Prior risk degree measurement graph, method for constructing same, driving method, and storage medium

Abstract

The application discloses a priori dangerous degree measurement graph and a construction method thereof, a driving method and a storage medium. Basic map information of a target area is acquired and a first corresponding relationship between the basic map information and the basic map information is saved. Historical driving behavior data of a vehicle in the target area is acquired, and road safety events are extracted from the historical driving behavior data according to a preset rule. A second corresponding relationship between the road safety events and position information of the target area is obtained. A dangerous degree measurement model is established according to the second corresponding relationship, and a third corresponding relationship between the position information of the target area and the dangerous degree measurement is obtained. The position information of the target area and the corresponding dangerous degree measurement are summarized according to the third corresponding relationship, and a priori dangerous degree measurement graph of the target area is constructed. In this way, the priori dangerous degree measurement graph can be obtained for an automatic driving area, and the dangerous degree can be directly inquired and obtained when needed, so that the good or bad of an automatic driving system and the safety degree of a road section can be more finely estimated.

Description

TECHNICAL FIELD

[0001] The present application belongs to the patent supported by Shanghai Pujiang Talent Plan (Automatic Driving Behavior and Trajectory Prediction Algorithm Based on Deep Neural Network (No. 22PJD087)), and the technical content relates to the technical field of vehicles, in particular to a prior hazard degree measurement map and a construction method thereof, a driving method and a storage medium. BACKGROUND

[0002] When a human driver drives on a familiar road section, he / she will generally remember that some special road sections need special attention. For example, at some intersections, bicycles often merge into the right turn lane, and some high-speed vehicles are rarely concerned about being cut in.

[0003] However, for automatic driving, there is no human driver to artificially judge the danger degree of a road section. But this danger degree of a road section is exactly an important requirement to ensure the safety of automatic driving, especially to quantify the risk under various conditions.

[0004] Therefore, how to endow the automatic driving with the same ability as the manual driving to judge the danger degree of a road section according to the prior geographical position, so as to help the automatic driving system to select a suitable strategy, becomes a problem to be solved. SUMMARY

[0005] The main purpose of the present application is to provide a prior hazard degree measurement map and a construction method thereof, a driving method and a storage medium, which can more finely estimate the good or bad of an automatic driving system and the safety degree of a road section.

[0006] To achieve the above purpose, the present application provides a method for constructing a prior hazard degree measurement map, which comprises the following steps:

[0007] S1: obtaining basic map information of a target area, and saving a first correspondence relationship between position information of the target area and the basic map information; wherein the basic map information comprises road data;

[0008] S2: obtaining historical driving behavior data of a target vehicle in the target area, and extracting road safety events from the historical driving behavior data according to a preset rule; matching the road safety events to corresponding position information according to the position information of the road safety events and the first correspondence relationship, to obtain a second correspondence relationship between the road safety events and the position information of the target area;

[0009] S3: establishing a hazard degree measurement model according to the second correspondence relationship, and obtaining a risk probability of each position information, which is non-linearly mapped to a hazard degree measurement, to obtain a third correspondence relationship between the position information of the target area and the hazard degree measurement.

[0010] S4: according to the third correspondence relationship, the position information of the target area and the corresponding dangerous degree measure are summarized to construct a prior dangerous degree measure map of the target area.

[0011] In a possible implementation, the step S1 includes:

[0012] obtaining basic map information of the target area;

[0013] obtaining position information of the target area;

[0014] matching the basic map information of the target area and the position information of the target area to obtain and save a first correspondence relationship between the position information of the target area and the basic map information;

[0015] The road data includes at least one of the following: the type of each road, the number of road lanes, the number of intersections, and the road curvature.

[0016] And / or the basic map information further includes historical traffic data.

[0017] The historical traffic data includes at least one of the following: historical traffic volume, average speed, congestion index, passenger flow, passenger-vehicle ratio, truck ratio, and number of traffic accidents.

[0018] In a possible implementation, after obtaining the position information of the target area, the method further includes:

[0019] using a clustering algorithm to perform clustering processing on the position information of the target area to obtain processed position information of the target area.

[0020] In a possible implementation, the step S2 includes:

[0021] obtaining historical driving behavior data of a vehicle in the target area;

[0022] The historical driving behavior data includes state information of the vehicle at each time point and vehicle speed and position information around the vehicle, and the state information of the vehicle at each time point includes at least one of the following: position, speed, acceleration / deceleration, and turning angle.

[0023] According to a preset rule, a road safety event is extracted from the historical driving behavior data, and the road safety event includes a self-vehicle safety event and a he-vehicle safety event.

[0024] The self-vehicle safety event includes at least one of the following: sudden braking, sudden turning, horn, and high beam.

[0025] The other vehicle safety event includes at least one of the following: the distance between the ego vehicle and the other vehicle is less than a preset value, the acceleration or deceleration of the other vehicle is greater than a preset value, dangerous merging lane changing, and collision between the other vehicles;

[0026] Assigning an importance value to the road safety event;

[0027] According to the basic map information of the road safety event and the first correspondence, the road safety event is assigned to the corresponding position information according to a preset ratio, and a second correspondence between the road safety event and the position information of the target area is calculated and saved according to the weight of the corresponding position information and the importance value of the road safety event.

[0028] In a possible implementation, the step S3 includes:

[0029] According to the second correspondence, a danger degree measurement model is established;

[0030] Using maximum likelihood estimation, the data points of the second correspondence are taken as a pre-fitted distribution to obtain a probability value of each position information;

[0031] According to the probability value of each position information, a risk probability of each position information encountering danger is obtained;

[0032] The risk probability is non-linearly mapped to a danger degree measurement to obtain a third correspondence between the position information of the target area and the danger degree measurement.

[0033] In addition, to achieve the above-mentioned purpose, the present application further proposes a driving method using the constructed prior danger degree measurement map as described above, wherein the prior danger degree measurement map is a summary of the position information of the target area road and the corresponding danger degree measurement, and the prior danger degree measurement map includes a third correspondence between the position information of the target area and the danger degree measurement.

