Vehicle driving control methods, systems, electronic devices and storage media

Abstract

This invention provides a vehicle driving control method, system, electronic device, and storage medium, relating to the field of vehicle control technology. The method includes: acquiring multiple vital sign data and multiple medical data of the driver within a target vehicle; determining the probability value of the driver under each driving ability category label based on the vital sign data and medical data; acquiring the driver's driving ability category identification result based on the probability value; acquiring target driving warning information and target driving control information based on the driving ability category identification result; executing driving warnings based on the target driving warning information; and executing driving control on the target vehicle based on the target driving control information. This invention achieves multi-dimensional and multi-level driving ability category identification, and adaptively executes different driving warning actions and driving control actions for different driving ability categories, thereby improving the accuracy of driving ability assessment and vehicle driving control.

Description

Technical Field

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

[0002] With the development of society and the economy, vehicles have become an indispensable means of transportation in people's production and daily life. However, when a driver's physical condition is abnormal, it can easily lead to vehicle accidents. Therefore, how to achieve efficient and precise vehicle driving control is an important issue that the industry urgently needs to address.

[0003] In related technologies, a breathalyzer system is configured to detect drunk driving by comparing single-signature data, such as data collected by an alcohol sensor, pulse sensor, or body temperature sensor, with built-in thresholds to trigger in-vehicle announcements and power cuts to control the vehicle. However, because the causes of driving accidents are complex, it is difficult to accurately assess a driver's ability and thus difficult to perform precise driving control by using only single-signature data for simple logical comparisons.

[0004] Therefore, there is an urgent need to provide a vehicle driving control method, system, electronic device, and storage medium to solve the above problems. Summary of the Invention

[0005] This invention provides a vehicle driving control method, system, electronic device, and storage medium to address the shortcomings of existing technologies that use single vital sign data to trigger corresponding driving control through comparison with built-in thresholds, making it difficult to accurately assess the driver's driving ability and thus difficult to perform precise driving control on the vehicle. This invention aims to improve the accuracy of driving ability assessment and vehicle driving control.

[0006] This invention provides a vehicle driving control method, comprising:

[0007] Acquire multiple vital signs data of the driver inside the target vehicle and multiple medical data of the driver;

[0008] Based on the vital signs data and medical data, determine the probability value of the driver under each driving ability category label, and obtain the driving ability category identification result of the driver based on the probability value.

[0009] Based on the driving ability category identification results, target driving warning information and target driving control information are obtained;

[0010] The driving warning is executed according to the target driving warning information, and the driving control is executed on the target vehicle according to the target driving control information.

[0011] According to a vehicle driving control method provided by the present invention, determining the probability value of the driver under each driving ability category label based on each of the said vital sign data and each of the said medical data includes:

[0012] For each of the vital signs data and each of the medical data, normalization processing is performed on each data item according to the target interval corresponding to each data item to obtain the normalization processing result of each data item; the target interval is the data interval formed by the data collected when each data item is in a normal state;

[0013] Based on the normalization result, the target feature vector of the driver is obtained;

[0014] Based on the target feature vector, determine the probability value of the driver under each of the driving ability category labels.

[0015] According to a vehicle driving control method provided by the present invention, the step of normalizing each piece of data according to a target interval corresponding to each piece of data to obtain a normalization result for each piece of data includes:

[0016] Based on the maximum and minimum values ​​in the target interval corresponding to each data item, construct multiple reference intervals corresponding to each data item;

[0017] Among the multiple reference intervals, determine the reference interval to which each data item belongs;

[0018] Calculate the deviation coefficient value corresponding to each data item according to the deviation coefficient calculation formula corresponding to the reference interval to which each data item belongs;

[0019] Based on the deviation coefficient value, the normalization result of each data item is obtained.

[0020] According to a vehicle driving control method provided by the present invention, the step of constructing multiple reference intervals corresponding to each data item based on the maximum and minimum values ​​in the target interval corresponding to each data item includes:

[0021] Based on the first difference, a first reference interval is constructed for each data item; the first difference is the difference between a first preset multiple of the minimum value in the target interval and the maximum value in the target interval;

[0022] Based on the first difference and the minimum value in the target interval, a second reference interval is constructed for each data item;

[0023] Based on the minimum value and the maximum value in the target interval, a third reference interval is constructed for each data item.

[0024] Based on the maximum value in the target interval and the second difference, a fourth reference interval is constructed for each data item; the second difference is the difference between a second preset multiple of the maximum value in the target interval and the minimum value in the target interval.

[0025] Based on the second difference, a fifth reference interval is constructed for each of the data items;

[0026] Wherein, the maximum value in the first reference interval is less than the minimum value in the second reference interval, the maximum value in the second reference interval is less than the minimum value in the third reference interval, the maximum value in the third reference interval is less than the minimum value in the fourth reference interval, and the maximum value in the fourth reference interval is less than the minimum value in the fifth reference interval.

[0027] According to a vehicle driving control method provided by the present invention, the step of obtaining the driver's driving ability category identification result based on the probability value includes:

[0028] Among the multiple driving ability category labels, determine the driving ability category label corresponding to the highest probability value;

[0029] The driver's driving ability category identification result is determined based on the driving ability category label corresponding to the maximum probability value.

[0030] According to a vehicle driving control method provided by the present invention, the step of obtaining target driving warning information and target driving control information based on the driving ability category identification result includes:

[0031] If the driving ability category identification result is a Level 1 abnormal driving ability category, the target driving warning information is determined as the first warning information, and the target driving control information is determined as the first control information; the first warning information is used to call for emergency rescue, and the first control information is used to activate the automatic driving mode to drive the target vehicle to a safe area.

[0032] If the driving ability category identification result is a Level 2 abnormal driving ability category, the target driving warning information is determined as the second warning information, and the target driving control information is determined as the second control information. The second warning information is used to call for emergency rescue and initiate a driving ability abnormality warning prompt. The second control information is used to invoke the first vehicle control command and the second vehicle control command to control the target vehicle. The first vehicle control command is used to control the operating parameters of the target vehicle. The second vehicle control command is used to control the environmental parameters of the target vehicle.

