A driving style recognition method, device and electronic equipment

Abstract

The present disclosure provides a driving style recognition method and device, electronic equipment, chip and medium, and relates to the field of vehicle big data. The method comprises: obtaining driving big data of a vehicle, the driving big data comprising longitudinal acceleration, lateral acceleration and driving speed; determining acceleration longitudinal score and lateral score by respectively performing weighted summation on the distribution proportion of the longitudinal acceleration and the lateral acceleration in each corresponding interval; obtaining a vehicle speed score by performing weighted summation on the distribution proportion of the driving speed in each interval, and taking the weight value corresponding to the interval in which the average of the vehicle speed score is located as a vehicle speed correction parameter; and determining the driving style by multiplying the weighted sum of the acceleration longitudinal score and the lateral score and the vehicle speed correction parameter. Through the technical solution provided by the present disclosure, the problem of single reference data in driving style evaluation and the problem of inability to truly reflect the driving style are solved, the reference data for driving style evaluation is enriched, and the accuracy of driving style recognition is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle big data, and in particular to a driving style recognition method, device, and electronic device. Background Technology

[0002] With the increasing number of cars in my country and the rapid evolution of vehicle-to-everything (V2X) technology, massive amounts of user driving data can be obtained. Based on this driving big data, vehicle performance and driver driving styles can be evaluated, providing data support and development direction for vehicle intelligence. Among these, driving style recognition based on vehicle big data focuses on enabling vehicles to understand driver habits, creating a driver driving style profile, and thus providing drivers with a safer and more comfortable driving experience.

[0003] In related technologies, longitudinal acceleration data is usually used to model and analyze data based on engineering experience in order to evaluate driving style. However, since the acceleration capabilities of the same vehicle model vary at different speeds, using only longitudinal acceleration data as reference data and models built based on engineering experience cannot truly reflect driving style. Summary of the Invention

[0004] This disclosure provides a driving style recognition method, device, electronic device, chip, and medium to address the problem of limited reference data that fails to accurately reflect driving style. It acquires large amounts of vehicle driving data; determines longitudinal and lateral acceleration scores by weighted summation of the distribution ratios of longitudinal and lateral acceleration in their respective intervals; obtains a vehicle speed score by weighted summation of the distribution ratios of driving speed in each interval; and uses the weight value corresponding to the interval containing the average vehicle speed score as a vehicle speed correction parameter. Finally, it determines the driving style by multiplying the weighted sum of the longitudinal and lateral acceleration scores with the vehicle speed correction parameter. This enriches the reference data for driving style evaluation and improves the accuracy of driving style recognition.

[0005] A first aspect of this disclosure provides a driving style recognition method, the method comprising:

[0006] Acquire vehicle driving big data, which includes longitudinal acceleration, lateral acceleration, and driving speed;

[0007] The longitudinal acceleration score and lateral acceleration score are determined by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals. The intervals are multiple numerical ranges for longitudinal acceleration and lateral acceleration based on their numerical values. The longitudinal acceleration score and lateral acceleration score are used to characterize the influence factors of longitudinal acceleration and lateral acceleration on driving style, respectively.

[0008] The vehicle speed score is obtained by weighted summation of the distribution ratio of driving speed in each interval. The weight value corresponding to the interval where the average vehicle speed score is located is used as the vehicle speed correction parameter. The vehicle speed correction coefficient is used to characterize the influence factor of driving speed on driving style.

[0009] The driving style is determined by multiplying the weighted sum of the longitudinal and lateral acceleration scores with the vehicle speed correction parameter.

[0010] In some embodiments, obtaining vehicle driving big data includes:

[0011] To track the vehicle's mileage;

[0012] If the mileage is greater than or equal to the mileage threshold, then the vehicle's driving big data is obtained.

[0013] In some embodiments, the longitudinal acceleration score and the lateral acceleration score are determined by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals, including:

[0014] The longitudinal acceleration is divided into at least two first intervals according to its numerical value. The first distribution ratio in each of the at least two intervals is statistically analyzed. The longitudinal score of the acceleration is determined by weighted summation of the at least two first distribution ratios and their corresponding first weight lists. The first interval is the numerical range determined by the value of the longitudinal acceleration, and the first weight list is the weight sequence of the at least two first distribution ratios.

[0015] Lateral acceleration is divided into at least two second intervals according to its numerical value. The second distribution ratio in each of the at least two intervals is statistically analyzed. The lateral acceleration score is determined by weighted summation of the at least two second distribution ratios and their corresponding second weight lists. The second interval is the numerical range determined by the value of lateral acceleration, and the second weight list is the weight sequence of the at least two second distribution ratios.

[0016] In some embodiments, before obtaining the vehicle speed score by weighted summation of the distribution ratios of driving speeds in each interval, and using the weight value corresponding to the interval where the average vehicle speed score is located as the vehicle speed correction parameter, the method further includes:

[0017] Remove driving data where the driving speed is less than the speed threshold.

[0018] In some embodiments, a vehicle speed score is obtained by weighted summation of the distribution ratios of driving speeds across different intervals, and the weight value corresponding to the interval containing the average vehicle speed score is used as the vehicle speed correction parameter, including:

[0019] The driving speed is divided into at least two third intervals according to its numerical value. The third distribution ratio in each of the at least two intervals is statistically analyzed. The vehicle speed correction parameter is determined by the average of the weighted sum of the at least two third distribution ratios and their corresponding third weight lists. The third interval is the numerical range determined by the driving speed value, and the third weight list is the weight sequence of the at least two third distribution ratios.

[0020] In some embodiments, prior to acquiring the vehicle's driving big data, the method further includes:

[0021] Based on preset data and the total score of driving style, a first weight list, a second weight list, and a third weight list are determined. The first weight list, the second weight list, and the third weight list are the weight parameter sequences of the first distribution ratio, the second distribution ratio, and the third distribution ratio, respectively. The preset data is collected from vehicles whose power performance, braking performance, and handling performance all correspond to the same range of performance parameters.

[0022] In some embodiments, the vehicle speed is divided into at least two third intervals according to its numerical value, the proportion of the third distribution in each of the at least two intervals is calculated, and the vehicle speed correction parameter is determined by the weighted average of the at least two third distribution proportions and their corresponding third weight lists. The method further includes:

[0023] Determine the average speed of driving in the big data of driving;

[0024] Based on the average speed, the speed weight corresponding to the average speed is determined in the third interval, and the third weight list includes the speed weights;

[0025] Speed ​​weights are used as vehicle speed correction parameters.

[0026] In some embodiments, the longitudinal acceleration score and the lateral acceleration score are determined by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals, and further include:

[0027] The sum of each first score value in at least two first intervals is determined as the acceleration longitudinal score. The first score value is the product of the preset upper limit of the score and the first distribution ratio and its corresponding first weight in the first weight list.

[0028] The sum of each second score value in at least two second intervals is determined as the acceleration lateral score. The second score value is the product of the preset upper limit of the score and the second distribution ratio and its corresponding second weight in the second weight list.

[0029] In some embodiments, determining the product of a weighted sum of longitudinal acceleration scores and lateral acceleration scores with a vehicle speed correction parameter to determine driving style includes:

[0030] The weighted sum of the longitudinal acceleration score and the lateral acceleration score is determined as the acceleration influence parameter;

[0031] The product of the acceleration effect parameter and the vehicle speed correction parameter is determined as the total driving style score;

[0032] The style category corresponding to the range of the total driving style score is determined as the driving style.