[0034] In addition, to achieve the above-mentioned purpose, the present application further proposes a driving method using the constructed prior danger degree measurement map as described above, wherein the prior danger degree measurement map is a summary of the position information of the target area road and the corresponding danger degree measurement, and the prior danger degree measurement map includes a third correspondence between the position information of the target area and the danger degree measurement.

[0035] A1: obtaining a prior danger degree measurement map of a target area, and obtaining a prior danger degree measurement value of an ego vehicle attention area according to the prior danger degree measurement map of the target area;

[0036] A2: performing planning control of the ego vehicle based on the obtained prior danger degree measurement value.

[0037] In a possible implementation, the step A1 includes the following steps:

[0038] obtaining a prior dangerous degree metric value of the self-vehicle's attention area in a future preset time, comprising:

[0039] obtaining first position information of the self-vehicle; wherein the first position information comprises at least one of the following: current coordinates, future expected coordinates;

[0040] obtaining attention area information corresponding to the first position information of the self-vehicle according to the prior dangerous degree metric map and the first position information of the self-vehicle;

[0041] obtaining a dangerous degree metric corresponding to the attention area information according to the third correspondence relationship, and obtaining a weighted average of the dangerous degree metrics corresponding to all the attention area information to obtain a prior dangerous degree metric value of the self-vehicle's attention area in a future preset time.

[0042] In a possible implementation, the step A2 comprises the following steps:

[0043] dangerously prompting a road section with a prior dangerous degree metric value greater than a first preset threshold; and / or,

[0044] sorting according to the prior dangerous degree metric value, and recommending a route with the lowest prior dangerous degree metric value as a driving route; and / or,

[0045] recommending a conservative driving style for a road section with a prior dangerous degree metric value greater than a second preset threshold, and recommending an aggressive driving style for a road section with a prior dangerous degree metric value not greater than the second preset threshold.

[0046] In addition, to achieve the above object, the application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the method for constructing a prior dangerous degree metric map or the steps of the driving method using the prior dangerous degree metric map.

[0047] The technical scheme of the present application obtains basic map information of a target area, saves a first corresponding relationship between position information of the target area and the basic map information, wherein the basic map information comprises road data, obtains historical driving behavior data of a target vehicle in the target area, extracts road safety events from the historical driving behavior data according to a preset rule, matches the road safety events to corresponding position information according to the position information of the road safety events and the first corresponding relationship, obtains a second corresponding relationship between the road safety events and the position information of the target area, establishes a danger degree measurement model according to the second corresponding relationship, obtains a risk probability of each position information, and non-linearly maps the risk probability to a danger degree measurement, obtains a third corresponding relationship between the position information of the target area and the danger degree measurement, and according to the third corresponding relationship, the position information of the target area and the corresponding danger degree measurement are summarized to construct a prior danger degree measurement map of the target area. In this way, the prior danger degree measurement map of the target area can be obtained, and the good or bad of the automatic driving system and the safety degree of the road section can be estimated more finely.

[0048] The technical scheme of the present application, after constructing the prior danger degree measurement map of the target area, can obtain the prior danger degree measurement map of the target area, and obtain a prior danger degree measurement value of a self-vehicle attention area according to the prior danger degree measurement map of the target area. The planning control of the self-vehicle is performed based on the obtained prior danger degree measurement value. In this way, after obtaining the prior danger degree measurement map of the target area, the danger degree can be obtained by directly querying the coordinates of the prior danger degree measurement map when needed, and the good or bad of the automatic driving system and the safety degree of the road section can be estimated more finely. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 A flowchart of a method for constructing a prior danger degree measurement map is provided.

[0050] Figure 2 A flowchart of step S1 in a method for constructing a prior danger degree measurement map is provided.

[0051] Figure 3 A flowchart of step S2 in a method for constructing a prior danger degree measurement map is provided.

[0052] Figure 4 A flowchart of step S3 in a method for constructing a prior danger degree measurement map is provided.

[0053] Figure 5 A flowchart of a driving method based on a prior danger degree measurement map is provided.

[0054] Figure 6 The figure is a flow chart of step A1 in a driving method based on a priori danger degree measurement map provided by the present invention.

[0055] Figure 7 It is a schematic diagram of the structure of a vehicle in the hardware operating environment involved in the embodiment of the present invention.

[0056] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0057] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and more understandable, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention.

[0058] In the subsequent description, suffixes such as "module," "component," or "unit" used to represent elements are only used to facilitate the description of the present invention and have no specific meaning. Therefore, "module," "component," or "unit" can be used interchangeably.

[0059] 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.

[0060] Please refer to Figure 1 As shown, the present invention provides a method for constructing a priori risk degree measurement map, the method comprising:

[0061] Step S1: Obtain basic map information of a target area, and save a first correspondence between the location information of the target area and the basic map information; wherein the basic map information includes road data.

[0062] Step S2: Obtain historical driving behavior data of the target vehicle in the target area, and extract road safety events from the historical driving behavior data according to preset rules; match the road safety events to the corresponding location information based on the location information of the road safety events and the first correspondence, and obtain a second correspondence between the road safety events and the location information of the target area.

[0063] Step S3: Establish a danger level measurement model based on the second corresponding relationship, obtain the risk probability of each location information, and nonlinearly map it to the danger level measurement to obtain a third corresponding relationship between the location information of the target area and the danger level measurement.

[0064] Step S4: according to the third correspondence relationship, the position information of the target area and its corresponding risk degree measure are summarized to construct a prior risk degree measure map of the target area.

[0065] In the embodiment, basic map information of a target area is acquired, and a first correspondence relationship between position information of the target area and the basic map information is saved, wherein the basic map information includes road data. Historical driving behavior data of a target vehicle in the target area is acquired, and a road safety event is extracted from the historical driving behavior data according to a preset rule. The road safety event is matched to corresponding position information according to the position information of the road safety event and the first correspondence relationship, to obtain a second correspondence relationship between the road safety event and the position information of the target area. A risk degree measure model is established according to the second correspondence relationship, and a risk probability of each position information is acquired and nonlinearly mapped to a risk degree measure, to obtain a third correspondence relationship between the position information of the target area and the risk degree measure. The position information of the target area and its corresponding risk degree measure are summarized according to the third correspondence relationship, to construct a prior risk degree measure map of the target area. In this way, a prior risk degree measure map of the target area can be obtained, the good or bad of an automatic driving system and the safety degree of a road section can be estimated in a more refined manner for a specific road, and a basis is provided for subsequent use of the prior risk degree measure map.

