Driving ability evaluation method and device, storage medium, electronic equipment and vehicle
By obtaining driver's driving behavior and physiological characteristics data, inputting driving ability evaluation models, and identifying driving characteristics and physiological characteristics, the problem that the existing technology cannot monitor and evaluate driver's driving skills and safety in real time is solved, and the driver is realized Real-time assessment and security improvement.
Patent Information
- Application Number
- CN202310643848.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-01
- Publication Date
- 2024-12-03
AI Technical Summary
The existing driver driving capability assessment system cannot monitor and evaluate the driver's driving skills and safety in real time, resulting in safety risks in vehicle driving.
By obtaining the driver's driving behavior data and physiological characteristic data, inputting the pre-trained driving ability evaluation model, identifying driving characteristics and physiological characteristics, and determining driving ability evaluation indicators, such as driving skill level, safety scores and driving behavior problems, to achieve Real-time monitoring and evaluation.
It can promptly detect and correct drivers' bad driving habits, improve driving skills, reduce the incidence of traffic accidents, and improve vehicle driving safety.
Smart Images

Figure CN119058715A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle control, and in particular to a driving ability assessment method, device, storage medium, electronic device and vehicle. Background Art
[0002] In the process of rapid development of smart cars, the evaluation of drivers' driving ability is an important means to improve driving safety. Real-time monitoring of drivers' driving behavior and collection of driving data can accurately analyze and evaluate driving ability, timely discover and correct drivers' bad driving habits, quickly improve driving skills, and reduce the incidence of traffic accidents.
[0003] At present, whether the driver's operation and behavior meet the driver's specifications is mostly statically judged at a fixed position, or subjectively evaluated by safety officers, and there is no mature driving ability evaluation system. Existing methods cannot monitor and evaluate the driver's driving skills and safety in real time, which leads to certain safety hazards in vehicle driving. Summary of the invention
[0004] In view of this, the present application provides a driving ability assessment method, device, storage medium, electronic device and vehicle, which can monitor and assess the driver's driving skills and safety in real time, thereby improving the driving safety of the vehicle.
[0005] According to a first aspect of the present application, a driving ability assessment method is provided, comprising:
[0006] Acquiring driving behavior data and physiological characteristic data of the driver, wherein the driving behavior data is data containing driving characteristics related to the driving ability evaluation index, and the physiological characteristic data is data containing physiological characteristics related to the driving ability evaluation index;
[0007] The driving behavior data and the physiological characteristic data are input into a pre-trained driving ability assessment model to obtain a driving ability assessment result, wherein the driving ability assessment model is used to determine an assessment score under a driving ability assessment index by identifying driving characteristics in the physiological characteristic data and identifying physiological characteristics in the physiological characteristic data, and determine the driving ability assessment result based on the assessment score, and the driving ability assessment index includes at least one of a driving skill level, a safety score, and a driving behavior problem.
[0008] According to a second aspect of the present application, a driving ability assessment device is provided, comprising:
[0009] An acquisition module, used to acquire driving behavior data and physiological characteristic data of the driver, wherein the driving behavior data is data containing driving characteristics related to the driving ability evaluation index, and the physiological characteristic data is data containing physiological characteristics related to the driving ability evaluation index;
[0010] An input module is used to input the driving behavior data and the physiological characteristic data into a pre-trained driving ability assessment model to obtain a driving ability assessment result, wherein the driving ability assessment model is used to determine an assessment score under a driving ability assessment indicator by identifying driving characteristics in the physiological characteristic data and identifying physiological characteristics in the physiological characteristic data, and determine the driving ability assessment result based on the assessment score, and the driving ability assessment indicator includes at least one of a driving skill level, a safety score, and a driving behavior problem.
[0011] According to a third aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the driving ability assessment method described in the first aspect is implemented.
[0012] According to a fourth aspect of the present application, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the driving ability assessment method described in the first aspect when executing the computer program.
[0013] According to a fifth aspect of the present application, a vehicle is provided, comprising: a driving ability evaluation device as described in the second aspect, or an electronic device as described in the fourth aspect.
[0014] By means of the above technical solution, the present application provides a driving ability assessment method, device, storage medium, electronic device and vehicle, which can first obtain the driver's driving behavior data corresponding to the driving characteristics related to the driving ability assessment index and the physiological characteristic data containing the physiological characteristics related to the driving ability assessment index; then input the driving behavior data and the physiological characteristic data into the pre-trained driving ability assessment model to obtain the driving ability assessment result, and the driving ability assessment index includes at least one of the driving skill level, safety score and driving behavior problems. The technical solution disclosed in the present invention can monitor and evaluate the driver's driving skills and safety in real time from multiple feature dimensions based on the driver's driving behavior and physiological characteristics, and can timely discover and correct the driver's bad driving habits, quickly improve driving skills, reduce the incidence of traffic accidents, and thus improve the safety of vehicle driving.
