A method, device, vehicle and storage medium for predicting accident probability

Abstract

The embodiment of the present invention provides a method, device, vehicle and storage medium for predicting the probability of an accident. The method includes: obtaining the user's usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from the scene information of the assisted driving system, the control information in the process of using the assisted driving system and the system status information of the assisted driving system, and the number of triggering alarm behaviors corresponding to the evaluation factor; according to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by the number of triggering alarm behaviors corresponding to the evaluation factor; and the predicted probability of the user having an accident is determined. In the embodiment of the present invention, the evaluation factor is obtained through the user's usage behavior information, and the predicted probability of the user having an accident is determined by determining the user's total deduction value, so as to classify the users, so that different risk avoidance strategies can be formulated for different users to improve the user's safety awareness.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent assisted driving systems, and in particular to a method for predicting the probability of an accident, a device for predicting the probability of an accident, a vehicle and a computer-readable storage medium. Background Art

[0002] With the development of modern society, more and more vehicles are equipped with intelligent assistance system functions, which facilitates our daily life. However, due to the limitations of software and hardware, the current intelligent assistance system functions cannot cope with all vulnerable scenarios, or the prompt information of the assisted driving system is relatively simple, which makes it easy for users to ignore the prompt information of the assisted driving system.

[0003] In order to deal with all vulnerable scenarios during driving and regulate the driver's driving behavior, relying solely on the prompt information of a single assisted driving system cannot effectively solve the problem that individual users will have different driving habits based on their own driving habits and the usage habits of the assisted driving system. Summary of the invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a user security awareness scoring method based on user behavior and a corresponding user security awareness scoring device based on user behavior that overcome the above problems or at least partially solve the above problems.

[0005] In order to solve the above problems, an embodiment of the present invention discloses a user security awareness scoring method based on user behavior, the method comprising:

[0006] Obtaining user usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from scene information of using the assisted driving system, control information during the use of the assisted driving system, and system state information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor;

[0007] According to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by using the number of triggering of the alarm behavior corresponding to the evaluation factor;

[0008] The predicted probability of an accident occurring to the user is determined based on the total deduction score of the user.

[0009] Optionally, the evaluation factor is correlated with the accident record, and the total deduction value of the user is determined according to a preset deduction rule for the evaluation factor and the number of triggering times of the alarm behavior corresponding to the evaluation factor, including:

[0010] For an evaluation factor with a positive correlation, when the number of triggering times of the alarm behavior corresponding to the evaluation factor is greater than the first number threshold, points are deducted according to the corresponding preset deduction value;

[0011] For an evaluation factor with a negative correlation, when the number of triggering times of the alarm behavior corresponding to the evaluation factor is less than the second numerical threshold, points are deducted according to the corresponding preset deduction value;

[0012] Determine the total deduction value for the user after deductions are made for each evaluation factor.

[0013] Optionally, determining the predicted probability of the user having an accident according to the total deduction value of the user includes:

[0014] Determine a target score interval in which the total deduction value of the user is located from a plurality of preset score intervals; the plurality of preset score intervals respectively correspond to different accident occurrence probabilities;

[0015] The accident occurrence probability corresponding to the target score interval is used as the predicted probability of the user having an accident.

[0016] Optionally, it also includes:

[0017] Obtain the user's historical usage behavior information and accident record information of the assisted driving system; the historical usage behavior information includes the scene information of the assisted driving system, the control information during the use of the assisted driving system, and the system status information of the assisted driving system; the scene information, the control information, and the system status information include multiple parameters

[0018] Determine the correlation coefficients between various parameters of the scene information, the control information, and the system status information and the accident record information;

[0019] According to the correlation coefficients of various parameters of the scene information, the control information and the system status information and the accident record information, an evaluation factor is selected from various parameters of the scene information, the control information and the system status information.

[0020] Optionally, the historical usage behavior information also includes an alarm behavior triggered by the user when using the assisted driving system; the method further includes:

[0021] Determine the triggering number of the alarm behavior corresponding to the evaluation factor;

[0022] Calculate the reference number according to the triggering number of the alarm behavior corresponding to each evaluation factor;

[0023] Selecting a value smaller than the reference number of times to determine the first number threshold;

[0024] A value greater than the reference number is selected to determine the second number threshold.