[0066] It should be noted that, in the embodiment, the definition of the risk degree measure is that only a risk degree measure based on a geographical position is considered, that is, real-time interaction of a scene is not considered. In order to simplify and compress the size of the prior risk degree measure map, in the embodiment, only an area in which an automatic driving vehicle can travel is plotted: according to different automatic driving tasks, generally only a hardening road surface existing in a map is included.

[0067] In the embodiment, absolute safety is set as a risk degree measure = 0: that is, the road completely does not exist any other dynamic participant, and there is no any static obstacle that can cause a collision. Of course, this situation is obviously impossible to exist in reality, because a road boundary itself is one of the obstacles, and the absolute safety 0 exists as a theoretical value. Absolute danger is set as a risk degree measure = 1: that is, driving to a certain point will inevitably cause an accident.

[0068] As a specific embodiment, the step S1 is collection and processing of basic map information. That is, in order to make the risk degree calculation more accurate, some basic information needs to be collected first.

[0069] Specifically, basic map information of the target area is acquired, wherein the basic map information at least includes road data. Then, for position information in the target area, a first correspondence relationship between position information of the target area after matching the basic map information and the basic map information is matched.

[0070] That is, finally, the step S1 will obtain a first matrix with a length of the number of position information and a width of the dimension of the basic map information.

[0071] In the embodiment, the specific content of the step S1 can further refer to 2, as shown in the following table. Figure 2 The step S1 includes the following steps.

[0072] Step 101: Acquire basic map information of the target area.

[0073] In the embodiment, the data corresponding to the dimension of the danger degree measurement subject model is filtered from the basic map information including a plurality of data sources, wherein the basic map information includes road data, and the data sources are very rich, based on which the danger degree calculation is more accurate.

[0074] In implementation, big data technology can be used, such as hadoop cluster processing massive data, to realize data mining, summarization, crawler and other data processing processes.

[0075] The road data related to the road as the most important part of the basic map information includes but is not limited to: the type of each road, the number of road lanes, the number of intersections, the road curvature, etc.

[0076] Of course, the basic map information can also include historical traffic data, which can also use big data technology, such as hadoop cluster processing massive data, to realize data mining, summarization, crawler and other data processing processes.

[0077] The historical traffic data includes but is not limited to: road historical traffic volume, average speed, congestion index, passenger flow, vehicle ratio, truck ratio, and the number of traffic accidents.

[0078] Step 102: Acquire position information of the target area.

[0079] In the embodiment, after a target area is delimited, each concerned position in the target area is taken as a point of interest, and the point of interest coordinates, i.e. position information, are obtained. It can be understood that the target area can be a full city map of a certain area, such as A city. It can be understood that there can be a certain interval between each concerned position, for example, 10 meters per point.

[0080] Step 103: matching the basic map information of the target area and the position information of the target area to obtain and save the first correspondence between the position information of the target area and the basic map information.

[0081] In this embodiment, after obtaining the basic map information and the position information in the target area, for each position of interest, i.e. position information, the basic map information of the target area and the position information of the target area are matched to obtain and save the first correspondence between the position information of the target area and the basic map information. For example, a discrete value (classification: for example, narrow road, auxiliary road, expressway) or a continuous value (for example, average daily traffic volume) vector can be given to all basic map information.

[0082] That is, finally, based on the steps 101 to 103, a first matrix with a length of the number of position information and a width of the dimension of the basic map information will be obtained.

[0083] Of course, as an optional embodiment, the position information of the target area obtained in step S1 can be further processed in subsequent use.

[0084] Specifically, the position information of the target area can be clustered using a clustering algorithm to obtain the processed position information of the target area.

[0085] For example, a clustering algorithm can be used to cluster each point of interest into M classes, where the size of M can be set according to the amount of data, and the verification period can be set to 50-100, and then set to 100-1000.

[0086] Of course, considering the need for continuity, the spatial correlation of coordinates needs to be considered when clustering. In actual use, a complete road, such as from intersection 1 to intersection 2, or the entire intersection 3, is forced to have coordinates of the same classification.

[0087] In the early verification period, a simple decision tree algorithm can be used for clustering: for example, class B is defined as a highway section with a lane number greater than or equal to 4 and no on-ramp or off-ramp within 50 meters.

[0088] It should be noted that the position information of the target area before processing can also be used, or the position information of the target area after processing can also be used, which is not limited in this embodiment. It can be understood that the difference between the two is only the amount of data calculated, and the amount of data of the position information of the target area before processing is greater than that of the position information of the target area after processing, and the processing efficiency is lower than that of the position information of the target area after processing. However, both can achieve the technical effects of the present application.

[0089] As a specific embodiment, the step S2 is the collection and processing of historical driving behavior data.

[0090] Specifically, by obtaining historical driving behavior data of a target vehicle, and filtering road safety events from the historical driving behavior data according to a preset rule; then processing the road safety events to obtain a second correspondence between the road safety events and the position information of the target area.

[0091] That is, finally, the step S3 will obtain a second matrix with a length of the position information quantity and a width of the road safety event category; wherein the value of the second matrix is the weighted event number, that is, the number of road safety events in a unit space.

[0092] In this embodiment, the specific content of the step S2 can further refer to 3, as shown in Figure 3 The step S2 includes:

[0093] Step 201: Obtain historical driving behavior data of a vehicle in the target area.

[0094] In this embodiment, a sufficient amount of historical driving behavior data needs to be sorted, where the source of these historical driving behavior data can be based on automatic driving, and can also be based on manual driving, which is not limited in this embodiment.

[0095] It can be understood that the global historical driving behavior data is obtained here, and the "target vehicle" referred to here can be any vehicle.

[0096] The historical driving behavior data considered includes but is not limited to: state information of the vehicle at each time point and vehicle speed and position information around the vehicle; the state information of the vehicle at each time point includes at least one of the following: position, speed, acceleration and deceleration, and turning angle.