[0033] In some embodiments, after determining the product of the weighted sum of the longitudinal acceleration score and the lateral acceleration score with the vehicle speed correction parameter to determine the driving style, the method further includes:

[0034] Obtain the latest driving data of vehicles;

[0035] Based on the latest driving data, the driving style has been updated.

[0036] A second aspect of this disclosure provides a driving style recognition device, the device comprising:

[0037] The acquisition module is used to acquire big data on vehicle movement, including longitudinal acceleration, lateral acceleration, and speed.

[0038] The first scoring module is used to determine the longitudinal acceleration score and the lateral acceleration score by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals. The intervals are multiple numerical ranges for longitudinal acceleration and lateral acceleration based on their numerical values. The longitudinal acceleration score and the lateral acceleration score are used to characterize the influence factors of longitudinal acceleration and lateral acceleration on driving style, respectively.

[0039] The second scoring module is used to obtain the vehicle speed score by weighted summation of the distribution ratio of driving speed in each interval. The weight value corresponding to the interval where the average vehicle speed score is located is used as the vehicle speed correction parameter. The vehicle speed correction coefficient is used to characterize the influence factor of driving speed on driving style.

[0040] The determination module is used to determine the product of the weighted sum of the longitudinal and lateral acceleration scores and the vehicle speed correction parameters to determine the driving style.

[0041] A third aspect of this disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the methods described in the first aspect of this disclosure.

[0042] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, characterized in that the computer instructions are used to cause a computer to perform the method described in the first aspect of this disclosure.

[0043] A fifth aspect of this disclosure provides a computer program product characterized by comprising a computer program that, when executed by a processor, implements the method of any one of the first aspects of this disclosure.

[0044] A sixth aspect of this disclosure provides a chip including at least one processor and a communication interface; the communication interface is used to receive signals input to the chip or signals output from the chip, and the processor communicates with the communication interface and implements the method of any one of the first aspects of this disclosure through logic circuits or executing code instructions.

[0045] A seventh aspect of this disclosure provides a vehicle including a driving style recognition device according to a second aspect embodiment.

[0046] In summary, based on the driving style recognition method proposed in this disclosure, large-scale vehicle driving data is acquired, including longitudinal acceleration, lateral acceleration, and driving speed, providing a massive data source for driving style recognition. The longitudinal and lateral acceleration scores are determined by weighted summation of the distribution ratios within their respective intervals. Each interval represents a numerical range for both longitudinal and lateral acceleration based on their magnitude. The longitudinal and lateral acceleration scores are used to characterize the influence factors of longitudinal and lateral acceleration on driving style, providing multi-directional acceleration influence factors for driving style recognition. The vehicle speed score is obtained by weighted summation of the distribution ratios of driving speed across each interval. The weight value corresponding to the interval containing the average vehicle speed score is used as the vehicle speed correction parameter. The vehicle speed correction coefficient characterizes the influence factor of driving speed on driving style, providing a driving speed influence factor for driving style recognition. The driving style is determined by multiplying the weighted sum of the longitudinal and lateral acceleration scores with the vehicle speed correction parameter, thus completing the recognition of the driver's driving style. This enriches the reference data for driving style evaluation and improves the accuracy of driving style recognition.

[0047] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0049] Figure 1 This is a flowchart of a driving style recognition method according to an embodiment of the present disclosure;

[0050] Figure 2 This is a flowchart illustrating one method of acquiring vehicle driving big data according to an embodiment of this disclosure;

[0051] Figure 3 This is a flowchart illustrating an embodiment of the present disclosure of determining the longitudinal acceleration score and the lateral acceleration score by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective corresponding intervals.

[0052] Figure 4 This is a flowchart illustrating a method for cleaning driving speed data according to an embodiment of this disclosure;

[0053] Figure 5 This is a flowchart illustrating an embodiment of the present disclosure of obtaining a vehicle speed score by weighted summation of the distribution ratios of driving speeds in various intervals, and using the weight value corresponding to the interval where the average vehicle speed score is located as the vehicle speed correction parameter.

[0054] Figure 6 This is a flowchart illustrating a calibration weight data according to an embodiment of the present disclosure;

[0055] Figure 7 This is a flowchart of an embodiment of the present disclosure, which describes how to divide the driving speed into at least two third intervals according to the numerical value, statistically analyze the third distribution ratio in each of the at least two intervals, and determine the vehicle speed correction parameter by weighted summation of the at least two third distribution ratios and their corresponding third weight lists.

[0056] Figure 8 This is a flowchart illustrating an embodiment of the present disclosure of determining the longitudinal acceleration score and the lateral acceleration score by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective corresponding intervals.

[0057] Figure 9 This is a flowchart illustrating an embodiment of the present disclosure of determining the product of a weighted sum of longitudinal acceleration scores and lateral acceleration scores with a vehicle speed correction parameter to determine a driving style.

[0058] Figure 10 This is a flowchart illustrating an embodiment of the present disclosure of updating driving style;

[0059] Figure 11 This is a schematic diagram of a different driving style curve according to an embodiment of the present disclosure;

[0060] Figure 12 This is a schematic diagram of the structure of a driving style recognition device according to an embodiment of the present disclosure;

[0061] Figure 13 This is a block diagram illustrating an electronic device for implementing the driving style recognition method of the present disclosure, according to an exemplary embodiment;

[0062] Figure 14 This is a schematic diagram of the chip structure according to an embodiment of the present disclosure. Detailed Implementation

[0063] Embodiments of this disclosure are described in detail below, with examples of embodiments shown in the accompanying drawings, wherein the same or similar reference numerals identify the same or similar originals or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0064] First, let's briefly introduce the relevant terms used in this disclosure:

[0065] Longitudinal acceleration: In this disclosure, it refers to the acceleration along the direction of vehicle movement, which is generally defined as the positive x-axis direction in the vehicle coordinate system.

[0066] Lateral acceleration: In this disclosure, it refers to the acceleration in the direction perpendicular to the vehicle's forward movement, which is generally defined as the positive y-axis direction in the vehicle coordinate system.

[0067] Dynamic performance: In this disclosure, it refers to the speed performance of a vehicle when traveling in a straight line on a good road surface, determined by the longitudinal external forces acting on the vehicle. It is mainly evaluated by three aspects: maximum speed, acceleration time, and maximum gradeability. Maximum speed reflects the highest speed that the vehicle can reach; acceleration time shows the time required for the vehicle to reach a certain speed from a standstill, reflecting the vehicle's responsiveness; and maximum gradeability indicates the maximum slope angle that the vehicle can climb when fully loaded.

[0068] Braking performance: In this disclosure, it refers to the ability of a vehicle to decelerate to a stop while in motion, or to maintain a certain speed while descending a slope. Indicators for evaluating braking performance include braking deceleration, braking time, and braking distance. Braking deceleration reflects how quickly a vehicle decelerates to a stop; braking time refers to the time required from when the driver depresses the brake pedal until the vehicle comes to a complete stop; and braking distance is the distance traveled from the start of braking to a complete stop. The shorter the distance, the better the braking performance.

[0069] Handling performance: In this disclosure, it refers to the vehicle's ability to steer and maintain stable driving under the driver's control. It encompasses steering response, vehicle stability during cornering, and handling at the limits. Steering performance involves the driver's response to steering inputs under normal driving conditions, including steering wheel feedback and lateral movement of the vehicle; handling at the limits refers to the vehicle's response and stability under extreme maneuvers, such as rapid obstacle avoidance or high-speed cornering.

