Method and device for identifying vehicles and their driving patterns

Abstract

The present invention discloses a method and device for identifying vehicles and their driving patterns. The method comprises: obtaining driving data of a target vehicle from its onboard bus; identifying the target vehicle's driving path based on the driving data to obtain the target driving path; determining target trip information for the target vehicle based on the driving data and the target driving path; and determining the driving pattern of the target vehicle based on the target trip information. The present invention solves the technical problem in related technologies where the extraction of user travel data is limited to GPS technology and GPS information is difficult to obtain, resulting in an inability to extract relevant information from vehicle travel pattern statistics.

Description

Technical Field

[0001] The present invention relates to the field of vehicles, and in particular to a method and device for identifying vehicles and their driving patterns. Background Art

[0002] Currently, personalized vehicle services are becoming increasingly diverse, and user travel patterns are a crucial information foundation for these services. Failure to successfully extract user travel data makes it impossible to assess their travel patterns. Due to increasing user awareness of privacy protection and national legislation on user privacy, GPS (Global Positioning System) information is becoming increasingly difficult to obtain, and some users may forgo personalized services to protect their privacy. However, traditional travel pattern statistics methods rely on GPS technology, making it impossible to extract complete user travel data and thus hindering the implementation of personalized services.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] An embodiment of the present invention provides a method and device for identifying vehicles and their driving patterns, so as to at least solve the technical problem in related technologies that the extraction of user travel data is limited to GPS technology and GPS information is difficult to obtain, resulting in the inability to extract relevant information from the statistics of vehicle travel patterns.

[0005] According to one aspect of an embodiment of the present invention, a method for identifying vehicle driving patterns is provided, comprising: obtaining driving data of a target vehicle from an on-board bus of the target vehicle; identifying a driving path of the target vehicle based on the driving data to obtain a target driving path; determining target travel information of the target vehicle based on the driving data and the target driving path; and determining the driving pattern of the target vehicle based on the target travel information.

[0006] Optionally, the driving path of the target vehicle is identified based on the driving data to obtain the target driving path of the target vehicle, including: identifying the driving behavior of the target vehicle based on the driving data to obtain the target driving behavior; generating a target behavior sequence based on the target driving behavior; performing similarity matching between the target behavior sequence and multiple historical behavior sequences; in response to the target behavior sequence successfully matching the target historical behavior sequence in the multiple historical behavior sequences, determining that the historical driving path corresponding to the target historical behavior sequence is the target driving path.

[0007] Optionally, the target behavior sequence is matched with multiple historical behavior sequences for similarity, including: obtaining the dynamic time-warped distance between the target behavior sequence and the multiple historical behavior sequences to obtain multiple first distances; determining the target distance that is less than a preset threshold among the multiple distances; obtaining the historical behavior sequence corresponding to the minimum distance among the target distances to obtain the target historical behavior sequence.

[0008] Optionally, the dynamic time warping distance between the target behavior sequence and multiple historical behavior sequences is obtained to obtain multiple first distances, including: obtaining the distance between each first node in the target behavior sequence and each second node in each historical behavior sequence to obtain a distance matrix; obtaining multiple element sums based on the sum of the element values ​​of all elements in a preset direction in the distance matrix; obtaining the minimum element sum among the multiple element sums to obtain the first distance.

[0009] Optionally, the method also includes: obtaining multiple historical driving paths of the target vehicle; generating multiple behavior sequences based on the multiple historical driving paths; obtaining dynamic time warping distances of the multiple behavior sequences to obtain multiple second distances; clustering the multiple second distances to obtain multiple cluster distances; and determining multiple historical behavior sequences based on the behavior sequences corresponding to the multiple cluster distances.

[0010] Optionally, the driving behavior of the target vehicle is identified based on the driving data to obtain the target driving behavior, including: identifying the driving behavior of the target vehicle based on the driving data to obtain multiple driving behaviors; determining multiple driving cycles based on the power-on behaviors and power-off behaviors in the multiple driving behaviors; merging the multiple driving cycles based on the interval time of the multiple driving cycles to obtain multiple driving trips; and obtaining the target driving behavior based on the driving behaviors included in each driving trip.

[0011] Optionally, the driving behavior of the target vehicle is identified based on the driving data to obtain multiple driving behaviors, including: based on the power status in the driving data, determining whether the multiple driving behaviors include power-on behavior and power-off behavior; based on the vehicle speed, gear status and yaw angular velocity in the driving data, determining whether the multiple driving behaviors include straight-moving behavior, left-turning behavior, right-turning behavior and U-turning behavior.

