Driver portrait generation method and device, computer device, and medium

Abstract

Embodiments of the present application provide a driver portrait generation method and device, computer equipment and a medium, and relate to the technical field of vehicle driving, wherein the method comprises: obtaining the identity information of a driver when the vehicle is in a starting state through a vehicle terminal; collecting driving-related data of the driver during driving of the vehicle through the vehicle terminal; generating record data from the identity information of the driver, the unique identifier of the vehicle and the driving-related data collected at the same time; obtaining the travel data of the driver according to the record data, wherein each piece of travel data comprises all record data of the same driver continuously driving the same vehicle; and according to the driving behavior information of the driver obtained from the travel data, generating the driving behavior portrait of the driver. The scheme can improve the accuracy of the driver portrait.

Description

Technical Field

[0001] This invention relates to the field of vehicle driving technology, and in particular to a method, apparatus, computer equipment, and medium for generating a driver profile. Background Technology

[0002] Currently, the method for generating a driver's driving behavior profile involves identifying the driver's behavioral information that matches the preset alarm type based on the driving data collected during the driver's driving process; identifying the warning information associated with the behavioral information; statistically analyzing the warning information attributed to the driver; and generating a driver profile.

[0003] However, the method for generating the driver's driving behavior profile has a flaw: it cannot determine whether the driving data is from the same driver's driving process. This can lead to the generation of a driving behavior profile for a particular driver based on driving-related data from different drivers, thus affecting the accuracy of the driving behavior profile. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method for generating a driver profile to solve the technical problem of inaccurate driver profiles in the prior art. The method includes:

[0005] When the vehicle is determined to be running via the in-vehicle terminal, the driver's identity information is obtained.

[0006] The vehicle-mounted terminal collects driving-related data from the driver while driving the vehicle.

[0007] Generate record data by combining the driver's identity information, the vehicle's unique identifier, and the driving-related data collected at the same time.

[0008] The driver's trip data is obtained based on the recorded data, and each trip data entry includes all the recorded data of the same driver driving the same vehicle consecutively;

[0009] Based on the trip data, the driver's driving behavior information is statistically analyzed, and a driving behavior profile of the driver is generated based on the driving behavior information.

[0010] This invention also provides a driver profile generation apparatus to address the technical problem of inaccurate driver profiles in the prior art. The apparatus includes:

[0011] The identity information acquisition module is used to acquire the driver's identity information when the vehicle is determined to be in a running state by the vehicle terminal;

[0012] The driving data acquisition module is used to collect driving-related data from the driver while driving the vehicle through the vehicle terminal.

[0013] The data generation module is used to generate record data by combining the driver's identity information, the vehicle's unique identifier, and the driving-related data collected at the same time.

[0014] The trip data segmentation module is used to obtain the driver's trip data based on the recorded data, and each trip data includes all the recorded data of the same driver driving the same vehicle continuously;

[0015] The profile generation module is used to collect driving behavior information of the driver based on the trip data, and generate a driving behavior profile of the driver based on the driving behavior information.

[0016] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for generating any of the driver profiles, thereby solving the technical problem of inaccurate driver profiles in the prior art.

[0017] This invention also provides a computer-readable storage medium storing a computer program that executes any of the above-described methods for generating driver profiles, in order to solve the technical problem of inaccurate driver profiles in the prior art.

[0018] Compared with the prior art, the beneficial effects achieved by at least one of the above-mentioned technical solutions adopted in the embodiments of this specification include at least the following: When the vehicle is determined to be in a running state, the driver's identity information is obtained, realizing the dynamic association or binding of the vehicle with the driver's identity information; driving-related data is collected during the driver's operation of the vehicle; the driving-related data collected at the same time, the driver's identity information, and the vehicle's unique identifier are used to generate record data; and the driver's trip data is obtained based on the record data. Furthermore, the real-time association of driving-related data collected during driving with the driver's identity information and the vehicle's unique identifier is achieved, effectively ensuring that the driver's identity information and... The strong correlation between the driver's own vehicle information and the driver's own driving-related data allows for the acquisition of the driver's trip data. This trip data includes the recorded data of the same driver continuously driving the same vehicle. In other words, the driver's trip data is the relevant data generated by the driver (or the driver alone) continuously driving the same vehicle. Based on the driver's trip data, the driver's driving behavior information is statistically analyzed to generate a driver's driving behavior profile. This ensures that for each driver, a profile can be generated based on the relevant data of each driver continuously driving the same vehicle. Compared with existing technologies, this avoids the problem of using data that includes non-drivers to generate driver profiles, which helps to improve the accuracy of driver profiles. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a method for generating a driver profile according to an embodiment of the present invention;

[0021] Figure 2 This is a flowchart illustrating the binding of driver and vehicle information according to an embodiment of the present invention;

[0022] Figure 3 This is another flowchart of driver and vehicle information binding provided by an embodiment of the present invention;

[0023] Figure 4 This is a flowchart of a stroke segmentation process provided in an embodiment of the present invention;

[0024] Figure 5 This is a flowchart of a user profiling process provided in an embodiment of the present invention;

[0025] Figure 6 This is a flowchart illustrating a method for generating the above-described driver profile, provided by an embodiment of the present invention.

[0026] Figure 7 This is a structural block diagram of a computer device provided in an embodiment of the present invention;

[0027] Figure 8 This is a structural block diagram of a driver portrait generation device provided in an embodiment of the present invention. Detailed Implementation

[0028] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0029] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] In this embodiment of the invention, a method for generating a driver profile is provided, such as... Figure 1 As shown, the method includes:

[0031] Step S101: When the vehicle is determined to be in a running state by the vehicle terminal, obtain the driver's identity information;

[0032] Step S102: Collect driving-related data from the driver while driving the vehicle via the vehicle-mounted terminal;

[0033] Step S103: Generate record data by combining the driver's identity information, the vehicle's unique identifier, and the driving-related data collected at the same time;

[0034] Step S104: Obtain the driver's trip data based on the recorded data, wherein each trip data entry includes the recorded data of the same driver driving the same vehicle consecutively;

[0035] Step S105: Calculate the driver's driving behavior information based on the trip data, and generate the driver's driving behavior profile based on the driving behavior information.