[0033] If the driving ability category identification result is a level three driving ability abnormality category, the target driving warning information is determined to be the third warning information, and the target driving control information is determined to be the third control information; the third warning information is used to initiate a driving ability abnormality warning prompt, and the third control information is used to call the first vehicle control command to control the target vehicle;

[0034] If the driving ability category identification result is a level four abnormal driving ability category, the target driving warning information is determined to be the third warning information, and the target driving control information is determined to be the fourth control information; the fourth control information is used to invoke the second vehicle control command to control the target vehicle.

[0035] According to a vehicle driving control method provided by the present invention, the step of acquiring multiple vital sign data of the driver in the target vehicle and multiple medical data of the driver includes:

[0036] Multiple vital sign data are collected based on a first sensor and / or a second sensor; the first sensor is a sensor that communicates with the target vehicle, and the second sensor is a sensor installed inside the target vehicle.

[0037] Obtain the driver's electronic medical record, the driver's physical examination report, and the driver's medical records;

[0038] Based on the electronic medical record, the physical examination report, and the medical records, obtain multiple medical data.

[0039] Among them, the vital signs data include multiple data such as temperature data, exhaled breath alcohol concentration data, pulse data, gaze deviation information, blood pressure data, driving posture data, and pressure data applied to the steering wheel corresponding to the driver's seat in the target vehicle.

[0040] The medical data mentioned includes multiple data points such as vision data, hearing data, cardiovascular disease data, and neurological disease data.

[0041] The present invention also provides a vehicle driving control system, comprising:

[0042] The data acquisition unit is used to acquire multiple vital signs data of the driver inside the target vehicle and multiple medical data of the driver.

[0043] The data analysis unit is used to determine the probability value of the driver under each driving ability category label based on each of the vital sign data and each of the medical data, and to obtain the driving ability category identification result of the driver based on the probability value.

[0044] The scheduling unit is used to obtain target driving warning information and target driving control information based on the driving ability category identification results.

[0045] An execution unit is configured to execute a driving warning based on the target driving warning information and to execute driving control on the target vehicle based on the target driving control information.

[0046] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle driving control method described above.

[0047] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle driving control method as described above.

[0048] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the vehicle driving control method as described above.

[0049] The vehicle driving control method, system, electronic device, and storage medium provided by this invention comprehensively analyze the probability values ​​of the driver under various driving ability category labels by combining multiple vital sign data and multiple medical data of the driver. Based on the probability values, the driving ability category identification result of the driver is estimated, realizing multi-dimensional and multi-level identification of the driver's driving ability category, so as to accurately and timely identify different driving ability categories of the driver. Furthermore, based on the different driving ability categories of the driver, the corresponding target driving warning information and target driving control information are adaptively determined to execute different driving warning actions and driving control actions for the target vehicle. This improves the accuracy of driving ability assessment and vehicle driving control, thereby improving driving safety. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating the control method of a drunk driving control system provided by existing technology;

[0052] Figure 2 This is one of the flowcharts of the vehicle driving control method provided by the present invention;

[0053] Figure 3 This is the second flowchart of the vehicle driving control method provided by the present invention;

[0054] Figure 4 This is a schematic diagram of the structure of the multilayer perceptron model provided by the present invention;

[0055] Figure 5 This is a schematic diagram of the vehicle driving control system provided by the present invention;

[0056] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0058] For public transportation and private cars, drivers often find it difficult to make accurate driving decisions when encountering emergencies or abnormal physical characteristics. In such cases, emergency driving control is needed to guide or assist drivers in dealing with sudden abnormal situations, greatly reducing the risk of abnormal driving and lowering the accident rate.

[0059] Among related technologies, some in-vehicle systems offer features such as fatigue driving alerts, drunk driving warnings, and voice-activated assistance. These systems operate at a superficial level, enabling vehicle control. Such emergency systems comprehensively analyze various indicators of the human body to determine if driving conditions are met, thereby significantly reducing the risk of abnormal driving and lowering the accident rate.

[0060] However, in related technologies, such as drunk driving warnings and reminders, etc. Figure 1As shown, its configuration includes a drunk driving control system that compares single vital sign data, such as data collected by an alcohol detection sensor, pulse sensor, and body temperature sensor, with thresholds built into the central processing unit to trigger the execution unit to perform corresponding driving control actions, namely, issuing prompts on the vehicle's infotainment system and cutting off the vehicle's power. However, since the causes of driving accidents are quite complex, it is difficult to accurately assess the driver's driving ability and perform precise driving control by using only a single vital sign data (i.e., drunk driving data) for simple logical comparison and executing a single driving control action.

[0061] To address the aforementioned problems, this embodiment provides a vehicle driving control method. This method is applied to a vehicle, which includes a vehicle infotainment system, an onboard control device, and onboard sensors. The vehicle infotainment system provides a human-machine interface; the onboard control device is the executing entity, used to execute the vehicle driving control method; and the onboard sensors can be used to collect at least several vital signs data of the driver.

[0062] Figure 2 This is one of the flowcharts illustrating the vehicle driving control method provided by the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0063] Step 201: Obtain multiple vital signs data of the driver inside the target vehicle and multiple medical data of the driver;

[0064] The target vehicle here is the vehicle for which driving control is currently required; the driver is the user driving the target vehicle.

[0065] Optionally, when vehicle driving control is required, on-board sensors or external sensors that communicate with the target vehicle can be used to collect multiple vital signs data of the driver; at the same time, multiple medical data of the driver can be downloaded from Internet medical institutions, or multiple medical data generated by the user through user input on the user terminal can be received.

[0066] The user input referred to may be information input through command line interface, graphical interface, touch input, drop-down selection input, voice input, gesture input, visual input, brain-computer input, etc. This embodiment does not specifically limit it.

[0067] The vital signs data here include multiple data points used to characterize the driver's physical characteristics, and the medical data includes multiple data points used to characterize the driver's medical characteristics.

[0068] Step 202: Based on the vital signs data and the medical data, determine the probability value of the driver under each driving ability category label, and obtain the driving ability category identification result of the driver based on the probability value;

[0069] The driving ability category labels here can be broadly categorized as "normal driving ability" and "abnormal driving ability," or further refined into multiple categories based on different levels of driving impairment, such as Level 1, Level 2, Level 3, and Level 4 abnormal driving ability labels. The level of driving impairment decreases sequentially from Level 1 to Level 4. A Level 1 abnormal driving ability label indicates the driver is unable to drive; a Level 2 label indicates severe driving impairment; a Level 3 label indicates moderate driving impairment; and a Level 4 label indicates mild driving impairment.