[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0018] Figure 1 A flowchart of a driving ability assessment method provided by an embodiment of the present disclosure;
[0019] Figure 2 A flowchart of a driving ability assessment method provided by another embodiment of the present disclosure;
[0020] Figure 3 A schematic diagram of the structure of a driving ability assessment device provided by an embodiment of the present disclosure;
[0021] Figure 4 A schematic diagram of the structure of a driving ability assessment device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0022] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0023] The following describes a driving ability assessment method, an apparatus, a storage medium, an electronic device, and a vehicle according to embodiments of the present disclosure with reference to the accompanying drawings.
[0024] In related technologies, whether the driver's operation and behavior meet the driver's specifications is mostly statically judged at a fixed position, or subjectively evaluated by a safety officer, and there is no mature driving ability evaluation system. Existing methods cannot monitor and evaluate the driver's driving skills and safety in real time, which leads to certain safety hazards in vehicle driving.
[0025] To solve the above technical problems, the present disclosure provides a driving ability assessment method, device, storage medium, electronic device and vehicle, which can monitor and assess the driver's driving skills and safety in real time, thereby improving the driving safety of the vehicle.
[0026] like Figure 1 As shown, an embodiment of the present disclosure provides a driving ability assessment method, comprising:
[0027] Step 101: Acquire the driving behavior data and physiological characteristic data of the driver.
[0028] Among them, driving behavior data is data used to reflect the driving characteristics related to the driving ability evaluation indicators such as the driver's driving skills, driving safety and driving problems, including but not limited to speed, throttle, steering angle, driving route, mileage, window switch, door lock switch, electronic airbag status, handbrake status, brake pedal, wiper status, air conditioning switch gear, engine intake temperature, etc. In specific application scenarios, different data acquisition devices can be used in conjunction to obtain the driver's driving behavior data, such as using a driving recorder, camera, sensor, etc. to dynamically obtain driver behavior information and vehicle status information, and further obtain driving behavior data. Physiological characteristic data is data used to reflect the physiological characteristics related to the driving ability evaluation indicators such as the driver's driving skills, driving safety and driving problems, and may include but not limited to: facial features (such as eye opening and closing degree and facial expressions, etc.), human posture characteristics, blood volume pulse, respiratory rate and heart rate. In specific application scenarios, the driver's physiological characteristic data can be collected through sensors, biometrics and other technologies, and the driver's physiological state can be automatically identified to extract the driver's physiological characteristic data.
[0029] Step 102: Input the driving behavior data and the physiological characteristic data into the pre-trained driving ability assessment model to obtain a driving ability assessment result.
[0030] Among them, the driving ability evaluation model is used to determine the evaluation score under the driving ability evaluation index by identifying the driving characteristics in the physiological characteristic data, and identifying the physiological characteristics in the physiological characteristic data, and determine the driving ability evaluation result according to the evaluation score. The driving ability evaluation index includes but is not limited to at least one of the driving skill level, safety score and driving behavior problems. The driving ability evaluation model is any task model that can output the corresponding driving behavior evaluation result according to the driving characteristics and physiological characteristics. Such as a neural network model, a deep learning model, etc. Exemplarily, the driving ability evaluation model in the present disclosure can be selected as a hidden Markov model, a conditional random field and a neural network model, etc., which are not specifically limited here. In a specific application scenario, before executing the steps of this embodiment, the driving ability evaluation model can also be trained for the driving ability evaluation task based on a certain number of training samples through supervised learning, or unsupervised learning, semi-supervised learning, and reinforcement learning. Until it is determined that the driving ability evaluation model has reached a convergence state, it is determined that the driving ability evaluation model has completed training. Then, the trained driving ability assessment model can be directly put into the specific application of driving ability assessment, that is, the driving behavior data and physiological characteristic data are input into the trained driving ability assessment model, and the driving ability assessment model will directly output the driving ability assessment result for the driver. In the following embodiment steps in the present disclosure, the driving ability assessment model is a time recurrent neural network model (LSTM) as an example to illustrate the technical solution in the present disclosure, but it does not constitute a specific limitation.
