is specifically used for: The vehicle's driving data stream under the preset driving conditions is acquired in real time; and the vehicle's operating parameters are extracted from the driving data stream for a preset number of channels.

8. The vehicle driving behavior evaluation device according to claim 6, characterized in that, The user's driving behavior includes at least standard driving behavior and non-standard driving behavior; The score evaluation module is specifically used for: Obtain the percentage of non-standard driving behaviors in each downhill sub-condition; and generate a user evaluation score based on the percentage of behaviors and the preset weights.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the vehicle driving behavior evaluation method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the vehicle driving behavior evaluation method according to any one of claims 1 to 5.

Images