[0070] The following description uses the driving ability category labels, including normal driving ability category label, Level 1 abnormal driving ability category label, Level 2 abnormal driving ability category label, Level 3 abnormal driving ability category label and Level 4 abnormal driving ability category label, as examples to illustrate the method provided in this embodiment.

[0071] Optionally, after obtaining the vital signs data and medical data, in order to improve the accuracy and efficiency of vehicle driving control, the vital signs data and medical data can be preprocessed, such as missing value filling, duplicate value deletion, normalization processing, etc., to obtain the driver's driving feature vector. Then, by combining the driving feature vector, the probability value of the driver under each driving ability category label can be obtained. Based on the probability value, the driver's driving ability category recognition result can be determined.

[0072] Here, the methods for obtaining the driver's probability value under each driving ability category label include: implementation based on similarity calculation, or implementation based on a pre-built recognition model; for example, calculating the similarity value between the driving feature vector and each driving ability category label to obtain the driver's probability value under each driving ability category label; or, pre-collecting a large number of sample driving feature vectors and corresponding real values ​​of driving ability categories, using the sample driver's feature vector as supervised training samples, and using the real values ​​of the driving ability categories corresponding to the sample driver as supervised training labels, to train a neural network model, thereby obtaining a recognition model that can output the corresponding probability value of the sample driver under each driving ability category label based on the input driving feature vector. Afterwards, the obtained driving feature vector of the driver in the target vehicle can be input into the recognition model to obtain the driver's probability value under each driving ability category label.

[0073] Here, the method for obtaining the driver's driving ability category identification result can be to compare the probability value under each driving ability category label with the probability threshold to obtain the driver's driving ability category identification result; or to select the driving ability category label with the highest probability value from multiple driving ability category labels to determine the driver's driving ability category identification result.

[0074] Step 203: Based on the driving ability category identification result, obtain target driving warning information and target driving control information;

[0075] It should be noted that there are direct or indirect correlations between the identification results of different driving ability categories and different driving warning information and different driving control information; such correlations can be pre-configured according to driving control safety requirements.

[0076] Optionally, after obtaining the driving ability category identification results, target driving warning information and target driving control information can be obtained based on the correlation mapping.

[0077] For example, when there is a direct correlation between the driving ability category identification result and the driving warning information and driving control information, the corresponding target driving warning information and target driving control information can be directly obtained through this correlation.

[0078] In cases where there is an indirect association between the driving ability category identification result and driving warning information and driving control information, such as when the driving ability category identification result is associated with the identifiers of driving warning information and driving control information, the identifiers of driving warning information and driving control information can be obtained first based on the driving ability category identification result, and then the corresponding target driving warning information and target driving control information can be obtained based on the identifiers of driving warning information and driving control information; similarly, when the driving ability category identification result is associated with a combined identifier of driving warning information and driving control information, the combined identifier of driving warning information and driving control information can be obtained first based on the driving ability category identification result, and then the corresponding target driving warning information and target driving control information can be obtained based on the combined identifier of driving warning information and driving control information.

[0079] Step 204: Execute a driving warning based on the target driving warning information, and execute driving control on the target vehicle based on the target driving control information.

[0080] Optionally, after obtaining the target driving warning information and the target driving control information, the corresponding driving warning action can be executed based on the target driving warning information, and the corresponding driving control action can be executed on the target vehicle based on the target driving control information. This enables different actions to be executed for different levels of driving ability, thereby ensuring the accuracy of vehicle control and improving driving safety.

[0081] The driving warning actions include, but are not limited to, warning actions that call for emergency assistance from the outside and / or warning actions that initiate abnormal driving ability prompts internally; driving control actions include, but are not limited to, operating parameter control actions and / or environmental parameter control actions, or control actions that switch to automatic driving mode.

[0082] The vehicle driving control method provided in this embodiment combines multiple vital signs and medical data of the driver to comprehensively analyze the probability values ​​of the driver under each driving ability category label. Based on the probability values, it estimates the driver's driving ability category identification result, realizing multi-dimensional and multi-level identification of the driver's driving ability category to accurately and timely identify different driving ability categories of the driver. Furthermore, based on the different driving ability categories of the driver, it adaptively determines the corresponding target driving warning information and target driving control information to execute different driving warning actions and driving control actions for the target vehicle. This improves the accuracy of driving ability assessment and vehicle driving control, thereby enhancing driving safety.

[0083] In some embodiments, step 201, acquiring multiple vital sign data of the driver inside the target vehicle and multiple medical data of the driver, includes:

[0084] Multiple vital sign data are collected based on a first sensor and / or a second sensor; the first sensor is a sensor that communicates with the target vehicle, and the second sensor is a sensor installed inside the target vehicle.

[0085] Obtain the driver's electronic medical record, the driver's physical examination report, and the driver's medical records;

[0086] Based on the electronic medical record, the physical examination report, and the medical records, obtain multiple medical data.

[0087] Among them, the vital signs data include multiple data such as temperature data, exhaled breath alcohol concentration data, pulse data, gaze deviation information, blood pressure data, driving posture data, and pressure data applied to the steering wheel corresponding to the driver's seat in the target vehicle.

[0088] The medical data mentioned includes multiple data points such as vision data, hearing data, cardiovascular disease data, and neurological disease data.

[0089] The second sensor here is a sensor built into the target vehicle, including but not limited to at least one of the following sensors:

[0090] Temperature sensors, such as infrared body temperature sensors, are installed on the driver's seat to collect the driver's body temperature.

[0091] An alcohol sensor is installed above the center of the steering wheel, corresponding to the driver's seat, to detect the alcohol concentration in the driver's breath.

[0092] An eye tracker installed above the steering wheel or on the top of the dashboard corresponding to the driver's seat is used to track the driver's eye gaze direction and, in conjunction with the vehicle's direction of travel, determine the eye gaze deviation information between the eye gaze direction and the vehicle's direction of travel.

[0093] A pressure sensor is installed on the steering wheel corresponding to the driver's seat to collect data on the pressure applied by the driver to the steering wheel, in order to help determine whether the driver's hands have left the steering wheel.

[0094] An onboard pulse sensor is installed on the driver's seat or the steering wheel corresponding to the driver's seat to collect the driver's pulse data.

[0095] An in-vehicle driving posture sensor or in-vehicle camera is installed on the driver's seat or the steering wheel corresponding to the driver's seat to collect the driver's driving posture data.

