Driving behavior analysis report generation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data analysis, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a driving behavior analysis report generation method which comprises the following steps: acquiring driving data and user behavior data, analyzing the driving data to obtain a first preset type of driving risk behavior; identifying the frequency and the risk level of the driving risk behavior of the first preset type, and obtaining a first driving risk score according to the frequency and the risk level of the driving risk behavior of the first preset type; analyzing the user behavior data to obtain a second preset type of driving risk behavior, identifying the number of times of the driving risk behavior, and obtaining a second driving risk score according to the number of times of the driving risk behavior of the second preset type; and according to the first and second driving risk scores, calculating a comprehensive risk score, and according to the driving data and the comprehensive risk score, generating a driving behavior analysis report and feeding back the driving behavior analysis report to the target user. The driving behavior is comprehensively evaluated from multiple dimensions, and it is ensured that the evaluation result is more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a method, device, equipment and storage medium for generating a driving behavior analysis report. Background Art

[0002] With the continuous development of modern transportation systems, analyzing user driving behavior is crucial for improving road safety, reducing accident risks, and optimizing auto insurance claims costs. However, existing methods for analyzing user driving behavior have many limitations and cannot meet the needs of accurate assessment and personalized services.

[0003] For example, existing driving behavior analysis primarily relies on vehicle accident records or single sensor data (such as on-board OBD devices). These methods are unable to comprehensively capture a variety of user behavior data during driving, such as distracted driving and fatigued driving, resulting in a lack of comprehensiveness and accuracy in the analysis results. Existing user driving behavior analysis reports typically only focus on a single dimension of data (such as mileage or average speed) and lack systematic and multi-dimensional analysis. In addition, the report generation method is relatively simple and cannot provide customized risk assessments and improvement suggestions based on the needs of different users.

[0004] For example, in healthcare scenarios, driving behavior is closely related to the driver's health status. Fatigue and distracted driving, for example, not only increase the risk of traffic accidents but can also have long-term impacts on the driver's physical and mental health. Existing driving behavior analysis methods are unable to effectively identify these potential health risk factors or provide targeted health advice to drivers.

[0005] For example, in the FinTech context, auto insurance claims costs are a key metric for insurance companies to assess risk and set prices. Traditional auto insurance pricing relies primarily on static factors such as vehicle type, driver age, and gender, but lacks dynamic assessment of driving behavior. For example, a driver with good driving habits may pay a higher premium due to the lack of personalized assessment, while a driver with poor driving habits may pay a lower premium due to the masking of static factors. This not only affects the accuracy of insurance companies' risk assessments but also reduces the fairness and rationality of auto insurance pricing.

[0006] Therefore, how to comprehensively collect and analyze driving data and generate multi-dimensional personalized driving behavior analysis reports is a technical problem that needs to be solved urgently. Summary of the Invention

[0007] In view of the above, it is necessary to provide a method for generating a driving behavior analysis report. Its purpose is to comprehensively collect driving data, identify driving hazards in the driving data, calculate driving scores for driving hazards and generate multi-dimensional personalized reports, so as to provide users with accurate and personalized driving behavior evaluations and improvement suggestions.

[0008] In a first aspect, a method for generating a driving behavior analysis report is provided, the method comprising:

[0009] Collecting driving data generated by a target user driving a target vehicle within a preset time period, the driving data including travel data of the target vehicle and user behavior data generated by the target user during the driving process;

[0010] Identifying, from the driving data, a first preset type of driving risk behavior that occurs during driving by the target user, identifying, from the driving data, a frequency and a risk level of the first preset type of driving risk behavior, and obtaining a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior;

[0011] analyzing the user behavior data to obtain a second preset type of driving risk behavior that occurs during driving by the target user, identifying a number of occurrences of the second preset type of driving risk behavior from the driving data, and obtaining a second driving risk score for the target user based on the number of occurrences of the second preset type of driving risk behavior;

[0012] Calculate the comprehensive risk score of the target user based on the first driving risk score and the second driving risk score, generate a driving behavior analysis report for the target user based on the driving data and the comprehensive risk score, and feed the driving behavior analysis report back to the target user terminal.

[0013] In a second aspect, a driving behavior analysis report generating device is provided, comprising:

[0014] A detection module is used to collect driving data generated by a target user driving a target vehicle within a preset time period, wherein the driving data includes travel data of the target vehicle and user behavior data generated by the target user during the driving process;

[0015] an analysis module, configured to identify, from the driving data, a first preset type of driving risk behavior that occurs during driving by the target user, identify, from the driving data, a frequency and a risk level of the first preset type of driving risk behavior, and obtain a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior;

[0016] an identification module, configured to analyze the user behavior data to obtain a second preset type of driving risk behavior that occurs during the driving process of the target user, identify the number of occurrences of the second preset type of driving risk behavior from the driving data, and obtain a second driving risk score for the target user based on the number of occurrences of the second preset type of driving risk behavior;

[0017] A calculation module is configured to calculate a comprehensive risk score for the target user based on the first driving risk score and the second driving risk score, generate a driving behavior analysis report for the target user based on the driving data and the comprehensive risk score, and feed the driving behavior analysis report back to the target user terminal.

[0018] In a third aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned driving behavior analysis report generation method are implemented.

[0019] Compared to existing technologies, this invention automatically collects all relevant information, including driving data and user behavior data. This addresses the problem that previous risk assessments often relied on limited data sources (such as accident records or static information) and failed to fully reflect the driver's actual driving behavior. By monitoring the entire process, this invention can obtain richer and more accurate data.

[0020] Based on driving data, the system identifies a first set of pre-defined risk behaviors (e.g., speeding, sudden acceleration, sudden deceleration, sharp turns, and other potential safety hazards). This addresses the problem of traditional assessment methods focusing only on a single behavior (e.g., speeding) while ignoring other important driving behaviors. This system provides a more comprehensive risk assessment through multi-dimensional analysis.

[0021] By analyzing user behavior data, we can identify second-tier driving risk behaviors, such as fatigue driving, making or receiving phone calls, and sending or reading text messages. This addresses the significant safety impact of second-tier driving risk behaviors (such as mobile phone use) that are often overlooked in traditional driving assessments. This invention specifically analyzes these behaviors, filling this gap.