[0031] LSTM is a special type of RNN network, which is a recursive neural network that uses back propagation time training and overcomes the vanishing gradient problem. Different from the previous deep neural network method that can only train each sample, LSTM can model the sequence data and "remember" the user's behavior at different times. The output data of each layer will be used as the input data of the next layer for training. While making full use of the object's sequence attribute information, it can better "remember" the long-term object behavior information. For the disclosed embodiment, the driving ability evaluation model can fit the standard of driving ability evaluation based on the time series characteristics of the input data, accurately evaluate the driver's ability, and then obtain the driver's driving skill level (such as skilled or unskilled), safety score, and specific problems in the driving process (such as illegal operation, fatigue driving), etc.
[0032] In summary, according to the driving ability evaluation method provided by the present disclosure, the driving behavior data corresponding to the driver including driving characteristics related to the driving ability evaluation index and the physiological characteristic data including physiological characteristics related to the driving ability evaluation index can be obtained first; then the driving behavior data and the physiological characteristic data are input into the pre-trained driving ability evaluation model to obtain the driving ability evaluation result, and the driving ability evaluation index includes at least one of the driving skill level, safety score and driving behavior problems. The technical solution in the present disclosure can monitor and evaluate the driver's driving skills and safety in real time from multiple feature dimensions based on the driver's driving behavior and physiological characteristics, and can timely discover and correct the driver's bad driving habits, quickly improve driving skills, reduce the incidence of traffic accidents, and thus improve the safety of vehicle driving.
[0033] Further, as a refinement and extension of the above embodiment, in order to fully illustrate the specific implementation process of the method of this embodiment, this embodiment provides the following Figure 2 The specific method shown includes:
[0034] Step 201: Acquire the driver's driving behavior data and physiological characteristic data.
[0035] For the embodiment of the present disclosure, the specific implementation process can refer to the relevant description in step 101 of the embodiment, which will not be repeated here.
[0036] Step 202: pre-process the driving behavior data and the physiological characteristic data to obtain the driving behavior data and the physiological characteristic data in a preset data format.
[0037] Among them, the preprocessing may include filtering out useless data and converting data formats, and may also include filling in missing values according to scenario requirements, etc., which are not specifically limited here.
[0038] In a specific application scenario, the extracted driving behavior data and physiological characteristic data may contain a large amount of data that is not compatible with the driving ability assessment. In order to reduce the amount of calculation for the subsequent driving ability assessment, the driving behavior data and physiological characteristic data may be screened first to remove some irrelevant data that should have missing information, incorrect data format, repeated appearance, or cannot reflect abnormal driving ability. In order to ensure the evaluation accuracy of the subsequent driving ability assessment model, the format conversion of the filtered useful data can also be performed in one step, so that the format-converted driving behavior data and physiological characteristic data are suitable for the input format of the driving ability assessment model. Among them, the preset data format is the feature input format of the driving ability assessment model. Exemplarily, when the driving ability assessment model is a long short-term memory network (Long Short Term Memory, LSTM), the preset data format may be a discrete time series format. Accordingly, when the driving behavior data and physiological characteristic data are preprocessed, the continuous driving behavior data and physiological characteristic data may be converted into discrete time series data.
[0039] For the disclosed embodiment, in order to reduce the amount of calculation for subsequent driving ability assessment, useful information screening can be performed on the driving behavior data and physiological characteristic data, specifically, the driving behavior data corresponding to the preset driving characteristics can be screened in the driving behavior data, and the physiological characteristic data corresponding to the preset physiological characteristics can be screened in the physiological characteristic data. Among them, the preset driving characteristics are driving characteristics that can distinguish abnormal driving behavior, such as vehicle speed characteristics, throttle characteristics, steering angle control characteristics, etc.; the preset physiological characteristics are physiological characteristics that can distinguish abnormal driving behavior, such as facial characteristics (such as eye opening and facial expressions, etc.), human posture characteristics, blood volume pulse, respiratory rate and heart rate, etc.
[0040] In order to ensure the accuracy of the subsequent driving ability assessment model, the format of the useful data after filtering can be further converted so that the data format of the driving behavior data and physiological characteristic data after the format conversion is suitable for the input format of the driving ability assessment model. Accordingly, the steps of the embodiment may include: converting the driving behavior data and the physiological characteristic data into a preset data format respectively, and the preset data format is the feature input format of the driving ability assessment model. Among them, the preset data format is the feature input format of the driving ability assessment model;
[0041] Step 203: input the driving behavior data and physiological characteristic data in a preset data format into the pre-trained driving ability assessment model to obtain a driving ability assessment result.