[0070] In related technologies, evaluating a driver's driving style solely based on longitudinal acceleration is prone to judgment errors. For example, driver A's average acceleration may be greater than driver B's, but driver A frequently drives on surface roads at relatively lower speeds, making it easier to achieve greater acceleration, while driver B drives more on highways at relatively higher speeds, making it harder to achieve greater acceleration. Therefore, directly comparing longitudinal acceleration easily leads to misjudgment. Furthermore, the limited data available for driving style evaluation cannot fully reflect a driver's style. For instance, on a straight road, driver A's longitudinal acceleration may be greater than driver B's, but driver A's speed, longitudinal acceleration, and lateral acceleration are all low on curves, while driver B, despite having lower longitudinal acceleration, exhibits high speed, longitudinal acceleration, and lateral acceleration on curves. Overall, driver B's driving style appears more aggressive. Analyzing and judging solely based on longitudinal acceleration can lead to identification biases. Moreover, the relevant technologies only analyze and model acceleration based on engineering experience, without using massive amounts of data to create a comprehensive profile of the entire user to determine driving style. This results in a lack of authenticity in the evaluation of the driver's driving style and a low accuracy rate in identification.

[0071] This disclosure aims to address the problem of limited reference data and inability to accurately reflect driving style in driving style evaluation, ensuring a true and accurate assessment of a driver's driving style. By employing a big data-based driving style recognition method, richer reference data can be obtained, leading to a more accurate identification of the driver's driving style.

[0072] The method proposed in this disclosure is applied to driving style recognition tasks, with a wide range of applications. It can be applied to the field of autonomous driving systems, helping them better understand human driver behavior patterns and make decisions similar to humans in similar traffic situations, thus improving the safety and reliability of autonomous vehicles. Furthermore, by assessing the driver's perception of autonomous driving operations, it can increase driver trust and acceptance of autonomous vehicles. It can also be applied to traffic safety, analyzing driver behavior to identify potential dangerous driving habits and designing more effective traffic safety interventions. This helps reduce traffic accidents and improve overall road safety. It can also be applied to personalized services, where automakers can use driving style evaluation technology to develop personalized driver assistance systems that adjust vehicle responsiveness and handling characteristics based on the driver's specific style, achieving a more personalized driving experience. Finally, it can be applied to insurance pricing, where insurance companies can use driving style evaluation technology to assess customers' risk levels and adjust insurance rates accordingly. This usage-based insurance can incentivize drivers to adopt safer driving behaviors while providing insurance companies with more accurate risk assessment tools. It can also be applied to driver training and assessment scenarios. Driving style evaluation technology can serve as a tool for driver training and assessment, helping driving schools and traffic enforcement departments identify drivers' strengths and weaknesses, develop targeted training plans, and improve the overall quality of drivers. It can also be applied to vehicle design and testing. Automotive designers and engineers can use driving style evaluation technology to design and test new models, ensuring they meet the needs of different driving styles and provide better performance and comfort. Furthermore, it can be applied to road planning and management. Urban planners and traffic managers can analyze driving style data to optimize road design and traffic flow management, reduce congestion, and improve road utilization efficiency. The application scenarios are not limited in this disclosure.

[0073] The driving style recognition method provided in this disclosure will now be described in detail with reference to the accompanying drawings. This method can be executed on the vehicle's infotainment system, server, or edge computing device.

[0074] Figure 1 This is a flowchart illustrating a driving style recognition method according to an embodiment of the present disclosure. This driving style recognition method can be executed on a vehicle's in-vehicle infotainment system or on a cloud server, such as... Figure 1 The driving style recognition method shown in the embodiment includes:

[0075] Step 101: Obtain vehicle driving big data, which includes longitudinal acceleration, lateral acceleration, and driving speed.

[0076] In this embodiment, the vehicle's driving big data consists of acceleration and speed data collected by sensors during vehicle operation, including longitudinal acceleration, lateral acceleration, and speed. To identify driving style, the vehicle's driving big data is first collected or retrieved from a database.

[0077] Step 102: The longitudinal acceleration score and the lateral acceleration score are determined by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals. The intervals are multiple numerical ranges for longitudinal acceleration and lateral acceleration based on their numerical values. The longitudinal acceleration score and the lateral acceleration score are used to characterize the influence factors of longitudinal acceleration and lateral acceleration on driving style, respectively.

[0078] In this embodiment, driving style refers to the driver's operating habits when driving the vehicle. Optionally, driving style can be divided into mild, normal, and aggressive. This mainly depends on the frequency and intensity of the driver's use of the vehicle's power unit, braking system, and steering system. For example, if a driver frequently accelerates the power unit by pressing the accelerator, frequently decelerates by pressing the brake (braking system), and frequently adjusts the direction by using the steering wheel (steering system), then that driver's driving style is aggressive. The longitudinal acceleration score is a numerical value used to characterize the influence factor of longitudinal acceleration on driving style. Similar to the longitudinal acceleration score, the lateral acceleration score is also a numerical value used to characterize the influence factor of lateral acceleration on driving style. An interval refers to a numerical range; one interval corresponds to one numerical range. The longitudinal acceleration score is determined by weighted summation of the distribution ratios of each interval corresponding to longitudinal acceleration, and the lateral acceleration score is determined by weighted summation of the distribution ratios of each interval corresponding to lateral acceleration. The distribution ratio refers to the proportion of acceleration values ​​in a certain interval (numerical range) to the total number of acceleration values.

[0079] Step 103: The vehicle speed score is obtained by weighted summation of the distribution ratio of driving speed in each interval. The weight value corresponding to the interval where the average vehicle speed score is located is used as the vehicle speed correction parameter. The vehicle speed correction coefficient is used to characterize the influence factor of driving speed on driving style.

[0080] In this embodiment, the speed correction coefficient is a numerical value used to characterize the influence of vehicle speed on driving style. From the vehicle's large-scale driving data, the weighted sum of the distribution ratios of driving speeds across different intervals yields a speed score, which represents the magnitude of the vehicle's speed during driving. The average speed during driving is obtained by averaging these speed scores, and the weight value corresponding to the speed interval containing this average speed is used as the speed correction parameter. Each speed interval corresponds to a different weight value, representing the sensitivity to changes in vehicle speed.

[0081] Step 104: Determine the product of the weighted sum of the longitudinal acceleration score and the lateral acceleration score with the vehicle speed correction parameter to determine the driving style.

[0082] In this embodiment, the driving style score is obtained by weighted summation of the longitudinal acceleration score and the lateral acceleration score, and multiplied by the vehicle speed correction parameter. The driving style can be determined by classifying the driving style using this score.

[0083] In summary, based on the driving style recognition method proposed in this disclosure, large-scale vehicle driving data is acquired, including longitudinal acceleration, lateral acceleration, and driving speed, providing a massive data source for driving style recognition. The longitudinal and lateral acceleration scores are determined by weighted summation of the distribution ratios within their respective intervals. Each interval represents a numerical range for both longitudinal and lateral acceleration based on their magnitude. The longitudinal and lateral acceleration scores are used to characterize the influence factors of longitudinal and lateral acceleration on driving style, providing multi-directional acceleration influence factors for driving style recognition. The vehicle speed score is obtained by weighted summation of the distribution ratios of driving speed across each interval. The weight value corresponding to the interval containing the average vehicle speed score is used as the vehicle speed correction parameter. The vehicle speed correction coefficient characterizes the influence factor of driving speed on driving style, providing a driving speed influence factor for driving style recognition. The driving style is determined by multiplying the weighted sum of the longitudinal and lateral acceleration scores with the vehicle speed correction parameter, thus completing the recognition of the driver's driving style. This enriches the reference data for driving style evaluation and improves the accuracy of driving style recognition.