[0012] Optionally, based on the vehicle speed, gear status and yaw angular velocity in the driving data, straight-moving behavior, left-turning behavior, right-turning behavior and U-turning behavior are determined, including: in response to the vehicle speed being greater than a first vehicle speed threshold, the gear status being a forward gear state, and the yaw angular velocity being less than or equal to a preset threshold, determining that multiple driving behaviors include straight-moving behavior; in response to the vehicle speed being greater than the first vehicle speed threshold, the gear status being a forward gear state, and the yaw angular velocity being greater than a preset threshold, determining that multiple driving behaviors include left-turning behavior, right-turning behavior or U-turning behavior based on lateral working condition characteristic values, wherein the lateral working condition characteristic values ​​include: the vehicle body axis angle, the steering wheel angle, the direction corresponding to the steering wheel angle, and the target duration, and the target duration is used to characterize the time from the yaw angular velocity being greater than the preset threshold to the yaw angular velocity being less than the preset threshold.

[0013] Optionally, based on the lateral working condition characteristic value, multiple driving behaviors are determined to include left turn behavior, right turn behavior or U-turn behavior, including: in response to the vehicle body axis angle being within a first preset range, the steering wheel angle being within a second preset range, and the target duration being less than a preset time threshold, based on the direction corresponding to the steering wheel angle, multiple driving behaviors are determined to include left turn behavior or right turn behavior; in response to the vehicle body axis angle being greater than a first maximum value of the first preset range, the steering wheel angle being greater than a second maximum value of the second preset range, multiple driving behaviors are determined to include U-turn behavior.

[0014] Optionally, determining the driving pattern of the target vehicle based on the target travel information includes: obtaining multiple travel information within a preset time period; determining a first number of preset travel information among the multiple travel information, wherein the preset travel information is travel information among the multiple travel information that successfully matches multiple historical behavior sequences; obtaining a ratio of the first number to a second number of the multiple travel information; and determining the driving pattern based on the ratio.

[0015] According to another aspect of an embodiment of the present invention, a device for identifying vehicle driving patterns is also provided, including: an acquisition module for acquiring driving data of a target vehicle from an on-board bus of the target vehicle; an identification module for identifying the driving path of the target vehicle based on the driving data to obtain the target driving path; a travel determination module for determining target travel information of the target vehicle based on the driving data and the target driving path; and a pattern determination module for determining the driving pattern of the target vehicle based on the target travel information.

[0016] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the vehicle driving pattern identification method of any one of the above embodiments.

[0017] According to another aspect of the present invention, a processor is provided, which is used to run a program, wherein when the program is run, the method for identifying the vehicle driving pattern of any one of the above embodiments is executed.

[0018] According to another aspect of an embodiment of the present invention, a vehicle is provided, including: a device for identifying vehicle driving patterns.

[0019] In an embodiment of the present invention, after obtaining driving data from the target vehicle's onboard bus, the target vehicle's path is identified based on the driving data to obtain a target driving path. Target trip information for the target vehicle is further determined based on the driving data and the target driving path. Further, the target vehicle's travel pattern is determined based on the target trip information, thereby enabling evaluation of the travel patterns of driving behavior. It is readily apparent that by identifying vehicle trip information through vehicle driving data and then determining the vehicle's travel pattern, a route regularity evaluation algorithm based on driving behavior is constructed, achieving the goal of statistically analyzing vehicle travel patterns without obtaining GPS information. This achieves the technical effect of improving the accuracy of identifying vehicle travel patterns, thereby resolving the technical problem in related technologies where the extraction of user travel data is limited to GPS technology and GPS information is difficult to obtain, resulting in an inability to extract relevant information from the statistical analysis of vehicle travel patterns. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0021] Figure 1 is a flow chart of a method for identifying vehicle driving patterns according to an embodiment of the present invention;

[0022] Figure 2 is a flow chart of an optional vehicle path identification according to an embodiment of the present invention;

[0023] Figure 3 is a flow chart of an optional vehicle driving behavior recognition according to an embodiment of the present invention;

[0024] Figure 4 is a flow chart of an optional travel pattern evaluation method according to an embodiment of the present invention;

[0025] Figure 5 2 is a schematic diagram of a device for identifying vehicle driving patterns according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Example 1

[0029] According to an embodiment of the present invention, a method for identifying vehicle driving patterns is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 FIG. 1 is a flow chart of a method for identifying vehicle driving patterns according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0031] Step S102, obtaining the target vehicle's driving data from the target vehicle's onboard bus;

[0032] The on-board bus of the above-mentioned target vehicle can be a communication network for interconnecting vehicle devices or vehicle instruments at the bottom layer of the on-board network, for example, it can be a CAN bus (Controller Area Network), a LIN bus (Local Interconnect Network), a FlexRay bus (a high-speed, deterministic, fault-tolerant bus technology for automobiles) and a MOST bus (Media Oriented Systems Transport, a network system for multimedia data transmission). The driving data can be data obtained and parsed from the on-board bus, and can be divided into data for driving behavior recognition and data for trip information extraction. For example, the data for driving behavior recognition can include but is not limited to: vehicle power-on status, vehicle speed, steering wheel angle, and yaw angular velocity; the data for trip information extraction can include but is not limited to: the vehicle's remaining fuel / battery level and the vehicle's charging status.