[0036] Depend on Figure 1 As shown in the process, in this embodiment of the invention, when the vehicle is determined to be in a running state via the in-vehicle terminal, the driver's identity information is obtained. This dynamically associates or binds the vehicle with the driver's identity information, and collects driving-related data during the driver's operation. The driving-related data, the driver's identity information, and the vehicle's unique identifier collected at the same time are used to generate record data. Based on this record data, the driver's trip data is obtained. This further enables real-time association between the driving-related data collected during driving and the driver's identity information and the vehicle's unique identifier, effectively ensuring the establishment of a connection between the driver's identity information and the vehicle being driven. The system establishes a strong correlation between vehicle information and the driver's own driving-related data to obtain the driver's trip data. This trip data includes the recorded data of the same driver continuously driving the same vehicle. In other words, the driver's trip data is the relevant data generated by the driver (or the driver alone) continuously driving the same vehicle. Based on the driver's trip data, the system statistically analyzes the driver's driving behavior information to generate a driver's driving behavior profile. This ensures that for each driver, a profile can be generated based on the relevant data of each driver continuously driving the same vehicle. Compared with existing technologies, this avoids the problem of using data that includes non-drivers to generate driver profiles, which helps to improve the accuracy of driver profiles.

[0037] In practical implementation, the inventors of this application discovered that for drivers of fleet operation vehicles, the vehicle driven for each mission may not be the same. This can lead to the same driver having driving data in different vehicles. Furthermore, there may be scenarios where two drivers are assigned to the same transport mission, resulting in different drivers having driving data in the same vehicle. If the existing technology only collects driving data during the driving process based on the vehicle, without dynamically binding the driver's identity information with the driving data and vehicle information in real time, the driving data collected based on the vehicle may be from multiple different drivers. That is, in many-to-many vehicle-driver relationships, it is impossible to distinguish whether the collected driving data belongs to the same driver. Generating a driver profile based on such driving data cannot pinpoint the specific driver or accurately generate a profile for a particular driver. To solve this problem, the inventors of this application proposed the aforementioned driver profile generation method, which dynamically binds vehicle information with driver identity information in real time, and binds driving data collected at the same time with vehicle information and driver identity information. This allows for the clear and distinct identification of each driver's continuous driving data in the same vehicle, enabling the accurate generation of a profile for each driver based on their individual driving data. The above method for generating driver profiles can be used to generate profiles of fleet drivers.

[0038] In practice, the aforementioned vehicle-mounted terminal can be implemented through devices such as a Tbox or a standard marking machine on the vehicle.

[0039] In practical implementation, in order to accurately determine the vehicle's startup status and dynamically bind vehicle information with the driver's identity information, in this embodiment, the process of the on-board terminal determining that the vehicle is in a startup state can be implemented through the following method:

[0040] The CNA signal of the vehicle is acquired, and the vehicle is determined to be in the start state based on the CNA signal.

[0041] Specifically, the vehicle's CAN signal can be monitored in real time to determine whether the vehicle is running. For example, the CAN signal may contain vehicle status information that can be seen on the dashboard or not, such as the acquisition time, vehicle speed, ACC status, and GPS positioning information (which may include longitude, latitude, and direction of travel). The process of determining whether the vehicle is running based on the CAN signal can be implemented using the vehicle speed data. If the previously acquired vehicle speed was 0, and the currently acquired vehicle speed is greater than 0, then the vehicle is considered to be running; if the currently acquired vehicle speed is also 0, then the vehicle is not running. After the vehicle starts, the onboard terminal will power on, and during its initialization, it can obtain driver information. Alternatively, the ACC status (i.e., the ignition key's on / off state) can also be used to determine whether the vehicle is running.

[0042] In practical implementation, to achieve dynamic and accurate binding of vehicle information with driver identity information, this embodiment can obtain driver identity information through different methods. For example, it can obtain driver identity information through an NFC card reader; however, this method significantly increases hardware costs. To reduce costs and accurately obtain identity information, this application proposes using image acquisition devices such as DMS cameras or cameras to capture images of the driver, and then obtaining driver identity information based on the images. For example...

[0043] Acquire images of the driver (which may be a full-body image of the driver or a partial image including certain biometric features), and obtain the driver's biometric features from the images;

[0044] Based on the pre-stored correspondence between biometric features and identity information, the driver's identity information is determined according to the collected biometric features.

[0045] Specifically, the process of determining the driver's identity information based on the pre-stored correspondence between biometric features and identity information can be implemented on the vehicle terminal or through the server. For example, after the driver's image is captured, the biometric features of the captured image are compared with the pre-stored images or biometric features of each driver (i.e., the pre-stored correspondence between biometric features and identity information) through the vehicle terminal or the server to obtain the identity information of the driver corresponding to the successfully matched biometric feature, i.e., the current driver's identity information. The vehicle terminal stores the acquired driver's identity information, thereby binding the driver's identity information with the vehicle.

[0046] Specifically, the aforementioned biometric features can be facial features, iris, fingerprints, etc.

[0047] For example, the specific process of binding driver's identity information with vehicle information using facial recognition is as follows: Figure 2 As shown, the following steps may be included:

[0048] S201: When the vehicle terminal starts up, it first performs an initialization operation and clears the historically saved driver information.

[0049] S202: Monitors whether the vehicle has just started or started from idle. After the vehicle starts, it counts the number of GPS measurements. When the count is 0, it is determined that the vehicle has just started. When the vehicle speed measured in the last measurement was 0 and the vehicle speed measured in the current measurement is greater than 0, it is determined that the vehicle has started moving.

[0050] S203: The vehicle terminal will capture a frame image from the DMS driver fatigue camera;

[0051] S204: Request the server interface based on the face image captured in S203 to obtain the driver's identity information. That is, the server will compare the captured face image with the face information in the driver information database according to the pre-built face comparison service. If the comparison is successful, the server will return the matched driver's identity information to the vehicle terminal; otherwise, it will return failure.

