Travel event prediction apparatus and method of operation thereof

Abstract

The operation method of the driving event prediction device includes the following steps: acquiring vehicle data of a first vehicle by using a transceiver for wireless communication and at least one sensor; determining whether the first vehicle is in an abnormal state and whether the first vehicle has an accident event based on the vehicle data; determining the first vehicle as being in a crisis state when the first vehicle is in the abnormal state and the first vehicle has not had the accident event; and predicting a driving event of the first vehicle based on information related to the crisis state.

Description

TECHNICAL FIELD

[0001] The present invention is designed to detect a driving state of a vehicle and predict a driving event of the vehicle using telematics and sensors. BACKGROUND

[0002] Generally, a vehicle driver can face many dangerous situations that cannot be predicted due to his or her own or others' fatigue driving, novice driving, off-road driving, road conditions, and the like.

[0003] In this regard, recently, in order to safely drive, an advanced driver assistance system (ADAS) that makes a vehicle itself judge a part of many dangerous situations occurring during driving to assist a driver's safe driving has been spotlighted.

[0004] Also, among many vehicle telematics systems, a function of monitoring a state of a driver using an optical sensor or the like, grasping a state of a vehicle and a state when an accident occurs to analyze an accident danger rate is provided. SUMMARY

[0005] The present invention provides a method and an apparatus that can detect a driving state of a vehicle and predict a driving event of the vehicle using telematics and sensors, thereby detecting a situation in which an accident danger rate is high or a crisis situation, and can reduce an accident rate of a vehicle.

[0006] The present invention has an effect that a driving state of a vehicle can be detected and a driving event of the vehicle can be predicted using telematics and sensors, thereby detecting a situation in which an accident danger rate is high or a crisis situation, and an accident rate of a vehicle can be reduced.

[0007] The present invention has an effect that a possibility of an accident between vehicles in a normal state, a possibility of an accident between vehicles in an abnormal state, and a possibility of an accident between vehicles in a mixed state of the normal state and the abnormal state are predicted, thereby reducing an accident rate of a vehicle.

[0008] According to an aspect of the present disclosure, an operating method of a driving event prediction apparatus is provided, and the operating method includes acquiring vehicle data of a first vehicle using a transceiver for wireless communication and at least one sensor, determining whether the first vehicle is in an abnormal state and whether an accident event occurs in the first vehicle based on the vehicle data, determining the first vehicle as a crisis state in a case in which the first vehicle is in the abnormal state and the accident event does not occur in the first vehicle, and predicting a driving event of the first vehicle based on information related to the crisis state.

[0009] According to one aspect of this disclosure, a driving event prediction device is provided, characterized in that it includes: a data acquisition unit that acquires vehicle data of a first vehicle using a transceiver for wireless communication and at least one sensor; a vehicle state determination unit that, based on the vehicle data, determines whether the first vehicle is in an abnormal state and whether the first vehicle has experienced an accident, or, if the first vehicle is in the abnormal state and the first vehicle has not experienced an accident, determines the first vehicle as being in a crisis state; and a vehicle driving prediction unit that predicts driving events of the first vehicle based on information related to the crisis state. Attached Figure Description

[0010] Figure 1 A diagram illustrating a driving event prediction device according to an embodiment of the present invention.

[0011] Figure 2 A diagram illustrating a crisis state in an embodiment of the present invention.

[0012] Figure 3 This is a flowchart illustrating the process of classifying driving events for various driving states according to an embodiment of the present invention.

[0013] Figure 4 This diagram illustrates the process of classifying the current driving conditions of a vehicle as a crisis state, according to an embodiment of the present invention.

[0014] Figure 5 A flowchart illustrating the process of calculating the accident risk rate of a vehicle based on its driving status, according to an embodiment of the present invention.

[0015] Figure 6 The diagram illustrates a scenario where a warning signal is provided to a vehicle according to an embodiment of the present invention.

[0016] Figure 7 Provided for illustration Figure 6 The flowchart shows the situation of the warning signal.

[0017] Figure 8 The diagram illustrates a scenario where a warning signal is provided to a vehicle according to another embodiment of the present invention.

[0018] Figure 9 Provided for illustration Figure 8 The flowchart shows the situation of the warning signal.