[0033] The above-mentioned driving behavior information may be the driver's behavioral actions while driving, and may include but is not limited to: vehicle power on, vehicle power off, straight driving, left turn, right turn, and U-turn.

[0034] In an optional embodiment, while the target vehicle is in operation, driving data is transmitted via the vehicle bus. Therefore, data for driving behavior recognition and data for trip information extraction can be directly obtained from the vehicle bus, thereby obtaining the vehicle power status, vehicle speed, steering wheel angle and yaw angular velocity, vehicle remaining fuel / battery level, and vehicle charging status.

[0035] Step S104, identifying the driving path of the target vehicle based on the driving data to obtain the target driving path;

[0036] It should be noted that, when the driver is driving the target vehicle, the driver controls the target vehicle based on the target driving path. Therefore, the driving data of the target vehicle can reflect the driving process of the target driving path.

[0037] The above-mentioned driving path can be identified based on the uploaded driving behavior information, and the regularity of the route can be analyzed. It can be counted in units of driving trips, where a driving trip can be defined as the driving process of a driver driving from one location to another for a certain purpose. In a driving trip, the driver can control the target vehicle to power on at the starting point, and control the target vehicle to power off after arriving at the destination to determine the vehicle's driving route, that is, the driving trip only includes one power-on and power-off cycle. However, the driver often controls the target vehicle to power on and off multiple times in a driving trip, that is, the driving trip includes multiple power-on and power-off cycles, and the interval between the two power-on and power-off cycles is short, so the present invention combines two power-on and power-off cycles with an interval of less than 20 minutes into one trip.

[0038] In an optional embodiment, the behavior data may be statistically analyzed by driving trip, and two power-on and power-off cycles with an interval of less than 20 minutes may be combined into one trip. A driving behavior sequence may be established based on the behavior data that meets the above statistical conditions. The dynamic time warping (DTW) distance of all trips may be calculated using the driving behavior sequence. The DTW distance may be clustered using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering method. The central driving behavior sequence of each cluster may be used as a standard template, and the DTW distance between the driving behavior sequence and all template sequences may be calculated. When the DTW distance of any template sequence is less than a preset distance threshold, the one with the smallest DTW distance is selected as the path for the current trip.

[0039] Step S106, determining target travel information of the target vehicle based on the driving data and the target driving path;

[0040] The above-mentioned trip information can be determined based on the recognition result of the trip path (i.e., the target driving path) and the vehicle condition data in the driving data. For example, the trip congestion situation can be determined based on the average vehicle speed; wherein, the vehicle condition data can be defined as the vehicle condition information of the vehicle during the driving process, which may include but is not limited to: trip congestion situation, the location of gas stations / charging stations along the trip route, trip energy consumption, driving time, trip mileage, idling time, travel time, whether there are refueling / charging events during the trip, and the time when the refueling / charging events occur.

[0041] In an optional embodiment, the trip information can be obtained by judging the trip congestion, the location of gas stations / charging stations along the trip, the trip energy consumption, the driving time, etc. based on the recognition result of the trip path and the vehicle condition data. The trip congestion can be judged based on the average vehicle speed, and the location of gas stations / charging stations along the trip can be judged based on the refueling / charging events and the corresponding time during the trip, which are stored as a specific driving route and a driving behavior sequence relative to the starting point of the trip.

[0042] Step S108: determining the driving pattern of the target vehicle based on the target travel information.

[0043] The aforementioned driving patterns can be derived from user trip information, showing periodic changes in the user's trip information over a period of time. These patterns may include, but are not limited to, overall trip patterns, weekday trip patterns, and weekend trip patterns. Specifically, the regularity of all target trip information within a period is evaluated, and the regularity of all trips within the evaluation period is evaluated based on the proportion of regular trips to the total number of trips. The aforementioned period can be the period of repeated occurrence of the same vehicle driving trajectory, that is, the time between two consecutive occurrences of the same driving trajectory.

[0044] In an optional embodiment, after obtaining the vehicle driving trajectory data through the vehicle bus, the travel regularity can be divided into the total travel regularity and the weekday travel regularity. The travel regularity can be evaluated for all trips in the cycle based on the proportion of the number of regular trips to the total number of trips, and the travel regularity can be evaluated for all weekday trips in the cycle based on the proportion of the number of regular trips to the total number of trips.

[0045] Through the above steps, after obtaining the driving data of the target vehicle's onboard bus, the target vehicle's path is identified based on the driving data to obtain a target driving path. The target vehicle's target trip information is further determined based on the driving data and the target driving path. The target vehicle's driving pattern is further determined based on the target trip information, thereby achieving an evaluation of the driving behavior's travel patterns. It is easy to note that by identifying vehicle trip information through vehicle driving data and then determining the vehicle's travel patterns, a route regularity evaluation algorithm based on driving behavior is constructed. This achieves the purpose of statistically analyzing vehicle travel patterns without obtaining GPS information, thereby achieving the technical effect of improving the accuracy of vehicle travel pattern identification. This solves the technical problem in related technologies where the extraction of user travel data is limited to GPS technology and GPS information is difficult to obtain, resulting in an inability to extract relevant information from the statistical analysis of vehicle travel patterns.

