Vehicle warning method, device and apparatus

Abstract

The application discloses a vehicle warning method, device and equipment, and relates to the technical field of computers.The method comprises the following steps: obtaining a plurality of driving behavior data corresponding to a target vehicle; performing clustering analysis on the plurality of driving behavior data to obtain a target clustering result; determining a driving score corresponding to a driver based on the target clustering result; and displaying driving warning information on a vehicle terminal of the target vehicle if the driving score meets preset warning conditions. The driving score of the driver is determined by analyzing the driving behavior of the driver of the vehicle. If the driving score meets the preset warning conditions, it indicates that the driving safety risk of the driver under the current driving style is relatively high. Therefore, the driving warning information is displayed on the vehicle terminal of the vehicle, so as to prompt the driver that the driver is currently in a dangerous driving state and remind the driver to adjust the driving behavior, thereby reducing the probability of traffic accidents caused by the driving style of the driver.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of computer, in particular to a vehicle warning method, device and equipment. BACKGROUND

[0002] With the continuous progress of society and the continuous innovation of technology, the field of automobiles has experienced rapid development and has become an indispensable part of modern social life. With the increasing number of automobiles, traffic accidents are also increasing.

[0003] In the related art, traffic accidents can be prevented by predicting road conditions, for example, real-time monitoring of road conditions, vehicle driving trajectories and other data, and analyzing these data through an algorithm model to predict potential traffic accident risks, and displaying warning information in the vehicle terminal of the car based on the prediction results to guide the driver to adjust the driving plan, thereby reducing the probability of traffic accidents.

[0004] However, the main consideration for preventing traffic accidents by predicting road conditions is external factors such as road and vehicle driving state, and the effect of reducing the probability of traffic accidents is limited. SUMMARY

[0005] Embodiments of the present application provide a vehicle warning method, device and equipment, which can reduce the probability of traffic accidents caused by the driving style of the driver by analyzing the driving behavior of the driver. The technical solution is as follows:

[0006] On the one hand, a vehicle warning method is provided, the method comprising:

[0007] obtaining a plurality of driving behavior data corresponding to a target vehicle, the plurality of driving behavior data being used to indicate the driving behavior of a driver of the target vehicle during driving;

[0008] performing cluster analysis on the plurality of driving behavior data to obtain a target cluster result, the target cluster result being used to represent a target driving style of the driver;

[0009] determining a driving score corresponding to the driver based on the target cluster result, the driving score being used to represent the driving safety risk of the driver under the target driving style;

[0010] in a case where the driving score meets a preset warning condition, displaying driving warning information on a vehicle terminal of the target vehicle.

[0011] On the other hand, a vehicle warning device is provided, the device comprising:

[0012] obtain a plurality of driving behavior data corresponding to a target vehicle in a historical time period, the plurality of driving behavior data being used to indicate driving behavior of a driver of the target vehicle in a driving process;

[0013] perform clustering analysis on the plurality of driving behavior data to obtain a target clustering result, the target clustering result being used to represent a target driving style of the driver in the historical time period;

[0014] determine a driving score corresponding to the driver based on the target clustering result, the driving score being used to represent driving safety risk of the driver in the target driving style;

[0015] display driving alarm information on a vehicle terminal of the target vehicle in a case where the driving score meets a preset alarm condition.

[0016] In another aspect, a computer device is provided, which includes a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement any of the vehicle alarm methods described above.

[0017] In another aspect, a computer readable storage medium is provided, which stores at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by a processor to implement any of the vehicle alarm methods described above.

[0018] In another aspect, a computer program product or a computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform any of the vehicle alarm methods described above.

[0019] The technical solutions provided by the embodiments of the present application bring at least the following beneficial effects:

[0020] In one aspect, a driving score of a driver is determined by analyzing the driving behavior of the driver, and if the driving score meets a preset warning condition, indicating that the driver has a high driving safety risk under the current driving style, a driving warning information is displayed on a vehicle terminal of the vehicle, prompting the driver that the driver is currently in a dangerous driving, reminding the driver to adjust the driving behavior, thereby reducing the probability of traffic accidents caused by the driving style of the driver. On the other hand, clustering analysis is performed on a plurality of driving behavior data, and the clustering analysis can classify similar driving behavior data into a category, thereby identifying the main driving style of the driver, which is helpful to better understand the driving habits of the driver, thereby improving the accuracy of the driving score of the driver. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a structural block diagram of a computer system provided by an exemplary embodiment of the present application;

[0023] Figure 2 is a flowchart of a vehicle warning method provided by an exemplary embodiment of the present application;

[0024] Figure 3 is a flowchart of a vehicle warning method provided by another exemplary embodiment of the present application;

[0025] Figure 4 is a system schematic diagram provided by an exemplary embodiment of the present application;

[0026] Figure 5 is a structural block diagram of a vehicle warning device provided by an exemplary embodiment of the present application;

[0027] Figure 6 is a structural block diagram of a vehicle warning device provided by another exemplary embodiment of the present application;

[0028] Figure 7 is a structural block diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the purposes, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0030] The terms "first", "second" and the like are used to distinguish between similar or identical items or items having substantially the same function, and it should be understood that there is no logical or chronological dependency between "first" and "second", and the number and execution order are not limited.

[0031] It should be noted that the information (including but not limited to driving behavior data, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals involved in the present application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions. For example, the framework data involved in the present application is obtained under full authorization.

[0032] Figure 1 The structural block diagram of a computer system 100 provided by an exemplary embodiment of the present application is shown. The computer system 100 can be implemented as a system architecture of a vehicle warning method. The computer system 100 includes a vehicle 110.

[0033] The vehicle 110 includes a vehicle terminal. The vehicle includes at least one of a fuel automobile, a hybrid automobile, an electric automobile, a fuel cell automobile, etc., and the embodiments of the present application do not limit this.

[0034] In some embodiments, the above computer system 100 further includes a terminal 120. The terminal 120 includes but is not limited to a vehicle terminal, a mobile phone, a computer, a smart voice interaction device, a smart home appliance, an aircraft, etc.