[0025] Optionally, it also includes:

[0026] For the evaluation factor with a positive correlation coefficient, a first deduction condition is set; the first deduction condition is: if the number of triggering times of the corresponding alarm behavior is greater than the first number threshold, then deduction is performed;

[0027] For the evaluation factor with a negative correlation coefficient, a second deduction condition is set; the second deduction condition is: if the number of triggering times of the corresponding alarm behavior is less than the second number threshold, then deduction is performed;

[0028] Set multiple score intervals, and different score intervals correspond to different accident probabilities;

[0029] Fitting the deduction value of the warning behavior corresponding to each evaluation factor when the preset condition is met; the preset condition is: when the probability of accident occurrence corresponding to different score intervals is a set value, according to the first deduction condition and the first deduction condition, after deduction is performed according to the deduction value for the generated warning behavior, the sum of the deduction values ​​of each evaluation factor of the user meets the score interval.

[0030] Optionally, calculating the reference number according to the number of times the alarm behavior corresponding to each evaluation factor is triggered includes:

[0031] The absolute median and average values ​​are calculated by using the triggering times of the alarm behaviors corresponding to each evaluation factor;

[0032] The numerical value of the reference number is determined according to the absolute median value and the average value.

[0033] The embodiment of the present invention also discloses a user safety awareness scoring device based on user behavior, the device comprising:

[0034] A first acquisition module is used to acquire the user's usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from the scene information of using the assisted driving system, the control information in the process of using the assisted driving system, and the system state information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor;

[0035] A score determination module, configured to determine the total score deduction value of the user according to a preset score deduction rule for the evaluation factor and the number of triggering times of the alarm behavior corresponding to the evaluation factor;

[0036] The probability determination module is used to determine the predicted probability of the user having an accident based on the total deduction value of the user.

[0037] Optionally, the evaluation factor is correlated with the accident record, and the score determination module includes:

[0038] A first deduction submodule is used for deducting points according to a corresponding preset deduction value for an evaluation factor with a positive correlation when the number of triggering times of the alarm behavior corresponding to the evaluation factor is greater than a first number threshold;

[0039] The second deduction submodule is used for deducting points according to the corresponding preset deduction value for the evaluation factor with negative correlation when the number of triggering times of the alarm behavior corresponding to the evaluation factor is less than the second numerical threshold;

[0040] The score determination submodule is used to determine the total score deduction value of the user after deducting points for each evaluation factor.

[0041] Optionally, the probability determination module includes:

[0042] A first determination submodule is used to determine a target score interval in which the total deduction value of the user is located from a plurality of preset score intervals; the plurality of preset score intervals respectively correspond to different accident occurrence probabilities;

[0043] The second determination submodule is used to use the accident occurrence probability corresponding to the target score interval as the predicted probability of the user's accident.

[0044] Optionally, it also includes:

[0045] A second acquisition module is used to obtain historical usage behavior information and accident record information of the user using the assisted driving system; the historical usage behavior information includes scene information of using the assisted driving system, control information during the use of the assisted driving system, and system status information of the assisted driving system; the scene information, the control information, and the system status information include multiple parameters;

[0046] A coefficient determination module, used to determine the correlation coefficients of various parameters of the scene information, the control information and the system status information with the accident record information;

[0047] The first selection module is used to select an evaluation factor from various parameters of the scene information, the control information and the system status information according to the correlation coefficient of various parameters of the scene information, the control information and the system status information with the accident record information.

[0048] Optionally, the historical usage behavior information also includes an alarm behavior triggered by the user when using the assisted driving system; the device also includes:

[0049] A triggering number determination module, used to determine the triggering number of the alarm behavior corresponding to the evaluation factor;

[0050] A reference calculation module, used to calculate a reference number of times according to the triggering number of alarm behaviors corresponding to each evaluation factor;

[0051] A first threshold determination module, used for selecting a value less than the reference number of times to determine the first number threshold;

[0052] The second threshold determination module is used to select a value greater than the reference number of times to determine the second number threshold.

[0053] Optionally, it also includes:

[0054] A first deduction module is used to set a first deduction condition for an evaluation factor with a positive correlation coefficient; the first deduction condition is: if the number of triggering times of the corresponding alarm behavior is greater than the first number threshold, then deduction is performed;

[0055] A second deduction module is used to set a second deduction condition for the evaluation factor with a negative correlation coefficient; the second deduction condition is: if the number of triggering times of the corresponding alarm behavior is less than the second number threshold, then deduction is performed;

[0056] The first setting module is used to set multiple score intervals, and different score intervals correspond to different accident occurrence probabilities;

[0057] The first fitting module is used to fit the deduction value of the alarm behavior corresponding to each evaluation factor when the preset condition is met; the preset condition is: when the probability of accident occurrence corresponding to different score intervals is a set value, according to the first deduction condition and the first deduction condition, after deduction is performed according to the deduction value for the generated alarm behavior, the sum of the deduction values ​​of the user's various evaluation factors meets the score interval.