[0046] In the above-mentioned embodiment of the present invention, the driving path of the target vehicle is identified based on the driving data to obtain the target driving path of the target vehicle, including: identifying the driving behavior of the target vehicle based on the driving data to obtain the target driving behavior; generating a target behavior sequence based on the target driving behavior; performing similarity matching between the target behavior sequence and multiple historical behavior sequences; in response to the target behavior sequence successfully matching with the target historical behavior sequence in the multiple historical behavior sequences, determining that the historical driving path corresponding to the target historical behavior sequence is the target driving path.

[0047] The above-mentioned driving data can be data used for driving behavior identification and data used for travel information extraction; the above-mentioned behavior sequence can be a sequence of all behaviors generated during the vehicle driving process arranged according to the time of generation; the target behavior sequence can be a driving behavior sequence recorded in chronological order within a certain time period and generated based on driving behavior; the historical behavior sequence can be a behavior sequence that has been obtained within a historical time period.

[0048] Optionally, obtain similarity matching between the target behavior sequence and multiple historical behavior sequences: obtain the dynamic time warping distance between the target behavior sequence and multiple historical behavior sequences to obtain multiple first distances; determine the target distance that is less than a preset threshold among the multiple distances; obtain the historical behavior sequence corresponding to the minimum distance among the target distances to obtain the target historical behavior sequence.

[0049] The above-mentioned preset threshold value may be a preset distance critical value, which is used to determine whether the obtained first distance is less than a target distance of the preset threshold value.

[0050] Furthermore, multiple first distances can be obtained in the following manner: obtain the distance between each first node in the target behavior sequence and each second node in each historical behavior sequence to obtain a distance matrix; obtain multiple element sums based on the sum of the element values ​​of all elements in a preset direction in the distance matrix; obtain the minimum element sum among the multiple element sums to obtain the first distance.

[0051] The distance matrix can be composed of the distances between any two nodes in the two behavior sequences, i.e., each element in the distance matrix corresponds to a distance. Since the nodes corresponding to the elements in the distance matrix increase in order from left to right and from top to bottom, the preset direction can be from the upper left corner to the lower right corner.

[0052] Optionally, obtaining multiple historical driving paths of the target vehicle includes: generating multiple behavior sequences based on the multiple historical driving paths; obtaining dynamic time warping distances of the multiple behavior sequences to obtain multiple second distances; clustering the multiple second distances to obtain multiple cluster distances; and determining multiple historical behavior sequences based on the behavior sequences corresponding to the multiple cluster distances.

[0053] In an optional embodiment, the vehicle's driving route is identified based on the driving behavior information uploaded by the vehicle, and the regularity of the route is analyzed and statistics are collected in units of driving trips, where a trip is defined as the process of a driver driving from one location to another for a certain purpose. In actual scenarios, a single driving trip may cause multiple power-on and power-off events due to temporary stops and other reasons. The present invention combines two power-on and power-off cycles with an interval of less than 20 minutes into one trip. In this embodiment of the present invention, the path identification and judgment process is as follows: Figure 2 As shown in the figure, "Power-on" represents a vehicle power-on event, "Power-off" represents a vehicle power-off event, 0 represents the previous power-on / off cycle, and 1 represents the current power-on / off cycle. The path recognition module first establishes a driving behavior sequence based on the driving behavior information data. For straight driving conditions, a straight driving condition code of 3 is repeated every kilometer. For decimal fractions greater than 0.5 kilometers, a 3 is added; otherwise, it is discarded. For example, in a trip, if the driver drives straight for 5 kilometers, turns left, then drives straight for 2.5 kilometers, turns right, and reaches the destination, the driving behavior sequence is: 3 3 3 3 3 4 33 3 5. The path recognition module is divided into a training process and an inference process. The training process includes: obtaining the trip information of the training vehicle over a period of time and expanding it into a driving behavior sequence according to the above rules; calculating the dynamic time warping (DTW) distance of all trips; clustering the DTW distances of all trips using the DBSCAN clustering method; and selecting the central driving behavior sequence of each cluster as a standard template. To accommodate users with multiple frequently used driving routes, each user can have up to three standard templates. The reasoning process includes: taking the trip information to be classified and expanding it into a driving behavior sequence according to the above rules; calculating the DTW distance between the driving behavior sequence of the trip to be classified and all template sequences; when the DTW distance of the template sequence is less than the preset distance threshold, taking the path with the smallest DTW distance as the path of this trip, and defining the current trip as a regular trip; when the DTW distance of the template sequence is less than the preset distance, defining the current trip as an irregular trip. Among them, the DTW algorithm assumes that two time series are: A = (a1, a2, ..., an) and B = (b1, b2, ..., bn). The process of calculating their DTW distance is: calculating the distance between each point in the two sequences and generating a distance matrix M i =|A i -B j |, 1≤i, j≤n, find a path from the upper left corner to the lower right corner of the matrix so that the sum of the elements on the path is minimized. This minimum distance is the DTW distance between the two time series.