[0019] Explanation of reference numerals in the attached figures

[0020] 100: Driving event prediction device; 110: Data acquisition unit

[0021] 111: Transceiver Unit; 113: Sensor Unit

[0022] 120: vehicle state determination unit 130: vehicle travel prediction unit DETAILED DESCRIPTION

[0023] Hereinafter, the present disclosure will be described with reference to the accompanying drawings. The present disclosure can have various modifications and can have various embodiments, and a specific embodiment is illustrated in the drawings and a detailed description is written. However, this does not mean that the present disclosure is limited to a specific embodiment, but includes all modifications and / or equivalent or alternative technical solutions within the spirit and technical scope of the present disclosure. With regard to the description of the drawings, similar reference numerals are used for similar structural elements.

[0024] In the present disclosure, the expression "include" or "may include" or the like means the presence of the disclosed corresponding function, action, or structural element, and one or more functions, actions, or structural elements are added without limitation. Also, in the present disclosure, the term "include" or "have" or the like is used to specify the presence of the features, numbers, steps, actions, structural elements, components, or combinations described in the specification, and does not exclude the presence or addition of one or more other features, numbers, steps, actions, structural elements, components, or combinations.

[0025] In the present disclosure, the expression "or" or the like includes any or all combinations of the listed words. For example, "A or B" can mean that A can be included, B can be included, or both A and B can be included.

[0026] In the present disclosure, the expression "first", "second", "first" or "second" or the like can modify various structural elements of the present disclosure, but does not limit the corresponding structural elements. For example, the above expression does not limit the order and / or importance of the corresponding structural elements. The above expression is used to distinguish between two structural elements. For example, the first user device and the second user device are both user devices, and represent different user devices. For example, without exceeding the scope of the claimed invention of the present disclosure, the first structural element can be named as the second structural element, and similarly, the second structural element can be named as the first structural element.

[0027] When referring to one structural element "connected" or "coupled" to another structural element, it can be directly connected or coupled to other structural elements, or other structural elements can be present in the middle. Conversely, when referring to one structural element "directly connected" or "directly coupled" to another structural element, it can be understood that there are no other structural elements in the middle.

[0028] The terms used in the present disclosure are only used to describe specific embodiments, and are not used to limit the present disclosure. As long as there is no explicit indication in the context, the singular expression includes the plural expression.

[0029] Unless explicitly defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an overly literal or overly formal sense unless expressly so defined herein.

[0030] Among the numerous vehicle telematics systems, there is a function of monitoring the state of the driver using a living body sensor, an optical sensor, grasping the state of the vehicle and the state at the time of an accident to analyze the accident risk.

[0031] However, in the conventional vehicle telematics system, since only the event of the accident occurrence is measured, the situation where the accident risk is high or the situation where the accident can occur (crisis situation or Close Call situation) cannot be grasped, communication with the surrounding vehicles is not performed, and thus only independent measurement is performed.

[0032] Therefore, in the driving event detection system according to the present application, the situation where the accident risk is high and the crisis situation are detected, and the vehicle data is collected using various data such as living body data, camera-based monitoring, and car-to-object data, and thus the accident rate of the vehicle can be further reduced.

[0033] That is, the present application is a patent in which the vehicle user can grasp the moment when the dangerous accident occurs and is linked to the accident prevention system. The accident prevention system according to the present application can grasp the driving state of the vehicle and grasp which driving event is in, predict which driving event the vehicle is in next using the grasped driving state.

[0034] Figure 1 FIG. 1 is a diagram illustrating a driving event prediction device according to an embodiment of the present application.

[0035] Referring to Figure 1 The driving event prediction device 100 includes a data acquisition part 110, a vehicle state determination part 120, and a vehicle driving prediction part 130. The data acquisition part 110 can include a transceiver part 111 and a sensor part 113.

[0036] The driving event prediction device 100 is embodied inside the vehicle, can detect the driving state of the vehicle, and can predict the driving event.

[0037] The data acquisition part 110 acquires the vehicle data of the vehicle using the transceiver part 111 for wireless communication and the sensor part 113.

[0038] ​The transceiver 111 can be embodied in a telematics-based communication device or a vehicle-to-everything-based communication device.

[0039] The transceiver 111 embodied in the telematics-based communication device can acquire at least one of information about a speed, a brake position, a steering angle, etc. of the vehicle. The transceiver 111 embodied in the vehicle-to-everything-based communication device can acquire at least one of a position between vehicles, a position of a near miss, driving information (e.g., a driving intention of a surrounding vehicle) of a surrounding vehicle.