[0035] Optionally, the terminal 120 is implemented as a mobile control terminal of the vehicle 110, and the terminal 120 can control the vehicle 110 to perform a target operation (for example: parking, closing the window, starting, etc.). Illustratively, the terminal 120 has a client of a target application installed and running therein, and the target application includes at least one of a vehicle control application, an instant messaging application, a navigation application (for example: a map application), and an application having a vehicle control function, and the embodiments of the present application do not limit this. In addition, the present application does not limit the form of the target application, including but not limited to an App (Application) installed in the terminal 120, a mini program, etc., and can also be in the form of a web page.

[0036] Optionally, the vehicle 110 and the terminal 120 communicate through a wireless network (such as 4G / 5G, Wi-Fi, etc.) or a wired connection (such as USB, Bluetooth, etc.).

[0037] In some embodiments, the computer system 100 further includes a server 130, which can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system, and can also be a cloud server providing cloud computing services. Optionally, the server 130 can also be implemented as a node in a blockchain system.

[0038] Illustratively, if the server 130 is implemented as a cloud server, the vehicle 110 and the server 130 communicate through a wireless network, and the terminal 120 and the server 130 communicate through a wireless network.

[0039] In some embodiments, the computer system 100 can be implemented as a T-box (Telematic BOX) Internet of Vehicles system, and the vehicle terminal in the vehicle 110 can be implemented as an intelligent vehicle terminal in the T-box Internet of Vehicles system, the terminal 120 can be implemented as a mobile terminal (such as a smartphone, a tablet computer, etc.) installed with a vehicle control application in the T-box Internet of Vehicles system, and the server 130 can be implemented as a remote server in the T-box Internet of Vehicles system.

[0040] The intelligent vehicle terminal is responsible for collecting various data of the vehicle and sending these data to the remote server through the communication interface, and at the same time, the intelligent vehicle terminal can also receive instructions from the remote server and perform corresponding operations, such as remotely controlling the vehicle, updating the vehicle software, etc. The vehicle owner can communicate with the remote server through the vehicle control application on the mobile terminal, thereby realizing remote control and monitoring of the vehicle. For example, the vehicle owner can view the location and status information of the vehicle, remotely control the start of the vehicle, lock the door, turn on the air conditioner, etc. through the vehicle control application on the mobile terminal. The remote server receives data from the intelligent vehicle terminal and the mobile terminal, and stores, analyzes and processes the data. At the same time, the remote server can also send corresponding instructions to the intelligent vehicle terminal and the mobile terminal according to the needs of the vehicle owner, so as to realize remote control and management of the vehicle.

[0041] Optionally, the vehicle warning method provided by the embodiments of the present application can be executed by the vehicle 110, the terminal 120, or the server 130; or executed by any two of the vehicle 110, the terminal 120, and the server 130; or executed by the vehicle 110, the terminal 120, and the server 130, which is not limited in the embodiments of the present application.

[0042] Illustratively, the vehicle 110 includes a driver A, and the vehicle terminal can obtain a plurality of driving behavior data of the driver A during driving of the vehicle 110, such as accelerator opening, vehicle speed, rotation speed, acceleration, lane changing times, and the like. After obtaining the plurality of driving behavior data, the vehicle terminal first performs clustering analysis on the plurality of driving behavior data to obtain a target clustering result, and finally determines a driving score corresponding to the driver based on the target clustering result. After obtaining the driving score, the vehicle terminal displays driving warning information when the driving score meets a preset warning condition, for example, when the driving score is less than or equal to a preset score, the vehicle terminal displays a warning message to remind the driver that he is in dangerous driving. Alternatively, the vehicle 110 also sends the driving warning information to the terminal 120, and the terminal 120 displays the driving warning information.

[0043] In some embodiments, the determination process of the driving score described above can also be performed in the server 130, that is, the server 130 obtains a plurality of driving behavior data of the driver A during driving of the vehicle 110, and analyzes the data to obtain a driving score. After obtaining the driving score, the server 130 determines rendering data corresponding to the driving warning information according to the driving score, and sends the rendering data to the vehicle 110. After receiving the rendering data, the vehicle 110 can display the driving warning information in the vehicle terminal according to the rendering data. Alternatively, the server 130 also sends the rendering data to the terminal 120, and the terminal 120 receives the rendering data and displays the driving warning information according to the rendering data.

[0044] With the continuous progress of society and the continuous innovation of technology, the automobile field has experienced rapid development and has become an indispensable part of modern social life. With the increasing number of cars, traffic accidents are also increasing. In related technologies, traffic accidents can be prevented by predicting road conditions, for example, real-time monitoring of road conditions, vehicle driving trajectories, and the like, and analyzing these data through an algorithm model to predict potential traffic accident risks, and displaying warning information in the vehicle terminal of the car based on the prediction results to guide the driver to adjust the driving plan, thereby reducing the probability of traffic accidents. However, the prediction of road conditions to prevent traffic accidents mainly considers external factors such as road and vehicle driving state, and the effect of reducing the probability of traffic accidents is limited.

[0045] Based on this, the application provides a vehicle warning method. On the one hand, the driving score of the driver is determined by analyzing the driving behavior of the driver of the vehicle. If the driving score meets the preset warning condition, it means that the driving safety risk of the driver under the current driving style is high, and the driving warning information is displayed on the vehicle terminal of the vehicle, so as to prompt the driver that he is currently in dangerous driving and remind the driver to adjust the driving behavior, thereby reducing the probability of traffic accidents caused by the driving style of the driver. On the other hand, the clustering analysis is performed on the plurality of driving behavior data. The clustering analysis can classify similar driving behavior data into a category, so as to identify the main driving style of the driver, which is helpful to further understand the driving habit of the driver, thereby improving the accuracy of the driving score of the driver.

[0046] The vehicle warning method provided by the embodiment of the application will be described below.

[0047] In combination with the above description, Figure 2 is a flowchart of a vehicle warning method provided by the embodiment of the application. The method is applied to, for example, the vehicle 110 as shown in the figure. Figure 1 The method includes the following steps 210 to 240.

[0048] Step 210: Obtain a plurality of driving behavior data corresponding to the target vehicle.

[0049] The plurality of driving behavior data is used to indicate the driving behavior of the driver of the target vehicle during driving.

[0050] Optionally, the plurality of driving behavior data corresponding to the target vehicle in a target time period is obtained.