[0052] S205: When the driver's identity information is obtained in S204, the vehicle terminal will save the driver's identity information locally. If the record does not exist, it will be created. If the driver's identity information already exists, the newly created driver's identity information will overwrite the existing driver's identity information. If obtaining the driver's identity information fails, the driver's identity information that already exists locally will be deleted.

[0053] S206: The vehicle terminal periodically collects driving-related data and merges it into a single record before sending it to the server. This data includes collection time, vehicle speed, ACC status, vehicle GPS positioning data (e.g., longitude, latitude, and direction of travel), ADAS alarm data (including alarm start time and type), DMS alarm data (including alarm start time and type), and driver identity information (e.g., a unique driver identifier). When driver identity information is empty, or when server-side face verification fails and the vehicle terminal's cached driver identity information is empty, the driver identity information is set to empty in the record. Similarly, when no alarm information exists, the alarm information is set to empty in the record. Specifically, within each data collection cycle, the latest CAN data is used as the collected data. Multiple ADAS and DMS alarm records may exist within the same collection cycle.

[0054] For example, CAN data can be collected and reported every 5 seconds. Within this reporting period, there may be multiple ADS and DMS alarm messages. The alarm messages will be associated with the latest CAN data to form a record data report to the server.

[0055] In practical implementation, to reduce costs and ensure accurate and convenient acquisition of driver identity information during the process of binding driver identity information with vehicle information, this embodiment proposes using Bluetooth tags to acquire driver identity information. Specifically, Bluetooth tags with on / off or status indicators are used to bind driver identity information with vehicle information. For example,

[0056] The Bluetooth tag information and Bluetooth signal data of the vehicle's Bluetooth device are collected, wherein each driver wears a unique Bluetooth tag;

[0057] The Bluetooth signal with the strongest signal strength is determined from the signal data, and the Bluetooth tag information corresponding to the Bluetooth signal with the strongest signal strength is determined.

[0058] Based on the pre-stored correspondence between Bluetooth tag information and driver identity information, the driver's identity information corresponding to the determined Bluetooth tag information is obtained.

[0059] In practice, based on the Bluetooth tag information and Bluetooth signal data of the Bluetooth device, after determining the Bluetooth tag information corresponding to the Bluetooth signal with the strongest signal strength, the determined Bluetooth tag information can be matched with the pre-stored correspondence between the Bluetooth tag information and the driver's identity information through the vehicle terminal or server to obtain the driver's identity information corresponding to the determined Bluetooth tag information.

[0060] In practical implementation, Bluetooth functionality is a standard feature in many vehicle infotainment systems during the development of vehicle electronics and information technology. When the driver equips and activates the electronic tag, the tag periodically broadcasts agreed-upon identification signal data. When there are two drivers, the backup driver needs to turn off the Bluetooth tag or switch the Bluetooth tag's broadcast information from driving mode to rest mode. For example... Figure 3 As shown below, the process of binding driver identification information to vehicle information using a Bluetooth tag with a switch may include the following steps:

[0061] S301: When the vehicle terminal starts up, it first performs an initialization operation and clears the historically saved driver information.

[0062] S302: Monitors whether the vehicle has just started or started from idle. After the vehicle starts, it counts the number of GPS measurements. When the count is 0, it determines that the vehicle has just started. When the vehicle speed measured in the last measurement was 0 and the vehicle speed measured in the current measurement is greater than 0, it determines that the vehicle has started moving.

[0063] S303: The vehicle terminal scans a list of Bluetooth devices, which includes the identification information of each Bluetooth tag and its corresponding Bluetooth signal data, and filters out the identification information of the Bluetooth devices equipped by the fleet drivers based on the broadcast information.

[0064] S304: Sort the scanned Bluetooth device list according to Bluetooth signal strength. The vehicle terminal defaults to the Bluetooth device equipped by the driver at the front of the vehicle having the strongest signal strength. Traverse the Bluetooth device list to determine the identification information of the Bluetooth tag with the strongest signal strength. Based on the device MAC information, call the server interface to obtain the driver's identity information bound to the identification information of the determined Bluetooth tag.

[0065] S305: When S304 obtains driver identity information, it will save the driver identity information locally. If the record does not exist, it will be created; if driver identity information already exists, it will be overwritten. If obtaining driver identity information fails, the driver identity information that already exists locally will be deleted.

[0066] S306: The vehicle terminal periodically collects driving-related data such as vehicle speed, ACC status, vehicle GPS positioning data (e.g., longitude, latitude, and direction of travel), ADAS alarm data (e.g., alarm start time and alarm type), DMS alarm data (e.g., alarm start time and alarm type), collection time, and driver identity information (e.g., driver's unique identifier). It then merges the driving-related data for a given period into a single record and sends it to the server. When the driver's identity information is empty, or when the server-side face comparison fails and the vehicle terminal's cached driver's identity information is empty, the driver's identity information is set to empty in the record. Similarly, when no alarm information exists, the alarm information is set to empty in the record.

[0067] In practice, during the process of the driver driving the vehicle, the driving-related data collected can include any driving-related data, such as the vehicle's GPS positioning information, vehicle speed, ACC status, collection time (e.g., the time point of data collection), and alarm information (such as the alarm start time, alarm type, etc. of various driving-related alarms, for example, ADAS alarm data, DMS alarm data, etc.).

[0068] In practice, after collecting the aforementioned driving-related data during the driver's operation, record data can be generated using the driver's identity information, the vehicle's unique identifier, and the driving-related data collected at the same time. This can be achieved by generating a single record data entry from the driving-related data collected at each moment during the driver's continuous driving process, along with the driver's identity information and the vehicle's unique identifier. Alternatively, a record data entry can be generated from the driving-related data collected at each moment within a preset second cycle during the driver's continuous driving process, along with the driver's identity information and the vehicle's unique identifier. In other words, at least one record data entry can be obtained throughout the driver's continuous driving process. For example, each record data entry can include multiple ADAS and DMS alarm messages. These alarm messages are associated with the latest CAN data to generate a single record data entry. CAN data can be collected every 5 seconds.