[0084] Figure 2 This is a flowchart illustrating one method of acquiring vehicle driving big data according to an embodiment of this disclosure. Figure 2 Yes Figure 1 Further explanation of step 101, based on Figure 2 The illustrated embodiment includes the following steps:

[0085] Step 201: Calculate the vehicle's mileage.

[0086] In this embodiment, the mileage of the vehicle is counted during the process of acquiring the vehicle's driving big data.

[0087] Step 202: If the mileage is greater than or equal to the mileage threshold, then obtain the vehicle's driving big data.

[0088] In this embodiment, the mileage threshold is a numerical value used to represent a large distance traveled. If the mileage is greater than or equal to the mileage threshold, then large amounts of vehicle driving data are acquired. This yields the raw data for driving style recognition.

[0089] Figure 3 This is a flowchart illustrating an embodiment of the present disclosure, which calculates the longitudinal acceleration score and the lateral acceleration score by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals. Figure 3 Yes Figure 1 Further explanation of step 102, based on Figure 3 The illustrated embodiment includes the following steps:

[0090] Step 301: Divide the longitudinal acceleration into at least two first intervals according to its numerical value, calculate the first distribution ratio in each of the at least two intervals, and determine the longitudinal score of the acceleration by weighted summation of the at least two first distribution ratios and their corresponding first weight lists. Here, the first interval is the numerical range determined by the value of the longitudinal acceleration, and the first weight list is the weight sequence of the at least two first distribution ratios.

[0091] In this embodiment, the first interval refers to the numerical range determined by the longitudinal acceleration values. The first distribution ratio refers to the proportion of the longitudinal acceleration value in each first interval to the total number of longitudinal acceleration values. The first weight list refers to the weight sequence of at least two first distribution ratios. In the vehicle's driving big data, the longitudinal acceleration is divided into intervals according to its numerical value. Optionally, it is divided into at least two first intervals, and the first distribution ratio of each interval in the at least two first intervals is calculated. The at least two first distribution ratios and their corresponding first weight lists are used to perform a weighted summation to obtain the longitudinal acceleration score.

[0092] In one embodiment of this example, the maximum longitudinal acceleration is 0.5g, and the minimum is -0.5g, where g represents gravitational acceleration. The longitudinal acceleration from -0.5g to 0.5g is divided into 10 first intervals: A1 = [-0.5g, -0.4g), A2 = [-0.4g, -0.3g), A3 = [-0.3g, -0.2g), A4 = [-0.2g, -0.1g), A5 = [-0.1g, 0g], A6 = [0, 0.1g], A7 = (0.1g, 0.2g], A8 = (0.2g, 0.3g], A9 = (0.3g, 0.4g], A10 = (0.4g, 0.5g). A6 to A10 represent the acceleration generated by the vehicle during refueling, and are in the positive direction of longitudinal acceleration. A1 to A5... This represents the acceleration generated during vehicle braking, which is opposite to the positive direction of longitudinal acceleration. The driving big data consists of longitudinal acceleration, lateral acceleration, and speed statistics collected by the driver over 1000 kilometers. Measured in seconds, for example, 1500 kilometers corresponds to 150,000 seconds, or 150,000 data points. After removing data points with a speed of 0, 120,000 data points remain. These 120,000 data points are then statistically calculated to determine their first distribution proportion within the aforementioned 10 first intervals. If braking was performed throughout the entire driving process, the first distribution proportions for these 120,000 seconds, corresponding to the five first intervals A6-A10, are 70%, 15%, 10%, 5%, and 0%, respectively.

[0093] Corresponding to this first distribution ratio, the first weight list is set to K11, K12, K13, K14, and K15, as shown in Table 1 below. The longitudinal acceleration score corresponding to the longitudinal acceleration can be expressed as X = 0.7K11 + 0.15K12 + 0.1K13 + 0.05K14 + 0.

[0094] Table 1 List of first weights corresponding to the first interval

[0095] First section A6 A7 A8 A9 A10 First distribution ratio 70％ 15％ 10％ 5％ 0％ First weight K11 K12 K13 K14 K15 Score 0.7K11 0.15K12 0.1K13 0.05K14 0

[0096] Step 302: Divide the lateral acceleration into at least two second intervals according to its numerical value, and calculate the second distribution ratio in each of the at least two intervals. Then, perform a weighted summation using the at least two second distribution ratios and their corresponding second weight lists to determine the lateral acceleration score. Here, the second interval is the numerical range determined by the value of the lateral acceleration, and the second weight list is the weight sequence of the at least two second distribution ratios.

[0097] In this embodiment, the second interval refers to the numerical range determined by the lateral acceleration values. The second distribution ratio refers to the proportion of the lateral acceleration value in each second interval to the total number of lateral acceleration values. The second weight list refers to the weight sequence of at least two second distribution ratios. In the vehicle's driving big data, the lateral acceleration is divided into intervals according to its numerical value. Optionally, it is divided into at least two second intervals, and the second distribution ratio of each interval is calculated. The weighted sum of the at least two second distribution ratios and their corresponding second weight lists is used as the lateral acceleration score.

[0098] In one embodiment of this example, the maximum value of the lateral acceleration is 0.3g and the minimum value is 0. The lateral acceleration is divided into three second intervals: B1 = [0, 0.1g], B2 = (0.1g, 0.2g], and B3 = (0.2g, 0.3g). Of the 120,000 data points, the proportion of the second distribution in B1 is 80%, in B2 it is 15%, and in B3 it is 5%. The second weight list is set to K21, K22, and K23. Therefore, the lateral acceleration score corresponding to the lateral acceleration can be expressed as Y = 0.8K21 + 0.15K22 + 0.05K23.

[0099] In this embodiment, the influence scores X and Y of acceleration on driving style establishment are determined based on longitudinal and lateral acceleration data from the vehicle's driving big data.

[0100] Figure 4 This is a flowchart illustrating a method for cleaning driving speed data according to an embodiment of this disclosure. Figure 4 Yes Figure 1 The specific explanation prior to step 103 is based on Figure 4 The illustrated embodiment includes the following steps:

[0101] Step 401: Remove driving data with a speed lower than the speed threshold.

[0102] In this embodiment, the speed threshold is a numerical value used to represent an extremely slow vehicle speed. Data with speeds lower than the speed threshold from the vehicle's large driving data is removed, retaining only speeds greater than or equal to the speed threshold, longitudinal acceleration, and lateral acceleration for driving style recognition. For example, removing speed values ​​when the vehicle is stationary, thus "cleaning" the driving speed data, can improve data processing efficiency.

[0103] Figure 5 This is a flowchart illustrating an embodiment of the present disclosure where a vehicle speed score is obtained by weighted summation of the distribution ratios of driving speeds across various intervals, and the weight value corresponding to the interval containing the average vehicle speed score is used as a vehicle speed correction parameter. Figure 5 Yes Figure 1 The specific explanation of step 103 is based on Figure 5 The illustrated embodiment includes the following steps:

[0104] Step 501: Divide the driving speed into at least two third intervals according to the numerical value, and calculate the third distribution ratio in each of the at least two intervals. Determine the vehicle speed correction parameter by weighted summation of the at least two third distribution ratios and their corresponding third weight lists. Here, the third interval is the numerical range determined by the driving speed value, and the third weight list is the weight sequence of the at least two third distribution ratios.