[0051] Illustratively, the target time period refers to the time period between the historical time and the current time, for example, the plurality of driving behavior data of the driver in the target vehicle in the last 30 minutes is obtained.

[0052] Optionally, the plurality of driving behavior data only includes a single type of behavior data, for example, only the throttle opening data of the driver; or the plurality of driving behavior data includes a plurality of types of behavior data. The embodiment of the application does not limit this.

[0053] Illustratively, the target time period includes a plurality of time points, and the driving behavior data is collected at each time point to obtain the driving behavior data corresponding to each time point as the plurality of driving behavior data.

[0054] Optionally, the type of driving behavior data includes at least one of the following types:

[0055] 1. Vehicle speed: the vehicle speed refers to the speed of the target vehicle during driving.

[0056] 2. Acceleration: The acceleration refers to the acceleration of the target vehicle during driving, reflecting the change in speed of the target vehicle per unit time.

[0057] 3. Throttle opening: The throttle opening is used to indicate the depth (or angle) of the driver stepping on the throttle pedal of the target vehicle.

[0058] 4. Throttle opening: The throttle opening is a parameter in the engine management system, which is used to indicate the opening angle of the throttle valve in the engine of the target vehicle. The size of the throttle opening is determined by the throttle opening, but it may also be regulated by the engine management system.

[0059] 5. Speed: The speed refers to the speed of the engine of the target vehicle, which reflects the speed of the crankshaft rotation inside the engine.

[0060] 6. Lane changing frequency: The lane changing frequency refers to the frequency of the driver changing the driving lane of the target vehicle during driving.

[0061] 7. Steering data: The steering data refers to the angle and frequency of the target vehicle turning.

[0062] 8. Brake data: Brake data includes the braking force of the driver, braking frequency, etc.

[0063] It should be noted that the above examples of driving behavior data are only illustrative, for example: driving behavior data can also include biological feature data of the driver, such as heart rate, breathing rate, etc., which can reflect the physiological state and psychological changes of the driver during driving.

[0064] Optionally, a data acquisition device is installed in the target vehicle, and the plurality of driving behavior data is obtained through the data acquisition device. Illustratively, different types of driving behavior data correspond to different data acquisition devices, such as collecting the vehicle speed data of the target vehicle through a vehicle speed sensor; collecting the acceleration of the target vehicle through an acceleration sensor; collecting the throttle opening through a throttle opening sensor; collecting the biological feature data of the driver through a vehicle-mounted biological recognition device, etc., which will not be repeated here.

[0065] Step 220, clustering analysis is performed on the plurality of driving behavior data to obtain a target clustering result.

[0066] Illustratively, the clustering analysis of the plurality of driving behavior data means classifying the plurality of driving behavior data according to their similarity, that is, clustering similar data points into the same cluster, wherein each data point contains driving behavior data collected at the same time point.

[0067] The target clustering result is used to represent the target driving style of the driver.

[0068] Illustratively, after the plurality of driving behavior data are classified according to the similarity therebetween, one or more clusters can be obtained, and different clusters represent different driving styles. For example, a certain cluster can represent an aggressive driving style, which is characterized by high-speed driving, frequent acceleration and sudden braking; and another cluster can represent a conservative driving style, which is characterized by stable speed and gentle driving action.

[0069] If only one cluster is obtained by clustering, the driving style corresponding to the cluster is determined as the target driving style, and if a plurality of clusters are obtained by clustering, the driving styles corresponding to the plurality of clusters are taken as the target driving styles.

[0070] In some embodiments, the plurality of driving behavior data are subjected to clustering analysis by a target clustering algorithm to obtain a target clustering result.

[0071] The target clustering algorithm includes at least one of a K-means clustering algorithm, a Canopy clustering algorithm, a DBSCAN clustering algorithm, etc., and embodiments of the present application do not limit this.

[0072] In some embodiments, after the plurality of driving behavior data are obtained, the plurality of driving behavior data are preprocessed, and the plurality of driving behavior data after preprocessing are subjected to clustering analysis to obtain a target clustering result.

[0073] The preprocessing includes at least one of the following methods:

[0074] 1. Data cleaning.

[0075] Data cleaning is used to identify and filter outliers in the plurality of driving behavior data. After data cleaning, data repair can be performed, which refers to, after data cleaning, performing algorithm prediction according to the data type corresponding to the outliers, and performing data supplement.

[0076] 2. Data normalization.

[0077] Since the driving behavior data can come from different sensors, the dimensions and ranges of the data can be different. In order to eliminate such differences, the data need to be normalized to convert them to the same order of magnitude, which is convenient for subsequent data analysis and processing.

[0078] Step 230, determining a driving score corresponding to the driver based on the target clustering result.

[0079] wherein the driving score is used to represent the driving safety risk of the driver under the target driving style.

[0080] In some embodiments, the target clustering result only indicates one driving style.

[0081] Optionally, each driving style corresponds to a preset driving score, and the preset driving score corresponding to the driving style indicated by the target clustering result is taken as the driving score corresponding to the driver. Alternatively, the target clustering result is input into a driving score prediction model, and the target clustering result is analyzed by the driving score prediction model to determine the driving score corresponding to the driver.

[0082] In some other embodiments, the target clustering result includes a plurality of sub-clustering results, and each sub-clustering result corresponds to a different driving style.

[0083] Optionally, a plurality of sub-driving scores corresponding to the plurality of sub-clustering results are obtained, and the driving score corresponding to the driver is determined based on the plurality of sub-driving scores corresponding to the plurality of sub-clustering results.

[0084] Optionally, each driving style corresponds to a preset driving score, and the preset driving score corresponding to the driving style indicated by the sub-clustering result is taken as the sub-driving score corresponding to the sub-clustering result. Alternatively, the sub-clustering result is input into a driving score prediction model, and the sub-clustering result is analyzed by the driving score prediction model to obtain the sub-driving score corresponding to the sub-clustering result.

[0085] After obtaining the plurality of sub-driving scores, an average of the plurality of sub-driving scores is calculated as the driving score corresponding to the driver, or a median of the plurality of sub-driving scores is calculated as the driving score corresponding to the driver, or a mode of the plurality of sub-driving scores is calculated as the driving score corresponding to the driver, etc.