[0097] Step 202: Extract road safety events from the historical driving behavior data according to a preset rule, wherein the road safety events include self-vehicle safety events and other-vehicle safety events.

[0098] In this embodiment, the events related to road safety can be captured from the historical driving behavior data by setting a preset rule condition, and the road safety events include self-vehicle safety events and other-vehicle safety events.

[0099] The self-vehicle safety events include at least one of the following: sudden braking, sudden turning, horn, flashing high beam, and manual takeover during automatic driving.

[0100] For example, typical ego safety events include: one hard braking (e.g., deceleration greater than 1 m / s 2 ); one hard steering (e.g., angular velocity greater than 1 rad / s); one horn honking; one high beam flashing; one takeover in autonomous driving (i.e., the driver thinks the autonomous driving is currently unable to handle the current scene, and there may be safety problems); one important takeover in autonomous driving (i.e., after simulation, it is indeed that if not taken over, a collision or other safety problems will occur).

[0101] The other car safety events include at least one of the following: the distance between the ego car and the other car is less than a preset value, the acceleration or deceleration of the other car is greater than a preset value, a dangerous merging lane, and a collision between the other cars.

[0102] For example, the other car related events include: the ego car is too close to other cars (e.g., less than 1 meter); the acceleration or deceleration of the other car is too large; one dangerous merging lane; a collision between the other cars; and the like.

[0103] Step 203: assigning an importance value to the road safety event.

[0104] In this embodiment, each road safety event contains an importance value, and the road safety event can be assigned an importance value, for example: one hard braking with a deceleration of -8 m / s 2 has a greater importance value than one hard braking with a deceleration of -2 m / s 2 .

[0105] Step 204: according to the basic map information of the road safety event and the first correspondence relationship, assigning the road safety event to the corresponding position information according to a preset ratio, and calculating and saving a second correspondence relationship between the road safety event and the position information of the target area according to the weight of the corresponding position information and the importance value of the road safety event.

[0106] In this embodiment, each road safety event can be assigned to the nearest K coordinates in proportion, for example: when K = 4, the coordinates of a road safety event are in the square surrounded by its nearest four points, then according to the distance, the four points are added to part of the weight of this event multiplied by the importance value. According to the distance, the weight is assigned according to the principle of proportional distribution, which can be according to the logic of "the closer the distance, the greater the weight", for example, the reciprocal of the distance can be used as the weight.

[0107] That is, finally, based on the steps 301 to 304, a second matrix with a length of position information quantity and a width of road safety event categories will be obtained; wherein the value of the second matrix is the weighted event number.

[0108] As a specific embodiment, the step S3 is modeling and calculating of the danger degree metric.

[0109] Specifically, a danger degree metric model can be established according to the second correspondence relationship, and a risk probability of each position information is calculated, and then is non-linearly mapped to a danger degree metric to obtain a third correspondence relationship between the position information and the danger degree metric of the target area.

[0110] That is, finally, the step S3 will obtain a second vector with a length of the number of position information; wherein the value of the second vector is the danger degree metric of the position information.

[0111] That is, the second correspondence relationship is (position information, road safety event), which is converted into the third correspondence relationship (position information, danger degree metric) according to the model.

[0112] In the embodiment, the specific content of the step S3 can be further referred to 4, as shown in Figure 4 The step S4 includes:

[0113] Step 301: establishing a danger degree metric model according to the second correspondence relationship.

[0114] Step 302: using maximum likelihood estimation to obtain a probability value of each position information by taking the data points of the second correspondence relationship as a pre-fitting distribution.

[0115] Step 303: obtaining a risk probability of each position information encountering danger according to the probability value of each position information.

[0116] Step 304: non-linearly mapping the risk probability to a danger degree metric to obtain a third correspondence relationship between the position information and the danger degree metric of the target area.

[0117] In the embodiment, we can model the danger degree as a Latent Dirichlet Allocation (LDA) topic model. It is assumed that the probability of the ego vehicle encountering danger in a scene is composed of multiple possible road safety events X_1, X_2,..., X_k, and each road safety event is determined by some factors, and whether each factor occurs or not is related to multiple state information. Of course, in the embodiment, the state information is simply divided into two categories: state information related to spatial coordinates and other irrelevant information. Since only spatial information is discussed in the embodiment, other state information can be discarded.

[0118] Specifically, the data points of the second correspondence obtained in step S2 can be taken as a pre-fitted distribution, and the probability value of each position information is obtained by using maximum likelihood estimation, and the risk probability of encountering danger is obtained, and then it is nonlinearly mapped to the danger degree measure of 0-1, and the third correspondence between the position information and the danger degree measure of the target area is obtained.

[0119] That is, finally, based on the steps 301 to 304, a second vector with a length of the number of position information is obtained; wherein the value of the second vector is the danger degree measure of the position information.

[0120] It should be noted that the modeling in step S3 can also directly model the probability into a more general energy model or Gaussian mixture model, and replace the energy / parameters with a deep neural network to improve the accuracy of the model. However, it should be noted that more complex neural networks require more data for training, and if the amount of data is not enough, it may not reach the effect of a simple model.

[0121] As a specific embodiment, the step S4 is to construct a prior danger degree measure map.

[0122] Specifically, after obtaining the third correspondence in step S3, the position information of the target area and the corresponding danger degree measure can be summarized according to the third correspondence, so as to construct a prior danger degree measure map of the target area.

[0123] It can be understood that the prior danger degree measure map constructed in the embodiment can be an offline calculation process, and only online calculation is required when the prior danger degree measure map is used.