[0058] Optionally, the reference calculation module includes:

[0059] The first calculation submodule is used to calculate the absolute median value and the average value by using the triggering times of the alarm behaviors corresponding to each evaluation factor;

[0060] The reference determination submodule is used to determine the value of the reference number according to the absolute median value and the average value.

[0061] An embodiment of the present invention also discloses a vehicle, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store computer programs; and the processor is used to implement the method described above when executing the program stored in the memory.

[0062] The embodiment of the present invention further discloses one or more computer-readable media having instructions stored thereon, which, when executed by one or more processors, enable the processors to execute the method as described above.

[0063] The embodiments of the present invention include the following advantages:

[0064] In an embodiment of the present invention, the user's usage behavior information of the assisted driving system is obtained; the usage behavior information includes: an evaluation factor selected from the scene information of the assisted driving system, the control information in the process of using the assisted driving system, and the system status information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by using the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the total deduction value of the user, the predicted probability of the user having an accident is determined. In an embodiment of the present invention, the evaluation factor is obtained through the user's usage behavior information of the assisted driving system, and the predicted probability of the user having an accident is determined by determining the total deduction value of the user, so as to classify the users, so that different risk avoidance strategies can be formulated for different users to improve the users' safety awareness. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flowchart of the steps of a method for predicting the probability of an accident occurrence provided by an embodiment of the present invention;

[0066] Figure 2 is a flowchart of another method for predicting the probability of an accident occurrence provided by an embodiment of the present invention;

[0067] Figure 3 is a flow chart of extracting evaluation factors based on user behavior provided by an embodiment of the present invention;

[0068] Figure 4 This is a flow chart of user stratification and score adjustment based on user behavior provided by an embodiment of the present invention;

[0069] Figure 5 is a flow chart of predicting the probability of an accident occurrence provided by an embodiment of the present invention;

[0070] Figure 6 It is a structural block diagram of a device for predicting the probability of an accident occurrence provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0072] When users use the assisted driving system to drive vehicles to deal with vulnerable scenarios, the system may not be able to respond in time due to software and hardware operation delays, nor can it send safety prompts to users in time to prompt users to take over the vehicle and exit the function, or it can only use a single prompt signal to remind users, which will make users easily ignore the signal, thus bringing certain risks. In addition, due to the lack of certain measurement standards for whether the user's response to the safety prompt meets the safety use standards of the assisted driving system, some users will selectively ignore the safety prompts. In order to solve the risks brought by this problem, it is necessary to strengthen user safety awareness. Therefore, it is necessary to objectively evaluate the user's driving safety awareness through a scoring system and predict the probability of accidents for users, so as to achieve user stratification and adopt different prompt schemes for users at different levels.

[0073] One of the core concepts of the embodiments of the present invention is to deduct points from users based on their usage behavior information of the assisted driving system, and then determine the predicted probability of an accident occurring to the user by determining the user's total deduction value, so as to improve the user's safety awareness. In addition, potential high-risk users can be predicted in advance and risk avoidance strategies can be formulated.

[0074] Reference Figure 1 , shows a flowchart of a method for predicting the probability of an accident occurrence provided by an embodiment of the present invention, and the method may specifically include the following steps:

[0075] Step 101, obtaining user usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from scene information of using the assisted driving system, control information during the use of the assisted driving system, and system state information of the assisted driving system, and the number of triggering alarm behaviors corresponding to the evaluation factor;

[0076] In an embodiment of the present invention, the user's usage behavior information of the assisted driving system is divided into scenario information of using the assisted driving system, control information during the use of the assisted driving system, and system status information of the assisted driving system through the distributed data warehouse technology ETL (Extract-Transform-Load) technology.

[0077] For example, the scene information of the user's assisted driving system mainly includes the time of user use, weather, etc.; the control information during the use of the assisted driving system mainly includes the activation time of the user's vehicle functions, steering wheel angle, accelerator pedal force, brake pedal force, etc.; the system status information of the assisted driving system includes the activation of the assisted driving system, the exit of the assisted driving system, the number of various safety information prompts, etc. Specifically, it can be determined according to actual conditions, and the embodiments of the present invention are not limited to this.

[0078] In an embodiment of the present invention, based on the scenario information of the user using the assisted driving system, the control information during the use of the assisted driving system, and the system status information of the assisted driving system, the correlation coefficients are classified through a machine learning algorithm, so as to select an evaluation factor from the data with the largest positive and negative correlation coefficients, and record the correlation coefficient corresponding to the evaluation factor.

[0079] In the embodiment of the present invention, the evaluation factor may correspond to the number of times the alarm behavior is triggered; whether to deduct points from the user is determined by the number of times the corresponding evaluation factor occurs.