[0022] The first and second driving risk scores are combined to calculate a comprehensive risk score that comprehensively reflects the driver's overall driving risk. This addresses the lack of transparency in traditional auto insurance pricing and services, making it difficult for users to understand how their premiums are calculated. This invention increases service transparency through a clear scoring mechanism and detailed reporting.

[0023] The present invention comprehensively evaluates driving behavior from multiple dimensions (driving data and user behavior data) to ensure that the evaluation results are more accurate and reliable. It monitors driving behavior in real time, can detect problems and provide improvement suggestions in the first place, and play a role in preventing accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a schematic diagram of an application environment of a method for generating a driving behavior analysis report according to an embodiment of the present invention;

[0025] Figure 2 A flowchart of a method for generating a driving behavior analysis report according to an embodiment of the present invention is provided;

[0026] Figure 3 A schematic diagram of the modules of a driving behavior analysis report generating device provided by an embodiment of the present invention;

[0027] Figure 4 is a structural diagram of a computer device in one embodiment of the present invention;

[0028] Figure 5 FIG. 2 is another structural diagram of a computer device according to an embodiment of the present invention.

[0029] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0031] It should be noted that the descriptions of "first", "second", etc. in the present invention are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0032] The driving behavior analysis report generation method provided by the embodiment of the present invention can be applied in the following Figure 1In an application environment, the client communicates with the server through a network. Driving data generated by a target user driving a target vehicle within a preset time period is collected, and the driving data includes the driving data of the target vehicle and the user behavior data of the target user during the driving process; the driving data is analyzed to obtain a first preset type of driving risk behavior of the target user during the driving process, the frequency and risk level of the first preset type of driving risk behavior are identified from the driving data, and a first driving risk score of the target user is obtained based on the frequency and risk level of the first preset type of driving risk behavior; the user behavior data is analyzed to obtain a second preset type of driving risk behavior of the target user during the driving process, the number of the second preset type of driving risk behavior is identified from the driving data, and a second driving risk score of the target user is obtained based on the number of the second preset type of driving risk behavior; based on the first driving risk score and the second driving risk score, a comprehensive risk score of the target user is calculated, and based on the driving data and the comprehensive risk score, a driving behavior analysis report of the target user is generated, and the driving behavior analysis report is fed back to the target user. The present invention comprehensively evaluates driving behavior from multiple dimensions to ensure that the evaluation results are more accurate and reliable, monitors driving behavior in real time, can discover problems and provide improvement suggestions in the first place, and plays a role in preventing accidents. The client can be, but is not limited to, various personal computers, laptops, smartphones, tablet computers, and portable wearable devices. The server can be implemented as an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0033] Reference Figure 2 FIG. 1 is a flow chart of a method for generating a driving behavior analysis report according to an embodiment of the present invention. The method is executed by a device.

[0034] In this embodiment, the driving behavior analysis report generation method includes:

[0035] S1. Collecting driving data generated by a target user driving a target vehicle within a preset time period, wherein the driving data includes travel data of the target vehicle and user behavior data generated by the target user during the driving process;

[0036] In this embodiment, when the target vehicle's ignition signal is detected, it is determined that the target user has begun driving the target vehicle, automatically triggering the information collection device to start collecting driving data generated by the target user driving the target vehicle within a preset time period. The preset time period starts when the vehicle's ignition signal is detected and ends when the vehicle's ignition signal is detected. This preset time period ensures the integrity and specificity of data collection, recording only the target user's current driving behavior.

[0037] In other embodiments, the preset time period may also include a preset time period based on a fixed driving duration (for example, setting the collection duration of each driving behavior to a fixed time, such as 30 minutes, 1 hour, or 2 hours), a preset time period based on a fixed mileage (for example, setting the collection mileage of each driving behavior to a fixed value, such as 50 kilometers, 100 kilometers, or 200 kilometers), and a preset time period based on a fixed task (for example, from the start to the end of a long-distance transport task).

[0038] In the field of financial technology, driving data is a crucial basis for auto insurance pricing and claims risk assessment. By accurately collecting driving data, insurance companies can better assess users' driving risks, achieve personalized auto insurance pricing, and optimize the claims process.

[0039] User A starts his vehicle on the weekend and prepares to go on a road trip in the suburbs. When user A starts the vehicle, the vehicle's intelligent system detects the ignition signal and triggers the information collection device to start collecting driving data for this road trip.

[0040] In one embodiment, collecting driving data generated by the target user driving the target vehicle within a preset time period includes:

[0041] Using the target user's mobile terminal as a first information collection device and connecting it to the first information collection device;

[0042] Utilizing the camera function module in the first information collection device to collect user behavior data of the target user;

[0043] Calling the GPS positioning module and the sensor module in the first information collection device to record the driving data of the target vehicle;

[0044] The driving data and the user behavior data are collected to obtain the driving data of the target user.

[0045] When the target vehicle ignition signal is detected, the target user is automatically identified and starts driving. Ensure that the target user has explicit authorization to access the GPS positioning module, sensor module (such as accelerometer, gyroscope, etc.) and camera function module of the first information collection device (such as a mobile terminal).

[0046] The built-in GPS positioning module of the mobile terminal is used to track and record the driving data of the target vehicle in real time, such as the location information (latitude and longitude) of the target vehicle, the driving route, the start and end time of the trip, and the current speed, average speed, maximum speed and other speed-related information are obtained simultaneously.

[0047] The first information collection device uses sensors such as accelerometers and gyroscopes to monitor the target vehicle's driving data, including dynamic information such as acceleration, deceleration, turning angles and angular velocities. Key parameters such as driving time, acceleration and deceleration change rates in different speed ranges are recorded.

[0048] Using the mobile terminal's front-facing camera or another fixed camera, combined with a pre-set gaze detection model, the system monitors the driver's gaze in real time to determine if the gaze deviates from the normal driving direction. When gaze deviation is detected, the system immediately captures the current image and saves it as a behavior image. This process is repeated to accumulate a series of behavior images as user behavior data.