[0096] The first sensor here is a sensor that has established a communication connection with the target vehicle, including but not limited to at least one of the following sensors:

[0097] The driver wears a wristband that can detect pulse and connects to the vehicle's Bluetooth or mobile data network to collect the driver's pulse data.

[0098] The driver wears a wristband that can monitor blood pressure and connects to the vehicle's Bluetooth or mobile data network to collect the driver's blood pressure data.

[0099] Figure 3 This is the second schematic diagram of the vehicle driving control process provided in this embodiment; during the data acquisition process, the data acquisition unit can be invoked to perform the following data acquisition steps:

[0100] Based on the aforementioned first and / or second sensors, multiple vital signs data are collected, including temperature data, exhaled breath alcohol concentration data, pulse data, gaze deviation information, blood pressure data, driving posture data, and pressure data applied to the steering wheel corresponding to the driver's seat in the target vehicle.

[0101] Simultaneously, it can also acquire electronic medical records, physical examination reports, and medical records entered by users through the vehicle's infotainment system, or download electronic medical records, physical examination reports, and medical records by connecting to an internet hospital; and perform text recognition on electronic medical records, physical examination reports, and medical records to obtain multiple medical data, including vision data, hearing data, cardiovascular disease data, and nervous system disease data.

[0102] The method provided in this embodiment fully utilizes multiple vital sign data collected by multiple sensors and integrates multiple medical data from medical institutions to achieve comprehensive monitoring and assessment of the driver's health status. By combining vital sign data and medical data, rich vital sign data is obtained, which in turn more refined and accurately characterizes the driver's vital sign features. This allows for a more accurate assessment of the driver's health status, timely warnings of potential health risks, and prompt emergency vehicle control actions, thereby improving the precision of driving control and driving safety.

[0103] In some embodiments, step 202, determining the probability value of the driver under each driving ability category label based on each of the vital sign data and each of the medical data, includes:

[0104] For each of the vital signs data and each of the medical data, normalization processing is performed on each data item according to the target interval corresponding to each data item to obtain the normalization processing result of each data item; the target interval is the data interval formed by the data collected when each data item is in a normal state;

[0105] Based on the normalization result, the target feature vector of the driver is obtained;

[0106] Based on the target feature vector, determine the probability value of the driver under each of the driving ability category labels.

[0107] The target range for each data point here is the data range formed by collecting data under normal conditions, that is, the normal range limit for each data point; for example, the target range for body temperature data includes 36.1 to 37.2 degrees Celsius; the target range for gas alcohol concentration data includes 0 to 0.01%; the target range for pulse data includes 60 to 100 beats / minute; when the vehicle speed is greater than 0, the target range for the duration of deviation in the line of sight information includes 0 to 30 seconds; the target range for pressure data includes 0.3 to 2 kg; the target range for visual acuity data includes 0.8 to 1.5; the target range for hearing data includes 0 to 25 dB, etc.

[0108] As can be seen from the target intervals corresponding to each data item defined above, there is a dimensional bias between different vital sign data items and different medical data items. To reduce the impact of this dimensional bias on the driver's driving ability category identification results, as follows... Figure 3 As shown, before obtaining the driver's driving ability category recognition results, the following data analysis steps can be performed in the data analysis unit:

[0109] First, data processing, such as normalization, is performed on each data point in the vital signs and medical data to unify the dimensions of different vital signs and medical data within the same range. This eliminates the impact of dimensional bias on the driver's driving ability category identification results, thereby improving the accuracy and efficiency of obtaining the driving ability category identification results.

[0110] Here, the normalization process can be achieved by matching each data point with its corresponding target interval to obtain the normalization result for each data point based on the matching result. For example, if a data point is within the normal range (i.e., the target interval), its deviation coefficient is 0, indicating that there is no deviation. For instance, the normal range for body temperature data is 36.1 to 37.2℃, so the deviation value for a temperature value of 37℃ is 0. Similarly, if the duration of deviation in human line of sight deviation information is outside the normal range, the deviation value is 1; if the duration of deviation is within the normal range, it is 0, and so on, to obtain the normalization result for each data point. Alternatively, each data point can be input as a variable into a maximum-minimum value normalization calculation formula based on the target interval corresponding to each data point to calculate the normalization result for each data point.

[0111] Next, after obtaining the normalization results, the normalized data can be concatenated to form the driver's target feature vector. For example, normalizing multiple data points collected from a driver, including body temperature, breath alcohol concentration, pulse, gaze deviation, stress, vision, hearing, cardiovascular disease, and nervous system disease, yields the driver's target feature vector as [0.73,0,0,1,0,0.29,0.6,0,0]. This data indicates that the driver has issues such as abnormal body temperature, poor concentration, poor vision, and hearing impairment.

[0112] Next, the driver's target feature vector can be input into a classification model, which learns the target feature vector to output the probability value of the driver under each driving ability category label. Based on the probability value under the driving ability category label, the driver's driving ability category prediction result can be determined, and then the corresponding target driving warning information and target driving control information can be obtained.

[0113] In some embodiments, step 202, obtaining the driver's driving ability category identification result based on the probability value, includes:

[0114] Among multiple driving ability category labels, determine the driving ability category label corresponding to the highest probability value;

[0115] The driver's driving ability category identification result is determined based on the driving ability category label corresponding to the maximum probability value.

[0116] Optionally, among multiple driving ability category labels, the driving ability category label corresponding to the highest probability value is determined, and the driving ability category label corresponding to the highest probability value is used as the driver's driving ability category recognition result, thereby achieving convenient and fast determination of the driving ability category recognition result.

[0117] The classification model here is pre-trained. Training the classification model can be done based on the following steps:

[0118] First, multiple historical vital sign data and multiple medical data of different sample drivers are collected. Data preprocessing is then performed on these data, such as discarding invalid sample driver data and normalizing the data, to obtain the target feature vector set X corresponding to the multiple sample drivers.

[0119]

[0120] Furthermore, the label values ​​corresponding to each driving ability category label are defined. For example, the range of driving ability category label values ​​is an integer from 0 to 4 points. The label value of the Level 1 abnormal driving ability category label is 0, the label value of the Level 2 abnormal driving ability category label is 1, the label value of the Level 3 abnormal driving ability category label is 2, the label value of the Level 4 abnormal driving ability category label is 3, and the label value of the normal driving ability category label is 4. The smaller the value, the worse the current driving ability.