[0069] In practice, after obtaining the above-mentioned recorded data, the recorded data can be divided into trip data for each driver through an in-vehicle terminal or other devices such as a server outside the in-vehicle terminal. The trip data includes the recorded data of the same driver driving the same vehicle continuously.

[0070] In practice, the recorded data can be divided into trip data for each driver using other devices such as a server in addition to the vehicle terminal. For example, at least one trip data of the driver within the duration of the first preset period can be obtained according to the first preset period.

[0071] In practice, to accurately segment the trip data of each driver, this embodiment uses the following method to obtain the driver's trip data based on the recorded data:

[0072] The recorded data is grouped according to the unique identifier of the vehicle to obtain a recorded data group corresponding to each vehicle; the recorded data in the recorded data group corresponding to each vehicle is sorted according to the collection time; in the recorded data group corresponding to each vehicle, the first duration of continuous driving of the same vehicle by the same driver is determined; the recorded data within the first duration is determined as a trip data of the same driver.

[0073] In practical implementation, to further accurately and effectively determine the trip data of each driver, this embodiment proposes a method for determining the first duration of continuous driving of the same vehicle by the same driver within the recorded data group corresponding to each vehicle. For example,

[0074] In each vehicle's corresponding data group, each data record is traversed, and the data content of the current data record is used to determine whether the current data record was collected when the vehicle was in the starting state.

[0075] Determine whether the vehicle already has trip data. If so, the trip data that is closest to the collection time of the current recorded data among the existing trip data is regarded as the current trip data. If not, the current recorded data is created as the current trip data of the vehicle, and the process continues to traverse the next recorded data.

[0076] When the vehicle already has trip data, if the time difference between the latest collection time of the current trip data and the collection time of the current record data is less than a preset threshold, and the driver identity information in the current trip data is consistent with the driver identity information in the current record data, then the current record data is added to the current trip data, and the process continues to traverse the next record data; otherwise, the process of dividing the current trip data ends, the latest collection time of the current trip data is regarded as the end time of the first duration, and the earliest collection time of the current trip data is regarded as the start time of the first duration.

[0077] Specifically, each trip data includes all recorded data within a first period of continuous driving of the same vehicle by the same driver.

[0078] In specific implementation, such as Figure 4 As shown, dividing the recorded data into trip data for each driver via the server can include the following steps:

[0079] S401: Load the recorded data, including vehicle trajectory and alarm data, reported by the vehicle terminal according to the preset cycle (i.e. the first preset cycle mentioned above).

[0080] S402: Group the recorded data according to the unique vehicle identifier to obtain a record data group corresponding to each vehicle, and sort the recorded data in each record data group according to the data collection time.

[0081] S403: Traverse each record data group and process the trip data of each vehicle.

[0082] S404: When traversing the data list (i.e., recorded data) of a certain vehicle in each recorded data group, determine whether the vehicle is in the starting state at the time of data collection, i.e., whether the vehicle's ACC status is in the starting state. If not, the process will proceed to step S408 to end the current vehicle's trip data division process. If yes, proceed to step S405.

[0083] S405: When the condition in step S404 is met, determine whether the trip data for this vehicle is cached. If not, and the trip data for this vehicle does not exist, proceed to step S406 to create and initialize the trip data for this vehicle. The trip data includes the vehicle's unique identifier VIN, the current driver's information (driverid), the trip start time, the start location, and information about the vehicle's latest data point. If the trip data for this vehicle already exists, proceed to step S407.

[0084] S406: Create and initialize the trip data for this vehicle.

[0085] S407: When the vehicle's trip data already exists, compare the collection time of the current data point (i.e., the current recorded data) with the collection time of the latest data point on the trip (i.e., the latest collection time in the current trip data) to obtain the time difference between the two, and determine whether the trip is continuous. If the time difference between the two is less than the preset threshold of 30 minutes, determine whether the driver information has changed, that is, determine whether the driver information of the current data point (i.e., the driver's identity information) is consistent with the driver information of the latest data point on the trip. If yes, proceed to step S408. If no, when the condition is not met, proceed to S409 and end the vehicle's trip information.

[0086] S408: When the S407 condition is met, calculate the mileage and duration between the two points using the current data and the latest information of the trip, and accumulate them into the total mileage and total duration of the trip. When there is alarm data, the number of various alarms in the trip will be accumulated.

[0087] S409: When conditions S404 or S407 are not met, the process of dividing the vehicle's current trip data will end, the current trip data will be written to the database, and the cached data of the current trip data will be cleared.

[0088] In practice, after obtaining the driver's trip data, the driver's driving behavior information can be statistically analyzed based on the trip data, thereby generating a driver profile. For example, according to a first preset period, the total driving mileage of the driver can be calculated based on the vehicle's location information in each of the driver's trip data within the first preset period.

[0089] Based on the vehicle alarm information in each of the driver's trip data within the first preset period, the total number of alarms for each alarm indicator of the driver is counted.

[0090] Based on the driver's total driving mileage and the total number of alarms for each alarm indicator, a driving behavior profile of the driver within the first preset period is generated.

[0091] In specific implementation, based on the driver's trip data within the first preset period, the driving time is calculated according to the collection time in each trip data, and the driving time of each trip data is summed to obtain the driver's total driving time; similarly, the driving mileage is calculated according to the location information in each trip data, and the driving mileage of each trip data is summed to obtain the driver's total driving mileage; similarly, the number of alarms for each alarm indicator is calculated according to the alarm information in each trip data, and the number of alarms for each alarm indicator in each trip data is summed to obtain the total number of alarms for each alarm indicator of the driver.

[0092] In practical implementation, the aforementioned alarm indicators can be various alarm information related to driving the vehicle. For example, lane departure warnings, vehicle monitoring alarms, and forward collision warnings can be obtained from ADAS alarm information in the trip data, and the alarm frequency can be determined. Similarly, DMS alarm information in the trip data can be used to obtain alarm indicators such as closing eyes, looking down, yawning, looking around, making phone calls, and smoking, and the alarm frequency can be determined. Furthermore, alarm indicators such as rapid acceleration, speeding, rapid deceleration, sharp turns, and other alarms can be obtained from data collection time (time), vehicle speed (speed), and driving direction information in the trip data, and the alarm frequency can be determined. For instance, timed CAN data includes collection time (time), vehicle speed (speed), and driving direction information (direction).