[0124] In the embodiment of the present application, basic map information of a target area is acquired, and a first correspondence relationship between position information of the target area and the basic map information is saved, wherein the basic map information comprises road data; historical driving behavior data of a target vehicle in the target area is acquired, and a road safety event is extracted from the historical driving behavior data according to a preset rule; the road safety event is matched to corresponding position information according to the first correspondence relationship based on position information of the road safety event, so as to obtain a second correspondence relationship between the road safety event and the position information of the target area; a dangerous degree measurement model is established according to the second correspondence relationship, and a risk probability of each position information is acquired and nonlinearly mapped to a dangerous degree measurement, so as to obtain a third correspondence relationship between the position information of the target area and the dangerous degree measurement; the position information of the target area and the corresponding dangerous degree measurement are summarized according to the third correspondence relationship, so as to construct a prior dangerous degree measurement map of the target area. In this way, the prior dangerous degree measurement map of the target area can be obtained, the good or bad of the automatic driving system and the safety degree of a road section can be estimated in a more refined manner, and a basis is provided for subsequent use of the prior dangerous degree measurement map.

[0125] The present application also provides a prior dangerous degree measurement map, which is constructed by using the above method, and is a summary of position information of a target area road and corresponding dangerous degree measurement thereof, and comprises a third correspondence relationship between the position information of the target area and the dangerous degree measurement.

[0126] It can be understood that the prior dangerous degree measurement map can be used after being constructed.

[0127] Reference is made to Figure 5 The present application provides a driving method based on a prior dangerous degree measurement map, which comprises:

[0128] Step A1: acquiring a prior dangerous degree measurement map of a target area, and acquiring a prior dangerous degree measurement value of a self-vehicle attention area according to the prior dangerous degree measurement map of the target area.

[0129] Step A2: performing planning control of the self-vehicle based on the acquired prior dangerous degree measurement value.

[0130] In the embodiment of the present application, after the prior dangerous degree measurement map of the target area is obtained, the dangerous degree can be directly queried from the coordinates of the prior dangerous degree measurement map when it is needed to be used, so that the good or bad of the automatic driving system and the safety degree of a road section can be estimated in a more refined manner.

[0131] That is, the embodiment is a use method after drawing the prior danger degree measurement map, so that the prior danger warning can be performed based on the prior danger degree measurement map.

[0132] In the embodiment, the specific content of step A1 can further refer to 6, as shown in the figure, step S5 includes: Figure 6

[0133] Step 501: obtaining first position information of the ego vehicle; wherein the first position information includes at least one of the following: current coordinates, future expected coordinates.

[0134] Step 502: obtaining attention region information corresponding to the first position information of the ego vehicle according to the prior danger degree measurement map and the first position information of the ego vehicle.

[0135] Step 503: obtaining attention region information corresponding to the first position information of the ego vehicle according to the prior danger degree measurement map and the first position information of the ego vehicle.

[0136] Specifically, the prior danger degree measurement map of the target region can be used to obtain the first position information of the ego vehicle, which includes at least one of the following: current coordinates, future expected coordinates, i.e. the current position or the position in a future period of time. Then, according to the prior danger degree measurement map and the first position information of the ego vehicle, the attention region information corresponding to the first position information of the ego vehicle is obtained. It should be noted that the attention region information can be obtained by taking the distance less than a certain distance, or the region of a certain road or relationship can be forcibly set as the same region, which is not limited in the embodiment. Finally, according to the third corresponding relationship, the danger degree measurement corresponding to the attention region information is obtained, and the danger degree measurements corresponding to all the attention region information are weighted and averaged, so as to obtain the prior danger degree measurement value of the attention region of the ego vehicle in a future preset time.

[0137] It can be understood that if it is necessary to calculate the danger degree of the scene where the vehicle is at a certain moment, a difference algorithm can be used. For the current coordinates (x, y) of the vehicle, all points in the prior danger degree measurement map with a distance less than a certain threshold, for example, = 10 meters, are found, and the danger degree measurements of these points are weighted and averaged to obtain the final danger degree measurement value of the point.

[0138] Wherein, the "weighted average" can take some weighting coefficients as 0, so as to form any way of taking the middle value, removing the maximum and minimum to obtain the mean value, taking the maximum value, etc., which is not limited in the embodiment.

[0139] ​Of course, it can be understood that if the vehicle itself has a plan or prediction of the future direction of movement, the planned coordinate points can be used to make an expected risk level measurement, that is, how high the risk level is in the near future (for example, within 30 seconds). If the future planned trajectory has 100 points, the sum of the risk level measurements of the 100 points can be directly used.

[0140] In this embodiment, the specific content of step A2 is how to perform planning control of the ego vehicle based on the obtained prior risk level measurement value.

[0141] It can be understood that for the planning control of the ego vehicle based on the obtained prior risk level measurement graph of the risk level, there can be multiple ways, including giving a risk prompt for a road segment whose prior risk level measurement value is greater than a first preset threshold; and / or, sorting according to the prior risk level measurement value, and recommending a route with the lowest prior risk level measurement value as a driving route; and / or, recommending a conservative driving style for a road segment whose prior risk level measurement value is greater than a second preset threshold; and / or, recommending an aggressive driving style for a road segment whose prior risk level measurement value is not greater than the second preset threshold.

[0142] For example, the following is illustrated:

[0143] 1. Reminder to human driving drivers: For dangerous road segments, prompt during navigation that the current road segment is dangerous, please pay attention.

[0144] 2. To the automatic driving system, use a more aggressive driving style on a road segment with a lower prior risk level, with progress as the priority; use a more conservative driving style on a road segment with a higher prior risk level, with safety as the priority, including active defensive driving and speed reduction.

[0145] 3. To the automatic driving system, give some active signal prompts, such as turning on high beams and appropriately honking on a road segment with a higher prior risk level to more explicitly interact with road participants.

[0146] 4. To the traffic department, for road segments with a higher prior risk level, carry out targeted road dredging or lane improvement, etc.

[0147] 5. To the navigation software, if multiple routes have similar times, the prior risk level can be used for sorting to give a safer path.

[0148] In the embodiment of the present application, the prior danger degree measurement map of the target area is obtained, and the prior danger degree measurement value of the ego vehicle attention area is obtained according to the prior danger degree measurement map of the target area. In this way, after obtaining the prior danger degree measurement map of the target area, the danger degree can be directly obtained by querying the coordinates of the prior danger degree measurement map when needed, and the prior danger warning can be performed based on the prior danger degree measurement map, and the good or bad of the automatic driving system and the safety degree of the road section can be estimated in more detail.