[0080] Step 102, according to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by using the number of triggering of the alarm behavior corresponding to the evaluation factor;

[0081] In an embodiment of the present invention, the preset deduction rules may be composed of evaluation factors and the number of triggering of the corresponding alarm behaviors; the user's deduction points are determined by the preset deduction rules and the number of triggering of the alarm behaviors corresponding to the evaluation factors, thereby determining the user's total deduction value.

[0082] In an embodiment of the present invention, the preset deduction rule includes an evaluation factor and a deduction threshold corresponding to the evaluation factor.

[0083] Step 103, determining the predicted probability of the user having an accident according to the total deduction value of the user.

[0084] In an embodiment of the present invention, users are predicted to be stratified according to their total deduction points, thereby determining the predicted probability of an accident occurring to the user, wherein the user stratification is related to the predicted probability of an accident occurring.

[0085] In an embodiment of the present invention, the user's usage behavior information of the assisted driving system is obtained; the usage behavior information includes: an evaluation factor selected from the scene information of the assisted driving system, the control information in the process of using the assisted driving system, and the system status information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by using the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the total deduction value of the user, the predicted probability of the user having an accident is determined. In an embodiment of the present invention, the evaluation factor is obtained through the user's usage behavior information of the assisted driving system, and the predicted probability of the user having an accident is determined by determining the total deduction value of the user, so as to classify the users, so that different risk avoidance strategies can be formulated for different users to improve the users' safety awareness.

[0086] Reference Figure 2, shows a flowchart of another method for predicting the probability of an accident occurrence provided by an embodiment of the present invention, wherein the method may specifically include the following steps:

[0087] Step 201, obtaining user usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from scene information of using the assisted driving system, control information during the use of the assisted driving system, and system state information of the assisted driving system, and the number of triggering alarm behaviors corresponding to the evaluation factor;

[0088] In the embodiment of the present invention, the evaluation factor may include the number of times the corresponding alarm behavior is triggered, and whether to deduct points from the user is determined based on the number of times the corresponding alarm behavior is triggered.

[0089] In the embodiment of the present invention, the evaluation factors may be selected through the following steps:

[0090] Acquiring historical usage behavior information and accident record information of the user using the assisted driving system; the historical usage behavior information includes scenario information of using the assisted driving system, control information during the use of the assisted driving system, and system status information of the assisted driving system; the scenario information, the control information, and the system status information include multiple parameters;

[0091] Determine the correlation coefficients between various parameters of the scene information, the control information, and the system status information and the accident record information;

[0092] According to the correlation coefficients of various parameters of the scene information, the control information and the system status information and the accident record information, an evaluation factor is selected from various parameters of the scene information, the control information and the system status information.

[0093] In an embodiment of the present invention, the historical usage behavior information of the user using the auxiliary driving system can be divided into scene information, control information and system status information, and includes multiple parameters accordingly. A correlation coefficient can be determined based on multiple parameters of the scene information, control information and system status information and accident record information. Based on the correlation coefficient, an evaluation factor is selected from each parameter of the scene information, control information and system status information.

[0094] In one example, user assisted driving system usage information and accident records are first loaded into the data analysis platform, and through machine learning, factor correlation coefficients and evaluation factors based on the factor correlation coefficients are obtained;

[0095] In the embodiment of the present invention, there is a correlation between the evaluation factor and the accident record. The total deduction value of the user based on the evaluation factor can be determined by the following steps:

[0096] Step 202: for an evaluation factor with a positive correlation, when the number of triggering times of the alarm behavior corresponding to the evaluation factor is greater than a first number threshold, deduction is performed according to the corresponding preset deduction value;

[0097] Step 203: for an evaluation factor with a negative correlation, when the number of triggering times of the alarm behavior corresponding to the evaluation factor is less than the second numerical threshold, deduction is performed according to the corresponding preset deduction value;

[0098] In the embodiment of the present invention, the evaluation factor is correlated with the accident record. Specifically, the corresponding correlation coefficient is evaluated based on the user's usage behavior information of the assisted driving system and whether there is an accident record during the use period; specifically, the classification member with the largest positive correlation coefficient and the classification member with the largest negative correlation coefficient can be selected as the evaluation factor, and the correlation coefficient corresponding to the evaluation factor is recorded.

[0099] In an embodiment of the present invention, the evaluation factor and its corresponding threshold value can constitute a preset deduction rule. For an evaluation factor that is positively correlated with the accident record, the more times the user behavior corresponds to the evaluation factor, the greater the probability of an accident; for an evaluation factor that is negatively correlated with the accident record, the more times the user behavior corresponds to the evaluation factor, the smaller the probability of an accident.