[0105] In this embodiment, the third interval refers to the numerical range determined by the driving speed values. The third distribution ratio refers to the proportion of the driving speed value in each third interval to the total number of driving speed values. The third weight list refers to the weight sequence of at least two third distribution ratios. In the vehicle's large driving data, the driving speed is divided into intervals according to its numerical value. Optionally, it is divided into at least two third intervals, and the third distribution ratio of each interval in the at least two third intervals is calculated. The at least two third distribution ratios and their corresponding third weight lists are weighted and summed, and then the average is calculated as the vehicle speed correction parameter.

[0106] In one embodiment of this example, the driving speed is divided into five third intervals: C1 = (0, 30 km / h), C2 = (30 km / h, 50 km / h), C3 = (50 km / h, 70 km / h), C4 = (70 km / h, 100 km / h), and C5 = (100 km / h, +∞). In the vehicle's large-scale driving data, among 120,000 data points, the driving speed falls within the C1 range by 10%, within the C2 range by 20%, within the C3 range by 50%, within the C4 range by 10%, and within the C5 range by 10%. The third weight lists corresponding to these five third intervals are K31, K32, K33, K34, and K35, respectively. The vehicle speed correction coefficient V = (0.1K31 + 0.2K32 + 0.5K33 + 0.1K34 + 0.1K35) / 5.

[0107] In this embodiment, a vehicle speed correction coefficient corresponding to the driving speed is determined, which provides an influencing factor of the speed variable for driving style recognition, and is conducive to obtaining a more accurate and realistic driving style.

[0108] Figure 6 This is a flowchart illustrating a calibration weight data according to an embodiment of the present disclosure. Figure 6 Yes Figure 1 The specific explanation given before step 101 is for Figure 3First weight list, second weight list or Figure 5 The interpretation of the third weighted list is based on Figure 6 The illustrated embodiment includes the following steps:

[0109] Step 601: Based on the preset data and the total score of driving style, determine the first weight list, the second weight list and the third weight list. The first weight list, the second weight list and the third weight list are the weight parameter sequences of the first distribution ratio, the second distribution ratio and the third distribution ratio, respectively. The preset data is collected from vehicles whose power performance, braking performance and handling performance all correspond to the same range of performance parameters.

[0110] In this embodiment, driving style is calibrated in a laboratory by collecting driving big data from vehicles with three standard driving styles: mild, normal, and aggressive. This standard driving big data is preset data. To ensure the accuracy of the calibration data, vehicles with similar power performance, braking performance, and handling performance are selected as data collection vehicles. Optionally, in terms of performance, the difference in acceleration time from 0 to 100 km / h is within 15%; in terms of braking performance, the difference in stopping distance from 100 km / h to 0 is within 5%; and in terms of handling performance, the difference in maximum lateral acceleration is within 10%. Vehicles that meet all three aspects are selected as target data collection vehicles. Optionally, the conditions of a wheelbase difference of 200 mm and a weight difference of 200 kg within 200 kg can be added as additional conditions to filter target data collection vehicles. The corresponding scores are driving style scores for different driving data. Using preset data and the total score of driving style, the first weight list, the second weight list, and the third weight list are calculated, where the first weight list, the second weight list, and the third weight list are the weight parameter sequences of the first distribution ratio, the second distribution ratio, and the third distribution ratio, respectively.

[0111] In this embodiment, the weight values ​​in the first weight list, second weight list, and third weight list corresponding to longitudinal acceleration, lateral acceleration, and driving speed are calibrated by using preset data and the total score of driving style, thereby ensuring accurate identification of the driver's driving style and improving the authenticity of the driving style judgment.

[0112] Figure 7 This is a flowchart illustrating an embodiment of the present disclosure, which describes how to divide driving speed into at least two third intervals according to numerical value, statistically analyze the third distribution ratio in each of the at least two intervals, and determine the vehicle speed correction parameter by weighted summation of the at least two third distribution ratios and their corresponding third weight lists. Figure 7 Yes Figure 5 Another explanation of step 501 is based on Figure 7The illustrated embodiment includes the following steps:

[0113] Step 701: Determine the average speed of the driving data.

[0114] In this embodiment, the average speed of driving in the big data of driving is taken as the average speed of driving.

[0115] Step 702: Based on the average speed, determine the speed weight corresponding to the average speed in the third interval. The third weight list includes the speed weights.

[0116] In this embodiment, based on the average speed, the speed weight corresponding to the average speed is determined in the third interval, wherein the speed weight is included in the third weight list.

[0117] Step 703: Use speed weight as the vehicle speed correction parameter.

[0118] In this embodiment, the speed weight is used as the vehicle speed correction coefficient, thereby determining the influence factor of speed on driving style recognition.

[0119] Figure 8 This is a flowchart illustrating an embodiment of the present disclosure, which calculates the longitudinal acceleration score and the lateral acceleration score by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals. Figure 8 Yes Figure 1 Step 102 and Figure 3 Another explanation is based on Figure 8 The illustrated embodiment includes the following steps:

[0120] Step 801: The sum of each first score value in at least two first intervals is determined as the acceleration longitudinal score. The first score value is the product of the preset upper limit of the score and the first distribution ratio and its corresponding first weight in the first weight list.

[0121] In this embodiment, the first score value refers to the product of a preset upper limit score and the first distribution ratio and its corresponding first weight in the first weight list, used to represent the score of each interval. The acceleration longitudinal score corresponding to longitudinal acceleration and the acceleration lateral score corresponding to lateral acceleration can also be set by deduction. The sum of each first score value in at least two first intervals is taken as the acceleration longitudinal score.

[0122] In one embodiment of this example, the preset score limit is 10 points, combined with... Figure 3 The data in Table 1 of the embodiment can be expressed as X = (10 - 0.7K11) + (10 - 0.15K12) + (10 - 0.1K13) + (10 - 0.05K14) + 0.

[0123] Step 802: The sum of each second score value in at least two second intervals is determined as the acceleration lateral score. The second score value is the product of the preset upper limit of the score and the second distribution ratio and its corresponding second weight in the second weight list.

[0124] In this embodiment, the second score value is the product of a preset upper limit score and the second distribution ratio and its corresponding second weight in the second weight list. The sum of each second score value in at least two second intervals is used as the acceleration lateral score.

[0125] In one embodiment of this invention, the preset score cap is 10 points, combined with... Figure 3 The lateral acceleration data of the embodiment is then calculated as follows: lateral acceleration score Y = (10 - 0.8K21) + (10 - 0.15K22) + (10 - 0.05K23).

[0126] In this embodiment, the calculation methods used for both the longitudinal acceleration score and the lateral acceleration score must be consistent. The method provided in this embodiment offers another way to calculate the longitudinal and lateral acceleration scores.

[0127] Figure 9 This is a flowchart illustrating an embodiment of the present disclosure of determining the product of a weighted sum of longitudinal acceleration scores and lateral acceleration scores with a vehicle speed correction parameter to determine a driving style. Figure 9 Yes Figure 1 The explanation in step 104 is based on Figure 9 The illustrated embodiment includes the following steps:

[0128] Step 901: The weighted sum of the longitudinal acceleration score and the lateral acceleration score is determined as the acceleration influence parameter.

[0129] In this embodiment, the acceleration influence parameter represents the total influence factor of acceleration on driving style in driving style recognition. The longitudinal acceleration score X and the lateral acceleration score Y are weighted and summed to form the acceleration influence parameter M, that is, M = k1*X + k2*Y, where k1 represents the weight factor of the longitudinal acceleration score X and k2 represents the weight factor of the lateral acceleration score Y.