[0149] In addition, in some optional embodiments, the position information such as coordinates can be two-dimensional coordinates or three-dimensional coordinates. That is, in order to better distinguish the road danger degree difference between morning and evening peak and flat peak periods, the coordinates can be derived into generalized space-time coordinates, that is, (x, y, t), where t can be 2 hours apart, and there are 12 discrete values in a day.

[0150] It can be understood that the processing mode of three-dimensional coordinates is basically the same as that of two-dimensional coordinates, and the embodiment will not be repeated here. Only the increase of the time dimension will cause the increase of the number of coordinates, and the collection of historical data needs to be further increased, and the collection amount of each area and time needs to be basically uniform. Although the amount of historical data increases, the number of coordinates does not decrease. In order to reduce the data demand, an optional scheme is as follows: if the amount of historical data is insufficient, one waypoint can be defined as the center line of the lane of a road, and one point every 10 meters, and these waypoints are used as coordinates, and all other coordinates are discarded. Such a method can be used to reduce the number of coordinates. Because: the smaller the number of coordinates, the smaller the amount of history required.

[0151] Reference Figure 7 , Figure 7 The structural schematic diagram of the vehicle related to the hardware running environment of the embodiment of the present application.

[0152] As Figure 7 shown, the vehicle can include a processor 1001 such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 can include a display screen (Display) and an input unit such as a keyboard (Keyboard). The optional user interface 1003 can also include a standard wired interface and a wireless interface. The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a WI-FI, 4G, 5G interface). The memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory) such as a disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0153] Those skilled in the art can understand that, Figure 7 The structure shown in the figure does not constitute a limitation on the vehicle, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0154] As Figure 7 As shown, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and a driving program based on a prior hazard degree metric map and a prior hazard degree metric map construction program.

[0155] In Figure 7 In the vehicle shown in the figure, the network interface 1004 is mainly used for data communication with the external network; the user interface 1003 is mainly used for receiving the input instructions of the user; the vehicle calls the driving program based on the prior hazard degree metric map stored in the memory 1005 through the processor 1001, and performs the following operations:

[0156] A1: Obtain the prior hazard degree metric map of the target area, and obtain the prior hazard degree metric value of the ego vehicle attention area according to the prior hazard degree metric map of the target area;

[0157] A2: Perform planning control of the ego vehicle based on the obtained prior hazard degree metric value.

[0158] In a possible implementation, the step A1 includes the following steps:

[0159] Obtaining the prior hazard degree metric value of the ego vehicle attention area within a future preset time, comprising:

[0160] Obtaining first position information of the ego vehicle; wherein the first position information comprises at least one of the following: current coordinates, future expected coordinates;

[0161] According to the prior hazard degree metric map and the first position information of the ego vehicle, the attention area information corresponding to the first position information of the ego vehicle is obtained;

[0162] According to the third correspondence, the hazard degree metric corresponding to the attention area information is obtained, and the hazard degree metrics corresponding to all the attention area information are weighted and averaged to obtain the prior hazard degree metric value of the ego vehicle attention area within a future preset time.

[0163] In a possible implementation, the step A2 includes the following steps:

[0164] Dangerous prompt is performed on the road section with a prior hazard degree metric value greater than a first preset threshold; and / or,

[0165] rank the routes according to the prior dangerousness metric values, and recommend the route with the lowest prior dangerousness metric value as the driving route; and / or

[0166] recommend a driving style of a road segment with a prior dangerousness metric value greater than the second preset threshold as conservative, and recommend a driving style of a road segment with a prior dangerousness metric value not greater than the second preset threshold as aggressive.

[0167] In ​ In the vehicle shown in FIG. 10, the vehicle further invokes a program for constructing a prior dangerousness metric map stored in the memory 1005 by the processor 1001, and performs the following operations:

[0168] S1: Obtain basic map information of a target region, and save a first correspondence relationship between location information of the target region and the basic map information; wherein the basic map information comprises road data;

[0169] S2: Obtain historical driving behavior data of a target vehicle in the target region, and extract road safety events from the historical driving behavior data according to a preset rule; match the road safety events to corresponding location information according to the location information of the road safety events and the first correspondence relationship, to obtain a second correspondence relationship between the road safety events and the location information of the target region;

[0170] S3: Establish a dangerousness metric model according to the second correspondence relationship, and obtain a risk probability of each location information, which is non-linearly mapped to a dangerousness metric, to obtain a third correspondence relationship between the location information of the target region and the dangerousness metric;

[0171] S4: Aggregate the location information of the target region and the corresponding dangerousness metric according to the third correspondence relationship, to construct a prior dangerousness metric map of the target region.

[0172] In a possible implementation, the step S1 comprises:

[0173] Obtain basic map information of the target region;

[0174] Obtain location information of the target region;

[0175] Match the basic map information of the target region and the location information of the target region, to obtain and save a first correspondence relationship between the location information of the target region and the basic map information;

[0176] The road data comprises at least one of the following: types of roads, numbers of road lanes, numbers of intersections, and road curvatures;

[0177] and / or the basic map information further comprises historical traffic data;

[0178] The historical traffic data comprises at least one of the following: road historical traffic volume, average vehicle speed, congestion index, passenger flow, passenger-vehicle ratio, truck ratio, and number of traffic accidents.

[0179] In a possible implementation, after the position information of the target area is acquired, the method further comprises:

[0180] The position information of the target area is clustered using a clustering algorithm to obtain processed position information of the target area.

[0181] In a possible implementation, the step S2 comprises:

[0182] The historical driving behavior data of the vehicle in the target area is acquired;

[0183] The historical driving behavior data comprises state information of the vehicle at each time point and vehicle speed and position information around the vehicle, and the state information of the vehicle at each time point comprises at least one of the following: position, speed, acceleration / deceleration, and turning angle.

[0184] The road safety events are extracted from the historical driving behavior data according to a preset rule, wherein the road safety events comprise self-vehicle safety events and other-vehicle safety events;

[0185] The self-vehicle safety events comprise at least one of the following: sudden braking, sudden turning, horn sounding, and high beam flashing; and manual takeover during automatic driving.