[0100] In the embodiment of the present invention, refer to Figure 3 , provides a flowchart for extracting evaluation factors based on user behavior, which may include the following steps:

[0101] Step 1: Loading user assisted driving system usage information and accident records to the data analysis platform;

[0102] Step 2: Using the user's assisted driving system usage information and accident records through machine learning, obtain factor correlation coefficients and evaluation factors based on the factor correlation coefficients;

[0103] Step 3: Statistically analyze the factor correlation coefficients and the evaluation factors based on the factor correlation coefficients to obtain the deduction rules.

[0104] In the embodiment of the present invention, the evaluation factor may also be provided with a preset deduction value corresponding to it. Specifically, whether it is necessary to deduct points according to the corresponding preset deduction value depends on the threshold value corresponding to the evaluation factor.

[0105] In an embodiment of the present invention, the historical usage behavior information includes the alarm behavior triggered during the user's use of the assisted driving system; the steps of determining the first number threshold and the second number threshold are: determining the number of triggering times of the alarm behavior corresponding to the evaluation factor; calculating the reference number according to the number of triggering times of the alarm behavior corresponding to each evaluation factor; selecting a value less than the reference number to determine the first number threshold; selecting a value greater than the reference number to determine the second number threshold.

[0106] In an embodiment of the present invention, the calculation of the reference number according to the triggering number of alarm behaviors corresponding to each evaluation factor includes: calculating the absolute median and the average value using the triggering number of alarm behaviors corresponding to each evaluation factor; and determining the value of the reference number according to the absolute median and the average value.

[0107] In an embodiment of the present invention, the corresponding absolute median and average values ​​are calculated by the triggering times of the alarm behaviors corresponding to each evaluation factor, so as to determine the numerical value of the reference times; based on the numerical value of the corresponding reference times, the number thresholds corresponding to the evaluation factors are selected, wherein a value less than the reference times is selected to determine the first number threshold; and a value greater than the reference times is selected to determine the second number threshold.

[0108] In an embodiment of the present invention, the evaluation factor may have the number of times the corresponding alarm behavior is triggered. The corresponding absolute median and average values ​​are calculated by the number of times the corresponding alarm behavior is triggered, so as to determine the value of the reference number. Specifically, the value of the reference number can be obtained from the statistical data of the actual use dimension of the user in the historical time period. For example, if the average number of times the user triggers alarm A per day in the past two months is d, then the corresponding threshold is calculated as X=2*1.4826*MAD(d)+Mean(d).

[0109] In the embodiment of the present invention, for the evaluation factor with a positive correlation coefficient, a first deduction condition is set; the first deduction condition is: if the number of triggering times of the corresponding alarm behavior is greater than the first number threshold, then deduction is performed;

[0110] For the evaluation factor with a negative correlation coefficient, a second deduction condition is set; the second deduction condition is: if the number of triggering times of the corresponding alarm behavior is less than the second number threshold, then deduction is performed;

[0111] Set multiple score intervals, and different score intervals correspond to different accident probabilities;

[0112] Fitting the deduction value of the warning behavior corresponding to each evaluation factor when the preset condition is met; the preset condition is: when the probability of accident occurrence corresponding to different score intervals is a set value, according to the first deduction condition and the second deduction condition, after deduction is performed according to the deduction value for the generated warning behavior, the sum of the deduction values ​​of each evaluation factor of the user meets the score interval.

[0113] In the embodiment of the present invention, deduction conditions are set for evaluation factors with positive and negative correlation coefficients, respectively, and points are deducted when the corresponding deduction conditions are met.

[0114] In the embodiment of the present invention, the score is divided into intervals to obtain multiple score intervals, and the multiple score intervals correspond to different accident probability. According to the multiple preset score intervals, the interval in which the total deduction value of the user is located is determined, thereby determining the predicted probability of the user's accident.

[0115] In an embodiment of the present invention, the alarm behavior triggered by the corresponding evaluation factor corresponds to different deduction values. According to the first deduction condition and the second deduction condition, points are deducted according to the corresponding deduction values ​​to obtain the total deduction value of the user. Different accident probabilities are determined based on the total deduction value of the user and multiple score intervals.

[0116] Step 204, determining the total deduction value of the user after deductions are made for each evaluation factor.

[0117] In an embodiment of the present invention, when the correlation between the evaluation factor and the accident record is positively correlated, and the number of triggering of the corresponding alarm behavior is greater than the first number threshold, points are deducted according to the corresponding preset deduction value; when the correlation between the evaluation factor and the accident record is negatively correlated, and the number of triggering of the corresponding alarm behavior is less than the second number threshold, points are deducted according to the corresponding preset deduction value; points are deducted accordingly for the evaluation factor to obtain a total deduction value.