[0086] For the above driving score prediction model, the driving score prediction model is used to score the clustering driving behavior data to obtain the driving score. Optionally, the driving score prediction model is a model trained by a sample data set, the sample data set includes a plurality of sample data groups, each sample data group includes a plurality of sample driving behavior data, and each sample data group is labeled with a reference driving score, wherein the reference driving score can be evaluated by an expert according to the safety of the driving behavior. The sample data group is input into the sample score prediction model to obtain a predicted driving score, and the sample score prediction model is trained based on the difference between the reference driving score and the predicted driving score to obtain the driving score prediction model.

[0087] Optionally, a plurality of weights corresponding to the plurality of sub-clustering results are obtained, and the plurality of sub-driving scores are weighted and fused based on the plurality of weights corresponding to the plurality of sub-clustering results to obtain the driving score corresponding to the driver.

[0088] In some embodiments, the weight of the sub-clustering result can be a preset weight, for example: the driving style 1 indicated by the sub-clustering result A, the driving style 1 corresponds to the preset weight as the weight of the sub-clustering result A.

[0089] In other embodiments, the weight of the sub-clustering result needs to be determined according to the clustering feature and the stationarity feature of the sub-clustering result. Then the method for obtaining the weights corresponding to the plurality of sub-clustering results further comprises the following steps:

[0090] Step 1: Obtain the clustering number and clustering variance corresponding to each of the plurality of sub-clustering results.

[0091] The clustering number of the sub-clustering result refers to the number of similar data points contained in the sub-clustering result, wherein each data point contains driving behavior data collected at the same time point. Considering the clustering number as a weight determining factor is because the sub-clustering result containing more data points can be considered more important because it represents the driving style more commonly used by the driver.

[0092] The clustering variance of the sub-clustering result is used to evaluate the tightness of the sub-clustering, and a smaller clustering variance means that the data points in the sub-clustering are more concentrated, and a larger clustering variance means that the data points in the sub-clustering are more dispersed. Considering the clustering variance as a weight determining factor is because the clustering variance represents the stability of the driving style indicated by the sub-clustering result, for example: the clustering variance of a sub-clustering result is small, which means that the driving style indicated by this sub-clustering result is more stable and consistent, and therefore can be given a higher weight.

[0093] Step 2: Obtain the stationarity feature corresponding to each of the plurality of sub-clustering results.

[0094] The stationarity feature is used to represent the driving stability of the driver under the driving style indicated by the sub-clustering result. Illustratively, the driving score in the embodiments of the present application is used to evaluate the driving safety of the driver, and the stability is an important factor in evaluating driving safety, so the stability feature of the sub-clustering result is considered as a weight determining factor.

[0095] Optionally, the stationarity feature can be quantified by at least one of the acceleration change, speed change, and brake frequency of the target vehicle, wherein the range of acceleration change is negatively correlated with the stationarity feature value, the range of speed change is negatively correlated with the stationarity feature value, and the brake frequency is negatively correlated with the stationarity feature value. The higher the stationarity feature value, the higher the driving stability of the driver.

[0096] Step 3: Determine the weight corresponding to each of the plurality of sub-clustering results based on the clustering number, the clustering variance, and the stationarity feature corresponding to each of the plurality of sub-clustering results.

[0097] Optionally, the number of clusters of the sub-cluster result is positively correlated with the weight; the cluster variance of the sub-cluster result is negatively correlated with the weight; and the stationary eigenvalue of the sub-cluster result is positively correlated with the weight.

[0098] Illustratively, the first weight is determined based on the number of clusters of the sub-cluster result; the second weight is determined based on the cluster variance of the sub-cluster result; and the third weight is determined based on the stationary eigenvalue of the sub-cluster result; and the average of the first weight, the second weight and the third weight is calculated as the weight of the sub-cluster result.

[0099] In the above embodiments, the multiple dimensions (the number of clusters, the cluster variance and the stationary eigenvalue) are used to determine the weight of the sub-cluster, which can more accurately reflect the contribution of different driving styles to the overall driving behavior evaluation, and improve the accuracy of the final driving score.

[0100] In other embodiments, the above driving score is also associated with the driving scene of the target vehicle.

[0101] Optionally, the driving score corresponding to the driver is determined based on the target cluster result and the driving scene.

[0102] The driving scene includes but is not limited to urban roads, highways, mountain roads, rainy and snowy weather, night driving, etc. Different driving scenes have different requirements for drivers, so when driving safety is considered, considering the driving scene can make the driving score more accurate and targeted.

[0103] Illustratively, the driving scene corresponding to the target vehicle is determined by recognizing information such as road type, traffic signs, light intensity, weather, etc. through the on-board camera of the target vehicle.

[0104] Optionally, a candidate driving score corresponding to the driver is determined based on the target cluster result; and the candidate driving score is adjusted based on the driving scene corresponding to the target vehicle to obtain the driving score corresponding to the driver.

[0105] The process of determining the candidate driving score corresponding to the driver based on the target cluster result can refer to the process of determining the driving score corresponding to the driver based on the target cluster result described above, which will not be described here.

[0106] After obtaining the candidate reference score, the driving scene corresponding to the target vehicle is matched with the driving style indicated by the target clustering result to obtain a matching score; the candidate reference score is adjusted according to the matching score to obtain the driving score corresponding to the driver, wherein the matching score and the candidate reference score are in a positive correlation, for example: if the matching score is 100%, the candidate reference score can be a coefficient of 1.5 to obtain the final reference score, and if the matching score is 60%, the candidate reference score can be a coefficient of 0.7 to obtain the final reference score.

[0107] The matching score is used to represent the matching degree of the driving scene and the driving style indicated by the target clustering result. The higher the matching score is, the more suitable the current driving scene is to the driving style exhibited by the driver. For example, when driving on a highway, if the driver maintains a stable speed and driving trajectory and does not perform frequent lane changing or emergency braking and other high-risk operations, the driving style of the driver is highly matched with the driving scene of the highway, thereby obtaining a higher matching score.

[0108] In step 240, if the driving score meets the preset warning condition, the driving warning information is displayed on the vehicle terminal of the target vehicle.