[0121] Next, based on the target feature vector set X corresponding to each sample driver and the label values ​​corresponding to each driving ability category label, the driving ability category of each sample driver is labeled, resulting in a set Y of true values ​​for the driving ability categories of multiple different sample drivers:

[0122]

[0123] The set of true values ​​for driving ability categories, Y, is a two-dimensional matrix. The horizontal axis represents the true values ​​of the five driving ability categories, and the vertical axis represents the number of sample drivers collected. If a sample driver has a label value of 1 under a certain driving ability category label, then that driving ability category label is a true value of the sample driver's driving ability. If a sample driver has a label value of 0 under a certain driving ability category label, then that driving ability category label is not a true value of the sample driver's driving ability.

[0124] Next, a sample dataset is constructed based on the target feature vectors of each sample driver and the corresponding true values ​​of driving ability categories. The sample dataset is then stored in the cloud to provide persistent analysis capabilities. The sample dataset is then input into the driving ability algorithm engine. The engine uses the normalized target feature vectors of the sample drivers obtained from the sample dataset as input values ​​and the true values ​​of driving ability categories as the expected output values. This input is then fed into a neural network model, such as a multilayer perceptron model. The driving ability category identification results of the sample drivers output by the neural network model and the true values ​​of driving ability categories are used to calculate the loss value using a cross-entropy function. The weights and bias vectors of the neural network model are adjusted based on the loss value, ultimately allowing the prediction results to gradually fit the actual results. In other words, when the neural network model converges, a classification model is obtained.

[0125] Figure 4 This is a schematic diagram of the structure of the multilayer perceptron model provided in this embodiment; as shown below. Figure 4 As shown, this multilayer perceptron model can be constructed from an input layer, hidden layers, and an output layer. This multilayer perceptron model can be built using the scikit-learn library for multilayer perceptrons in Python.

[0126] The calculation formula for the multilayer perceptron model is as follows:

[0127] o (i) =x (i) W+b;

[0128] Among them o (i) Let x be the confidence score of the i-th driver under each driving ability category label; W and b are the weight parameters and bias vector of the classification model, respectively. (i) W can be expressed using the matrix multiplication formula:

[0129]

[0130] Where n is the dimension of the target feature vector of the sample driver; m is the number of nodes in the hidden layer of the classification model; {w 11 w 12 w 13 {x1, x2, x3, ...} are the model parameters of the hidden layer; {x1, x2, x3, ...} are the target feature vectors of the sample drivers.

[0131] like Figure 4 As shown, h i The output of the hidden layer of the multilayer perceptron, o i This is the confidence score output by the multilayer perceptron. The corresponding output range includes: a label value of 0 for the Level 1 abnormal driving ability category, a label value of 1 for the Level 2 abnormal driving ability category, a label value of 2 for the Level 3 abnormal driving ability category, a label value of 3 for the Level 4 abnormal driving ability category, and a label value of 4 for the normal driving ability category, corresponding to 5 zeros. j ;

[0132] The target feature vectors of each driver sample are input into a multilayer perceptron model for training. This will be done for each driver. j The predicted output has a corresponding confidence level, which is then used to determine the confidence level for each o. j The predicted confidence values ​​are used to calculate probability values ​​to determine the driving ability category identification results for each sample driver.

[0133] Alternatively, each o can be j The predicted output confidence level is transformed into a probability distribution value with positive values ​​and a sum of 1, i.e.:

[0134] y^ (i) =softmax(o j );

[0135]

[0136] Among them, y^ (i) This represents the probability distribution of the i-th sample driver output by the classification model under each driving ability category label;

[0137] Therefore, this embodiment uses 5 categories of driving ability labels, so the above formula c=5 can be used to transform the probability distribution value into:

[0138]

[0139] During model training, it is necessary to combine the loss function to gradually fit the true probability distribution y. (i) Specifically, the cross-entropy function H(y) can be used. (i) y^ (i) )accomplish:

[0140]

[0141] Since the true value of the driving ability category of the i-th sample driver is y (i) = [0, 1, 0, 0, 0], meaning that only one of these five values ​​is 1, and the rest are 0; therefore, the above cross-entropy function can be simplified to:

[0142]

[0143] in, Let be the probability value of the i-th sample driver under the driving ability category label at the index position of its true driving ability category value.

[0144] For example, the true value y of the driving ability category of the i-th sample driver. (i) =[0,0,1,0,0] It can be seen that 1 is at index 2, so the true value of the driver's driving ability category is moderate driving impairment, that is, the true label is 2. Assume the probability of the multilayer perceptron model's predicted output is y^ (i) =[0.1,0.11,0.7,0.2,0.4] It can be seen that the prediction result is correct, and the corresponding loss H = -log 0.7. Furthermore, if the model predicts the output y^ (i) =[0.1,0.11,0.07,0.2,0.4] then corresponds to prediction result 4, which is normal driving. This prediction result is actually different from the actual label 2. Here, the corresponding loss H = -log 0.07, so -log 0.7 < -log 0.07. It can be seen that the loss H for a wrong prediction is larger than the loss for a correct prediction. Therefore, the simplified calculation formula above can quickly make the multilayer perceptron model converge, so as to obtain the probability value of the target feature vector output under each driving ability category label, and obtain the classification model of driving ability category recognition result.

[0145] The method provided in this embodiment trains a classification model based on a multilayer perceptron model, which can achieve multi-level nonlinear feature extraction of multiple vital signs data and multiple medical data, thereby ensuring the accuracy of the driver's driving ability category identification results, and thus achieving precise vehicle driving control.

[0146] In some implementations, the normalization process is performed on each data item according to the target interval corresponding to each data item to obtain the normalization result of each data item, including:

[0147] Based on the maximum and minimum values ​​in the target interval corresponding to each data item, construct multiple reference intervals corresponding to each data item;

[0148] Among the multiple reference intervals, determine the reference interval to which each data item belongs;

[0149] Calculate the deviation coefficient value corresponding to each data item according to the deviation coefficient calculation formula corresponding to the reference interval to which each data item belongs;

[0150] Based on the deviation coefficient value, the normalization result of each data item is obtained.