[0118] For example, the evaluation factors that are positively correlated with the accident record may be that the user cannot turn on the wipers in time on rainy days, the user uses the brake pedal with greater force, and forgets to wear a seat belt while driving, etc.; the evaluation factors that are negatively correlated with the accident record may be that the user can react in time on the vehicle on rainy and snowy days, can slowly brake when parking, can keep a good distance from the front and rear vehicles when driving on the road, etc. Specifically, it can be determined according to actual conditions, and the embodiment of the present invention is not limited to this.

[0119] In the embodiment of the present invention, refer to Figure 4 , a flowchart of user stratification and score adjustment based on user behavior is provided, which may specifically include the following steps:

[0120] Step 1, pre-select and set the deduction value;

[0121] Step 2, simulating deduction of points for the user through the user's assisted driving system usage information and the corresponding set deduction points;

[0122] Step 3, the total score after the simulated deduction is loaded into the data analysis platform, and statistical analysis is performed to obtain user stratification;

[0123] Step 4: Verify the relevance of user stratification through accident records;

[0124] Step 5: According to the stratified users, adjust the deduction value based on relevance.

[0125] Step 205: Determine a target score interval in which the total deduction value of the user is located from a plurality of preset score intervals; the plurality of preset score intervals correspond to different accident occurrence probabilities, respectively.

[0126] Step 206: Using the accident probability corresponding to the target score interval as the predicted probability of an accident occurring to the user.

[0127] In an embodiment of the present invention, the evaluation factor and its corresponding threshold value can constitute a preset deduction rule. For an evaluation factor that is positively correlated with the accident record, the more times the user behavior corresponds to the evaluation factor, the greater the probability of an accident; for an evaluation factor that is negatively correlated with the accident record, the more times the user behavior corresponds to the evaluation factor, the smaller the probability of an accident.

[0128] In one example, for example, in the past two months, the average number of times that alarm A is triggered based on positively correlated evaluation factors per day is counted as a, and the number of times that alarm B is triggered based on negatively correlated evaluation factors is counted as b.

[0129] If the value of a is larger and greater than the threshold corresponding to the positive correlation evaluation factor, the user will be deducted points accordingly;

[0130] If the value of b is smaller and smaller than the threshold corresponding to the negative correlation evaluation factor, the user will be deducted points accordingly.

[0131] Based on the number of times alarms A and B are triggered, points are deducted from users in a simulated manner to predict the probability of accidents occurring to them. Users are then stratified and given different safety tips based on their different levels.

[0132] In the embodiment of the present invention, refer to Figure 5 , a flowchart of predicting the probability of an accident is provided, which may specifically include the following steps:

[0133] Step 1, obtaining the deduction rule according to the setting of the deduction value;

[0134] Step 2: The user's assisted driving system usage information is used to predict the user's assisted driving system usage behavior through machine learning;

[0135] Step 3: simulate deducting points from the user based on the deducting rules and the prediction of the user's use behavior of the assisted driving system;

[0136] Step 4: stratify users based on their simulated deduction scores;

[0137] Step 5: Based on the user prediction stratification, the probability of accident occurring to the user is obtained.

[0138] In an embodiment of the present invention, the user's usage behavior information of the assisted driving system is obtained; the usage behavior information includes: an evaluation factor selected from the scene information of the assisted driving system, the control information in the process of using the assisted driving system, and the system status information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by using the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the total deduction value of the user, the predicted probability of the user having an accident is determined. In an embodiment of the present invention, the evaluation factor is obtained by the user's usage behavior information of the assisted driving system, and the predicted probability of the user having an accident is determined by determining the total deduction value of the user, so as to stratify the users and formulate different prompting plans according to different users to improve the user's safety awareness, or predict potential high-risk users and formulate risk avoidance strategies.

[0139] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0140] Reference Figure 6 , shows a structural block diagram of a device for predicting the probability of an accident occurrence provided by an embodiment of the present invention, which may specifically include the following modules:

[0141] The first acquisition module 601 is used to acquire the user's usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from the scene information of the assisted driving system, the control information in the process of using the assisted driving system, and the system state information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor;

[0142] The score determination module 602 is used to determine the total score deduction value of the user according to the preset score deduction rule for the evaluation factor and the number of triggering times of the alarm behavior corresponding to the evaluation factor;

[0143] The probability determination module 603 is used to determine the predicted probability of the user having an accident according to the total deduction value of the user.