[0093] Rapid acceleration and rapid deceleration are determined in the following ways:

[0094] The acceleration g is calculated based on the acquisition time (time) and vehicle speed (speed) from two consecutive CAN data acquisitions, where g = (speed2 - speed1) / (time2 - time1). When the acceleration is greater than the threshold a for n consecutive times, a rapid acceleration alarm is generated; when the acceleration is less than the threshold b for n consecutive times, a rapid deceleration alarm is generated.

[0095] A sharp turn is determined in the following way:

[0096] The rate of change of driving direction, turnRate, is calculated based on the driving direction information from two consecutive CAN data collections. turnRate = (direction2 - direction1) / (time2 - time1). When the rate of change of driving direction is greater than the threshold c, a sharp turn alarm is generated.

[0097] In practice, once the driver's driving behavior information is obtained, a driving behavior profile of the driver can be generated. To further improve the accuracy and effectiveness of the profile, this embodiment proposes a method for generating the driver's driving behavior profile within the first preset period based on the driver's total driving mileage and the total number of alarms for each alarm indicator. For example...

[0098] Based on the total driving mileage and the total number of alarms for each alarm indicator, calculate the number of alarms per 100 kilometers for each alarm indicator;

[0099] Calculate the score for each alarm indicator based on the number of alarms per 100 kilometers.

[0100] Calculate the weight of each alarm indicator based on the total number of alarms for each alarm indicator;

[0101] The driver's overall safety score is calculated based on the weights and scores of all warning indicators for the driver.

[0102] The driver's alarm score for each type is calculated based on the weight of each alarm indicator included in each alarm type and the score of the corresponding alarm indicator.

[0103] Based on the driver's overall safety score, the score for each type of alarm, and the score for each alarm indicator, a driving behavior profile of the driver within the first preset period is generated.

[0104] In practice, when generating a profile, the overall safety score can be used as the primary comprehensive indicator, and the alarm scores of various alarms can be used as the secondary comprehensive indicator. Various alarms can include fatigue driving alarms, handling alarm scores, stability alarms, distraction alarms, etc. Fatigue driving alarms can include alarm indicators such as closing eyes, looking down, and yawning. Handling alarms can include alarm indicators such as lane departure indicators, vehicle monitoring alarms, and forward collision alarms. Stability alarms can include alarm indicators such as rapid acceleration, rapid deceleration, sharp turns, and speeding. Distraction alarms can include alarm indicators such as looking left and right, making phone calls, and smoking.

[0105] In practice, the score for each alarm indicator can be calculated using the following formula based on the number of alarms per 100 kilometers:

[0106] score=(1-P(K))*100.0,

[0107] Wherein, score is the score of the alarm indicator, P(k) is the cumulative probability of the alarm indicator according to the Poisson distribution, P(k)=(λ^k)*(e^(-λ)) / k!, λ is the average of the total number of alarms per 100 kilometers for the alarm indicator for multiple drivers within the first preset period, and k is the total number of alarms per 100 kilometers for the alarm indicator.

[0108] For example, taking the alarm indicator of closed eyes as an example to calculate the score, the first preset period is October 2022 as an example.

[0109] 1. Statistical analysis of the total number of warnings per 100 kilometers for each driver in October when their eyes are closed.

[0110] 2. Calculate the average λ of the total number of alarms per 100 kilometers for multiple drivers (e.g., multiple drivers in a fleet) in October.

[0111] 3. The total number of times driver A's alarms were triggered while his eyes were closed during October was k.

[0112] 4. Driver A's score for the warning indicator of closed eyes is:

[0113] score=(1-P(K))*100.0=(1-(λ^k)*(e^(-λ)) / k!)*100.0,Poisson distribution cumulative probability P(k)=(λ^k)*(e^(-λ)) / k! .

[0114] In practice, the weight of each alarm indicator can be calculated using the following formula based on the total number of alarms for each indicator:

[0115]

[0116] Where, weight j Let be the weight of the j-th alarm indicator, m be the total number of alarm indicators, and d be the weight of the j-th alarm indicator. j Let be the difference coefficient of the j-th alarm indicator. P ij Let be the weight of the j-th alarm indicator for the i-th driver among multiple drivers. x ij Let be the total number of alarms for the j-th alarm indicator, and n be the total number of drivers.

[0117] In specific implementation, such as Figure 5 As shown, the process of generating a driving behavior profile for each driver based on their trip data may include the following steps:

[0118] S501: Load trip data according to the preset statistical period (i.e. the first preset period mentioned above), and filter out trip data with empty driver information. The duration of the preset statistical period can be the last 7 days, the last 30 days, or it can be determined by natural month, natural week, or the duration since operation.

[0119] S502: Based on the driver's unique identifier (driverid), the data for each driver is grouped and statistically analyzed, summarizing each driver's total driving mileage, total driving time, total number of warnings for various warning indicators, and the number of warnings per 100 kilometers for each warning indicator. The number of warnings per 100 kilometers = total number of warnings / total driving mileage (in kilometers) * 100.0. The primary indicator is the overall safety score. Secondary indicators include fatigue-related warning scores, handling-related warning scores, stability-related warning scores, and distraction-related warning scores. Tertiary indicators are scores for various specific warning indicators. Specifically, handling-related warnings include lane departure warnings, vehicle collision warnings, etc.; stability-related warnings include rapid acceleration, rapid deceleration, sharp turns, speeding, etc.; driver fatigue-related warnings include closing eyes, looking down, yawning, etc.; and distraction-related warnings include looking around, making phone calls, smoking, etc.