[0040] According to an embodiment, the data acquisition part 110 can receive driving state information of a surrounding vehicle located in a periphery of a vehicle including the data acquisition part 110.

[0041] The sensor part 113 includes at least one of a living body sensor and an optical sensor embodied inside the vehicle.

[0042] The living body sensor can detect living body information of a vehicle occupant. The living body information can include at least one of information about perspiration, respiration, heart rate, body temperature, noise, etc. of the vehicle occupant.

[0043] The optical sensor can detect body change information of the vehicle occupant. The body change information can include at least one of information about eye size, blinking degree, facial muscle change, etc. of the vehicle occupant.

[0044] The vehicle state determination part 120 can determine whether the vehicle is in an abnormal state or whether an accident event occurs in the vehicle based on vehicle data acquired from the data acquisition part 110.

[0045] The vehicle state determination part 120 can detect (or determine) a driving state of the vehicle and a driving event occurring in the vehicle based on vehicle data acquired from the data acquisition part 110.

[0046] The vehicle state determination part 120 can detect (or determine) whether the driving state of the vehicle is a normal state or an abnormal state based on vehicle data acquired from the data acquisition part 110.

[0047] Also, the vehicle state determination part 120 can detect (or determine) whether an accident event occurs in the vehicle although the driving state of the vehicle is the normal state and whether an accident event occurs in the vehicle although the driving state of the vehicle is the abnormal state based on vehicle data acquired from the data acquisition part 110.

[0048] Also, in a case where the vehicle is in the abnormal state and the vehicle does not have the accident event, the vehicle state determination part 120 can determine the corresponding vehicle as a crisis state.

[0049] According to an embodiment, the vehicle state determination part 120 can determine the driving condition of the vehicle classified as the crisis state based on the vehicle data and machine learning in order to determine the crisis state of the vehicle.

[0050] The vehicle driving prediction part 130 can predict the driving state and the driving event of the vehicle in the future based on the information about the past and current driving state and the driving event of the vehicle detected (or determined) in the vehicle state determination part 120.

[0051] In particular, the vehicle driving prediction part 130 can predict the driving event of the vehicle in the future based on the information about the crisis state determined in the vehicle state determination part 120.

[0052] The vehicle driving prediction part 130 can determine a plurality of accident risk rate values about a plurality of driving scenarios of the vehicle based on first driving state information of the vehicle including the vehicle driving prediction part 130 and second driving state information of a surrounding vehicle.

[0053] According to an embodiment, the first driving state information can include past driving information of the first vehicle and current driving information of the first vehicle, and the second driving state information can include past driving information of the second vehicle and current driving information of the second vehicle.

[0054] According to an embodiment, the first driving state information and the second driving state information can include at least one of information about whether an accident prevention system of a vehicle is activated, information about a sharp turn of the vehicle, information about a sharp braking of the vehicle, heart rate change information of an occupant in the vehicle, breathing information of the occupant, body temperature information of the occupant, noise information of the vehicle, sweating information of the occupant, and state information of the occupant.

[0055] The vehicle driving prediction part 130 can determine whether a maximum value among the plurality of accident risk rate values about the vehicle is greater than a threshold value, and if the accident risk rate value of the vehicle is greater than the threshold value, can provide a warning signal about the vehicle.

[0056] According to an embodiment, the threshold value can be determined with respect to average accident rate information of the vehicle about the plurality of driving scenarios.

[0057] Figure 2 A graph for explaining a crisis state according to an embodiment of the disclosure.

[0058] Referring to Figure 1 and Figure 2, the driving event prediction device 100 can determine whether the corresponding vehicle is in a normal state (a) or an abnormal state (b) based on the acquired vehicle data.

[0059] Further, the driving event prediction device 100 can determine whether an accident event (A) occurs in the corresponding vehicle based on the acquired vehicle data. In the case where the accident event (A) occurs in the corresponding vehicle, the driving event prediction device 100 can determine whether the accident event (A) occurs in the normal state (a) and whether the accident event (A) occurs in the abnormal state (b).

[0060] Further, in the case where the corresponding vehicle is in the abnormal state (b) but the accident event (A) does not occur, the driving event prediction device 100 can determine the state of the corresponding vehicle as a crisis state (C=b-d).