[0151] Optionally, the normalization process specifically includes:

[0152] The process involves multiplying one or both of the maximum and minimum values ​​in the target interval corresponding to each data point by one or more preset multiples, and then combining the maximum and minimum values ​​to generate multiple different reference thresholds. Next, multiple different reference intervals are constructed based on these reference thresholds. Then, each data point is matched with its corresponding reference intervals to determine which interval it belongs to. Next, each data point is input as a variable into the deviation coefficient calculation formula corresponding to the reference interval to which it belongs, and the deviation coefficient value for each data point is calculated. Finally, the deviation coefficient value for each data point is used as the normalization result for each data point.

[0153] The method provided in this embodiment generates multiple reference intervals based on the actual distribution and characteristics of each data point, and adaptively determines the corresponding deviation coefficient calculation formula for each reference interval to perform normalization processing, thereby providing a more refined normalization effect and improving the accuracy of vehicle driving control.

[0154] In some embodiments, constructing multiple reference intervals corresponding to each data item based on the maximum and minimum values ​​in the target interval corresponding to each data item includes:

[0155] Based on the first difference, a first reference interval is constructed for each data item; the first difference is the difference between a first preset multiple of the minimum value in the target interval and the maximum value in the target interval;

[0156] Based on the first difference and the minimum value in the target interval, a second reference interval is constructed for each data item;

[0157] Based on the minimum value and the maximum value in the target interval, a third reference interval is constructed for each data item.

[0158] Based on the maximum value in the target interval and the second difference, a fourth reference interval is constructed for each data item; the second difference is the difference between a second preset multiple of the maximum value in the target interval and the minimum value in the target interval.

[0159] Based on the second difference, a fifth reference interval is constructed for each of the data items;

[0160] Wherein, the maximum value in the first reference interval is less than the minimum value in the second reference interval, the maximum value in the second reference interval is less than the minimum value in the third reference interval, the maximum value in the third reference interval is less than the minimum value in the fourth reference interval, and the maximum value in the fourth reference interval is less than the minimum value in the fifth reference interval.

[0161] Optionally, when a data point belongs to the first reference interval and the fifth reference interval, its corresponding deviation coefficient calculation formula is a fixed value of 1; when a data point belongs to the third reference interval, its corresponding deviation coefficient calculation formula is a fixed value of 0; when a data point belongs to the second reference interval and the fourth reference interval, its corresponding deviation coefficient calculation formula is determined by an equation constructed based on the maximum value and the maximum value of the corresponding target interval.

[0162] The first preset multiplier and the second preset multiplier can be the same or different, and can be set according to actual needs, such as both being set to 2.

[0163] For example, the normalized result for each data item can be calculated based on the following improved normalization calculation formula:

[0164]

[0165] Where f(x) is the normalization result of data item x, used to limit the range of deviation coefficients to [0,1], thereby eliminating dimensional bias between different data items; x min and x maxThese are the minimum and maximum values ​​in the target interval corresponding to data item x, respectively.

[0166] For example, substituting a set of temperature data [35,37,38] into the formula yields a deviation coefficient of [1,0,0.73]. That is, if the value of the data item x is far outside the normal range, its deviation coefficient is defined as the maximum value of 1.

[0167] The method provided in this embodiment generates multiple reference intervals based on the actual distribution and characteristics of each data item, and adaptively determines the corresponding deviation coefficient calculation formula for each reference interval to perform normalization processing, thereby obtaining data that can be measured and compared between data items, thus providing a more refined normalization effect and improving the accuracy of vehicle driving control.

[0168] In some embodiments, step 203, which involves obtaining target driving warning information and target driving control information based on the driving ability category identification result, includes:

[0169] If the driving ability category identification result is a Level 1 abnormal driving ability category, the target driving warning information is determined as the first warning information, and the target driving control information is determined as the first control information; the first warning information is used to call for emergency rescue, and the first control information is used to activate the automatic driving mode to drive the target vehicle to a safe area.

[0170] If the driving ability category identification result is a Level 2 abnormal driving ability category, the target driving warning information is determined as the second warning information, and the target driving control information is determined as the second control information. The second warning information is used to call for emergency rescue and initiate a driving ability abnormality warning prompt. The second control information is used to invoke the first vehicle control command and the second vehicle control command to control the target vehicle. The first vehicle control command is used to control the operating parameters of the target vehicle. The second vehicle control command is used to control the environmental parameters of the target vehicle.

[0171] If the driving ability category identification result is a level three driving ability abnormality category, the target driving warning information is determined to be the third warning information, and the target driving control information is determined to be the third control information; the third warning information is used to initiate a driving ability abnormality warning prompt, and the third control information is used to call the first vehicle control command to control the target vehicle;

[0172] If the driving ability category identification result is a level four abnormal driving ability category, the target driving warning information is determined to be the third warning information, and the target driving control information is determined to be the fourth control information; the fourth control information is used to invoke the second vehicle control command to control the target vehicle.

[0173] The first vehicle control command here is used to control the operating parameters of the target vehicle, such as the control command to reduce the operating speed of the target vehicle; the second vehicle control command is used to control the environmental parameters of the target vehicle, such as the control command to open the windows, the control command to adjust the air conditioning temperature and humidity, and the control command to adjust the music, in order to alleviate the driver's abnormal physical condition.

[0174] like Figure 3 As shown, after obtaining the driving ability category identification result, the data analysis unit can continue to perform the following data analysis steps to obtain the target driving warning information and target driving control information, and the scheduling unit can process the execution unit scheduling steps to schedule the corresponding execution units to perform the action scheduling steps to achieve driving control:

[0175] When the data analysis unit determines that the driving ability category identification result is a Level 1 driving ability abnormal category (i.e., 0), it indicates that the driver is unable to drive. At this time, the target driving warning information is used to call for emergency rescue; the target driving control information is used to activate the automatic driving mode to drive the target vehicle to a safe area.

[0176] At this time, the dispatch unit can call the autonomous driving execution unit in the execution unit, which will automatically take over the driving control to switch the autonomous driving mode and drive the target vehicle to a safe area. At the same time, the dispatch unit can also call the outbound call execution unit in the execution unit to send an emergency rescue call to provide emergency assistance to the driver.

[0177] When the data analysis unit determines that the driving ability category identification result is a level 2 driving ability abnormality category (i.e., 1), it indicates that the driver has a severe driving impairment. At this time, the target driving warning information is used to call for emergency rescue and initiate warning prompts, and the target driving control information is used to call the first vehicle control command and the second vehicle control command to assist the driver in driving and controlling the target vehicle.