[0186] The other-vehicle safety events comprise at least one of the following: distance between the self-vehicle and the other-vehicle is less than a preset value, acceleration or deceleration of the other-vehicle is greater than a preset value, dangerous merging or lane changing, and collision between the other-vehicles.

[0187] The road safety events are assigned with importance values.

[0188] The road safety events are distributed to corresponding position information according to a preset proportion according to the basic map information of the road safety events and the first correspondence relationship, and a second correspondence relationship between the road safety events and the position information of the target area is calculated and saved according to the weight of the corresponding position information and the importance values of the road safety events.

[0189] In a possible implementation, the step S3 comprises:

[0190] A risk degree measurement model is established according to the second correspondence relationship.

[0191] using maximum likelihood estimation, to obtain a probability value of each position information;

[0192] According to the probability value of each position information, a risk probability of each position information encountering danger is obtained.

[0193] The risk probability is mapped to a danger degree metric in a non-linear manner to obtain a third correspondence between the position information of the target region and the danger degree metric.

[0194] The embodiment of the present application can obtain a prior danger degree metric map for an automatic driving region, and directly query the danger degree when needed, to more finely estimate the good or bad of an automatic driving system and the safety degree of a road section.

[0195] In addition, the embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a driving program based on a prior danger degree metric map and a program for constructing a prior danger degree metric map, wherein the driving program based on the prior danger degree metric map is executed by a processor to implement the following operations:

[0196] A1: obtaining a prior danger degree metric map of a target region, and obtaining a prior danger degree metric value of a self-vehicle concerned region according to the prior danger degree metric map of the target region;

[0197] A2: performing planning control of the self-vehicle based on the obtained prior danger degree metric value.

[0198] In a possible implementation manner, the step A1 includes the following steps:

[0199] obtaining the prior danger degree metric value of the self-vehicle concerned region within a future preset time, including:

[0200] obtaining first position information of the self-vehicle; wherein the first position information includes at least one of the following: a current coordinate, a future expected coordinate;

[0201] obtaining concerned region information corresponding to the first position information of the self-vehicle according to the prior danger degree metric map and the first position information of the self-vehicle;

[0202] obtaining a danger degree metric corresponding to the concerned region information according to the third correspondence, and performing weighted average on danger degree metrics corresponding to all the concerned region information to obtain the prior danger degree metric value of the self-vehicle concerned region within the future preset time.

[0203] In a possible implementation manner, the step A2 includes the following steps:

[0204] a dangerous prompt is given to a road segment whose prior dangerous degree metric value is greater than a first preset threshold; and / or

[0205] the routes are sorted according to the prior dangerous degree metric values, and a route with the lowest prior dangerous degree metric value is recommended as a driving route; and / or

[0206] a driving style of a road segment whose prior dangerous degree metric value is greater than a second preset threshold is recommended as a conservative type, and a driving style of a road segment whose prior dangerous degree metric value is not greater than the second preset threshold is recommended as an aggressive type.

[0207] When the program for constructing the prior dangerous degree metric map is executed by the processor, the following operations are implemented:

[0208] S1: Obtain basic map information of a target region, and save a first correspondence relationship between location information of the target region and the basic map information; wherein the basic map information comprises road data;

[0209] S2: Obtain historical driving behavior data of a target vehicle in the target region, and extract road safety events from the historical driving behavior data according to a preset rule; match the road safety events to corresponding location information according to the location information of the road safety events and the first correspondence relationship, to obtain a second correspondence relationship between the road safety events and the location information of the target region;

[0210] S3: Establish a dangerous degree metric model according to the second correspondence relationship, and obtain a risk probability of each location information, which is non-linearly mapped to a dangerous degree metric, to obtain a third correspondence relationship between the location information of the target region and the dangerous degree metric;

[0211] S4: According to the third correspondence relationship, the location information of the target region and the corresponding dangerous degree metric are summarized to construct a prior dangerous degree metric map of the target region.

[0212] In a possible implementation, the step S1 comprises:

[0213] Obtain basic map information of the target region;

[0214] Obtain location information of the target region;

[0215] Match the basic map information of the target region and the location information of the target region, to obtain and save the first correspondence relationship between the location information of the target region and the basic map information;

[0216] The road data comprises at least one of the following: types of roads, numbers of road lanes, numbers of intersections, and road curvatures;

[0217] and / or the basic map information further comprises historical traffic data;

[0218] The historical traffic data comprises at least one of the following: road historical traffic volume, average vehicle speed, congestion index, passenger flow, passenger-vehicle ratio, truck ratio, and number of traffic accidents.

[0219] In a possible implementation, after the position information of the target area is acquired, the method further comprises:

[0220] The position information of the target area is clustered using a clustering algorithm to obtain processed position information of the target area.

[0221] In a possible implementation, the step S2 comprises:

[0222] Acquiring historical driving behavior data of the vehicle in the target area;

[0223] The historical driving behavior data comprises state information of the vehicle at each time point and vehicle speed and position information around the vehicle, and the state information of the vehicle at each time point comprises at least one of the following: position, speed, acceleration / deceleration, and turning angle.

[0224] According to a preset rule, a road safety event is extracted from the historical driving behavior data, wherein the road safety event comprises a self-vehicle safety event and a he-vehicle safety event.

[0225] The self-vehicle safety event comprises at least one of the following: sudden braking, sudden turning, horn sounding, and high beam flashing; and manual takeover during automatic driving.

[0226] The he-vehicle safety event comprises at least one of the following: distance between the self-vehicle and the he-vehicle is less than a preset value, acceleration or deceleration of the he-vehicle is greater than a preset value, dangerous merging and lane changing, and collision between the he-vehicles.

[0227] An importance value is assigned to the road safety event.

[0228] According to the basic map information of the road safety event and the first correspondence relationship, the road safety event is distributed to corresponding position information according to a preset proportion, and a second correspondence relationship between the road safety event and the position information of the target area is calculated and saved according to a weight of the corresponding position information and the importance value of the road safety event.

[0229] In a possible implementation, the step S3 comprises:

[0230] A risk degree measurement model is established according to the second correspondence relationship.

[0231] The data points of the second correspondence are taken as a pre-fitted distribution, and a probability value of each position information is obtained by using maximum likelihood estimation;

[0232] According to the probability value of each position information, a risk probability of each position information encountering danger is obtained.