[0049] The driving data and user behavior data are merged in a preset structured format to form a complete driving dataset that contains all the key information involved in the entire driving process.

[0050] Using mobile terminals as the first information collection device to obtain driving data without relying on vehicles or other on-board equipment solves the problem of not having to install additional on-board equipment (such as OBD devices, dedicated cameras, etc.), reducing the hardware procurement and maintenance costs of users and insurance companies. Almost all mobile terminals are equipped with necessary sensors (GPS, accelerometers, gyroscopes, etc.) and cameras, which makes the solution widely applicable without the need for support from specific vehicle models.

[0051] In one embodiment, collecting driving data generated by the target user driving the target vehicle within a preset time period includes:

[0052] Using the in-vehicle camera of the target vehicle as a second information collection device, and using the second information collection device to collect user behavior data of the target user;

[0053] Using the onboard system of the target vehicle as a third information collection device, and using the third information collection device to record the driving data of the target vehicle;

[0054] The driving data and the user behavior data are collected to obtain the driving data of the target user.

[0055] When the target vehicle's ignition signal is detected, the target user is automatically identified and begins driving. A second information collection device (in-car camera) is combined with a preset gaze detection model to monitor the driver's gaze direction in real time to determine whether the gaze deviates from the normal driving direction. For example, if the driver frequently looks down at their phone or other objects, this may be considered distracted driving. The current scene is captured and saved as a behavioral image. This process is repeated to accumulate a series of behavioral images as user behavior data.

[0056] The GPS positioning module built into the third information collection device (on-board system) is used to track and record the target vehicle's driving data in real time, such as the target vehicle's location information (latitude and longitude), driving route, start time and end time of the trip, and synchronously obtain speed-related information such as current speed, average speed, and maximum speed.

[0057] The driving data and user behavior data are merged in a preset structured format to form a complete driving dataset that contains all the key information involved in the entire driving process.

[0058] Only using the vehicle's own equipment (such as the in-vehicle camera as the second information collection device, and the on-board system as the third information collection device) to collect driving data can solve the problem of not requiring additional external equipment or complex settings. All necessary sensors and data collection tools are integrated inside the vehicle, reducing the workload of users and technicians. The on-board equipment can directly read the most accurate data, such as speed, acceleration, etc., from the vehicle's core control system, ensuring the authenticity and accuracy of the data.

[0059] In healthcare scenarios, driving behavior analysis not only helps improve road safety but also serves as a component of health management. For example, behaviors such as fatigued and distracted driving can negatively impact a driver's physical and mental health, increasing the risk of traffic accidents. By collecting driving data, drivers can be provided with personalized health recommendations and linked to medical institutions or health management platforms.

[0060] In one embodiment, collecting the user behavior data of the target user includes:

[0061] Using a preset sight line detection model, detecting whether the target user's sight line deviates from a preset driving direction;

[0062] If so, controlling the first information collection device or the second information collection device to capture the current screen of the target user to obtain a behavior picture;

[0063] All behavior pictures are collected to obtain the user behavior data of the target user.

[0064] The driver's gaze direction is monitored in real time using a pre-trained gaze detection model. This model, based on computer vision technology, analyzes the position and state of the driver's eyes in camera-captured images.

[0065] The system compares the target user's actual gaze direction with the preset "normal" driving direction. If the target user's gaze is found to deviate from the normal driving direction for a long time (for example, frequently looking down at a phone or other objects), it is considered that there is a risk of distracted driving.

[0066] Once the gaze detection model detects that the driver's gaze has strayed from the preset driving direction, it controls the first or second information collection device (the front-facing camera of a mobile terminal or a specially installed in-car camera) to capture one or more photos of the current scene. These photos serve as evidence for subsequent analysis of whether the driver engaged in distracted driving. The captured behavioral images are named and saved according to specific rules to ensure that each image accurately corresponds to a specific time point or event.

[0067] By repeating the above process and continuously accumulating behavioral images, a complete user behavior dataset is eventually formed. This user behavior dataset not only includes instances of driver gaze deviation but may also include other types of user behavior data (such as making / receiving calls, sending / reading text messages, etc.), allowing for a comprehensive assessment of driver behavior habits.

[0068] For example, consider a healthcare scenario: Long-distance truck driver A frequently drives at night. After using the aforementioned system, during one driving session, the system detected that Mr. Li repeatedly looked down at his phone to check navigation, causing his gaze to wander. In-depth analysis of these behavioral images revealed that Mr. Li had recently experienced high levels of driving fatigue and was at risk of vision loss. Therefore, the system provided Mr. Li with the following recommendations: either remind him to rest regularly to avoid safety hazards caused by fatigued driving, or recommend that he schedule an appointment with an ophthalmologist for a comprehensive eye examination as soon as possible to ensure his vision is suitable for continued long-distance driving.

[0069] In one embodiment, recording the driving data of the target vehicle includes:

[0070] Recording and storing the driving information related to the target vehicle in a preset driving log;

[0071] The mileage of the target vehicle, the start and end time of the current trip, speed information, driving time in different speed ranges, acceleration information, deceleration information, angular velocity information and amplitude information of the turn are extracted from the driving log as the driving data of the target vehicle.

[0072] During the specified collection period, the following key driving data will be recorded:

[0073] Mileage: Records the total distance traveled by the target vehicle throughout the entire trip. Current trip start and end time: Accurately records the start and end time of the trip to facilitate subsequent analysis of the specific time period of the trip. Speed ​​information: Average speed (calculate the average speed of the vehicle throughout the trip), maximum speed (identify and record the maximum speed reached during the trip). Driving time in different speed ranges: Classifies and counts the driving time of the target vehicle in different speed ranges. For example, it can be divided into intervals such as 0-30km / h, 30-60km / h, etc., and the cumulative driving time in each interval is recorded separately.

[0074] Acceleration Information: Monitors and records the rate of change during vehicle acceleration, including but not limited to sudden acceleration. Deceleration Information: Similarly, monitors and records the rate of change during deceleration, paying particular attention to sudden deceleration events. Turn Angular Velocity and Amplitude Information: Records the angular velocity (i.e., angular velocity) and turn amplitude (i.e., turn radius or angle) of the target vehicle when turning, used to identify sharp turns.