[0130] Step 902: The product of the acceleration influence parameter and the vehicle speed correction parameter is determined as the total driving style score.

[0131] In this embodiment, the acceleration influence parameter M and the vehicle speed correction parameter V are multiplied together to obtain the total driving style score P, i.e., P = M * V.

[0132] Step 903: Determine the driving style by identifying the style category corresponding to the range of the total driving style score.

[0133] In this embodiment, based on the total driving style score P, the category of the driving style corresponding to the total driving style score P is determined using the numerical range defined for different driving styles. One possible implementation is to classify using a preset numerical range. Another possible implementation is to classify using a clustering algorithm.

[0134] In this embodiment, the total driving style score is determined by the lateral acceleration score, longitudinal acceleration score, and vehicle speed correction parameters, thereby classifying the driving style and providing the driver with accurate driving style identification.

[0135] Figure 10 This is a flowchart illustrating an updated driving style according to an embodiment of the present disclosure. Figure 10 Yes Figure 1 Further explanation following step 104, based on Figure 10 The illustrated embodiment includes the following steps:

[0136] Step 1001: Obtain the latest driving data of the vehicle.

[0137] In this embodiment, after the driving style is determined, the vehicle continues to acquire the latest driving big data.

[0138] Step 1002: Update the driving style based on the latest driving data.

[0139] In this embodiment, the driving style is continuously determined using the latest driving big data obtained and the aforementioned driving style recognition method to complete the data update of the driving style. This provides a continuously accurate recognition of the driver's driving style.

[0140] Figure 11 This is a schematic diagram of a different driving style curve according to an embodiment of this disclosure. Figure 11As shown, the horizontal axis represents the total driving style score, and the vertical axis represents the number of drivers. The graph contains four normal distribution curves, each corresponding to a target mode; that is, there are four modes in total: a, b, c, and d. The total driving style score for each mode depends on the weight values ​​of different acceleration and speed ranges. For example, in mode a, the total driving style score is generally lower compared to modes b, c, and d, corresponding to a lower speed correction coefficient or acceleration influence parameter. A lower speed correction coefficient indicates that the vehicle speed is concentrated in a certain range, with very little data in other excessively fast or slow speed ranges, suggesting that drivers in mode a maintain stable speed control. A lower acceleration influence parameter indicates that the longitudinal or lateral acceleration of the driver is likely relatively small, suggesting that drivers in mode a rarely accelerate or brake rapidly, instead using low acceleration and infrequent use of the accelerator and brake. Considering the speed and acceleration variation data of drivers in mode a, it can be concluded that the driving style of drivers in mode a is a stable and conservative type. Furthermore, in the overall driver data statistics, the number of drivers with a stable and conservative driving style is relatively large, only fewer than those in mode D, but more than those in modes C and D. In mode B, driving styles are very diverse, ranging from very conservative to very aggressive, with the majority being drivers with a moderate driving style score. This indicates that mode B drivers often cause significant changes in speed and acceleration. This mode includes both aggressive and stable / conservative drivers, with the majority having a normal driving style, but the number of mode B drivers is very small. In mode D, the total driving style score is almost entirely concentrated in the moderate range; in other words, mode D drivers have a normal driving style that is neither conservative nor aggressive, and the vast majority of drivers belong to this category. Mode C represents a transitional driving style between modes B and D, incorporating more slightly aggressive maneuvers than mode D, but the number of drivers with a normal driving style is higher than in mode B.

[0141] In summary, by setting the weights of speed, longitudinal acceleration, and lateral acceleration in different numerical ranges, we can focus on analyzing the current weighted pattern. In the distribution of the total driving style score corresponding to this pattern, the driver's fine operating habits or refined driving style can be further analyzed in detail.

[0142] In one embodiment of this example, as shown in Table 2 below, in the third weight list corresponding to the third interval, if it is necessary to analyze drivers with a low-speed driving style, the weight list corresponding to the third interval can be set as follows. This allows for the analysis of other fine-tuning driving habits of the driver after determining the processing mode for the driving speed.

[0143] Table 2. Weight list corresponding to the third interval.

[0144] Third section C1 C2 C3 C4 C5 Third weight 1.2 1.1 1 0.9 0.8

[0145] This disclosure provides a driving style recognition method. It acquires large-scale vehicle driving data, including longitudinal acceleration, lateral acceleration, and driving speed, providing a massive data source for driving style recognition. Weighted summations are performed on the distribution ratios of each corresponding interval to determine longitudinal and lateral acceleration scores. Each interval represents a numerical range for both longitudinal and lateral acceleration, and these scores characterize the influence of longitudinal and lateral acceleration on driving style, providing multi-directional acceleration influence factors for driving style recognition. A speed score is obtained by weighted summations of the distribution ratios of driving speed across intervals. The weight value corresponding to the interval containing the average speed score is used as a speed correction parameter. This speed correction coefficient characterizes the influence of driving speed on driving style, providing a speed influence factor for driving style recognition. The weighted sum of the longitudinal and lateral acceleration scores is multiplied by the speed correction parameter to determine the driving style, thus completing the recognition of the driver's driving style. This enriches the reference data for driving style evaluation and improves the accuracy of driving style recognition.

[0146] Corresponding to the methods provided in the above embodiments, this disclosure also provides a driving style recognition device. Since the device provided in this disclosure corresponds to the methods provided in the above embodiments, the implementation of the methods is also applicable to the device provided in this embodiment, and will not be described in detail in this embodiment.

[0147] Figure 12 This is a schematic diagram of the structure of a driving style recognition device 1200 according to an embodiment of this disclosure. Figure 12 As shown, the driving style recognition device includes:

[0148] The acquisition module 1210 is used to acquire the vehicle's driving big data, which includes longitudinal acceleration, lateral acceleration, and driving speed.

[0149] The first scoring module 1220 is used to determine the longitudinal acceleration score and the lateral acceleration score by weighted summation of the distribution ratios of longitudinal acceleration and lateral acceleration in their respective intervals. The intervals are multiple numerical ranges for longitudinal acceleration and lateral acceleration based on their numerical values. The longitudinal acceleration score and the lateral acceleration score are used to characterize the influence factors of longitudinal acceleration and lateral acceleration on driving style, respectively.

[0150] The second scoring module 1230 is used to obtain the vehicle speed score by weighted summation of the distribution ratio of driving speed in each interval. The weight value corresponding to the interval where the average vehicle speed score is located is used as the vehicle speed correction parameter. The vehicle speed correction coefficient is used to characterize the influence factor of driving speed on driving style.

[0151] The determination module 1240 is used to determine the product of the weighted sum of the longitudinal acceleration score and the lateral acceleration score and the vehicle speed correction parameter to determine the driving style.

[0152] In some embodiments, the acquisition module 1210 is used for:

[0153] To track the vehicle's mileage;

[0154] If the mileage is greater than or equal to the mileage threshold, then the vehicle's driving big data is obtained.

[0155] In some embodiments, the first scoring module 1220 is used for:

[0156] The longitudinal acceleration is divided into at least two first intervals according to its numerical value. The first distribution ratio in each of the at least two intervals is statistically analyzed. The longitudinal score of the acceleration is determined by weighted summation of the at least two first distribution ratios and their corresponding first weight lists. The first interval is the numerical range determined by the value of the longitudinal acceleration, and the first weight list is the weight sequence of the at least two first distribution ratios.

[0157] Lateral acceleration is divided into at least two second intervals according to its numerical value. The second distribution ratio in each of the at least two intervals is statistically analyzed. The lateral acceleration score is determined by weighted summation of the at least two second distribution ratios and their corresponding second weight lists. The second interval is the numerical range determined by the value of lateral acceleration, and the second weight list is the weight sequence of the at least two second distribution ratios.