[0109] Optionally, if the driving score is less than or equal to the preset driving score, the driving warning information is displayed on the vehicle terminal of the target vehicle, and the driving warning information is used to remind the driver that the driver is currently in dangerous driving.

[0110] The driving warning information includes full-screen warning effects, text notifications, icon notifications, etc., and the specific form of the driving warning information is not limited in the embodiments of the present application. Illustratively, the full-screen warning effect is displayed on the vehicle terminal of the target vehicle to cover the current interface, and the driver is notified that the driver is currently in dangerous driving.

[0111] It should be noted that, in addition to displaying the driving warning information on the vehicle terminal of the target vehicle to remind the driver that the driver is currently in dangerous driving, the driver can also be reminded that the driver is currently in dangerous driving through playing an alarm sound, vibrating the driver's seat, etc., which is not limited in the embodiments of the present application.

[0112] Optionally, the driving score is included in the above-mentioned driving warning information. Illustratively, the current driving score of the driver is displayed, which can enable the driver to intuitively understand his / her driving performance. Optionally, the recent driving score change of the driver can also be displayed to help the driver understand whether his / her driving behavior has improved.

[0113] Optionally, the driving warning information can further include a driving improvement suggestion. Illustratively, according to the driving behavior data of the driver, a specific driving improvement suggestion can be determined. For example, if the warning is caused by overspeed, the driving improvement suggestion can be implemented as “please reduce the driving speed and ensure the safety of driving”.

[0114] In some embodiments, the driving warning information is sent to a target terminal, and the target terminal includes other terminals connected with the vehicle terminal of the target vehicle.

[0115] The target terminal can be a smartphone, a tablet computer, a computer, another vehicle terminal, or the like device having a network connection function. Illustratively, the target terminal can communicate with the vehicle terminal of the target vehicle through a wireless network (such as 4G / 5G, Wi-Fi, etc.) or a wired connection (such as USB, Bluetooth, etc.).

[0116] For example, the target terminal is a mobile phone of the owner of the target vehicle. The mobile terminal has a target application program installed and running to control the target vehicle. When the driving score of the driver of the target vehicle is less than or equal to the preset driving score, the driving warning information is pushed to the vehicle terminal and the mobile phone of the owner at the same time.

[0117] In summary, the vehicle warning method provided by the embodiments of the present application can determine the driving score of the driver of the vehicle by analyzing the driving behavior of the driver. If the driving score meets the preset warning condition, it means that the driving safety risk of the driver under the current driving style is high. Therefore, the driving warning information is displayed on the vehicle terminal of the vehicle, prompting the driver that the driver is currently in dangerous driving and reminding the driver to adjust the driving behavior, thereby reducing the probability of traffic accidents caused by the driving style of the driver. On the other hand, the clustering analysis of the plurality of driving behavior data can classify similar driving behavior data into a category, thereby identifying the main driving style of the driver, which is helpful to better understand the driving habits of the driver, thereby improving the accuracy of the driving score of the driver.

[0118] In some embodiments, when the plurality of driving behavior data is analyzed by clustering, coarse-grained clustering analysis can be performed first, and then fine-grained clustering analysis can be performed, so as to obtain a target clustering result. Illustratively, the coarse-grained clustering analysis can be implemented as Figure 2 The embodiments shown can also be implemented as steps 310 to 340 as shown in Figure 3

[0119] Step 310: Obtain a plurality of driving behavior data corresponding to a target vehicle.

[0120] ​The plurality of driving behavior data is used to indicate the driving behavior of the driver of the target vehicle during driving. Optionally, the plurality of driving behavior data corresponding to the target vehicle in the target time period is obtained.

[0121] Illustratively, the target time period includes a plurality of time points, and driving behavior data is collected at each time point to obtain driving behavior data corresponding to each time point as the plurality of driving behavior data.

[0122] In step 321, coarse-grained clustering analysis is performed on the plurality of driving behavior data to obtain candidate cluster centers.

[0123] Illustratively, coarse-grained clustering analysis is used to perform preliminary clustering of data, thereby providing candidate cluster centers for subsequent fine-grained clustering.

[0124] Optionally, the coarse-grained clustering analysis is performed on the plurality of driving behavior data by a Canopy clustering algorithm to obtain candidate cluster centers.

[0125] The plurality of driving behavior data corresponds to a plurality of data points, and each data point includes driving behavior data collected at the same time point. Illustratively, taking speed, acceleration, and brake frequency as examples, these data need to be converted into numerical data for clustering analysis. For example, if there are the following driving behavior data: average speed (km / h), average acceleration (m / s 2 ), and the number of emergency braking. These data can be converted into a three-dimensional feature vector, and each dimension corresponds to a driving behavior indicator. The converted data set can be represented as an N x 4 matrix, where N is the number of data points, and N is an integer greater than 1.

[0126] Illustratively, the Canopy clustering algorithm sets two distance thresholds T1 and T2 (T1 < T2). The plurality of data points is traversed, and for each data point, the distance from the data point to all known clusters is checked. If the distance from a point to all known clusters is greater than T2, the point itself forms a new cluster. If the distance from a point to a known cluster is less than T1, the point is assigned to the known cluster. If the distance from a point to the nearest known cluster is between T1 and T2, the point is neither assigned to any known cluster nor forms a cluster by itself, but becomes an edge point that may form a new cluster with other points in the future. After all data points are traversed, a plurality of clusters and edge points are obtained, and the edge points are assigned to the nearest cluster according to their distance from the cluster. The cluster centers of the plurality of clusters obtained finally are the candidate cluster centers.

[0127] In step 322, fine-grained clustering analysis is performed on the plurality of driving behavior data based on the candidate cluster centers to obtain a target clustering result.

[0128] Illustratively, the fine-grained clustering analysis is used to perform a more refined clustering analysis based on the candidate clustering centers to obtain a more accurate and more specific driving style division.

[0129] Optionally, based on the candidate clustering centers, the K-means clustering algorithm is used to perform a fine-grained clustering analysis on the plurality of driving behavior data to obtain a target clustering result.