[0120] S503: Calculate the maximum, minimum, mean, and standard deviation of the number of alarms per 100 kilometers for each alarm indicator. Calculate the weight of each alarm indicator using the entropy weight method. Specifically, normalize the range of the number of alarms per 100 kilometers for each alarm indicator: positive alarm indicator = (current value - minimum value) / (maximum value - minimum value); negative alarm indicator = (maximum value - current value) / (maximum value - minimum value). Then, iterate through and calculate the difference coefficient and weight (weigh) of each alarm indicator. Finally, verify the correctness of the weights, i.e., whether the sum of the weights of all alarm indicators is 1.

[0121] S504: Within the same statistical time period, the number of alarms per unit mileage can be described by a Poisson distribution. Within the same statistical time period and the same driving mileage, for negative alarm indicators, fewer alarms result in higher scores. For positive alarm indicators, more alarms result in higher scores. The scores for each basic indicator are calculated using the cumulative probability of the Poisson distribution. The cumulative probability P(k) of each driver's current alarm indicator is P(k) = (λk) / ( ...

[0122] ^k)*(e^(-λ)) / k! , where λ is the average of the total number of alarms per 100 kilometers for this alarm indicator for multiple drivers, and k is the total number of alarms per 100 kilometers for this alarm indicator; the score of this alarm indicator is (1-P(K))*100.0.

[0123] S505: Calculate the overall safety score for each driver's primary indicators. This involves iterating through all warning indicator scores (calculated in step S504), multiplying them by their respective weights (calculated in step S503), and summing the results to obtain the total overall safety score. The secondary indicators are the scores for fatigue driving warnings, which consist of basic indicators such as closing eyes, looking down, and yawning.

[0124] score(fatigue driving warning score) = (score(eyes closed)*weight(eyes closed)+score(head down)*weight(head down)+score(yawning)*weight(yawning)) / (weight(eyes closed)+weight(head down)+weight(yawning)).

[0125] The handling warning score is composed of basic indicators such as lane departure warning, vehicle-to-vehicle monitoring warning, and forward collision warning. The stability warning score is composed of indicators such as rapid acceleration, rapid deceleration, sharp turning, and speeding. The distraction warning score is composed of indicators such as looking left and right, making phone calls, and smoking. The specific calculation process is the same as the calculation formula for the fatigue driving warning score above.

[0126] S506: Based on the statistical data from step S502 and the score data for each alarm indicator from step S505, specifically including the total driving mileage, total driving time, total number of alarms for each alarm indicator, number of alarms per 100 kilometers for each alarm indicator, and the score for each alarm indicator, as well as the results of secondary indicators such as fatigue score, handling score, stability score, distraction score, and primary comprehensive indicator, a driver's driving behavior profile is drawn.

[0127] In practice, the above method for generating driver profiles can be achieved through interaction between the vehicle terminal and the server. For example, after the vehicle terminal collects the driver's recorded data, it sends the recorded data to the server, which then divides the recorded data into trip data for each driver and uses the trip data to collect driving behavior information for each driver, thereby generating a driving behavior profile for each driver.

[0128] In practice, the aforementioned server can not only divide the recorded data into trip data for each driver, but also run pre-built management services, such as protocol parsing service, vehicle information management, driver information management that supports RFID readers to read identity cards and enter them into the system, facial feature extraction service, facial comparison service, and task scheduling service.

[0129] In practice, the method for generating the aforementioned driver profile involves an interaction between the in-vehicle terminal and the server, as follows: Figure 6 As shown, it includes the following steps:

[0130] S601: Vehicle and driver information are dynamically bound. The vehicle terminal monitors the vehicle's CAN signal in real time. When the vehicle starts or starts from idle, it will perform facial recognition through the pre-set monitoring camera in the vehicle to obtain the driver's facial identity information. Based on the facial identity information obtained by facial recognition, it calls the server interface to compare with the driver's identity information entered by the server. If the comparison is successful, the driver's identity information is returned to the vehicle terminal. If the comparison fails, a failure message is returned.

[0131] S602: The vehicle terminal collects CAN data such as vehicle GPS location and vehicle status, as well as alarm data such as ADAS and DMS, according to a fixed period. It then periodically generates and reports the CAN data and alarm data, along with the vehicle's unique identification number (VIN), SIM card information, and driver information, to the server in real time, based on the collection time.

[0132] S603: After receiving the data, the server stores it. Every morning at midnight, it loads the previous day's trajectory data, segments the trip data, and calculates key metrics. The trajectory data is grouped by vehicle and sorted by GPS collection time. When a vehicle starts, it initializes and begins its trip, accumulating trip duration, mileage, and various alarm counts. The trip ends when the vehicle is turned off or driver information changes. Each trip record includes a unique vehicle identifier and driver identifier, start and end time and locations, total mileage, total duration, and the number of ADAS and DMS alarms during the trip.

[0133] S604: Statistics are compiled based on the number of warnings per 100 kilometers for each driver warning indicator according to a preset statistical period, along with the indicator weights. Finally, scores for each level of indicator are calculated. The first-level indicator is the overall safety score; the second-level indicators are fatigue score, handling score, stability score, and distraction score. The third-level indicators are scores for various specific warning types, specifically categorized as follows: basic handling score indicators include lane departure warnings, vehicle detection warnings, and forward collision warnings; basic stability score indicators include rapid acceleration, rapid deceleration, sharp turns, and speeding; basic driver fatigue indicators include closing eyes, looking down, and yawning; and basic distraction indicators include looking around, making phone calls, and smoking.

[0134] In this embodiment, a computer device is provided, such as... Figure 7 As shown, it includes a memory 701, a processor 702, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for generating any of the driver profiles.

[0135] Specifically, the computer device can be a computer terminal, a server, or a similar computing device.

[0136] In this embodiment, a computer-readable storage medium is provided, which stores a computer program that performs any of the above-described methods for generating driver profiles.

[0137] Specifically, computer-readable storage media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0138] Based on the same inventive concept, this invention also provides a driver profile generation apparatus, as described in the following embodiments. Since the principle of the driver profile generation apparatus in solving the problem is similar to that of the driver profile generation method, the implementation of the driver profile generation apparatus can refer to the implementation of the driver profile generation method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0139] Figure 8 This is a structural block diagram of a driver portrait generation device according to an embodiment of the present invention, such as... Figure 8 As shown, the device includes:

[0140] The identity information acquisition module 801 is used to acquire the driver's identity information when the vehicle is in the starting state, as determined by the vehicle terminal.