[0158] In some embodiments, before the second scoring module 1230 obtains the vehicle speed score by weighted summation of the distribution ratio of driving speed in each interval, and uses the weight value corresponding to the interval where the average vehicle speed score is located as the vehicle speed correction parameter, it is further configured to:

[0159] Remove driving data where the driving speed is less than the speed threshold.

[0160] In some embodiments, the second scoring module 1230 is used for:

[0161] The driving speed is divided into at least two third intervals according to its numerical value. The third distribution ratio in each of the at least two intervals is statistically analyzed. The vehicle speed correction parameter is determined by the average of the weighted sum of the at least two third distribution ratios and their corresponding third weight lists. The third interval is the numerical range determined by the driving speed value, and the third weight list is the weight sequence of the at least two third distribution ratios.

[0162] In some embodiments, before acquiring the vehicle's driving big data, the acquisition module 1210 is further configured to:

[0163] Based on preset data and the total score of driving style, a first weight list, a second weight list, and a third weight list are determined. The first weight list, the second weight list, and the third weight list are the weight parameter sequences of the first distribution ratio, the second distribution ratio, and the third distribution ratio, respectively. The preset data is collected from vehicles whose power performance, braking performance, and handling performance all correspond to the same range of performance parameters.

[0164] In some embodiments, the second scoring module 1230 is further configured to:

[0165] Determine the average speed of driving in the big data of driving;

[0166] Based on the average speed, the speed weight corresponding to the average speed is determined in the third interval, and the third weight list includes the speed weights;

[0167] Speed ​​weights are used as vehicle speed correction parameters.

[0168] In some embodiments, the first scoring module 1220 is further configured to:

[0169] The sum of each first score value in at least two first intervals is determined as the acceleration longitudinal score. The first score value is the product of the preset upper limit of the score and the first distribution ratio and its corresponding first weight in the first weight list.

[0170] The sum of each second score value in at least two second intervals is determined as the acceleration lateral score. The second score value is the product of the preset upper limit of the score and the second distribution ratio and its corresponding second weight in the second weight list.

[0171] In some embodiments, the determining module 1240 is used to:

[0172] The weighted sum of the longitudinal acceleration score and the lateral acceleration score is determined as the acceleration influence parameter;

[0173] The product of the acceleration effect parameter and the vehicle speed correction parameter is determined as the total driving style score;

[0174] The style category corresponding to the range of the total driving style score is determined as the driving style.

[0175] In some embodiments, after determining the weighted sum of the longitudinal acceleration score and the lateral acceleration score and the product of the vehicle speed correction parameter to determine the driving style, the determining module 1240 is further configured to:

[0176] Obtain the latest driving data of vehicles;

[0177] Based on the latest driving data, the driving style has been updated.

[0178] In summary, this driving style recognition device acquires large-scale vehicle driving data, including longitudinal acceleration, lateral acceleration, and speed. The longitudinal and lateral acceleration scores are determined by weighted summation of the distribution ratios of longitudinal and lateral acceleration across their respective intervals. The intervals are multiple numerical ranges for both longitudinal and lateral acceleration based on their magnitude. These scores characterize the influence of longitudinal and lateral acceleration on driving style. The speed score is obtained by weighted summation of the distribution ratios of speed across different intervals. The weight value corresponding to the interval containing the average speed score is used as a speed correction parameter, representing the influence of speed on driving style. The driving style is determined by multiplying the weighted sum of the longitudinal and lateral acceleration scores by the speed correction parameter. This device addresses the problem of limited reference data in driving style evaluation, which fails to accurately reflect driving style, thus enriching the reference data for driving style evaluation and improving the accuracy of driving style recognition.

[0179] The methods and apparatus provided in the embodiments of this disclosure have been described above. To implement the functions of the methods provided in the embodiments of this disclosure, the electronic device may include a hardware structure and software modules, and may implement the above functions in the form of a hardware structure, software modules, or a hardware structure plus software modules. One of the above functions may be executed in the form of a hardware structure, software modules, or a hardware structure plus software modules.

[0180] Figure 13 This is a block diagram illustrating an electronic device 1300 for implementing the above-described driving style recognition method according to an exemplary embodiment.

[0181] For example, electronic device 1300 can be a mobile phone, computer, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0182] Reference Figure 13The electronic device 1300 may include one or more of the following components: a processing component 1302, a memory 1304, a power supply component 1306, a multimedia component 1308, an audio component 1310, an input / output (I / O) interface 1312, a sensor component 1314, and a communication component 1316.

[0183] Processing component 1302 typically controls the overall operation of electronic device 1300, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 1302 may include one or more processors 1320 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 1302 may include one or more modules to facilitate interaction between processing component 1302 and other components. For example, processing component 1302 may include a multimedia module to facilitate interaction between multimedia component 1308 and processing component 1302.

[0184] Memory 1304 is configured to store various types of data to support the operation of electronic device 1300. Examples of such data include instructions for any application or method operating on electronic device 1300, contact data, phonebook data, messages, pictures, videos, etc. Memory 1304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0185] Power supply component 1306 provides power to various components of electronic device 1300. Power supply component 1306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 1300.

[0186] Multimedia component 1308 includes a screen that provides an output interface between electronic device 1300 and a user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 1308 includes a front-facing camera and / or a rear-facing camera. When electronic device 1300 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0187] Audio component 1310 is configured to output and / or input audio signals. For example, audio component 1310 includes a microphone (MIC) configured to receive external audio signals when electronic device 1300 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 1304 or transmitted via communication component 1316. In some embodiments, audio component 1310 also includes a speaker for outputting audio signals.

[0188] I / O interface 1312 provides an interface between processing component 1302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0189] Sensor assembly 1314 includes one or more sensors for providing state assessments of various aspects of electronic device 1300. For example, sensor assembly 1314 may detect the on / off state of electronic device 1300, the relative positioning of components such as the display and keypad of electronic device 1300, changes in position of electronic device 1300 or a component of electronic device 1300, the presence or absence of user contact with electronic device 1300, the orientation or acceleration / deceleration of electronic device 1300, and temperature changes of electronic device 1300. Sensor assembly 1314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 1314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 1314 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0190] Communication component 1316 is configured to facilitate wired or wireless communication between electronic device 1300 and other devices. Electronic device 1300 can access wireless networks based on communication standards, such as WiFi, 2G or 3G, 4G LTE, 5G NR (NewRadio), or combinations thereof. In one exemplary embodiment, communication component 1316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 1316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0191] In an exemplary embodiment, the electronic device 1300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0192] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1304 including instructions, which can be executed by a processor 1320 of an electronic device 1300 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0193] Embodiments of this disclosure also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the driving style recognition method described in the above embodiments of this disclosure.

[0194] Embodiments of this disclosure also provide a computer program product, including a computer program that is executed by a processor using the driving style recognition method described in the above embodiments of this disclosure.

[0195] Figure 14 This is a schematic diagram of the structure of a chip 1400 for implementing the above-described driving style recognition method, according to an exemplary embodiment.

[0196] Reference Figure 14The chip 1400 includes at least one communication interface 1401 and a processor 1402; the communication interface 1401 is used to receive signals input to the chip 1400 or signals output from the chip 1400, and the processor 1402 communicates with the communication interface 1401 and implements the driving style recognition method described in the above embodiments through logic circuits or executing code instructions.