[0042] In a specific application scenario, before using the driving ability assessment model to determine the driver's driving ability assessment result, the driving ability assessment model needs to be pre-trained. After the training is completed, the driving ability assessment model can be repeatedly applied to subsequent driving ability assessment tasks. When training the driving ability assessment model, a training sample can be first constructed. The training sample is a character text configured with a preset feature label, and the preset feature label contains at least one feature label of a driving ability scoring indicator; the training sample is input into the driving ability assessment model, and the driving ability assessment model is trained for driving ability prediction. In the process of driving ability prediction training, the preset feature label is used as the training label, and the model parameters in the driving ability assessment model are updated until the accuracy of the driving ability assessment model for driving ability prediction is greater than the preset threshold, and the training of the driving ability assessment model is judged to be completed. Among them, the preset threshold can be a value greater than 0 and less than 1. The closer the setting value of the preset threshold is to 1, the higher the evaluation accuracy of the trained driving ability assessment model is. Its specific value can be set according to the actual application scenario, and is not specifically limited here.
[0043] Step 204: Based on the driving ability assessment result, a safety warning is performed on the driver's driving behavior.
[0044] In specific application scenarios, after obtaining the driving ability assessment results, personalized driving advice and training programs can be provided to the driver based on the driving ability assessment results to help the driver improve his driving skills and safety awareness. When providing personalized driving advice to the driver based on the driving ability assessment results, as a possible implementation method, the driver can be analyzed based on the driving ability assessment results to determine whether he has dangerous driving behavior; if the driver is analyzed to have dangerous driving behavior, a braking instruction matching the dangerous driving behavior is generated; and the braking instruction is sent to the vehicle end so that the vehicle end responds to the braking instruction and performs braking control on the vehicle.
[0045] Among them, safety warnings include but are not limited to collision warnings, sharp turn warnings, sudden deceleration warnings, sudden acceleration warnings, sudden lane change warnings, speeding warnings, fatigue driving warnings, long-term idling warnings, frequent lane change warnings, excessive speed warnings, and neutral coasting warnings. Dangerous driving behavior refers to bad driving behaviors that are likely to cause traffic accidents, and may include: driving when the driver is fatigued, drunk driving, inattentive, driving when in physical condition, emotionally unsuitable driving, and other emotional driving that endangers the driver's own and public safety, as well as various driving behaviors that may or have caused driving hazards; the braking command may carry braking information such as braking damping, braking duration, braking distance, and braking speed. Different braking information indicates different braking strengths. For example, the longer the braking duration, the lower the braking strength, and the shorter the braking duration, the higher the braking strength.
[0046] In a specific application scenario, when it is predicted that the driver has dangerous driving behavior, in order to ensure driving safety, a corresponding braking instruction can be generated for the dangerous driving behavior, so that the vehicle side can perform corresponding braking control on the vehicle based on the braking instruction. As a possible implementation method, a corresponding braking instruction can be generated in advance for the dangerous driving behavior, and when any intensity of dangerous driving behavior occurs, the pre-generated braking instruction is called to implement braking control of the vehicle; as a possible implementation method, braking instructions of different braking intensities can also be generated for different dangerous driving behaviors according to the severity of the dangerous driving behavior, so that the vehicle side can achieve safe braking based on the braking instruction, while avoiding the situation where the occupants in the car dive forward rapidly due to too short braking time, causing contusions or trauma to the cervical spine, head, waist, face and other parts, or reducing the service life of the car (such as tire wear, brake pad wear, suspension system impact deformation, transmission system impact damage, etc.).
[0047] Accordingly, when generating a braking instruction that matches a dangerous driving behavior, the steps of the embodiment may include: extracting a braking instruction that matches the dangerous driving behavior from a database, wherein the database pre-stores braking instructions that match different dangerous driving behaviors; or, determining a danger level of the dangerous driving behavior, and generating a braking instruction that matches the danger level, wherein the danger level is positively correlated with the braking intensity in the braking instruction.
[0048] For example, as shown in Table 1, the danger level may include level 1, level 2, and level 3. Accordingly, the braking command may include: level 1 braking command (e.g., for controlling the deceleration braking with a maximum deceleration of 7.5 to 8 m / s^2), level 2 braking command (e.g., for controlling the deceleration braking with a maximum deceleration of 3 to 4 m / s^2), and level 3 braking command (e.g., for controlling the deceleration braking with a maximum deceleration of 1.5 to 2.5 m / s^2). The relationship between the danger level and the braking command can be seen in Table 1:
[0049] Table 1:
[0050]
[0051]
[0052] Continuing with the above example, for this embodiment, if the danger level of the dangerous driving behavior is determined to be level two, a level two braking instruction matching the danger level (level two) can be generated so that the vehicle side can control the vehicle side to perform deceleration braking with a maximum deceleration of 3 to 4 m / s^2 according to the level two braking instruction.