[0054] Optionally, the driving behavior of the target vehicle is identified based on the driving data to obtain the target driving behavior, including: identifying the driving behavior of the target vehicle based on the driving data to obtain multiple driving behaviors; determining multiple driving cycles based on the power-on behaviors and power-off behaviors in the multiple driving behaviors; merging the multiple driving cycles based on the interval time of the multiple driving cycles to obtain multiple driving trips; and obtaining the target driving behavior based on the driving behaviors included in each driving trip.

[0055] The above-mentioned power-on behavior can be the behavior when the vehicle engine is started, that is, the vehicle power-on behavior is reported when the vehicle power state changes from power-off to power-on; the power-off behavior can be the behavior of the vehicle shutting down the engine, that is, the vehicle power-off behavior is reported when the vehicle power state changes from power-on to power-off; the driving cycle can be the action cycle from power-on behavior to power-off behavior in driving behavior; the driving journey can be a description of the user's path during the entire driving process; the driving behavior can be vehicle power-on, vehicle power-off, straight driving, left turn, right turn, U-turn, etc.

[0056] Furthermore, the driving behavior of the target vehicle is identified based on the driving data to obtain multiple driving behaviors, including: based on the power status in the driving data, determining whether the multiple driving behaviors include power-on behavior and power-off behavior; based on the vehicle speed, gear status and yaw angular velocity in the driving data, determining whether the multiple driving behaviors include straight-ahead behavior, left-turn behavior, right-turn behavior and U-turn behavior.

[0057] Specifically, a judgment is made based on the vehicle power status signal. When the vehicle power status changes from power off to power on, the vehicle power-on behavior is reported; conversely, when the vehicle power status changes from power on to power off, the vehicle power-off behavior is reported to determine vehicle power on and vehicle power off.

[0058] Furthermore, based on the vehicle speed, gear status and yaw angular velocity in the driving data, straight-moving behavior, left-turning behavior, right-turning behavior and U-turning behavior are determined, including: in response to the vehicle speed being greater than a first vehicle speed threshold, the gear status being a forward gear state, and the yaw angular velocity being less than or equal to a preset threshold, determining that multiple driving behaviors include straight-moving behavior; in response to the vehicle speed being greater than the first vehicle speed threshold, the gear status being a forward gear state, and the yaw angular velocity being greater than a preset threshold, determining that multiple driving behaviors include left-turning behavior, right-turning behavior or U-turning behavior based on lateral working condition characteristic values, wherein the lateral working condition characteristic values ​​include: the vehicle body axis angle, the steering wheel angle, the direction corresponding to the steering wheel angle, and the target duration, and the target duration is used to characterize the time from the yaw angular velocity being greater than the preset threshold to the yaw angular velocity being less than the preset threshold.

[0059] The above-mentioned first vehicle speed threshold can be a set vehicle speed limit value; the preset threshold can be a set lateral working condition start threshold; the lateral working condition characteristic value can be a characteristic of the vehicle during driving, namely, the lateral working condition duration, the vehicle body axis angle, the maximum steering wheel angle and the direction corresponding to the maximum steering wheel angle; the yaw angular velocity can be the deflection of the vehicle around the vertical axis, and the magnitude of the deflection represents the stability of the vehicle.

[0060] Specifically, the algorithm determines whether the vehicle is in a straight-ahead state based on vehicle speed and steering wheel angle. To eliminate the influence of situations such as reversing or exiting a parking garage, the algorithm only begins identifying driving behavior after the vehicle speed exceeds the first speed threshold and the gear is in forward gear. For straight-ahead driving, the algorithm determines if the vehicle is in a straight-ahead state if the yaw rate is less than or equal to the lateral operating condition start threshold while the vehicle speed exceeds the first speed threshold and the gear is in forward gear. For lateral operating condition determination, the algorithm determines if the vehicle has entered a lateral operating condition if the yaw rate is greater than the lateral operating condition start threshold while the vehicle is in forward gear. The algorithm determines if the vehicle has exited a lateral operating condition if the yaw rate is less than the lateral operating condition end threshold. When the vehicle exits a lateral operating condition, it uploads a lateral operating condition event and lateral operating condition characteristic values, which include the lateral operating condition duration, body axis angle, maximum steering wheel angle, and the direction corresponding to the maximum steering wheel angle. The cloud algorithm further divides the lateral working conditions into left turn, right turn and U-turn working conditions according to the lateral working condition characteristic value. In the embodiment of the present invention, the specific process of driving behavior recognition and judgment is as follows: Figure 3 shown.

[0061] Furthermore, based on the lateral working condition characteristic value, it is determined that multiple driving behaviors include left turning behavior, right turning behavior or U-turn behavior, including: in response to the vehicle body axis angle being within a first preset range, the steering wheel angle being within a second preset range, and the target duration being less than a preset time threshold, according to the direction corresponding to the steering wheel angle, it is determined that multiple driving behaviors include left turning behavior or right turning behavior; in response to the vehicle body axis angle being greater than a first maximum value of the first preset range, the steering wheel angle being greater than a second maximum value of the second preset range, it is determined that multiple driving behaviors include U-turn behavior.