[0130] Illustratively, assuming that the candidate clustering centers include K clustering centers (K is a positive integer), the K candidate clustering centers are used as the initial clustering centers of the K-means clustering algorithm to perform a refined clustering. The K-means clustering algorithm includes the following steps:

[0131] Step 1: Calculate the distance between each data point and the K clustering centers, and assign it to the nearest clustering center. Step 2: For each cluster, calculate the mean of all data points and set the mean as the new clustering center. Step 3: Repeat steps 1 and 2 until the clustering center changes value is less than a preset value or reaches a preset maximum iteration number, and obtain the cluster corresponding to at least one clustering center as the target clustering result.

[0132] Step 330, determine the driving score corresponding to the driver based on the target clustering result.

[0133] The driving score is used to represent the driving safety risk of the driver under the target driving style.

[0134] In some embodiments, the target clustering result only indicates one driving style. Optionally, each driving style corresponds to a preset driving score, and the preset driving score corresponding to the driving style indicated by the target clustering result is used as the driving score corresponding to the driver. Alternatively, the target clustering result is input into a driving score prediction model, and the target clustering result is analyzed by the driving score prediction model to determine the driving score corresponding to the driver.

[0135] In other embodiments, the target clustering result includes a plurality of sub-clustering results, each corresponding to a different driving style. Optionally, a plurality of sub-driving scores corresponding to the plurality of sub-clustering results are obtained; and the driving score corresponding to the driver is determined based on the plurality of sub-driving scores corresponding to the plurality of sub-clustering results.

[0136] Step 340, in the case where the driving score meets a preset warning condition, display driving warning information on the vehicle terminal of the target vehicle.

[0137] Optionally, in the case where the driving score is less than or equal to a preset driving score, display driving warning information on the vehicle terminal of the target vehicle, and the driving warning information is used to remind the driver that he is currently in dangerous driving.

[0138] The driving warning information includes a full-screen warning effect, a text notification, an icon notification, and the like. The specific form of the driving warning information is not limited in the embodiments of the present application. Illustratively, the full-screen warning effect is displayed on the vehicle terminal of the target vehicle, covering the current interface, and notifying the driver that the current driving is dangerous.

[0139] In summary, the embodiments of the present application provide a vehicle warning method. On the one hand, the driving score of the driver is determined by analyzing the driving behavior of the driver. If the driving score meets the preset warning condition, it means that the driving safety risk of the driver under the current driving style is high. Then, the driving warning information is displayed on the vehicle terminal of the vehicle, prompting the driver that the current driving is dangerous and reminding the driver to adjust the driving behavior, thereby reducing the probability of traffic accidents caused by the driving style of the driver. On the other hand, when analyzing the driving behavior of the driver, the coarse-grained clustering analysis is first performed on the plurality of driving behavior data to preliminarily classify a large amount of driving behavior data and form a candidate clustering center, thereby quickly narrowing the data range and improving the efficiency of clustering analysis. Then, the fine-grained clustering analysis is performed based on the candidate clustering center to more carefully divide the plurality of driving behavior data to obtain the target clustering result, thereby improving the accuracy of the target clustering result obtained finally while ensuring the efficiency of clustering analysis, and improving the efficiency and accuracy of the driving score of the driver.

[0140] Illustratively, the vehicle warning method provided by the embodiments of the present application can be implemented by a vehicle driver big data driving behavior analysis system. Figure 4 A schematic diagram of the vehicle driver big data driving behavior analysis system is shown.

[0141] As shown in Figure 4 The vehicle driver big data driving behavior analysis system mainly includes a data acquisition unit, a data storage unit, a data analysis unit, and a data display unit. Data preprocessing operations such as data cleaning are performed between the data acquisition unit and the data storage unit. The data storage unit mainly includes a clickhouse / hbase database 401 and a Mysql database cluster 402.

[0142] The data acquisition unit acquires driving behavior data such as throttle opening, throttle opening, vehicle speed, rotation speed, acceleration, and lane changing frequency. These dynamic data are transmitted to the clickhouse / hbase database 401 via a T-box for storage.

[0143] The data analysis unit calls the data in the clickhouse / hbase database 401 for data cleaning, which is used for abnormal data identification and screening. After data cleaning, data repair is performed, which means that after data cleaning, according to different state types of abnormal data, corresponding algorithm prediction is performed, and data supplement is performed.

[0144] After data preprocessing is completed, the preprocessed data is transmitted to the clickhouse / hbase database 401 again and covers the previous data. The data storage period of the clickhouse / hbase database 401 is one month, and after one month, the new data automatically covers the old data.

[0145] The data analysis unit includes driving behavior analysis algorithm code, and the data analysis unit calls the preprocessed data in the clickhouse / hbase database 401 and analyzes it through the driving behavior analysis algorithm code. In the driving behavior analysis algorithm code: a plurality of driving behavior data are clustered and analyzed by using a Canopy clustering algorithm to obtain a group of "rough" data, and the group of "rough" data includes K cluster center points; then, based on the K cluster center points, a plurality of driving behavior data are clustered and analyzed by using a K-Means clustering algorithm to obtain a clustering result; finally, the clustering result is further analyzed to obtain a driving score of the driver. The driving score is stored in the Mysql database cluster 402.

[0146] The data display unit includes a vehicle terminal and a vehicle owner APP. If the driving score of the driver is lower than the set default value, the system automatically pushes an alarm message to the intelligent vehicle terminal and the vehicle owner APP to remind the driver that he is in dangerous driving.

[0147] Figure 5 is a structural block diagram of a vehicle alarm device provided by an exemplary embodiment of the present application, as shown in the figure, the device includes the following parts: Figure 6

[0148] The acquisition module 510 is configured to acquire a plurality of driving behavior data corresponding to a target vehicle in a historical time period, and the plurality of driving behavior data are used to indicate the driving behavior of a driver of the target vehicle in a driving process.

[0149] The analysis module 520 is configured to perform clustering analysis on the plurality of driving behavior data to obtain a target clustering result, and the target clustering result is used to represent a target driving style of the driver in the historical time period.

[0150] ​The analysis module 520 is further configured to determine a driving score corresponding to the driver based on the target clustering result, where the driving score is used to represent a driving safety risk of the driver under the target driving style.

[0151] The display module 530 is configured to display driving warning information on a vehicle terminal of the target vehicle if the driving score meets a preset warning condition.