[0053] Accordingly, a database can be pre-created based on historical driving ability assessment cases, so that braking instructions matching dangerous driving behaviors can be quickly extracted directly from the pre-created database. The database creation step includes: extracting historical dangerous driving behaviors that are not suitable for vehicle driving safety based on historical driving ability assessment cases, and generating corresponding braking instructions according to the danger level of historical dangerous driving behaviors; and pre-storing historical dangerous driving behaviors and corresponding braking instructions in the database. In this way, the generation frequency of braking instructions can be reduced to reduce the consumption of computing resources.
[0054] If a braking instruction matching the dangerous driving behavior is not extracted from the database, a new braking instruction needs to be generated for the current dangerous driving behavior. After the new braking instruction is generated, the newly generated braking instruction and the corresponding current dangerous driving behavior can be updated and stored in the database for subsequent direct call.
[0055] Step 205: Generate feedback prompt information corresponding to the driving ability evaluation result, and send the feedback prompt information to the driver in a preset display format.
[0056] In specific application scenarios, in order to minimize the occurrence of accidents, in addition to enabling the vehicle end to respond to the braking command to execute the braking control of the vehicle, the corresponding auxiliary driving strategy can also be added to double guarantee the safety of driving. As a possible application scenario, feedback prompt information corresponding to the driving ability assessment results can be generated, and the feedback prompt information can be sent to the driver in a preset display form. Among them, the feedback prompt information includes but is not limited to voice warnings, video playback, output interface pop-up windows or lighting up prompt lights, etc. For example, the vehicle voice warning "speed is too fast", "driver's heart rate is too fast", etc. The preset display form includes but is not limited to visual graphics, text form, audio form, etc.
[0057] Accordingly, the steps of the embodiment may include: playing a first audio for soothing the driver's current emotional state or prompting safe driving; and / or, playing a second audio for reminding the surrounding environment that the vehicle is currently in a dangerous driving state; and / or, obtaining the terminal information pre-set by the driver, and establishing a communication connection with a predetermined terminal based on the terminal information; and / or, locating the vehicle position and navigating to a nearby temporary rest parking area. It should be noted that the added auxiliary driving strategy is not limited to this, and may also include other achievable methods that can prompt the vehicle to escape from a dangerous driving state, which is not specifically limited here. By playing the first audio for soothing the driver's current emotional state or prompting safe driving, the driver's bad mood can be effectively alleviated, and the driver can be aware of the danger of driving behavior through audio reminders, which can improve driving safety in a more targeted, accurate and efficient manner. By playing the second audio for reminding the surrounding environment that the vehicle is currently in a dangerous driving state, and / or establishing a communication connection with a predetermined terminal, the vehicle information in a dangerous driving state can be promptly prompted to the surrounding environment or a specific person, so that the vehicle or person in the surrounding environment can take timely measures to eliminate safety hazards. By locating the vehicle and navigating to a nearby temporary rest parking area, the vehicle can be intelligently driven to a safe area, allowing the driver to relieve his emotions in the area. At the same time, the safety issues caused by continued dangerous driving to the driver and the surrounding environment are eliminated, ensuring the safety of vehicle driving.
[0058] In specific application scenarios, in order to facilitate the understanding of the technical solution of the present disclosure, the following application scenarios to which the present disclosure may be applicable are specifically listed, but are not limited thereto:
[0059] Application scenario 1: Urban driving scenario
[0060] In urban driving scenarios, drivers need to deal with complex road environments and frequent traffic conditions. The intelligent car driving ability assessment and training system of the present invention can assess the characteristics of urban driving, such as turns, traffic lights, traffic congestion, etc. The assessment results will help drivers improve their driving skills on urban roads and enhance their safety awareness.
[0061] Application scenario 2: Highway driving scenario
[0062] In the highway driving scenario, the driver needs to maintain the distance between vehicles, comply with the speed limit regulations, and ensure safety while driving at high speed. The intelligent car driving ability evaluation and training system of the present invention can evaluate the driver's driving performance on the highway, such as speed control, distance maintenance, etc. The evaluation results will help the driver improve his high-speed driving skills and reduce the accident rate on the highway.
[0063] Application scenario 3: Emergency handling
[0064] The ability to handle emergencies is one of the key skills of drivers. The intelligent car driving ability evaluation and training system of the present invention can simulate emergency situations, such as emergency braking, emergency avoidance, etc., and evaluate the driver's performance in these situations. The evaluation results will help drivers improve their ability to deal with emergencies and improve driving safety.