[0075] S2. Identifying, from the driving data, a first preset type of driving risk behavior that occurs during driving by the target user, identifying, from the driving data, a frequency and a risk level of the first preset type of driving risk behavior, and obtaining a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior;

[0076] In this embodiment, the driving data is analyzed to obtain a first preset type of driving risk behavior of the target user during the driving process. The first preset type of driving risk behavior includes speeding, sudden acceleration, sudden deceleration, and sharp turning.

[0077] For each type of first-preset driving risk behavior, the number of times it occurs throughout the entire trip is counted. The severity of the behavior is assessed based on specific parameters (e.g., speed differential for speeding, acceleration rate of sudden acceleration / deceleration, angular velocity of sharp turns, etc.). For example, different thresholds can be set to categorize risk behaviors into three levels: mild, moderate, and severe.

[0078] A first-preset driving risk behavior scoring model, which includes predefined frequency weights and risk level weights corresponding to different first-preset driving risk behaviors, is retrieved from a preset database. Using the first-preset driving risk behavior scoring model, each identified first-preset driving risk behavior is quantitatively scored based on its frequency and level. The scores for all risk behaviors are summed to generate a comprehensive first driving risk score for the target user. This score reflects the driver's overall risk level for the trip.

[0079] In the field of financial technology, especially in auto insurance pricing and claims risk assessment, the process of using driving data to identify first-preset types of driving risk behaviors and calculating a first driving risk score based on the frequency and risk level of these potential risks can significantly improve insurance companies' ability to accurately assess risks. The following is an example based on a specific application scenario:

[0080] User A is a salesperson who frequently drives long distances. His vehicle is equipped with the aforementioned information collection equipment. After a period of data collection, it was discovered that User A occasionally speeds (but not to a critical level) and brakes suddenly several times. Based on this data, the system calculates User A's first driving risk score as 75 (out of 100).

[0081] In one embodiment, identifying, from the driving data, a first preset type of driving risk behavior of the target user during driving, includes:

[0082] Identifying whether the target user has exceeded the speed limit based on the speed information in the driving data;

[0083] Identifying, based on acceleration information in the driving data, whether the target user has sudden acceleration behavior;

[0084] identifying whether the target user has sudden deceleration behavior based on the deceleration information in the driving data;

[0085] identifying whether the target user has made a sharp turn based on the angular velocity information, amplitude information, and speed information in the driving data;

[0086] According to the recognition result of whether the target user has speeding behavior, sudden acceleration behavior, sudden deceleration behavior and sharp turning behavior, a first preset type of driving risk behavior of the target user during the driving process is obtained.

[0087] The legal speed limit for the target vehicle's location is obtained based on GPS positioning. The speed information recorded during the driving process is compared with the legal speed limit for that location. If the target vehicle's speed exceeds the speed limit, it is marked as a speeding violation, and the number of speeding violations during the entire trip is counted.

[0088] Define a standard for sudden acceleration, such as a speed increment greater than 45 km / h within 6 seconds. By analyzing acceleration information, identify time periods throughout the entire journey that meet these criteria, identify sudden acceleration events, and count the number of occurrences.

[0089] Define the criteria for sudden deceleration, such as a speed reduction of more than 45 km / h within 6 seconds. Use deceleration information to identify time periods in the trip that meet the sudden deceleration criteria, identify sudden deceleration behaviors, and record the number of sudden deceleration behaviors.

[0090] Combine angular velocity information, amplitude information, and speed information to determine whether there is a sharp turn. For example:

[0091] A sharp turn was recorded when the speed was greater than 100 km / h and the angular velocity was greater than 9° / s; a sharp turn was recorded when the speed was greater than 80 km / h and the angular velocity was greater than 12° / s; a sharp turn was recorded when the speed was greater than 60 km / h and the angular velocity was greater than 16° / s; and a sharp turn was recorded when the speed was greater than 40 km / h and the angular velocity was greater than 17° / s. The number of sharp turns was also counted.

[0092] Based on the speeding, sudden acceleration, sudden deceleration, and sharp turning behaviors identified in the previous steps, a complete list of driving risk behaviors of the first preset type is compiled. From the list of driving risk behaviors of the first preset type, various driving risk behaviors of the first preset type that the target user may have during driving can be obtained.

[0093] By identifying and quantifying various hidden dangers in driving behaviors, it provides insurance companies with a more accurate basis for risk assessment, while also helping drivers understand the potential risks in their own driving habits so that they can take measures to improve them.

[0094] In one embodiment, obtaining the first driving risk score of the target user based on the frequency and risk level of the first preset type of driving risk behavior includes:

[0095] Obtaining from a preset database a first preset type of driving risk behavior scoring model that pre-defines frequency weights and risk level weights corresponding to different first preset types of driving risk behaviors;

[0096] The frequency and risk level of the first preset type of driving risk behavior are scored using the first preset type of driving risk behavior scoring model to obtain a first driving risk score for the target user.

[0097] A first-preset driving risk behavior scoring model is obtained from a preset database, which includes predefined frequency weights and risk level weights corresponding to different first-preset driving risk behaviors. The first-preset driving risk behavior scoring model includes specific definitions of each first-preset driving risk behavior (e.g., speeding, sudden acceleration, sudden deceleration, sharp turns, etc.), as well as scoring criteria for each risk behavior based on frequency and severity.

[0098] Based on previously collected driving data (including speed information, acceleration information, deceleration information, angular velocity information, etc.), it is possible to identify whether the target user has any risk behaviors such as speeding, sudden acceleration, sudden deceleration, and sharp turns during driving.

[0099] For each identified potential risk behavior, count the number of times it occurs throughout the entire trip. For example, record the number of times speeding occurs, the number of sudden acceleration incidents, etc.

[0100] Each hazardous behavior is assessed for its severity level. For example, speeding can be categorized as mild (e.g., exceeding the speed limit by no more than 10%), moderate (10%-20% exceeding the speed limit), and severe (exceeding the speed limit by more than 20%) based on the percentage of speed exceeded. Rapid acceleration or deceleration can also be assessed for severity based on the rate of change of acceleration.