[0061] Figure 3 A flowchart for illustrating a process of classifying driving events in each driving state according to an embodiment of the present application.

[0062] Referring to Figures 1 to 3 , the driving event prediction device 100 can grasp the driving event of the vehicle.

[0063] The driving event prediction device 100 can collect vehicle data (step S310), and can classify driving events related to a normal state of a vehicle as a reference based on the above-described vehicle data (step S320).

[0064] The driving event prediction device 100 can classify driving events of an abnormal state of the vehicle (step S330), and classify driving events as an accident state in the normal state or the abnormal state of the vehicle (step S340).

[0065] Thereafter, the driving event prediction device 100 can determine the abnormal state and the accident state of the vehicle as a crisis state, and can classify driving events in which an accident risk is high or in which a crisis state is present (step S350).

[0066] Figure 4 A diagram for illustrating a process of classifying a driving condition of a current vehicle as a crisis state according to an embodiment of the present application.

[0067] Figure 4 An example of a specific embodiment of the driving event classification method illustrated in FIG. 1 is shown. Figure 3 Figure 4 The driving condition (DC) illustrated in FIG. 1 can be a driving state of a current vehicle.

[0068] ​The driving condition (or the current driving state of the vehicle) can include at least one of information about whether the accident prevention system of the vehicle is activated, information about a sharp turn of the vehicle, information about a sharp braking of the vehicle, heart rate change information of an occupant in the vehicle, breathing information of the occupant, body temperature information of the occupant, noise information of the vehicle, sweating information of the occupant, and state information of the occupant.

[0069] Referring to Figures 1 to 4 , the driving event prediction device 100 can determine whether the vehicle is in driving (step S401). According to step S401, the driving event prediction device 100 can derive the D i value corresponding to the current driving state during driving of the vehicle (step S403).

[0070] The driving event prediction device 100 can determine whether the D i value corresponding to the current driving state of the vehicle is within the normal state range (a) (step S405). In step S405, if the D i value corresponding to the current driving state of the vehicle is within the normal state range (a), the driving event prediction device 100 can classify the driving state (DC) of the current vehicle as a normal state.

[0071] In step S405, if the D i value corresponding to the current driving state is not within the normal state range (a), the driving event prediction device 100 can classify the driving state (DC) of the current vehicle as an abnormal state (step S411).

[0072] According to step S401, in the case where the vehicle does not belong to the driving process, the driving event prediction device 100 can set the D i value corresponding to the current driving state of the vehicle to the D i-1 value corresponding to the previous driving state of the vehicle (D i = D i-1 ) (step S409).

[0073] After step S409, the driving event prediction device 100 determines whether the D i value corresponding to the current driving state of the vehicle is within the accident state range (A) (step S413).

[0074] In step S413, if the D i value corresponding to the current driving state of the vehicle is within the accident state range (A), the driving event prediction device 100 can determine that the D iwhether the value is within the normal state range (a) (step S415).

[0075] In step S415, if the D value corresponding to the current driving state of the vehicle is within the normal state range (a), the driving event prediction device 100 can classify the driving state (DC) of the current vehicle as a normal accident event (step S417). i

[0076] In step S413, if the D value corresponding to the current driving state of the vehicle is not within the accident state range (A), the driving event prediction device 100 determines whether the D value corresponding to the current driving state of the vehicle is within the normal state range (a) (step S419). i i

[0077] In step S415, if the D value corresponding to the current driving state of the vehicle is not within the normal state range (a), the driving event prediction device 100 can classify the driving state (DC) of the current vehicle as an abnormal accident event (step S421). i

[0078] In step S419, if the D value corresponding to the current driving state of the vehicle is within the normal state range (a), the driving event prediction device 100 can classify the driving state (DC) of the current vehicle as a crisis state (C) (step S423). i

[0079] In step S419, if the D value corresponding to the current driving state of the vehicle is within the normal state range (a), the driving event prediction device 100 can classify the driving state (DC) of the current vehicle as a normal state (a) (step S425). i

[0080] Figure 4 The illustrated driving condition (or driving state) classification method can be embodied in a machine learning environment using "labeling". The data of "labeling" is a sample data set to which one or more labels (metadata) are attached.

[0081] In general, "labeling" refers to an act of attaching labels that can represent the state of each part by grasping the corresponding data, usually using a data set to which no label is attached.