[0065] Application scenario 4: Driving habit improvement
[0066] Driving habits have a great impact on driving safety. The intelligent car driving ability evaluation and training system of the present invention can identify bad driving habits, such as sudden acceleration, sudden braking, fatigue driving, etc., by monitoring the driver's driving behavior for a long time. The evaluation results will guide the driver to improve his driving habits and improve driving safety.
[0067] Application scenario 5: Novice driver training
[0068] For novice drivers, the intelligent automobile driving ability assessment and training system of the present invention can be used as an auxiliary tool to help them quickly master driving skills. The system will evaluate the driving behavior of novice drivers, find out where improvements are needed, and provide targeted training suggestions. The assessment results will help novice drivers adapt to the driving environment more quickly and improve their driving skills and safety awareness.
[0069] Application scenario 6: Ability assessment of elderly drivers
[0070] For elderly drivers, their driving ability may be affected to a certain extent due to factors such as age, vision and reaction ability. The intelligent automobile driving ability evaluation and training system of the present invention can evaluate the characteristics of elderly drivers, such as line of sight judgment, driving speed control, etc. The evaluation results will help elderly drivers understand their driving ability and shortcomings, so as to carry out targeted training and improvement.
[0071] Application scenario 7: Commercial vehicle driver training
[0072] The driving ability and safety awareness of commercial vehicle drivers are crucial to public safety. The intelligent automobile driving ability assessment and training system of the present invention can be applied to the training process of commercial vehicle drivers, such as taxis, buses, trucks, etc. The system will evaluate the characteristics of different types of commercial vehicle drivers and provide professional training suggestions to help them improve their driving skills and safety.
[0073] Application scenario 8: Regular driving ability assessment
[0074] In order to ensure that the driver's driving skills and safety awareness are always maintained at a high level, the intelligent automobile driving ability assessment and training system of the present invention can be used for regular assessment. According to the assessment results, the driver can receive targeted training for his or her own deficiencies to ensure driving safety. At the same time, relevant departments can formulate appropriate policies and measures based on the assessment results, such as improving the standards for driver's license renewal and implementing a driving ability grading system.
[0075] Through the above embodiments, the driving ability assessment method provided by the present disclosure can play its advantages in different scenarios and applications, and the advantages are as follows:
[0076] 1. Real-time monitoring of the driver's driving behavior can promptly detect and correct the driver's bad driving habits and improve driving safety.
[0077] 2. Provide targeted training suggestions to help drivers improve their driving skills and enhance their driving level.
[0078] 3. It can be used in various types of smart cars, including self-driving cars and semi-autonomous driving cars.
[0079] 4. By collecting a large amount of driving behavior data and physiological characteristic data, the system can analyze and evaluate the driver's driving behavior more accurately.
[0080] 5. It can help automobile manufacturers improve product quality and increase consumer satisfaction.
[0081] 6. It can help insurance companies assess risks more accurately and formulate more reasonable insurance policies.
[0082] 7. It can be used in intelligent car driving systems to provide drivers with more comprehensive driving assessment services and improve traffic safety. In addition, the system can also be used in driving school training and other scenarios to help students quickly improve their driving skills and reduce the incidence of traffic accidents.
[0083] In summary, according to the driving ability evaluation method provided by the present disclosure, the technical solution in the present disclosure can monitor and evaluate the driver's driving skills and safety in real time from multiple feature dimensions based on the driver's driving behavior and physiological characteristics, and can timely discover and correct the driver's bad driving habits, effectively improve the driver's driving skills and safety awareness, and reduce the incidence of traffic accidents. In addition, based on the driving ability evaluation results, the prediction of dangerous driving behavior can be automatically performed. When the vehicle is intelligently judged to have a tendency and danger of being in danger, an emergency braking command can be autonomously issued to the vehicle end, so that the vehicle end can perform braking control on the vehicle in time, thereby improving the driving safety of the vehicle. It is also possible to increase the corresponding auxiliary driving strategy, so that the vehicle end responds to the braking command to perform braking control on the vehicle, and at the same time, the corresponding auxiliary response measures can be executed, which can prompt the vehicle to leave the dangerous driving state, so that there is no need for on-site supervision by traffic police, and electronic equipment can be used to replace traffic police and other personnel to prompt drivers to pay attention to safe driving, thereby improving driving safety, reducing the occurrence of traffic accidents, and improving traffic safety.