[0062] Specifically, left turn and right turn judgment: During the lateral working condition, if the following conditions are met, it is judged that the vehicle is in a turning condition: the vehicle's body axis angle is greater than the first body axis angle threshold and less than the second body axis angle threshold; the maximum steering wheel angle is greater than the first steering wheel angle threshold and less than the second steering wheel angle threshold; the lateral working condition duration is less than the turning condition duration threshold; when the turning direction corresponding to the maximum steering wheel angle is left, it is marked as a left turn, otherwise it is a right turn. U-turn judgment: During the lateral working condition, if the following conditions are met, it is judged that the vehicle is in a turning condition: the vehicle's body axis angle is greater than the second body axis angle threshold; the vehicle's maximum steering wheel angle is greater than the second steering wheel angle threshold. Body axis angle calculation method: Let Ak and Bk represent the center points of the front and rear axles at time tk, L is the vehicle wheelbase, δk represents the front wheel angle at time tk, Δk is the steering wheel angle, is is the steering gear ratio, Zk is the steering center of the vehicle at time tk, the vehicle speed at time tk is vk, and the steering angles of Ak and Bk are θk and but: According to the kinematic relationship, the coordinates of Ak+1 and Bk+1 at time tk+1 are: According to the above formula, the body axis vector is continuously updated. After the lateral working condition is completed, the body axis angle is Among them, lafter and lbefore are the vehicle body axis vectors before and after the lateral working condition.

[0063] In an optional embodiment, the driving pattern of the target vehicle can be determined based on the target travel information by the following method, including: obtaining multiple travel information within a preset time period; determining a first number of preset travel information among the multiple travel information, wherein the preset travel information is travel information among the multiple travel information that successfully matches multiple historical behavior sequences; obtaining a ratio of the first number to a second number of the multiple travel information; and determining the driving pattern based on the ratio.

[0064] Specifically, the evaluation method includes: travel regularity can be divided into functions such as total travel regularity and weekday travel regularity; ① Total travel regularity: Total travel regularity is an evaluation of the regularity of all trips within a period. All trips within the evaluation period are taken and the travel regularity is evaluated based on the proportion of regular trips to the total number of trips. In this embodiment of the present invention, the evaluation criteria for total travel regularity are shown in Table 1 below:

[0065] Table 1

[0066] Percentage of regular trips Regularity evaluation results <0.1 Poor regularity 0.1～0.5 General regularity 0.5～0.9 Good regularity >0.9 Excellent regularity

[0067] ② Weekday travel regularity: Weekday travel regularity is an evaluation of the regularity of weekday trips within a period. All weekday trips within the evaluation period are taken and the regularity of the trips is evaluated based on the proportion of regular trips to the total number of trips. In this embodiment of the present invention, the evaluation criteria for weekday travel regularity are shown in Table 2 below:

[0068] Table 2

[0069] Percentage of regular trips Regularity evaluation results <0.3 Poor regularity 0.3～0.5 General regularity 0.5～0.9 Good regularity >0.9 Excellent regularity

[0070] Standard template: The standard template is a key factor in evaluating and counting user travel regularity. Since users' common travel routes may change, the user's standard template needs to be updated. This paper chooses to update the standard template once a week. The data from the update time is re-clustered and determined using the data within one month before the update time. To reduce the influence of older data, the logistic weight function is used to weight the data when updating the standard template. The logistic weight function formula is as follows:

[0071] In order to provide services as quickly as possible, the travel regularity evaluation results will be updated every two weeks for new users in the first month, and once a month for old users.

[0072] The following combination Figure 4 A preferred embodiment of the present invention is described in detail. Figure 4 As shown, the method includes: collecting on-board bus data, including data for driving behavior identification and data for trip information extraction, and performing data preprocessing on the data, processing outliers in the bus data and filtering valid data. Further driving behavior identification may include, but is not limited to, vehicle power on, vehicle power off, straight driving, left turn, right turn, and U-turn; and vehicle condition data collection, which is responsible for identifying vehicle driving data, including, but not limited to, mileage, driving time, average speed, average trip energy consumption, idling time, travel time, whether there are refueling / charging events during the trip, and the time when refueling / charging events occur. After obtaining driving behavior identification, the path is further identified. The vehicle's driving route is identified based on the driving behavior information uploaded by the vehicle, and the route regularity is analyzed. After obtaining the vehicle condition data, the trip information is extracted. Based on the trip path identification results and the vehicle condition data, the trip congestion situation, the location of refueling / charging stations along the route, the trip energy consumption, driving time, mileage, idling time, and trip time are determined. Finally, a trip regularity evaluation is made.