[0178] At this time, the dispatch unit can call the vehicle control execution unit in the execution unit. The vehicle control execution unit controls the operating parameters and environmental parameters of the target vehicle according to the first vehicle control command and the second vehicle control command. This alleviates the driver's driving obstacles while limiting the vehicle's operating parameters to ensure the safety of vehicle operation. At the same time, the dispatch unit can also call the outbound call execution unit and the early warning assistant in the execution unit to send out emergency rescue calls to provide emergency assistance to the driver; and to issue internal warnings of abnormal driving ability, alerting the driver and passengers that abnormal situations have occurred and that timely safety protection measures need to be taken.

[0179] When the data analysis unit determines that the driving ability category identification result is a level three driving ability abnormality category (i.e., 2), it indicates that the driver has a moderate driving impairment. At this time, the target driving warning information is determined to initiate a warning prompt; the target driving control information is used to call the first vehicle control command to assist the driver in driving and controlling the target vehicle.

[0180] At this time, the dispatch unit can invoke the vehicle control execution unit, which will control the operating parameters of the target vehicle according to the first vehicle control command, thereby limiting the vehicle's operating parameters and ensuring the safety of vehicle operation. Simultaneously, the dispatch unit can also invoke the early warning assistant to issue an internal warning of abnormal driving ability, alerting the driver and passengers that an abnormal situation has occurred and requiring timely safety precautions.

[0181] When the data analysis unit determines that the driving ability category identification result is a level four driving ability abnormality category (i.e., 3), it indicates that the driver has a slight driving impairment. At this time, the target driving warning information is determined to initiate a warning prompt; the target driving control information is used to call the second vehicle control command to assist the driver in driving the target vehicle.

[0182] At this point, the dispatch unit can invoke the vehicle control execution unit, which will then control the environmental parameters of the target vehicle according to the second vehicle control command, thereby alleviating the driver's driving difficulties. Simultaneously, the dispatch unit can also invoke the early warning assistant to issue an internal warning of abnormal driving ability, alerting the driver and passengers to any abnormal situations requiring timely safety measures.

[0183] If the data analysis unit determines that the driving ability category identification result is the normal driving ability category (i.e., 4), then the driver is in a normal state and no driving warning or automatic driving control intervention will be performed.

[0184] The so-called early warning assistant can provide early warning prompts through one or more of the following methods: voice, pop-up window, vibration, and icon.

[0185] It should be noted that the dispatching unit and various execution units on the vehicle terminal, such as the autonomous driving execution unit, outbound call execution unit, vehicle control execution unit, and warning assistant, can communicate with each other according to the relevant instruction protocols between the units.

[0186] The method provided in this embodiment allows the scheduling unit to determine, based on pre-established associations, which driving action should be initiated according to the current driver's driving ability category, and to promptly assist the driver in handling emergencies, thereby improving the timeliness and accuracy of driving control and ultimately enhancing driving safety.

[0187] The vehicle driving control system provided by the present invention is described below. The vehicle driving control system described below can be referred to in correspondence with the vehicle driving control method described above.

[0188] Figure 5 This is a schematic diagram of the vehicle driving control system provided in this embodiment; as shown. Figure 5 As shown, the system includes: a data acquisition unit 501 for performing... Figure 3 The data acquisition steps shown enable the acquisition of multiple vital sign data and multiple medical data of the driver inside the target vehicle; the data analysis unit 502 is used to perform... Figure 3 The data analysis steps shown implement the following: determining the probability value of the driver under each driving ability category label based on the vital sign data and the medical data; obtaining the driver's driving ability category identification result based on the probability value; obtaining target driving warning information and target driving control information based on the driving ability category identification result; the scheduling unit 503 is used to execute... Figure 3 The execution unit scheduling steps shown implement scheduling of the corresponding warning execution unit based on the target driving warning information, and scheduling of the corresponding driving control unit based on the target driving control information; the execution unit 504 is used to execute according to the built-in warning execution unit and driving control unit. Figure 3 The action execution steps shown enable the execution of driving warnings based on target driving warning information, and the execution of driving control on the target vehicle based on the target driving control information.

[0189] The vehicle driving control system provided in this embodiment comprehensively analyzes the probability values ​​of the driver under each driving ability category label by combining multiple vital signs and medical data of the driver. Based on the probability values, it estimates the driver's driving ability category identification result, realizing multi-dimensional and multi-level identification of the driver's driving ability category to accurately and timely identify different driving ability categories of the driver. Furthermore, based on the different driving ability categories of the driver, it adaptively determines the corresponding target driving warning information and target driving control information to execute different driving warning actions and driving control actions for the target vehicle. This improves the accuracy of driving ability assessment and vehicle driving control, thereby enhancing driving safety.

[0190] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6As shown, the electronic device may include a processor 601, a communications interface 602, a memory 603, and a communication bus 604, wherein the processor 601, communications interface 602, and memory 603 communicate with each other via the communication bus 604. The processor 601 can call logical instructions in the memory 603 to execute a vehicle driving control method. This method includes: acquiring multiple vital sign data and multiple medical data of the driver in the target vehicle; determining the probability value of the driver under each driving ability category label based on the vital sign data and the medical data; acquiring the driver's driving ability category identification result based on the probability value; acquiring target driving warning information and target driving control information based on the driving ability category identification result; executing a driving warning based on the target driving warning information; and executing driving control on the target vehicle based on the target driving control information.

[0191] Furthermore, the logical instructions in the aforementioned memory 603 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0192] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the vehicle driving control method provided by the above methods. The method includes: acquiring multiple vital sign data and multiple medical data of the driver in the target vehicle; determining the probability value of the driver under each driving ability category label based on each of the vital sign data and each of the medical data; acquiring the driving ability category identification result of the driver based on the probability value; acquiring target driving warning information and target driving control information based on the driving ability category identification result; executing a driving warning based on the target driving warning information; and executing driving control on the target vehicle based on the target driving control information.

[0193] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the vehicle driving control method provided by the above methods. The method includes: acquiring multiple vital sign data and multiple medical data of a driver in a target vehicle; determining a probability value of the driver under each driving ability category label based on each of the vital sign data and each of the medical data; acquiring a driving ability category identification result of the driver based on the probability value; acquiring target driving warning information and target driving control information based on the driving ability category identification result; executing a driving warning based on the target driving warning information; and performing driving control on the target vehicle based on the target driving control information.