[0084] Based on the above Figure 1 , Figure 2 The specific implementation of the method shown in the embodiment provides a driving ability evaluation device, such as Figure 3 As shown, the device comprises:
[0085] An acquisition module 31, which can be used to acquire driving behavior data and physiological characteristic data of the driver, wherein the driving behavior data is data containing driving characteristics related to the driving ability evaluation index, and the physiological characteristic data is data containing physiological characteristics related to the driving ability evaluation index;
[0086] The input module 32 can be used to input the driving behavior data and the physiological characteristic data into the pre-trained driving ability assessment model to obtain the driving ability assessment result, wherein the driving ability assessment model is used to determine the assessment score under the driving ability assessment index by identifying the driving characteristics in the physiological characteristic data and the physiological characteristics in the physiological characteristic data, and determine the driving ability assessment result according to the assessment score, and the driving ability assessment index includes at least one of the driving skill level, the safety score and the driving behavior problem.
[0087] In specific application scenarios, such as Figure 4 As shown, the device further includes: a processing module 33;
[0088] A processing module 33, which can be used to pre-process the driving behavior data and the physiological characteristic data to obtain the driving behavior data and the physiological characteristic data in a preset data format, where the preset data format is a feature input format of a driving ability assessment model;
[0089] Correspondingly, the input module 32 can be used to input the driving behavior data and physiological characteristic data in a preset data format into the pre-trained driving ability evaluation model to obtain a driving ability evaluation result.
[0090] In specific application scenarios, such as Figure 4 As shown, the device further includes: a training module 34;
[0091] The training module 34 can be used to generate training samples, where the training samples are character texts configured with preset feature labels, and the preset feature labels include at least one feature label of a driving ability scoring indicator; the training samples are input into the driving ability assessment model, and the driving ability assessment model is trained to predict driving ability, wherein, during the driving ability prediction training process, the preset feature labels are used as training labels, and the model parameters in the driving ability assessment model are updated until the accuracy of the driving ability prediction of the driving ability assessment model is greater than a preset threshold, and it is judged that the training of the driving ability assessment model is completed.
[0092] In specific application scenarios, such as Figure 4 As shown, the device further includes: an early warning module 35;
[0093] The warning module 35 can be used to perform safety warning processing on the driver's driving behavior based on the driving ability evaluation result.
[0094] In a specific application scenario, the early warning module 35 can be used to analyze whether the driver has dangerous driving behavior based on the driving ability assessment results; if the analysis shows that the driver has dangerous driving behavior, a braking command matching the dangerous driving behavior is generated; and the braking command is sent to the vehicle end, so that the vehicle end performs braking control on the vehicle in response to the braking command.
[0095] In a specific application scenario, the early warning module 35 can be used to extract braking instructions that match dangerous driving behaviors from a database, wherein braking instructions that match different dangerous driving behaviors are pre-stored in the database; or, determine the danger level of the dangerous driving behavior and generate braking instructions that match the danger level, wherein the danger level is positively correlated with the braking intensity in the braking instructions.
[0096] In specific application scenarios, such as Figure 4 As shown, the device also includes: a generating module 36 and a sending module 37;
[0097] A generating module 36, which can be used to generate feedback prompt information corresponding to the driving ability evaluation result;
[0098] The sending module 37 can be used to send feedback prompt information to the driver in a preset display form.
[0099] It should be noted that for other corresponding descriptions of the functional units involved in the driving ability evaluation device provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.
[0100] Based on the above Figure 1 and Figure 2 The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The method shown.
[0101] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.
[0102] Based on the above Figure 1 and Figure 2 The method shown, and Figure 3 and Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device that can be configured on the vehicle (such as an electric vehicle) side, and the device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The method shown.
[0103] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.
[0104] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.
[0105] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.
[0106] Based on the above electronic device, the embodiment of the present application further provides a vehicle, which may specifically include: the above driving ability evaluation device, or the above electronic device. The vehicle may specifically be an electric car, etc.
[0107] Through the description of the above implementation methods, the technical personnel in the field can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. The technical solution in the present disclosure can monitor and evaluate the driver's driving skills and safety in real time from multiple feature dimensions based on the driver's driving behavior and physiological characteristics, and can timely discover and correct the driver's bad driving habits, quickly improve driving skills, reduce the incidence of traffic accidents, and thus improve the safety of vehicle driving. In addition, based on the driving ability evaluation results, the prediction of dangerous driving behavior can be automatically performed. When the vehicle is intelligently judged to have a tendency and danger of being in danger, an emergency braking command can be autonomously issued to the vehicle end, so that the vehicle end can execute the braking control of the vehicle in time, thereby improving the driving safety of the vehicle. It is also possible to increase the corresponding auxiliary driving strategy, so that the vehicle end can respond to the braking command to execute the braking control of the vehicle, and at the same time, the corresponding auxiliary response measures can be executed, which can prompt the vehicle to leave the dangerous driving state, so that there is no need for on-site supervision by traffic police, and electronic equipment can be used to replace traffic police and other personnel to prompt drivers to pay attention to safe driving, thereby improving driving safety, reducing the occurrence of traffic accidents, and improving traffic safety.