[0101] The obtained frequency and risk level of each risky behavior are matched with the corresponding entry in the first preset type of driving risk behavior scoring model. For example, if a driver has three minor speeding violations in a trip, the scoring model stipulates that each minor speeding violation will result in a total of 15 points deducted.

[0102] For all identified hidden danger behaviors, the score of each hidden danger behavior is calculated one by one according to its frequency and risk level and the standards given by the first preset type of driving risk behavior scoring model, and then these scores are added up to obtain a comprehensive first driving risk score.

[0103] S3. Analyze the user behavior data to obtain a second preset type of driving risk behavior that occurs during the driving process of the target user, identify the number of occurrences of the second preset type of driving risk behavior from the driving data, and obtain a second driving risk score for the target user based on the number of occurrences of the second preset type of driving risk behavior;

[0104] In this embodiment, the second type of driving risk behavior includes fatigue driving, making / receiving phone calls, and sending / reading text messages. By analyzing the travel time information in the driving data, it is determined whether there has been continuous long-term driving. For example, if the target user is found to have driven continuously for more than two hours, it is marked as a fatigue driving behavior.

[0105] Use the preset image processing model to process each behavior picture in the user behavior data to identify whether the driver uses a communication device while driving. Specifically:

[0106] If the image shows that the driver is making / receiving a phone call, it is marked as a use of a communication device; if the image shows that the driver is sending / reading a text message, it is also marked as a use of a communication device.

[0107] The number of instances of fatigue driving, phone calls, and text message sending / reading during the entire trip is counted, and a second-preset driving risk behavior deduction model is obtained from a preset database, which specifies the deduction criteria for different second-preset driving risk behaviors. The second-preset driving risk behavior deduction model clearly lists different types of second-preset driving risk behaviors and their corresponding deduction values.

[0108] The number of identified second-preset driving risk behaviors is matched with the corresponding entries in the second-preset driving risk behavior deduction model, and the total deduction points are calculated. For example: each instance of fatigue driving will result in a deduction of 10 points; each instance of making or receiving a phone call will result in a deduction of 20 points; and each instance of sending or reading a text message will result in a deduction of 30 points.

[0109] In one embodiment, analyzing the user behavior data to obtain a second preset type of driving risk behavior of the target user during driving includes:

[0110] Identifying whether the target user has fatigue driving behavior based on travel time information in the driving data;

[0111] Using a preset image processing model to process each behavior image in the user behavior data, identifying whether the target user uses a communication device, including the number of times the target user makes or receives a call, and the number of times the target user sends or receives a text message;

[0112] According to the identification result of whether the target user has fatigue driving behavior and communication device usage behavior, a second preset type of driving risk behavior occurring in the driving process of the target user is obtained.

[0113] By analyzing the travel time information in the driving data, it is determined whether there is continuous long driving. For example, if the target user is found to have driven for more than 2 hours continuously, it will be marked as fatigue driving behavior.

[0114] Each behavioral image in the user behavior data is processed using a preset image processing model. The image processing model identifies whether the driver holds the phone to their ear while driving, which is considered making or receiving a call. It also identifies when the driver looks down at the phone screen or manipulates the screen with their fingers, which is considered sending or reading a text message.

[0115] The number of fatigue driving behaviors, phone making / receiving behaviors, and text message sending / reading behaviors that occur during the entire trip are counted to obtain a second preset type of driving risk behavior of the target user during the driving process.

[0116] In the field of financial technology, by identifying a second set of pre-defined risky driving behaviors (such as fatigue driving, making or receiving phone calls, and sending or reading text messages), drivers can be promptly alerted to these dangerous behaviors, thereby reducing the incidence of traffic accidents caused by distraction. Based on detailed driving data analysis, insurance companies can more accurately assess each customer's actual driving risk and thus formulate more fair and reasonable insurance rates.

[0117] In one embodiment, obtaining a second driving risk score for the target user based on the number of driving risk behaviors of the second preset type includes:

[0118] Obtaining from a preset database a second preset type of driving risk behavior deduction model that predefines deduction standards corresponding to different second preset types of driving risk behaviors;

[0119] The second preset type of driving risk behavior scoring model is used to score the number and type of the second preset type of driving risk behavior to obtain a second driving risk score for the target user.

[0120] A second-preset driving risk behavior deduction model is obtained from a preset database, which includes pre-defined deduction criteria for different second-preset driving risk behaviors. The second-preset driving risk behavior deduction model includes specific definitions of each second-preset driving risk behavior (such as fatigue driving, making / receiving phone calls, sending / reading text messages, etc.), as well as the deduction values ​​for each second-preset driving risk behavior in different situations. For example, fatigue driving deducts 10 points each time; making / receiving phone calls deducts 20 points each time; and sending / reading text messages deducts 30 points each time.

[0121] The number of identified driving risk behaviors of each second preset type is matched with the corresponding entry in the driving risk behavior deduction model of the second preset type. The score of each driving risk behavior of the second preset type is calculated according to the standards given by the driving risk behavior deduction model of the second preset type. The scores of all identified driving risk behaviors of the second preset type are added up to obtain a comprehensive second driving risk score.

[0122] Through a specific deduction mechanism, we can quantify the specific impact of different second-tier pre-set driving risk behaviors (such as fatigue driving, making or receiving phone calls, and sending or reading text messages) on overall driving risk. Combining the first and second driving risk scores creates a comprehensive driving score that more comprehensively reflects a driver's overall risk level and promotes the development of safe driving habits.

[0123] Meanwhile, traditional assessment methods often only provide summary reports after the fact, and cannot provide real-time guidance for drivers to correct bad habits. This invention supports real-time monitoring and feedback, which can immediately alert the driver when potential hazards are detected and provide improvement suggestions.

[0124] S4. Calculate a comprehensive risk score for the target user based on the first driving risk score and the second driving risk score, generate a driving behavior analysis report for the target user based on the driving data and the comprehensive risk score, and feed the driving behavior analysis report back to the target user.