[0073] Example 2

[0074] According to an embodiment of the present invention, a device for identifying vehicle driving patterns is provided. The device can execute the method for identifying vehicle driving patterns in the above embodiment. The specific implementation and preferred application scenarios are the same as those in the above embodiment and are not described in detail here.

[0075] Figure 5 FIG. 1 is a schematic structural diagram of a vehicle driving pattern recognition device according to an embodiment of the present invention. Figure 5 As shown, the vehicle driving pattern recognition device includes the following parts: an acquisition module 50 , an identification module 52 , a travel determination module 54 , and a pattern determination module 56 .

[0076] The acquisition module 50 is used to acquire the driving data of the target vehicle from the vehicle bus of the target vehicle.

[0077] The identification module 52 is used to identify the driving path of the target vehicle based on the driving data to obtain the target driving path.

[0078] The travel determination module 54 is configured to determine target travel information of the target vehicle based on the driving data and the target driving path.

[0079] The pattern determination module 56 determines the driving pattern of the target vehicle based on the target travel information.

[0080] Optionally, the identification module includes: an identification unit for identifying the driving behavior of the target vehicle based on the driving data to obtain the target driving behavior; a sequence generation unit for generating a target behavior sequence based on the target driving behavior; a matching unit for performing similarity matching between the target behavior sequence and multiple historical behavior sequences; and a first determination unit for determining that the historical driving path corresponding to the target historical behavior sequence is the target driving path in response to a successful match between the target behavior sequence and a target historical behavior sequence in multiple historical behavior sequences.

[0081] Optionally, the matching unit is also used to obtain the dynamic time-warped distance between the target behavior sequence and multiple historical behavior sequences to obtain multiple first distances; determine the target distance that is less than a preset threshold among the multiple distances; obtain the historical behavior sequence corresponding to the minimum distance among the target distances to obtain the target historical behavior sequence.

[0082] Optionally, the matching unit is also used to obtain the distance between each first node in the target behavior sequence and each second node in each historical behavior sequence to obtain a distance matrix; obtain multiple element sums based on the sum of the element values ​​of all elements in a preset direction in the distance matrix; obtain the minimum element sum among the multiple element sums to obtain a first distance.

[0083] Optionally, the device also includes: a path acquisition module for acquiring multiple historical driving paths of the target vehicle; a sequence generation module for generating multiple behavior sequences based on the multiple historical driving paths; a distance acquisition module for acquiring dynamic time warping distances of multiple behavior sequences to obtain multiple second distances; a clustering module for clustering the multiple second distances to obtain multiple clustering distances; and a sequence determination module for determining multiple historical behavior sequences based on the behavior sequences corresponding to the multiple clustering distances.

[0084] Optionally, the identification unit is further used to identify the driving behavior of the target vehicle based on the driving data to obtain multiple driving behaviors; determine multiple driving cycles based on the power-on behavior and the power-off behavior in the multiple driving behaviors; merge the multiple driving cycles based on the interval time of the multiple driving cycles to obtain multiple driving trips; and obtain the target driving behavior based on the driving behavior included in each driving trip.

[0085] Optionally, the identification unit is also used to determine whether multiple driving behaviors include power-on behavior and power-off behavior based on the power status in the driving data; and to determine whether multiple driving behaviors include straight-moving behavior, left-turning behavior, right-turning behavior and U-turning behavior based on the vehicle speed, gear status and yaw angular velocity in the driving data.

[0086] Optionally, the identification unit is also used to determine that multiple driving behaviors include straight-ahead behavior in response to the vehicle speed being greater than a first vehicle speed threshold, the gear state being a forward gear state, and the yaw angular velocity being less than or equal to a preset threshold; and to determine that multiple driving behaviors include left-turn behavior, right-turn behavior, or U-turn behavior based on lateral working condition characteristic values ​​in response to the vehicle speed being greater than a first vehicle speed threshold, the gear state being a forward gear state, and the yaw angular velocity being greater than a preset threshold, wherein the lateral working condition characteristic values ​​include: the vehicle body axis angle, the steering wheel angle, the direction corresponding to the steering wheel angle, and the target duration, and the target duration is used to characterize the time from the yaw angular velocity being greater than the preset threshold to the yaw angular velocity being less than the preset threshold.

[0087] Optionally, the identification unit is also used to determine that multiple driving behaviors include left turn behavior or right turn behavior according to the direction corresponding to the steering wheel angle in response to the vehicle body axis angle being within a first preset range, the steering wheel angle being within a second preset range, and the target duration being less than a preset time threshold; and to determine that multiple driving behaviors include U-turn behavior in response to the vehicle body axis angle being greater than a first maximum value of the first preset range and the steering wheel angle being greater than a second maximum value of the second preset range.

[0088] Optionally, the rule determination module includes: a travel information acquisition unit, used to acquire multiple travel information within a preset time period; a quantity determination unit, used to determine a first quantity of preset travel information among the multiple travel information, wherein the preset travel information is the travel information among the multiple travel information that successfully matches multiple historical behavior sequences; a ratio acquisition unit, used to acquire the ratio of the first quantity to the second quantity of the multiple travel information; and a rule determination unit, used to determine the driving rule based on the ratio.