[0141] The driving data acquisition module 802 is used to collect driving-related data of the driver driving the vehicle through the vehicle terminal;

[0142] The data generation module 803 is used to generate record data by combining the driver's identity information, the vehicle's unique identifier, and the driving-related data collected at the same time.

[0143] The trip data segmentation module 804 is used to obtain the driver's trip data based on the recorded data, wherein each trip data includes all the recorded data of the same driver driving the same vehicle continuously;

[0144] The profile generation module 805 is used to collect driving behavior information of the driver based on the trip data, and generate a driving behavior profile of the driver based on the driving behavior information.

[0145] In one embodiment, the trip data segmentation module is used to group the recorded data according to the unique identifier of the vehicle to obtain a recorded data group corresponding to each vehicle; sort the recorded data in the recorded data group corresponding to each vehicle according to the collection time; determine the first duration of continuous driving of the same vehicle by the same driver in the recorded data group corresponding to each vehicle; and determine the recorded data within the first duration as a trip data of the same driver.

[0146] In one embodiment, the trip data segmentation module is further configured to: traverse each set of recorded data in the recorded data group corresponding to each vehicle; determine whether the current recorded data was collected when the vehicle was in the starting state based on the data content of the current recorded data; determine whether the vehicle already has trip data; if so, consider the trip data among the existing trip data whose collection time is closest to the current recorded data as the current trip data; if not, create the current recorded data as the current trip data for the vehicle and continue traversing the next set of recorded data; when the vehicle already has trip data, if the time difference between the latest collection time of the current trip data and the collection time of the current recorded data is less than a preset threshold, and the driver identity information in the current trip data is consistent with the driver identity information in the current recorded data, then add the current recorded data to the current trip data and continue traversing the next set of recorded data; otherwise, end the segmentation process of the current trip data, consider the latest collection time of the current trip data as the end time of the first duration, and consider the earliest collection time of the current trip data as the start time of the first duration.

[0147] In one embodiment, the profile generation module is further configured to: calculate the driver's total driving mileage according to a first preset period, based on the vehicle's location information in each of the driver's trip data within the first preset period; calculate the total number of alarms for each alarm indicator of the driver according to the vehicle's alarm information in each of the driver's trip data within the first preset period; and generate a driving behavior profile of the driver within the first preset period based on the driver's total driving mileage and the total number of alarms for each alarm indicator.

[0148] In one embodiment, the profile generation module is further configured to: calculate the number of alarms per 100 kilometers for each alarm indicator based on the total driving mileage and the total number of alarms for each alarm indicator; calculate the score for each alarm indicator based on the number of alarms per 100 kilometers for each alarm indicator; calculate the weight of each alarm indicator based on the total number of alarms for each alarm indicator; calculate the driver's comprehensive safety score based on the weights and scores of all alarm indicators for the driver; calculate the driver's alarm score for each type of alarm based on the weights and scores of each alarm indicator included in each type of alarm; and generate a driving behavior profile of the driver within the first preset period based on the driver's comprehensive safety score, the alarm score for each type of alarm, and the score for each alarm indicator.

[0149] The embodiments of this invention achieve the following technical effects: When the vehicle is determined to be in a running state, the driver's identity information is obtained, dynamically associating or binding the vehicle with the driver's identity information. Driving-related data during the driver's operation is collected, and the driving-related data, the driver's identity information, and the vehicle's unique identifier collected simultaneously are used to generate record data. The driver's trip data is then obtained based on this record data. Furthermore, this achieves real-time association between driving-related data collected during driving and the driver's identity information and the vehicle's unique identifier, effectively ensuring the establishment of a link between the driver's identity information and the vehicle information driven by the driver. The system establishes a strong correlation between the driver's own driving-related data and the driver's trip data. This trip data includes the recorded data of the same driver continuously driving the same vehicle. In other words, the driver's trip data is the relevant data generated by the driver (or the driver alone) continuously driving the same vehicle. Based on the driver's trip data, the system statistically analyzes the driver's driving behavior information to generate a driver's driving behavior profile. This ensures that for each driver, a profile can be generated based on the relevant data of each driver continuously driving the same vehicle. Compared with existing technologies, this avoids the problem of using data that includes non-drivers to generate driver profiles, which helps to improve the accuracy of driver profiles.

[0150] Obviously, those skilled in the art should understand that the modules or steps of the above-described embodiments of the present invention can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of the present invention are not limited to any particular hardware and software combination.

[0151] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. For those skilled in the art, various modifications and variations of the embodiments of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating a driver profile, characterized in that, include: When the vehicle is determined to be in a running state by the in-vehicle terminal, the driver's identity information is obtained, and the vehicle information is bound to the driver's identity information in real time and dynamically. The vehicle-mounted terminal collects driving-related data from the driver while driving the vehicle. Generate record data by combining the driver's identity information, the vehicle's unique identifier, and the driving-related data collected at the same time. The driver's trip data is obtained based on the recorded data, and each trip data entry includes the recorded data of the same driver driving the same vehicle consecutively; Based on the trip data, the driver's driving behavior information is statistically analyzed, and a driving behavior profile of the driver is generated based on the driving behavior information; The driver's trip data is obtained based on the recorded data, including: The recorded data is grouped according to the unique identifier of the vehicle to obtain a record data group corresponding to each vehicle. The recorded data in the recorded data group corresponding to each vehicle are sorted according to the collection time, and the first duration of continuous driving of the same vehicle by the same driver is determined in the recorded data group corresponding to each vehicle. The recorded data within the first time period is identified as a single trip data point for the same driver; Within each vehicle's corresponding data set, determine the first duration of continuous driving of the same vehicle by the same driver, including: In each vehicle's corresponding data group, each data record is traversed, and the data content of the current data record is used to determine whether the current data record was collected when the vehicle was in the starting state. Determine whether the vehicle already has trip data. If so, the trip data that is closest to the collection time of the current recorded data among the existing trip data is regarded as the current trip data. If not, the current recorded data is created as the current trip data of the vehicle, and the process continues to traverse the next recorded data. When the vehicle already has trip data, if the time difference between the latest collection time of the current trip data and the collection time of the current record data is less than a preset threshold, and the driver identity information in the current trip data is consistent with the driver identity information in the current record data, then the current record data is added to the current trip data, and the process continues to traverse the next record data; otherwise, the process of dividing the current trip data ends, the latest collection time of the current trip data is regarded as the end time of the first duration, and the earliest collection time of the current trip data is regarded as the start time of the first duration.