[0152] Please refer to Figure 6 In some embodiments, the target clustering result includes a plurality of sub-clustering results, and each sub-clustering result corresponds to a different driving style; and the analysis module 520 includes:

[0153] The obtaining unit 521 is configured to obtain a sub-driving score corresponding to each of the plurality of sub-clustering results.

[0154] The determination unit 522 is configured to determine the driving score corresponding to the driver based on the sub-driving scores corresponding to the plurality of sub-clustering results.

[0155] In some embodiments, the obtaining unit 521 is configured to: take a preset driving score corresponding to the driving style indicated by the sub-clustering result as the sub-driving score corresponding to the sub-clustering result; or input the sub-clustering result into a driving score prediction model; and obtain the sub-driving score corresponding to the sub-clustering result by performing score prediction on the sub-clustering result through the driving score prediction model.

[0156] In some embodiments, the determination unit 522 is configured to: obtain a weight corresponding to each of the plurality of sub-clustering results; and obtain the driving score corresponding to the driver by performing weighted fusion on the plurality of sub-driving scores based on the weights corresponding to the plurality of sub-clustering results.

[0157] In some embodiments, the determination unit 522 is configured to: obtain a clustering number and a clustering variance corresponding to each of the plurality of sub-clustering results; obtain a stationarity feature corresponding to each of the plurality of sub-clustering results, where the stationarity feature is used to represent driving stability of the driver under the driving style indicated by the sub-clustering result; and determine the weight corresponding to each of the plurality of sub-clustering results based on the clustering number, the clustering variance, and the stationarity feature corresponding to each of the plurality of sub-clustering results.

[0158] In some embodiments, the determination unit 522 is configured to determine a candidate driving score corresponding to the driver based on the target clustering result; and the analysis module 520 further includes:

[0159] The matching unit 523 is configured to match the driving scene corresponding to the target vehicle with the driving style indicated by the target clustering result, to obtain a matching score, where the matching score is used to represent a matching degree between the driving scene and the driving style indicated by the target clustering result.

[0160] The adjusting unit 524 is configured to adjust the candidate reference score according to the matching score, to obtain the driving score corresponding to the driver.

[0161] In some embodiments, the display module 530 is configured to display the driving warning information on the vehicle terminal of the target vehicle in a case where the driving score is less than or equal to a preset driving score; and the apparatus further includes:

[0162] The sending module 540 is configured to send the driving warning information to a target terminal, where the target terminal includes another terminal connected to the vehicle terminal of the target vehicle.

[0163] In some embodiments, the analysis module 520 is configured to perform coarse-grained clustering analysis on the plurality of driving behavior data, to obtain a candidate clustering center; and perform fine-grained clustering analysis on the plurality of driving behavior data based on the candidate clustering center, to obtain the target clustering result.

[0164] In summary, the vehicle warning apparatus provided by the embodiments of the present application has the following advantages. On the one hand, the driving score of the driver of the vehicle is determined by analyzing the driving behavior of the driver, and if the driving score meets the preset warning condition, it indicates that the driving safety risk of the driver under the current driving style is high, and the driving warning information is displayed on the vehicle terminal of the vehicle, so as to prompt the driver that the driver is currently in dangerous driving, and remind the driver to adjust the driving behavior, thereby reducing the probability of traffic accidents caused by the driving style of the driver. On the other hand, the clustering analysis is performed on the plurality of driving behavior data, and the clustering analysis can classify similar driving behavior data into one category, so as to identify the main driving style of the driver, which is helpful to better understand the driving habit of the driver, thereby improving the accuracy of the driving score of the driver.

[0165] It should be noted that the vehicle warning apparatus provided by the above embodiments is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the vehicle warning apparatus and the vehicle warning method provided by the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be repeated here.

[0166] Figure 7A structural block diagram of a computer device 700 provided by an example embodiment of the present application is shown. The computer device 700 can be a portable mobile terminal, such as a smartphone, an in-vehicle terminal, a tablet computer, an MP3 player, an MP4 player, a notebook computer, or a desktop computer. The computer device 700 can also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal, or other names. The computer device 700 can also be a vehicle with an in-vehicle terminal, which is not limited in the present application.

[0167] Generally, the computer device 700 includes a processor 701 and a memory 702.

[0168] The processor 701 can include one or more processing cores, such as a 4-core processor, a 7-core processor, etc. The processor 701 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor 701 can also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 701 can be integrated with a GPU (Graphics Processing Unit) for rendering and drawing content required to be displayed by a display screen. In some embodiments, the processor 701 can also include an AI (Artificial Intelligence) processor for processing machine learning-related computing operations.

[0169] The memory 702 can include one or more computer-readable storage media. The memory 702 can also include high-speed random access memory and non-volatile, computer-readable storage media such as one or more magnetic disk storage devices, flash memory devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 702 is used to store at least one instruction for being executed by the processor 701 to implement the vehicle warning method provided by the method embodiments in the present application.

[0170] In some embodiments, the computer device 700 further includes one or more sensors. The one or more sensors include, but are not limited to, a proximity sensor, a gyroscope sensor, a pressure sensor.

[0171] The proximity sensor, also known as a distance sensor, is usually arranged on the front panel of the computer device 700. The proximity sensor is used to collect the distance between the user and the front of the computer device 700.

[0172] The gyroscope sensor can detect the body direction and rotation angle of the computer device 700. The gyroscope sensor can cooperate with the acceleration sensor to collect the 3D action of the user on the computer device 700. According to the data collected by the gyroscope sensor, the processor 701 can realize the following functions: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization when shooting, game control, and inertial navigation.

[0173] The pressure sensor can be arranged on the side frame of the computer device 700 and / or the lower layer of the display screen. When the pressure sensor is arranged on the side frame of the computer device 700, the grip signal of the user on the computer device 700 can be detected, and the left and right hand recognition or shortcut operation is performed by the processor 701 according to the grip signal collected by the pressure sensor. When the pressure sensor is arranged on the lower layer of the display screen, the operability control on the user interface is controlled by the processor 701 according to the pressure operation of the user on the display screen. The operability control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0174] In some embodiments, the computer device 700 further includes other component parts, which can be understood by those skilled in the art, Figure 7 The structure shown in the figure does not constitute a limitation on the computer device 700, and can include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0175] The embodiments of the present application also provide a computer device, which can be implemented as Figure 1The terminal or server or car shown. The computer device includes a processor and a memory, the memory stores at least one instruction, at least one program, a code set or instruction set, at least one instruction, at least one program, a code set or instruction set loaded and executed by the processor to implement the vehicle warning method provided by the above method embodiments.