[0089] Example 3

[0090] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the vehicle driving pattern identification method of any one of the above embodiments.

[0091] Example 4

[0092] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, the method for identifying a vehicle driving pattern according to any one of the above embodiments is executed.

[0093] Example 5

[0094] According to another aspect of an embodiment of the present invention, a vehicle is provided, characterized in that it includes: the device for identifying vehicle driving patterns in the above embodiment.

[0095] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0096] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0098] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0099] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0100] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0101] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for identifying vehicle driving patterns, characterized in that: include: Acquire driving data of the target vehicle from the vehicle bus of the target vehicle; Identifying a driving path of the target vehicle based on the driving data to obtain a target driving path; Determining target travel information of the target vehicle based on the driving data and the target driving path; Determining a driving pattern of the target vehicle based on the target travel information; Determining the driving pattern of the target vehicle based on the target trip information includes: obtaining a plurality of trip information within a preset time period; determining a first number of preset trip information among the plurality of trip information, wherein the preset trip information is trip information among the plurality of trip information that successfully matches a plurality of historical behavior sequences; obtaining a ratio of the first number to a second number of the plurality of trip information; and determining the driving pattern based on the ratio. The target driving path of the target vehicle is identified based on the driving data to obtain a target driving path, including: identifying the driving behavior of the target vehicle based on the driving data to obtain a target driving behavior; generating a target behavior sequence based on the target driving behavior; performing similarity matching between the target behavior sequence and multiple historical behavior sequences; and in response to a successful match between the target behavior sequence and a target historical behavior sequence in the multiple historical behavior sequences, determining that the historical driving path corresponding to the target historical behavior sequence is the target driving path.

2. The method according to claim 1, characterized in that Performing similarity matching between the target behavior sequence and multiple historical behavior sequences includes: Obtaining a dynamic time warping distance between the target behavior sequence and a plurality of historical behavior sequences to obtain a plurality of first distances; Determining a target distance among the multiple distances that is less than a preset threshold; Obtain a historical behavior sequence corresponding to a minimum distance among the target distances to obtain the target historical behavior sequence.

3. The method according to claim 1, characterized in that The method further comprises: Acquire multiple historical driving paths of the target vehicle; generating a plurality of behavior sequences based on the plurality of historical driving paths; Obtaining dynamic time warping distances of the plurality of behavior sequences to obtain a plurality of second distances; Clustering the multiple second distances to obtain multiple cluster distances; The multiple historical behavior sequences are determined based on the behavior sequences corresponding to the multiple clustering distances.

4. The method according to claim 1, wherein Identifying the driving behavior of the target vehicle based on the driving data to obtain the target driving behavior includes: Identifying a driving behavior of the target vehicle based on the driving data to obtain a plurality of driving behaviors; determining a plurality of driving cycles based on power-on behaviors and power-off behaviors in the plurality of driving behaviors; Merging the plurality of driving cycles based on intervals between the plurality of driving cycles to obtain a plurality of driving trips; The target driving behavior is obtained based on the driving behavior included in each driving trip.

5. The method according to claim 4, characterized in that The driving behavior of the target vehicle is identified based on the driving data to obtain multiple driving behaviors, including: determining, based on the power state in the driving data, whether the plurality of driving behaviors include the power-on behavior and the power-off behavior; Based on the vehicle speed, gear state, and yaw angular velocity in the driving data, it is determined whether the plurality of driving behaviors include a straight-ahead behavior, a left-turning behavior, a right-turning behavior, and a U-turn behavior.

6. A vehicle driving pattern recognition device, characterized in that: include: An acquisition module, configured to acquire the driving data of the target vehicle from the vehicle bus of the target vehicle; an identification module, configured to identify a driving path of the target vehicle based on the driving data to obtain a target driving path; a travel determination module, configured to determine target travel information of the target vehicle based on the driving data and the target driving path; A pattern determination module, configured to determine a driving pattern of the target vehicle based on the target travel information; The device is further configured to: obtain a plurality of trip information within a preset time period; determine a first number of preset trip information among the plurality of trip information, wherein the preset trip information is trip information among the plurality of trip information that successfully matches a plurality of historical behavior sequences; obtain a ratio of the first number to a second number of the plurality of trip information; and determine the driving pattern based on the ratio; The device is also used to: identify the driving behavior of the target vehicle based on the driving data to obtain a target driving behavior; generate a target behavior sequence based on the target driving behavior; perform similarity matching between the target behavior sequence and multiple historical behavior sequences; and in response to a successful match between the target behavior sequence and a target historical behavior sequence in the multiple historical behavior sequences, determine that the historical driving path corresponding to the target historical behavior sequence is the target driving path.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the vehicle driving pattern recognition method according to any one of claims 1 to 5.

8. A vehicle, characterized in that: include: The vehicle driving pattern recognition device according to claim 6.

Images