[0233] The risk probability is mapped to a danger degree metric in a non-linear manner to obtain a third correspondence between the position information and the danger degree metric of the target region.

[0234] According to the embodiments of the present application, a prior danger degree metric map can be obtained for an automatic driving region, and a danger degree can be directly obtained by querying when needed, so that the good or bad of an automatic driving system and the safety degree of a road section can be estimated in a more refined manner.

[0235] It should be noted that in this document, the terms "comprise", "comprising", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles, or systems that include a series of elements not only include those elements, but also include other elements not explicitly listed, or inherent to such processes, methods, articles, or systems. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of another identical element in the process, method, article, or system that includes the element.

[0236] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0237] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and a necessary general hardware platform, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk) as described above, and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, a controller, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0238] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method of constructing a priori risk level metric map, characterized by, The method comprises the following steps: S1: obtaining basic map information of a target area, and saving a first correspondence relationship between position information of the target area and the basic map information; wherein the basic map information comprises road data; S2: obtaining historical driving behavior data of a target vehicle in the target area, and extracting road safety events from the historical driving behavior data according to a preset rule; matching the road safety events to corresponding position information according to the position information of the road safety events and the first correspondence relationship, to obtain a second correspondence relationship between the road safety events and the position information of the target area; S3: establishing a danger degree measurement model according to the second correspondence relationship, and obtaining a risk probability of each position information, which is non-linearly mapped to a danger degree measurement, to obtain a third correspondence relationship between the position information of the target area and the danger degree measurement; S4: according to the third correspondence relationship, summarizing the position information of the target area and the corresponding danger degree measurement, to construct a prior danger degree measurement map of the target area.

2. The method of claim 1, wherein, The step S1 comprises: obtaining basic map information of the target area; obtaining position information of the target area; matching the basic map information of the target area and the position information of the target area, to obtain and save a first correspondence relationship between the position information of the target area and the basic map information; the road data comprises at least one of the following: types of roads, numbers of road lanes, numbers of intersections, and road curvatures; and / or the basic map information further comprises historical traffic data; the historical traffic data comprises at least one of the following: historical vehicle flow on roads, average vehicle speed, congestion index, human flow, human-vehicle ratio, truck ratio, and number of vehicle accidents.

3. The method of claim 2, wherein, After obtaining the position information of the target area, further comprising: using a clustering algorithm to perform clustering processing on the position information of the target area, to obtain processed position information of the target area.

4. The method according to claim 1 or 3, characterized in that, The step S2 comprises: obtaining historical driving behavior data of a vehicle in the target area; wherein the historical driving behavior data comprises state information of the vehicle at each time point and vehicle speed and position information around the vehicle; the state information of the vehicle at each time point comprises at least one of the following: position, speed, acceleration / deceleration, and turning angle; extracting road safety events from the historical driving behavior data according to a preset rule, wherein the road safety events comprise self-vehicle safety events and other-vehicle safety events; wherein the self-vehicle safety events comprise at least one of the following: sudden braking, sudden turning, horn sounding, and high beam flashing; and manual takeover during automatic driving; the other-vehicle safety events comprise at least one of the following: distance between the self-vehicle and other vehicles is less than a preset value, acceleration or deceleration of other vehicles is greater than a preset value, dangerous merging lane changing, and collision between other vehicles; assigning an importance value to the road safety events; According to the basic map information of the road safety event and the first correspondence, the road safety event is distributed to the corresponding position information according to a preset ratio, and a second correspondence between the road safety event and the position information of the target area is calculated and saved according to the weight of the corresponding position information and the importance value of the road safety event.

5. The method according to claim 1 or 3, characterized in that, The step S3 comprises: A dangerous degree measurement model is established according to the second correspondence; Data points of the second correspondence are used as a pre-fitting distribution to obtain a probability value of each position information by using maximum likelihood estimation; According to the probability value of each position information, a risk probability of each position information encountering danger is obtained; The risk probability is nonlinearly mapped to a dangerous degree measurement to obtain a third correspondence between the position information of the target area and the dangerous degree measurement.

6. A priori risk level metric map constructed using the method of any one of claims 1 to 5. The prior dangerous degree measurement map is a summary of the position information of the target area road and the corresponding dangerous degree measurement, and the prior dangerous degree measurement map comprises the third correspondence between the position information of the target area and the dangerous degree measurement.

7. A driving method using the a priori risk level metric map of claim 6, characterized by, The method comprises the following steps: A1: obtaining a prior dangerous degree measurement map of a target area, and obtaining a prior dangerous degree measurement value of a self-vehicle concerned area according to the prior dangerous degree measurement map of the target area; A2: performing planning control of the self-vehicle based on the obtained prior dangerous degree measurement value.

8. The method of claim 7, wherein, The step A1 comprises the following steps: The prior dangerous degree measurement value of the self-vehicle concerned area in a future preset time is obtained, comprising: obtaining first position information of the self-vehicle; wherein the first position information comprises at least one of the following: a current coordinate and a future expected coordinate; obtaining concerned area information corresponding to the first position information of the self-vehicle according to the prior dangerous degree measurement map and the first position information of the self-vehicle; obtaining a dangerous degree measurement corresponding to the concerned area information according to the third correspondence, and performing weighted average on the dangerous degree measurements corresponding to all the concerned area information to obtain the prior dangerous degree measurement value of the self-vehicle concerned area in the future preset time.

9. The method of claim 7, wherein, The step A2 comprises the following steps: dangerous prompt is performed on a road section whose prior dangerous degree measurement value is greater than a first preset threshold; and / or, a route whose prior dangerous degree measurement value is the lowest is recommended as a driving route according to the sorting of the prior dangerous degree measurement values; and / or, a driving style of a road section whose prior dangerous degree measurement value is greater than a second preset threshold is recommended as a conservative type, and a driving style of a road section whose prior dangerous degree measurement value is not greater than the second preset threshold is recommended as an aggressive type.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to realize the steps of the method of any one of claims 7 to 9 or the steps of the method of any one of claims 1 to 5.

Images