2. The method for generating a driver profile as described in claim 1, characterized in that, Based on the trip data, the driver's driving behavior information is statistically analyzed, and a driving behavior profile of the driver is generated based on the driving behavior information, including: According to the first preset period, based on the vehicle's location information in each of the driver's trip data within the first preset period, the driver's total driving mileage is calculated; Based on the vehicle alarm information in each of the driver's trip data within the first preset period, the total number of alarms for each alarm indicator of the driver is counted. Based on the driver's total driving mileage and the total number of alarms for each alarm indicator, a driving behavior profile of the driver within the first preset period is generated.

3. The method for generating a driver profile as described in claim 2, characterized in that, Based on the driver's total driving mileage and the total number of alarms for each alarm indicator, a driving behavior profile of the driver within the first preset period is generated, including: Based on the total driving mileage and the total number of alarms for each alarm indicator, calculate the number of alarms per 100 kilometers for each alarm indicator; Calculate the score for each alarm indicator based on the number of alarms per 100 kilometers. Calculate the weight of each alarm indicator based on the total number of alarms for each alarm indicator; The driver's overall safety score is calculated based on the weights and scores of all warning indicators for the driver. The driver's alarm score for each type is calculated based on the weight of each alarm indicator included in each alarm type and the score of the corresponding alarm indicator. Based on the driver's overall safety score, the score for each type of alarm, and the score for each alarm indicator, a driving behavior profile of the driver within the first preset period is generated.

4. The method for generating a driver profile as described in claim 3, characterized in that, The score for each alarm indicator is calculated using the following formula, based on the number of alarms per 100 kilometers: score= (1-P(K)) 100.0， Where score is the score of the alarm indicator, P(k) is the cumulative probability of the alarm indicator according to the Poisson distribution, and k is the total number of alarms per 100 kilometers for the alarm indicator.

5. The method for generating a driver profile as described in claim 3, characterized in that, The weight of each alarm metric is calculated based on the total number of alarms for each metric using the following formula: ， Where, weight j Let be the weight of the j-th alarm indicator, m be the total number of alarm indicators, and d be the weight of the j-th alarm indicator. j Let be the difference coefficient of the j-th alarm indicator. P ij Let be the weight of the j-th alarm indicator for the i-th driver among multiple drivers. x ij Let be the total number of alarms for the j-th alarm indicator, and n be the total number of drivers.

6. The method for generating a driver profile as described in any one of claims 1 to 5, characterized in that, Obtaining the driver's identity information includes: The driver's image is acquired, and the driver's biometric features are obtained from the image; Based on the pre-stored correspondence between biometric features and identity information, the driver's identity information is determined according to the collected biometric features.

7. The method for generating a driver's portrait as described in any one of claims 1 to 5, characterized in that, Obtaining the driver's identity information includes: The Bluetooth tag information and Bluetooth signal data of the vehicle's Bluetooth device are collected, wherein each driver wears a unique Bluetooth tag; The Bluetooth signal with the strongest signal strength is determined from the signal data, and the Bluetooth tag information corresponding to the Bluetooth signal with the strongest signal strength is determined. Based on the pre-stored correspondence between Bluetooth tag information and driver identity information, the driver's identity information corresponding to the determined Bluetooth tag information is obtained.

8. A device for generating a driver's portrait, characterized in that, include: The identity information acquisition module is used to acquire the driver's identity information when the vehicle is in the starting state through the vehicle terminal, and to bind the vehicle information with the driver's identity information in real time and dynamically. The driving data acquisition module is used to collect driving-related data from the driver while driving the vehicle through the vehicle-mounted terminal; The data generation module is used to generate record data by combining the driver's identity information, the vehicle's unique identifier, and the driving-related data collected at the same time. The trip data segmentation module is used to obtain the driver's trip data based on the recorded data, and each trip data includes all the recorded data of the same driver driving the same vehicle continuously; The profile generation module is used to collect driving behavior information of the driver based on the trip data, and generate a driving behavior profile of the driver based on the driving behavior information; The trip data segmentation module is used to group the record data according to the unique identifier of the vehicle, so as to obtain the record data group corresponding to each vehicle. The recorded data in the recorded data group corresponding to each vehicle are sorted according to the collection time, and the first duration of continuous driving of the same vehicle by the same driver is determined in the recorded data group corresponding to each vehicle. The recorded data within the first time period is identified as a single trip data point for the same driver; The trip data segmentation module is further configured to traverse each set of recorded data in the recorded data group corresponding to each vehicle, determine whether the current recorded data was collected when the vehicle was in the starting state based on the data content of the current recorded data, determine whether the vehicle already has trip data, if so, then the trip data with the closest collection time to the current recorded data among the existing trip data is regarded as the current trip data; if not, then the current recorded data is newly created as the current trip data of the vehicle, and the traversal of the next set of recorded data continues; when the vehicle already has trip data, if the time difference between the latest collection time of the current trip data and the collection time of the current recorded data is less than a preset threshold, and the driver identity information in the current trip data is consistent with the driver identity information in the current recorded data, then the current recorded data is added to the current trip data, and the traversal of the next set of recorded data continues; otherwise, the segmentation process of the current trip data ends, the latest collection time of the current trip data is regarded as the end time of the first duration, and the earliest collection time of the current trip data is regarded as the start time of the first duration.

9. A computer 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 computer program, it implements the method for generating a driver profile as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that performs the method for generating a driver portrait according to any one of claims 1 to 7.

Images