[0125] In this embodiment, based on the first driving risk score and the second driving risk score, a preset scoring formula is used to combine the first driving risk score and the deduction points to calculate the comprehensive risk score. The scoring formula is:

[0126] Comprehensive risk score = basic score + first driving risk score - second driving risk score. For example, if the basic score is 100 points, the first driving risk score is 50 points, and the second driving risk score is 30 points, then the comprehensive risk score is: 100 + 50 - 30 = 120 points.

[0127] An initial analysis report template with pre-defined content modules and display methods is obtained from a preset database, and a first preset type of driving risk behavior (such as speeding, sudden acceleration, etc.), a second preset type of driving risk behavior (such as fatigue driving, making / receiving phone calls, etc.), a first driving risk score, a second driving risk score, and a final comprehensive risk score are filled into the content module corresponding to the report template. The filled content module is displayed using a display method, for example, a chart or graphical representation, to generate a driving behavior analysis report for the target user.

[0128] The driving behavior analysis report can be fed back to the target user end in a variety of ways, such as sending a report link or directly pushing the report content through message notifications in the application, email or SMS.

[0129] Incorporating interactive elements into driving behavior analysis reports, such as allowing target users to view details of specific events, providing online consulting services, or guiding target users to participate in safe driving training courses, further enhances user experience and promotes positive change.

[0130] In the field of financial technology, especially in the auto insurance industry, using the above steps to analyze driving behavior, calculate driving scores, and generate driving behavior reports can help insurance companies more accurately assess risks and develop personalized insurance products.

[0131] Imagine an insurance company that wants to provide customers with personalized auto insurance pricing based on their actual driving behavior. They use an advanced driving data analytics system that monitors and analyzes customers' driving behavior in real time.

[0132] When customer A starts his vehicle, the in-vehicle information collection device (such as an OBD device or mobile application) automatically begins recording driving data. The data is analyzed according to preset rules, identifying risky behaviors such as speeding, sudden acceleration, sudden deceleration, and sharp turns. User behavior data is also analyzed to identify a second set of risky driving behaviors, such as fatigue driving, making or receiving phone calls, and sending or reading text messages. The first and second driving risk scores are combined to calculate a comprehensive risk score for customer A. A detailed driving behavior analysis report is generated based on the driving data and the comprehensive risk score, including all identified risky behaviors, their specific scores, and improvement suggestions. Customer A is notified via email or mobile application. The report details his speeding, sudden braking, and the number of times he used his phone during the trip. The report also recommends reducing speeding, avoiding phone use while driving, and provides tips for improving driving habits.

[0133] In one embodiment, calculating the comprehensive risk score of the target user based on the first driving risk score and the second driving risk score includes:

[0134] Obtaining a scoring formula for calculating a first driving risk score and a second driving risk score from a preset database;

[0135] The comprehensive risk score of the target user is obtained by subtracting the second driving risk score from the sum of the basic score in the scoring formula and the first driving risk score.

[0136] In one embodiment, generating a driving behavior analysis report of the target user based on the driving data and the comprehensive risk score includes:

[0137] Obtaining an initial analysis report template with predefined content modules and presentation methods from a preset database;

[0138] Filling the first preset type of driving risk behavior, the second preset type of driving risk behavior, the first driving risk score, the second driving risk score, and the comprehensive risk score into the content module corresponding to the initial analysis report template;

[0139] The content module filled with content is displayed using the display method, and a driving behavior analysis report of the target user is generated.

[0140] An initial analysis report template with predefined content modules and presentation methods is retrieved from a preset database. The initial analysis report template includes: the overall structure and layout of the report; the location and formatting requirements of each content module (e.g., charts, text boxes, etc.); and predefined presentation methods (e.g., color scheme, font size, etc.). The first preset type of driving risk behavior, the second preset type of driving risk behavior, the first driving risk score, the second driving risk score, and the overall risk score are populated into the corresponding content modules of the initial analysis report template.

[0141] For example, in the first section of the initial analysis report template (such as the "Driving Hazards" or "Safe Driving Recommendations" section), list in detail all identified driving risk behaviors of the first preset type and the specific circumstances of their occurrence (time, location, frequency, etc.). Similarly, in the second section of the initial analysis report template (such as the "Distracted Driving" or "Areas for Improvement" section), record all identified driving risk behaviors of the second preset type and the number of times they occurred. In the scoring section of the initial analysis report template, clearly list the first driving risk score, the second driving risk score, and the final comprehensive risk score.

[0142] Based on the above analysis results, personalized improvement suggestions are provided to the target users in the initial analysis report template (such as reducing the number of speeding, avoiding long-term continuous driving, not using mobile phones while driving, etc.).

[0143] According to the preset display method of the template (such as charts, lists, graphical representations, etc.), make appropriate adjustments to the filled content to ensure that the information is clear and easy to understand, and integrate the filled and adjusted content into a complete driving behavior analysis report.

[0144] Generating a driving behavior analysis report for the target user in step S4 not only helps improve road safety and optimize auto insurance pricing, but also addresses the shortcomings of existing single-dimensional assessments. Traditional methods often rely on vehicle accident records or single sensor data, failing to fully capture the complex behavioral patterns of the driving process. This also addresses the problem of previous auto insurance pricing being primarily based on static factors such as vehicle type and driver age, while ignoring the impact of dynamic driving behavior on risk. By monitoring driving behavior in real time, this present invention achieves usage-based insurance pricing, improving the fairness and rationality of pricing.

[0145] In steps S1-S4, all relevant information, including driving data and user behavior data, is automatically collected from the time the vehicle is started to when it is turned off. This addresses the problem that previous risk assessments often relied on limited data sources (such as accident records or static information) and failed to fully reflect the driver's actual driving behavior. By monitoring the entire process, the present invention can obtain richer and more accurate data.

[0146] Based on driving data, this system identifies potential safety hazards such as speeding, sudden acceleration, sudden deceleration, and sharp turns. This addresses the problem of traditional assessment methods focusing only on a single behavior (such as speeding) while ignoring other important driving behaviors. This system provides a more comprehensive risk assessment through multi-dimensional analysis.