[0197] Embodiments of this disclosure also propose a vehicle that includes the aforementioned driving style recognition device.

[0198] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0199] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0200] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0201] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0202] It should be understood that various parts of the embodiments of this disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0203] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0204] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a single processing module, or each unit can exist physically separately, or two or more units can be integrated into a single module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The aforementioned storage medium can be a read-only memory, a hard disk, or an optical disk, etc.

[0205] Although embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A driving style recognition method, characterized in that, The method includes: Acquire vehicle driving big data, including longitudinal acceleration, lateral acceleration, and driving speed; The longitudinal acceleration score and the lateral acceleration score are determined by weighted summation of the distribution ratio of the longitudinal acceleration in each corresponding first interval and the distribution ratio of the lateral acceleration in each corresponding second interval. The first interval is a range of values ​​for the longitudinal acceleration divided according to its numerical value, and the second interval is a range of values ​​for the lateral acceleration divided according to its numerical value. The longitudinal acceleration score and the lateral acceleration score are used to characterize the influence factors of the longitudinal acceleration and the lateral acceleration on the driving style, respectively. The vehicle speed score is obtained by weighted summation of the distribution ratios of the driving speed in each corresponding third interval. The third interval is a numerical range determined by the value of the driving speed. The weight value corresponding to the interval where the average of the vehicle speed scores is located is used as the vehicle speed correction parameter. The vehicle speed correction parameter is used to characterize the influence factor of the driving speed on the driving style. The driving style is determined by the weighted sum of the longitudinal acceleration score and the lateral acceleration score, and by multiplying the weighted sum with the vehicle speed correction parameter.

2. The method according to claim 1, characterized in that, Obtaining vehicle driving big data includes: The mileage of the vehicles was recorded. If the mileage is greater than or equal to the mileage threshold, then the vehicle's driving big data is obtained.

3. The method according to claim 1, characterized in that, The determination of longitudinal acceleration score and lateral acceleration score by weighted summation of the distribution ratio of longitudinal acceleration in each corresponding first interval and the distribution ratio of lateral acceleration in each corresponding second interval includes: The longitudinal acceleration is divided into at least two first intervals according to its numerical value. The first distribution ratio in each of the at least two first intervals is statistically analyzed. The longitudinal score of the acceleration is determined by weighted summation of the at least two first distribution ratios and their corresponding first weight lists. The first weight list is a weight sequence of the at least two first distribution ratios. The lateral acceleration is divided into at least two second intervals according to its numerical value. The second distribution ratio in each of the at least two second intervals is statistically analyzed. The lateral acceleration score is determined by weighted summation of the at least two second distribution ratios and their corresponding second weight lists. The second weight list is a weight sequence of the at least two second distribution ratios.

4. The method according to claim 1, characterized in that, Before obtaining the vehicle speed score by weighted summation of the distribution ratios of the driving speeds in each interval, and using the weight value corresponding to the interval where the average of the vehicle speed scores lies as the vehicle speed correction parameter, the method further includes: Remove driving data where the driving speed is less than the speed threshold.

5. The method according to claim 1, characterized in that, The process of obtaining a vehicle speed score by weighted summation of the distribution ratios of the driving speeds across different intervals, and using the weight value corresponding to the interval containing the average of the vehicle speed scores as the vehicle speed correction parameter, includes: The driving speed is divided into at least two third intervals according to its numerical value. The third distribution ratio in each of the at least two third intervals is statistically analyzed. The vehicle speed correction parameter is determined by the average of the weighted sum of the at least two third distribution ratios and their corresponding third weight lists. The third weight list is the weight sequence of the at least two third distribution ratios.

6. The method according to claim 3 or 5, characterized in that, Before acquiring the vehicle's driving big data, the following is also included: Based on preset data and the total score of the driving style, a first weight list, a second weight list, and a third weight list are determined. The first weight list, the second weight list, and the third weight list are weight parameter sequences of the first distribution ratio, the second distribution ratio, and the third distribution ratio, respectively. The preset data is collected from vehicles whose power performance, braking performance, and handling performance all correspond to the same range of performance parameters.

7. The method according to claim 5, characterized in that, The step of dividing the driving speed into at least two third intervals according to its numerical value, calculating the third distribution ratio in each of the at least two intervals, and determining the vehicle speed correction parameter by weighted summation of the at least two third distribution ratios and their corresponding third weight lists, further includes: Determine the average speed of the driving speed in the big data of driving; Based on the average speed, a speed weight corresponding to the average speed is determined in the third interval, and the third weight list includes the speed weight; The speed weight is used as the vehicle speed correction parameter.

8. The method according to claim 3, characterized in that, The method of determining the longitudinal acceleration score and the lateral acceleration score by weighted summation of the distribution ratios of the longitudinal acceleration and the lateral acceleration in their respective intervals also includes: The sum of each first score value in the at least two first intervals is determined as the acceleration longitudinal score, where the first score value is the product of a preset upper limit value and the first distribution ratio and its corresponding first weight in the first weight list. The sum of each second score value in the at least two second intervals is determined as the acceleration lateral score, where the second score value is the product of a preset upper limit value minus the second distribution ratio and its corresponding second weight in the second weight list.

9. The method according to claim 1, characterized in that, Determining the driving style by multiplying the weighted sum of the longitudinal acceleration score and the lateral acceleration score with the vehicle speed correction parameter includes: The weighted sum of the longitudinal acceleration score and the lateral acceleration score is determined as the acceleration influence parameter; The product of the acceleration influence parameter and the vehicle speed correction parameter is determined as the total driving style score; The driving style is defined by classifying the driving style according to the range of the total driving style score.

10. The method according to claim 1, characterized in that, After determining the product of the weighted sum of the longitudinal acceleration score and the lateral acceleration score with the vehicle speed correction parameter to determine the driving style, the method further includes: Obtain the latest driving big data of the vehicle; The driving style is updated based on the latest driving data.

11. A driving style recognition device, characterized in that, The device includes: The acquisition module is used to acquire big data on vehicle driving, including longitudinal acceleration, lateral acceleration, and driving speed. The first scoring module is used to determine the longitudinal acceleration score and the lateral acceleration score by weighted summing the distribution ratio of the longitudinal acceleration in each corresponding first interval and the distribution ratio of the lateral acceleration in each corresponding second interval. The first interval is a number of numerical ranges of the longitudinal acceleration divided according to its numerical value, and the second interval is a number of numerical ranges of the lateral acceleration divided according to its numerical value. The longitudinal acceleration score and the lateral acceleration score are used to characterize the influence factors of the longitudinal acceleration and the lateral acceleration on the driving style, respectively. The second scoring module is used to obtain a vehicle speed score by weighted summation of the distribution ratios of the driving speed in each corresponding third interval. The third interval is a numerical range determined by the value of the driving speed. The weight value corresponding to the interval where the average of the vehicle speed scores is located is used as a vehicle speed correction parameter. The vehicle speed correction parameter is used to characterize the influence factor of the driving speed on the driving style. A determination module is used to determine the weighted sum of the longitudinal acceleration score and the lateral acceleration score, and to determine the driving style based on the product of the weighted sum and the vehicle speed correction parameter.

12. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-10.

13. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-10.

14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-10.

15. A chip, characterized in that, It includes at least one processor and a communication interface; the communication interface is used to receive signals input to the chip or signals output from the chip, and the processor communicates with the communication interface and implements the method according to any one of claims 1-10 through logic circuits or executing code instructions.

16. A vehicle, characterized in that, Includes the driving style recognition device as described in claim 11.

Images