[0144] In one embodiment, the evaluation factor is correlated with the accident record, and the score determination module includes:

[0145] A first deduction submodule is used for deducting points according to a corresponding preset deduction value for an evaluation factor with a positive correlation when the number of triggering times of the alarm behavior corresponding to the evaluation factor is greater than a first number threshold;

[0146] The second deduction submodule is used for deducting points according to the corresponding preset deduction value for the evaluation factor with negative correlation when the number of triggering times of the alarm behavior corresponding to the evaluation factor is less than the second numerical threshold;

[0147] The score determination submodule is used to determine the total score deduction value of the user after deducting points for each evaluation factor.

[0148] In one embodiment, the probability determination module includes:

[0149] A first determination submodule is used to determine a target score interval in which the total deduction value of the user is located from a plurality of preset score intervals; the plurality of preset score intervals respectively correspond to different accident occurrence probabilities;

[0150] The second determination submodule is used to use the accident occurrence probability corresponding to the target score interval as the predicted probability of the user's accident.

[0151] In one embodiment, the second acquisition module is used to obtain historical usage behavior information and accident record information of the user using the assisted driving system; the historical usage behavior information includes scene information of using the assisted driving system, control information during the use of the assisted driving system, and system status information of the assisted driving system; the scene information, the control information, and the system status information include multiple parameters;

[0152] A coefficient determination module, used to determine the correlation coefficients of various parameters of the scene information, the control information and the system status information with the accident record information;

[0153] The first selection module is used to select an evaluation factor from various parameters of the scene information, the control information and the system status information according to the correlation coefficient of various parameters of the scene information, the control information and the system status information with the accident record information.

[0154] In one embodiment, the historical usage behavior information also includes an alarm behavior triggered by the user when using the assisted driving system; the device also includes:

[0155] A triggering number determination module, used to determine the triggering number of the alarm behavior corresponding to the evaluation factor;

[0156] A reference calculation module, used to calculate a reference number of times according to the triggering number of alarm behaviors corresponding to each evaluation factor;

[0157] A first threshold determination module, used for selecting a value less than the reference number of times to determine the first number threshold;

[0158] The second threshold determination module is used to select a value greater than the reference number of times to determine the second number threshold.

[0159] In one embodiment, the first deduction module is used to set a first deduction condition for the evaluation factor with a positive correlation coefficient; the first deduction condition is: if the number of triggering times of the corresponding alarm behavior is greater than the first number threshold, then deduction is performed;

[0160] A second deduction module is used to set a second deduction condition for the evaluation factor with a negative correlation coefficient; the second deduction condition is: if the number of triggering times of the corresponding alarm behavior is less than the second number threshold, then deduction is performed;

[0161] The first setting module is used to set multiple score intervals, and different score intervals correspond to different accident occurrence probabilities;

[0162] The first fitting module is used to fit the deduction value of the alarm behavior corresponding to each evaluation factor when the preset condition is met; the preset condition is: when the probability of accident occurrence corresponding to different score intervals is a set value, according to the first deduction condition and the first deduction condition, after deduction is performed according to the deduction value for the generated alarm behavior, the sum of the deduction values ​​of the user's various evaluation factors meets the score interval.

[0163] In one embodiment, the reference calculation module includes:

[0164] The first calculation submodule is used to calculate the absolute median value and the average value by using the triggering times of the alarm behaviors corresponding to each evaluation factor;

[0165] The reference determination submodule is used to determine the value of the reference number according to the absolute median value and the average value.

[0166] In an embodiment of the present invention, the user's usage behavior information of the assisted driving system is obtained; the usage behavior information includes: an evaluation factor selected from the scene information of the assisted driving system, the control information in the process of using the assisted driving system, and the system status information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by using the number of triggering of the alarm behavior corresponding to the evaluation factor; according to the total deduction value of the user, the predicted probability of the user having an accident is determined. In an embodiment of the present invention, the evaluation factor is obtained by the user's usage behavior information of the assisted driving system, and the predicted probability of the user having an accident is determined by determining the total deduction value of the user, so as to stratify the users and formulate different prompting plans according to different users to improve the user's safety awareness, or predict potential high-risk users and formulate risk avoidance strategies.