[0194] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0195] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0196] 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 of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle driving control method, characterized in that, include: Acquire multiple vital signs data of the driver inside the target vehicle and multiple medical data of the driver; Based on the vital signs data and medical data, determine the probability value of the driver under each driving ability category label, and obtain the driving ability category identification result of the driver based on the probability value. Based on the driving ability category identification results, target driving warning information and target driving control information are obtained; A driving warning is issued based on the target driving warning information, and driving control is applied to the target vehicle based on the target driving control information. The steps for determining the probability value of the driver under each driving ability category label include: For each of the vital signs data and each of the medical data, normalization processing is performed on each data item according to the target interval corresponding to each data item to obtain the normalization processing result of each data item; the target interval is the data interval formed by the data collected when each data item is in a normal state; Based on the normalization result, the target feature vector of the driver is obtained; Based on the target feature vector, determine the probability value of the driver under each of the driving ability category labels.

2. The vehicle driving control method according to claim 1, characterized in that, The step of normalizing each data item according to the target interval corresponding to each data item to obtain the normalization result of each data item includes: Based on the maximum and minimum values ​​in the target interval corresponding to each data item, construct multiple reference intervals corresponding to each data item; Among the multiple reference intervals, determine the reference interval to which each data item belongs; Calculate the deviation coefficient value corresponding to each data item according to the deviation coefficient calculation formula corresponding to the reference interval to which each data item belongs; Based on the deviation coefficient value, the normalization result of each data item is obtained.

3. The vehicle driving control method according to claim 2, characterized in that, The step of constructing multiple reference intervals for each data item based on the maximum and minimum values ​​in the target interval corresponding to each data item includes: Based on the first difference, a first reference interval is constructed for each data item; the first difference is the difference between a first preset multiple of the minimum value in the target interval and the maximum value in the target interval; Based on the first difference and the minimum value in the target interval, a second reference interval is constructed for each data item; Based on the minimum value and the maximum value in the target interval, a third reference interval is constructed for each data item. Based on the maximum value in the target interval and the second difference, a fourth reference interval is constructed for each data item; the second difference is the difference between a second preset multiple of the maximum value in the target interval and the minimum value in the target interval. Based on the second difference, a fifth reference interval is constructed for each of the data items; Wherein, the maximum value in the first reference interval is less than the minimum value in the second reference interval, the maximum value in the second reference interval is less than the minimum value in the third reference interval, the maximum value in the third reference interval is less than the minimum value in the fourth reference interval, and the maximum value in the fourth reference interval is less than the minimum value in the fifth reference interval.

4. The vehicle driving control method according to any one of claims 1-3, characterized in that, The step of obtaining the driver's driving ability category identification result based on the probability value includes: Among the multiple driving ability category labels, determine the driving ability category label corresponding to the highest probability value; The driver's driving ability category identification result is determined based on the driving ability category label corresponding to the maximum probability value.

5. The vehicle driving control method according to any one of claims 1-3, characterized in that, The step of obtaining target driving warning information and target driving control information based on the driving ability category identification result includes: If the driving ability category identification result is a Level 1 abnormal driving ability category, the target driving warning information is determined as the first warning information, and the target driving control information is determined as the first control information; the first warning information is used to call for emergency rescue, and the first control information is used to activate the automatic driving mode to drive the target vehicle to a safe area. If the driving ability category identification result is a Level 2 abnormal driving ability category, the target driving warning information is determined as the second warning information, and the target driving control information is determined as the second control information. The second warning information is used to call for emergency rescue and initiate a driving ability abnormality warning prompt. The second control information is used to invoke the first vehicle control command and the second vehicle control command to control the target vehicle. The first vehicle control command is used to control the operating parameters of the target vehicle. The second vehicle control command is used to control the environmental parameters of the target vehicle. If the driving ability category identification result is a level three driving ability abnormality category, the target driving warning information is determined to be the third warning information, and the target driving control information is determined to be the third control information; the third warning information is used to initiate a driving ability abnormality warning prompt, and the third control information is used to call the first vehicle control command to control the target vehicle; If the driving ability category identification result is a level four abnormal driving ability category, the target driving warning information is determined to be the third warning information, and the target driving control information is determined to be the fourth control information; the fourth control information is used to invoke the second vehicle control command to control the target vehicle.

6. The vehicle driving control method according to any one of claims 1-3, characterized in that, The acquisition of multiple vital signs and multiple medical data of the driver inside the target vehicle includes: Multiple vital sign data are collected based on a first sensor and / or a second sensor; the first sensor is a sensor that communicates with the target vehicle, and the second sensor is a sensor installed inside the target vehicle. Obtain the driver's electronic medical record, the driver's physical examination report, and the driver's medical records; Based on the electronic medical record, the physical examination report, and the medical records, obtain multiple medical data. Among them, the vital signs data include multiple data such as temperature data, exhaled breath alcohol concentration data, pulse data, gaze deviation information, blood pressure data, driving posture data, and pressure data applied to the steering wheel corresponding to the driver's seat in the target vehicle. The medical data mentioned includes multiple data points such as vision data, hearing data, cardiovascular disease data, and neurological disease data.

7. A vehicle driving control system, characterized in that, include: The data acquisition unit is used to acquire multiple vital signs data of the driver inside the target vehicle and multiple medical data of the driver. The data analysis unit is used to determine the probability value of the driver under each driving ability category label based on the vital sign data and the medical data, obtain the driving ability category identification result of the driver based on the probability value, and obtain target driving warning information and target driving control information based on the driving ability category identification result. An execution unit is configured to execute a driving warning based on the target driving warning information and to execute driving control on the target vehicle based on the target driving control information; The data analysis unit is specifically used for: For each of the vital signs data and each of the medical data, normalization processing is performed on each data according to the target interval corresponding to each data to obtain the normalization processing result of each data. The target interval is the data interval formed by the data collected when each data item is in a normal state; Based on the normalization result, the target feature vector of the driver is obtained; Based on the target feature vector, determine the probability value of the driver under each of the driving ability category labels.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the vehicle driving control method as described in any one of claims 1 to 6.

9. A non-transitory 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 vehicle driving control method as described in any one of claims 1 to 6.

Images