[0108] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0109] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.
Claims
1. A driving ability assessment method, characterized in that: include: Acquire driving behavior data and physiological characteristic data of the driver, wherein the driving behavior data is data containing driving characteristics related to the driving ability evaluation index, and the physiological characteristic data is data containing physiological characteristics related to the driving ability evaluation index; The driving behavior data and the physiological characteristic data are input into a pre-trained driving ability assessment model to obtain a driving ability assessment result, wherein the driving ability assessment model is used to determine an assessment score under a driving ability assessment index by identifying driving characteristics in the physiological characteristic data and identifying physiological characteristics in the physiological characteristic data, and determine the driving ability assessment result based on the assessment score, and the driving ability assessment index includes at least one of a driving skill level, a safety score, and a driving behavior problem.
2. The method according to claim 1, characterized in that Before inputting the driving behavior data and the physiological characteristic data into the pre-trained driving ability evaluation model to obtain the driving ability evaluation result, the method further includes: Preprocessing the driving behavior data and the physiological characteristic data to obtain the driving behavior data and the physiological characteristic data in a preset data format, wherein the preset data format is a feature input format of the driving ability assessment model; The step of inputting the driving behavior data and the physiological characteristic data into a pre-trained driving ability assessment model to obtain a driving ability assessment result includes: The driving behavior data and physiological characteristic data in the preset data format are input into the pre-trained driving ability evaluation model to obtain a driving ability evaluation result.
3. The method according to claim 1, characterized in that The training method of the driving ability assessment model includes: Generate a training sample, wherein the training sample is a character text configured with a preset feature label, wherein the preset feature label includes at least one feature label of a driving ability scoring indicator; The training samples are input into the driving ability assessment model, and the driving ability assessment model is trained for driving ability prediction, wherein, during the driving ability prediction training, the preset feature labels are used as training labels, and the model parameters in the driving ability assessment model are updated until the accuracy of the driving ability prediction by the driving ability assessment model is greater than a preset threshold, and it is judged that the training of the driving ability assessment model is completed.
4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Based on the driving ability assessment result, a safety warning process is performed on the driver's driving behavior.
5. The method according to claim 4, characterized in that The step of performing safety warning processing on the driver's driving behavior based on the driving ability evaluation result includes: Analyzing whether the driver has dangerous driving behavior based on the driving ability assessment result; If the analysis shows that the driver has dangerous driving behavior, generating a braking instruction matching the dangerous driving behavior; The braking command is sent to the vehicle end, so that the vehicle end performs braking control on the vehicle in response to the braking command.
6. The method according to claim 5, characterized in that The generating a braking instruction matching the dangerous driving behavior includes: Extracting a braking instruction matching the dangerous driving behavior from a database, wherein the database pre-stores braking instructions matching different dangerous driving behaviors; or, The danger level of the dangerous driving behavior is determined, and a braking instruction matching the danger level is generated, wherein the danger level is positively correlated with the braking intensity in the braking instruction.
7. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Generating feedback prompt information corresponding to the driving ability evaluation result; The feedback prompt information is sent to the driver in a preset display form.
8. A driving ability evaluation device, characterized in that: include: An acquisition module, used to acquire driving behavior data and physiological characteristic data of the driver, wherein the driving behavior data is data containing driving characteristics related to the driving ability evaluation index, and the physiological characteristic data is data containing physiological characteristics related to the driving ability evaluation index; An input module is used to input the driving behavior data and the physiological characteristic data into a pre-trained driving ability assessment model to obtain a driving ability assessment result, wherein the driving ability assessment model is used to determine an assessment score under a driving ability assessment indicator by identifying driving characteristics in the physiological characteristic data and identifying physiological characteristics in the physiological characteristic data, and determine the driving ability assessment result based on the assessment score, and the driving ability assessment indicator includes at least one of a driving skill level, a safety score, and a driving behavior problem.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.
11. A vehicle, characterized in that: include: The driving evaluation device according to claim 8, or the electronic device according to claim 10.