[0167] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0168] An embodiment of the present invention further provides an electronic device, including:

[0169] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned accident probability prediction method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0170] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned accident probability prediction method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0171] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0172] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0173] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0174] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0176] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0177] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0178] A method and a device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting the probability of an accident, characterized in that: The method comprises: Obtaining user usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from scene information of using the assisted driving system, control information during the use of the assisted driving system, and system state information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor; According to the preset deduction rule for the evaluation factor, the total deduction value of the user is determined by using the number of triggering of the alarm behavior corresponding to the evaluation factor; Determining a predicted probability of an accident occurring to the user based on the total deduction points of the user; There is a correlation between the evaluation factor and the accident record, and the total deduction value of the user is determined according to the preset deduction rule for the evaluation factor and the number of triggering times of the alarm behavior corresponding to the evaluation factor, including: For an evaluation factor with a positive correlation, when the number of triggering times of the alarm behavior corresponding to the evaluation factor is greater than the first number threshold, points are deducted according to the corresponding preset deduction value; For an evaluation factor with a negative correlation, when the number of triggering times of the alarm behavior corresponding to the evaluation factor is less than the second numerical threshold, points are deducted according to the corresponding preset deduction value; Determine the total deduction value for the user after deductions are made for each evaluation factor.

2. The method according to claim 1, characterized in that Determining the predicted probability of the user having an accident according to the total deduction score of the user includes: Determine a target score interval in which the total deduction value of the user is located from a plurality of preset score intervals; the plurality of preset score intervals respectively correspond to different accident occurrence probabilities; The accident occurrence probability corresponding to the target score interval is used as the predicted probability of the user having an accident.

3. The method according to claim 2, characterized in that Also includes: Obtaining historical usage behavior information and accident record information of the user using the assisted driving system; the historical usage behavior information includes scenario information of using the assisted driving system, control information during the use of the assisted driving system, and system status information of the assisted driving system; The scene information, the control information and the system status information include multiple parameters; Determine the correlation coefficients between various parameters of the scene information, the control information, and the system status information and the accident record information; According to the correlation coefficients of various parameters of the scene information, the control information and the system status information and the accident record information, an evaluation factor is selected from various parameters of the scene information, the control information and the system status information.

4. The method according to claim 3, characterized in that The historical usage behavior information also includes warning behaviors triggered by the user when using the assisted driving system; the method also includes: Determine the triggering number of the alarm behavior corresponding to the evaluation factor; Calculate the reference number according to the triggering number of the alarm behavior corresponding to each evaluation factor; Selecting a value smaller than the reference number of times to determine the first number threshold; A value greater than the reference number is selected to determine the second number threshold.

5. The method according to claim 4, characterized in that Also includes: For the evaluation factor with a positive correlation coefficient, set the first deduction condition; The first deduction condition is: if the number of times the corresponding alarm behavior is triggered is greater than the first number threshold, then points are deducted; For the evaluation factor with a negative correlation coefficient, a second deduction condition is set; the second deduction condition is: if the number of triggering times of the corresponding alarm behavior is less than the second number threshold, then deduction is performed; Set multiple score intervals, and different score intervals correspond to different accident probabilities; Fitting the deduction value of the warning behavior corresponding to each evaluation factor when the preset condition is met; the preset condition is: when the probability of accident occurrence corresponding to different score intervals is a set value, according to the first deduction condition and the second deduction condition, after deduction is performed according to the deduction value for the generated warning behavior, the sum of the deduction values ​​of each evaluation factor of the user meets the score interval.

6. The method according to claim 4, characterized in that The calculating of the reference number according to the triggering number of the alarm behavior corresponding to each evaluation factor includes: The absolute median and average values ​​are calculated by using the triggering times of the alarm behaviors corresponding to each evaluation factor; The numerical value of the reference number is determined according to the absolute median value and the average value.

7. A device for predicting the probability of an accident, characterized in that: The device comprises: A first acquisition module is used to acquire the user's usage behavior information of the assisted driving system; the usage behavior information includes: an evaluation factor selected from the scene information of the assisted driving system, the control information in the process of using the assisted driving system, and the system state information of the assisted driving system, and the number of triggering of the alarm behavior corresponding to the evaluation factor; A score determination module, configured to determine the total score deduction value of the user according to a preset score deduction rule for the evaluation factor and the number of triggering times of the alarm behavior corresponding to the evaluation factor; A probability determination module, used to determine the predicted probability of the user having an accident according to the total deduction points of the user; Wherein, the evaluation factor is correlated with the accident record, and the score determination module includes: A first deduction submodule is used for deducting points according to a corresponding preset deduction value for an evaluation factor with a positive correlation when the number of triggering times of the alarm behavior corresponding to the evaluation factor is greater than a first number threshold; The second deduction submodule is used for deducting points according to the corresponding preset deduction value for the evaluation factor with negative correlation when the number of triggering times of the alarm behavior corresponding to the evaluation factor is less than the second numerical threshold; The score determination submodule is used to determine the total score deduction value of the user after deducting points for each evaluation factor.

8. A vehicle, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 6 when executed by the processor.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images