[0176] Embodiments of the present application also provide a computer readable storage medium, which stores at least one instruction, at least one program, a code set or instruction set, which is loaded and executed by a processor to implement the vehicle warning method provided by the above method embodiments.

[0177] Embodiments of the present application also provide a computer program product or computer program, which includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to make the computer device execute the vehicle warning method described in any of the above embodiments.

[0178] Optionally, the computer readable storage medium can include: read only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), solid state disk (SSD, Solid State Drives) or optical disk, etc. Among them, the random access memory can include resistance random access memory (ReRAM, Resistance Random Access Memory) and dynamic random access memory (DRAM, Dynamic Random Access Memory). The above application embodiment serial number is only for description, not representing the pros and cons of the embodiment.

[0179] Those of ordinary skill in the art can understand that all or part of the steps of the above embodiments can be completed by hardware, or by programs instructing relevant hardware to complete, and the programs can be stored in a computer readable storage medium. The storage medium mentioned above can be a read only memory, a magnetic disk or an optical disk.

[0180] The above is only an optional embodiment of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A vehicle warning method characterized by, The method comprises: obtaining a plurality of driving behavior data corresponding to a target vehicle, the plurality of driving behavior data being used to indicate driving behavior of a driver of the target vehicle during driving; performing cluster analysis on the plurality of driving behavior data to obtain a target cluster result, the target cluster result being used to represent a target driving style of the driver; the target cluster result comprises a plurality of sub-cluster results, and different sub-cluster results correspond to different driving styles; obtaining a sub-driving score corresponding to each of the plurality of sub-cluster results; obtaining a cluster number, a cluster variance and a stationarity feature corresponding to each of the plurality of sub-cluster results, the stationarity feature being used to represent driving stability of the driver under the driving style indicated by the sub-cluster result, the cluster number of the sub-cluster result being positively correlated with a weight, the cluster variance of the sub-cluster result being negatively correlated with the weight, and the stationarity feature value of the sub-cluster result being positively correlated with the weight; determining a first weight based on the cluster number of the sub-cluster result; determining a second weight based on the cluster variance of the sub-cluster result; determining a third weight based on the stationarity feature value of the sub-cluster result; and calculating an average value of the first weight, the second weight and the third weight as the weight of the sub-cluster result; performing weighted fusion on the plurality of sub-driving scores based on the weight corresponding to each of the plurality of sub-cluster results to obtain a driving score corresponding to the driver, the driving score being used to represent driving safety risk of the driver under the target driving style; displaying driving warning information on a vehicle terminal of the target vehicle if the driving score meets a preset warning condition.

2. The method of claim 1, wherein, The method further comprises: inputting the sub-cluster result into a driving score prediction model; and performing score prediction on the sub-cluster result through the driving score prediction model to obtain a sub-driving score corresponding to the sub-cluster result. The method further comprises: determining a candidate driving score corresponding to the driver based on the target cluster result; 3. The method according to claim 1 or 2, characterized in that, matching a driving scene corresponding to the target vehicle with the driving style indicated by the target cluster result to obtain a matching score, the matching score being used to represent a matching degree between the driving scene and the driving style indicated by the target cluster result; adjusting the candidate driving score according to the matching score to obtain a driving score corresponding to the driver. The method further comprises: sending the driving warning information to a target terminal, the target terminal comprising another terminal connected to the vehicle terminal of the target vehicle.

4. The method according to claim 1 or 2, characterized in that, ​ ​ ​ ​ 5. The method according to claim 1 or 2, characterized in that, The clustering analysis on the plurality of driving behavior data comprises: performing coarse-grained clustering analysis on the plurality of driving behavior data to obtain candidate clustering centers; performing fine-grained clustering analysis on the plurality of driving behavior data based on the candidate clustering centers to obtain the target clustering result.

6. A vehicle warning device, characterized by The device comprises: an acquisition module configured to acquire a plurality of driving behavior data corresponding to a target vehicle in a historical time period, the plurality of driving behavior data being used to indicate driving behaviors of a driver of the target vehicle during driving; an analysis module configured to perform clustering analysis on the plurality of driving behavior data to obtain a target clustering result, the target clustering result being used to represent a target driving style of the driver, and the target clustering result comprising a plurality of sub-clustering results, different sub-clustering results corresponding to different driving styles; the analysis module is further configured to acquire a sub-driving score corresponding to each of the plurality of sub-clustering results, acquire a clustering number, a clustering variance and a stationarity feature corresponding to each of the plurality of sub-clustering results, the stationarity feature being used to represent driving stability of the driver under the driving style indicated by the sub-clustering result, the clustering number of the sub-clustering result being positively correlated with a weight, the clustering variance of the sub-clustering result being negatively correlated with the weight, and the stationarity feature value of the sub-clustering result being positively correlated with the weight, determine a first weight based on the clustering number of the sub-clustering result, determine a second weight based on the clustering variance of the sub-clustering result, determine a third weight based on the stationarity feature value of the sub-clustering result, calculate an average value of the first weight, the second weight and the third weight as the weight of the sub-clustering result, and perform weighted fusion on the plurality of sub-driving scores based on the weights corresponding to the plurality of sub-clustering results to obtain a driving score corresponding to the driver, the driving score being used to represent driving safety risk of the driver under the target driving style; a display module configured to display driving warning information on a vehicle-mounted terminal of the target vehicle if the driving score meets a preset warning condition.

7. A computer device, comprising: The computer device comprises a processor and a memory, the memory stores at least one program, the at least one program is loaded and executed by the processor to implement the vehicle warning method according to any one of claims 1 to 5.

8. A computer readable storage medium, the storage medium stores at least one program, the at least one program is loaded and executed by a processor to implement the vehicle warning method according to any one of claims 1 to 5.

9. A computer program product, characterised in that, The computer program is executed by a processor to implement the vehicle warning method according to any one of claims 1 to 5.

Images