[0147] By analyzing user behavior data, we can identify second-tier driving risk behaviors, such as fatigue driving, making or receiving phone calls, and sending or reading text messages. This addresses the significant safety impact of second-tier driving risk behaviors (such as mobile phone use) that are often overlooked in traditional driving assessments. This invention specifically analyzes these behaviors, filling this gap.

[0148] The first and second driving risk scores are combined to calculate a comprehensive risk score that comprehensively reflects the driver's overall driving risk. This addresses the lack of transparency in traditional auto insurance pricing and services, making it difficult for users to understand how their premiums are calculated. This invention increases service transparency through a clear scoring mechanism and detailed reporting.

[0149] The present invention comprehensively evaluates driving behavior from multiple dimensions to ensure that the evaluation results are more accurate and reliable. It monitors driving behavior in real time, can identify problems in the first place, and provide improvement suggestions, thereby preventing accidents.

[0150] like Figure 3 FIG. 1 is a module diagram of a driving behavior analysis report generating device provided by an embodiment of the present invention.

[0151] The driving behavior analysis report generating device 100 described in the present invention can be installed in a device. Depending on the functionality implemented, the driving behavior analysis report generating device 100 may include a detection module 110, an analysis module 120, an identification module 130, and a calculation module 140. A module, also referred to as a unit, is a series of computer program segments that can be executed by a device processor and perform a fixed function. These are stored in the device's memory.

[0152] In this embodiment, the functions of each module / unit are as follows:

[0153] The detection module 110 is configured to collect driving data generated by a target user driving a target vehicle within a preset time period, wherein the driving data includes travel data of the target vehicle and user behavior data generated by the target user during the driving process;

[0154] an analysis module 120 for identifying, from the driving data, a first preset type of driving risk behavior that occurs during driving by the target user, identifying a frequency and a risk level of the first preset type of driving risk behavior from the driving data, and obtaining a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior;

[0155] an identification module 130 configured to analyze the user behavior data to obtain a second preset type of driving risk behavior that occurs during the driving process of the target user, identify the number of occurrences of the second preset type of driving risk behavior from the driving data, and obtain a second driving risk score for the target user based on the number of occurrences of the second preset type of driving risk behavior;

[0156] The calculation module 140 is used to calculate the comprehensive risk score of the target user based on the first driving risk score and the second driving risk score, generate an analysis report on the driving behavior of the target user based on the driving data and the comprehensive risk score, and feed the driving behavior analysis report back to the target user terminal.

[0157] In one embodiment, the detection module 110 is specifically configured to:

[0158] Using the target user's mobile terminal as a first information collection device and connecting it to the first information collection device;

[0159] Utilizing the camera function module in the first information collection device to collect user behavior data of the target user;

[0160] Calling the GPS positioning module and the sensor module in the first information collection device to record the driving data of the target vehicle;

[0161] The driving data and the user behavior data are collected to obtain the driving data of the target user.

[0162] In one embodiment, the detection module 110 is specifically configured to:

[0163] The collecting driving data generated by the target user driving the target vehicle within a preset time period includes:

[0164] Using the in-vehicle camera of the target vehicle as a second information collection device, and using the second information collection device to collect user behavior data of the target user;

[0165] Using the onboard system of the target vehicle as a third information collection device, and using the third information collection device to record the driving data of the target vehicle;

[0166] The driving data and the user behavior data are collected to obtain the driving data of the target user.

[0167] In one embodiment, the analysis module 120 is specifically configured to:

[0168] Identifying whether the target user has exceeded the speed limit based on the speed information in the driving data;

[0169] Identifying, based on acceleration information in the driving data, whether the target user has sudden acceleration behavior;

[0170] identifying whether the target user has sudden deceleration behavior based on the deceleration information in the driving data;

[0171] identifying whether the target user has made a sharp turn based on the angular velocity information, amplitude information, and speed information in the driving data;

[0172] According to the recognition result of whether the target user has speeding behavior, sudden acceleration behavior, sudden deceleration behavior and sharp turning behavior, a first preset type of driving risk behavior of the target user during the driving process is obtained.

[0173] In one embodiment, the analysis module 120 is specifically configured to:

[0174] Obtaining a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior includes:

[0175] Obtaining from a preset database a first preset type of driving risk behavior scoring model that pre-defines frequency weights and risk level weights corresponding to different first preset types of driving risk behaviors;

[0176] The frequency and risk level of the first preset type of driving risk behavior are scored using the first preset type of driving risk behavior scoring model to obtain a first driving risk score for the target user.

[0177] In one embodiment, the identification module 130 is specifically configured to:

[0178] The analyzing the user behavior data to obtain a second preset type of driving risk behavior of the target user during driving includes:

[0179] Identifying whether the target user has fatigue driving behavior based on travel time information in the driving data;

[0180] Using a preset image processing model to process each behavior image in the user behavior data, identifying whether the target user uses a communication device, including the number of times the target user makes or receives a call, and the number of times the target user sends or receives a text message;

[0181] According to the identification result of whether the target user has fatigue driving behavior and communication device usage behavior, a second preset type of driving risk behavior occurring in the driving process of the target user is obtained.

[0182] In one embodiment, the identification module 130 is specifically configured to:

[0183] Obtaining a second driving risk score for the target user based on the number of driving risk behaviors of the second preset type includes:

[0184] Obtaining from a preset database a second preset type of driving risk behavior deduction model that predefines deduction standards corresponding to different second preset types of driving risk behaviors;

[0185] The second preset type of driving risk behavior scoring model is used to score the number and type of the second preset type of driving risk behavior to obtain a second driving risk score for the target user.

[0186] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the server side of a driving behavior analysis report generation method.

[0187] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, memory, network interface, display screen, and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps on the client side of a driving behavior analysis report generation method.

[0188] In one embodiment, a computer device is provided, 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, the following steps are performed:

[0189] Collecting driving data generated by a target user driving a target vehicle within a preset time period, the driving data including travel data of the target vehicle and user behavior data generated by the target user during the driving process;

[0190] Identifying, from the driving data, a first preset type of driving risk behavior that occurs during driving by the target user, identifying, from the driving data, a frequency and a risk level of the first preset type of driving risk behavior, and obtaining a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior;

[0191] analyzing the user behavior data to obtain a second preset type of driving risk behavior that occurs during driving by the target user, identifying a number of occurrences of the second preset type of driving risk behavior from the driving data, and obtaining a second driving risk score for the target user based on the number of occurrences of the second preset type of driving risk behavior;

[0192] Calculate the comprehensive risk score of the target user based on the first driving risk score and the second driving risk score, generate a driving behavior analysis report for the target user based on the driving data and the comprehensive risk score, and feed the driving behavior analysis report back to the target user terminal.

[0193] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can be found in the relevant descriptions of the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0194] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0195] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0196] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. If any software tools or components other than those of the company appear in the application embodiments, they are merely used for illustration and do not represent actual use. Although the present invention has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above-mentioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for generating a driving behavior analysis report, characterized in that: The method comprises: Collecting driving data generated by a target user driving a target vehicle within a preset time period, the driving data including travel data of the target vehicle and user behavior data generated by the target user during the driving process; Identifying, from the driving data, a first preset type of driving risk behavior that occurs during driving by the target user, identifying, from the driving data, a frequency and a risk level of the first preset type of driving risk behavior, and obtaining a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior; analyzing the user behavior data to obtain a second preset type of driving risk behavior that occurs during driving by the target user, identifying a number of occurrences of the second preset type of driving risk behavior from the driving data, and obtaining a second driving risk score for the target user based on the number of occurrences of the second preset type of driving risk behavior; Calculate the comprehensive risk score of the target user based on the first driving risk score and the second driving risk score, generate a driving behavior analysis report for the target user based on the driving data and the comprehensive risk score, and feed the driving behavior analysis report back to the target user terminal.

2. The method for generating a driving behavior analysis report according to claim 1, wherein: The collecting driving data generated by the target user driving the target vehicle within a preset time period includes: Using the target user's mobile terminal as a first information collection device and connecting it to the first information collection device; Utilizing the camera function module in the first information collection device to collect user behavior data of the target user; Calling the GPS positioning module and the sensor module in the first information collection device to record the driving data of the target vehicle; The driving data and the user behavior data are collected to obtain the driving data of the target user.

3. The method for generating a driving behavior analysis report according to claim 1, wherein: The collecting driving data generated by the target user driving the target vehicle within a preset time period includes: Using the in-vehicle camera of the target vehicle as a second information collection device, and using the second information collection device to collect user behavior data of the target user; Using the onboard system of the target vehicle as a third information collection device, and using the third information collection device to record the driving data of the target vehicle; The driving data and the user behavior data are collected to obtain the driving data of the target user.

4. The method for generating a driving behavior analysis report according to claim 1, wherein: The identifying, from the driving data, a first preset type of driving risk behavior of the target user during driving, includes: Identifying whether the target user has exceeded the speed limit based on the speed information in the driving data; Identifying, based on acceleration information in the driving data, whether the target user has sudden acceleration behavior; identifying whether the target user has sudden deceleration behavior based on the deceleration information in the driving data; identifying whether the target user has made a sharp turn based on the angular velocity information, amplitude information, and speed information in the driving data; According to the recognition result of whether the target user has speeding behavior, sudden acceleration behavior, sudden deceleration behavior and sharp turning behavior, a first preset type of driving risk behavior of the target user during the driving process is obtained.

5. The method for generating a driving behavior analysis report according to claim 1, wherein: Obtaining a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior includes: Obtaining from a preset database a first preset type of driving risk behavior scoring model that pre-defines frequency weights and risk level weights corresponding to different first preset types of driving risk behaviors; The frequency and risk level of the first preset type of driving risk behavior are scored using the first preset type of driving risk behavior scoring model to obtain a first driving risk score for the target user.

6. The method for generating a driving behavior analysis report according to claim 1, wherein: The analyzing the user behavior data to obtain a second preset type of driving risk behavior of the target user during driving includes: Identifying whether the target user has fatigue driving behavior based on travel time information in the driving data; Using a preset image processing model to process each behavior image in the user behavior data, identifying whether the target user uses a communication device, including the number of times the target user makes or receives a call, and the number of times the target user sends or reads text messages; According to the identification result of whether the target user has fatigue driving behavior and communication device usage behavior, a second preset type of driving risk behavior occurring in the driving process of the target user is obtained.

7. The method for generating a driving behavior analysis report according to claim 1, wherein: Obtaining a second driving risk score for the target user based on the number of driving risk behaviors of the second preset type includes: Obtaining from a preset database a second preset type of driving risk behavior deduction model that predefines deduction standards corresponding to different second preset types of driving risk behaviors; The second preset type of driving risk behavior scoring model is used to score the number and type of the second preset type of driving risk behavior to obtain a second driving risk score for the target user.

8. A driving behavior analysis report generating device, characterized in that: The device comprises: A detection module is used to collect driving data generated by a target user driving a target vehicle within a preset time period, wherein the driving data includes travel data of the target vehicle and user behavior data generated by the target user during the driving process; an analysis module, configured to identify, from the driving data, a first preset type of driving risk behavior that occurs during driving by the target user, identify, from the driving data, a frequency and a risk level of the first preset type of driving risk behavior, and obtain a first driving risk score for the target user based on the frequency and risk level of the first preset type of driving risk behavior; an identification module, configured to analyze the user behavior data to obtain a second preset type of driving risk behavior that occurs during the driving process of the target user, identify the number of occurrences of the second preset type of driving risk behavior from the driving data, and obtain a second driving risk score for the target user based on the number of occurrences of the second preset type of driving risk behavior; A calculation module is configured to calculate a comprehensive risk score for the target user based on the first driving risk score and the second driving risk score, generate a driving behavior analysis report for the target user based on the driving data and the comprehensive risk score, and feed the driving behavior analysis report back to the target user terminal.

9. A device, characterized in that The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a driving behavior analysis report generation program that can be executed by the at least one processor, and the driving behavior analysis report generation program is executed by the at least one processor so that the at least one processor can execute the driving behavior analysis report generation method 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 driving behavior analysis report generation program, and the driving behavior analysis report generation program can be executed by one or more processors to implement the driving behavior analysis report generation method according to any one of claims 1 to 7.

Images