[0082] For example, labels such as "4 legs", "reptile", etc. can be attached to an animal photo.

[0083] The sequence of the "labeling" function of the present patent is as follows. ​​​​​​

[0084] 1) Determine the reference point for each input value, and extract a plurality of characteristics around the corresponding reference point.

[0085] A. Definition of initial reference point is determined by analyzing data newly collected by past methods (for judging fatigue driving or dangerous driving, etc.) or past data.

[0086] B. driving Condition generalizes and determines the reference point and the change value within the determined time frame based on the evaluation of past methods (the determined time frame varies depending on the data source and type).

[0087] 2) Use the reference point to "label" data of normal state.

[0088] A. Using the reference point data, refer to general statistical methods and related data to classify data within a certain range as normal data.

[0089] B. Error range is classified using past statistical methods.

[0090] 3) Classify data deviating from the reference point as abnormal data.

[0091] A. Using the reference point data, refer to general statistical methods and related data to classify data outside a certain range as abnormal data.

[0092] 4) "Label" data according to event type.

[0093] A. Use the event information (airbag explosion, accelerometer exceeding a certain range, etc.) that occurs when an accident occurs to "label" related data as accident data.

[0094] B. "Label" non-normal data data classified as not "labeled" as accident data as "close call".

[0095] Figure 5 A flowchart showing the process of calculating the accident risk rate of a vehicle based on the driving state according to an embodiment of the present application.

[0096] Referring to Figures 1 to 5 , the driving event prediction device 100 can predict the driving event of the vehicle thereafter.

[0097] The driving event prediction device 100 can collect vehicle data (step S510), and can grasp the driving state of the vehicle based on the collected vehicle data (step S520). Thereafter, the driving event prediction device 100 can calculate the dangerous accident rate of the vehicle based on the grasped driving state, in comparison with past data (step S530).

[0098] The travel event prediction device 100 can predict a travel event that is likely to occur after the vehicle based on the calculated accident risk rate.

[0099] Figure 6 A diagram showing a case where a warning signal is provided to a vehicle according to an embodiment of the present application.

[0100] With reference to Figure 1 , Figure 2 and Figure 6 , the travel event prediction device 100 embodied in the first vehicle (V1) or the second vehicle (V2) can calculate an accident risk probability (P k，l (x)) for each case based on the current driving state (D i，1 ) of the first vehicle (V1) and the current driving state (D i，2 ) of the second vehicle (V2).

[0101] Meanwhile, the travel event prediction device 100 can calculate a comprehensive accident risk rate (Γ k，l ) related to an accident event among the accident risk probabilities (P k，l (x)) for each case.

[0102] Figure 6 In the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 =a), the current driving state (D i，2 ) of the second vehicle (V2) is the normal state (a) (D i，1 =a), and the driving result is the normal state where no accident event occurs, the probability can be P a，a (a).

[0103] Also, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is (a) (D i，1 =a), the current driving state (D i，2 ) of the second vehicle (V2) is the normal state (a) (D i，2 =a), and the driving result is the normal state where an accident event occurs, the probability can be P a，a (c).

[0104] Also, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 =a), the current driving state (D i，2 ) of the second vehicle (V2) is the abnormal state (b) (D i，2= b), the probability can be P a，b (a).

[0105] And, in a case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D i，2 ) of the second vehicle (V2) is the abnormal state (b) (D i，2 = b), and the driving result is the abnormal state in which the accident event does not occur, the probability can be P a，b (b).

[0106] And, in a case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D i，2 ) of the second vehicle (V2) is the abnormal state (b) (D i，2 = b), and the driving result is the normal state in which the accident event occurs, the probability can be P a，b (c).

[0107] And, in a case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D i，2 ) of the second vehicle (V2) is the abnormal state (b) (D i，2 = b), and the driving result is the abnormal state in which the accident event occurs, the probability can be P a，b (d).

[0108] And, in a case where the current driving state (D i，1 ) of the first vehicle (V1) is the abnormal state (b) (D i，1 = b), the current driving state (D i，2 ) of the second vehicle (V2) is the abnormal state (b) (D i，2 = b), and the driving result is the abnormal state in which the accident event does not occur, the probability can be P b，b (b).

[0109] And, in a case where the current driving state (D i，1 ) of the first vehicle (V1) is the abnormal state (b) (D i，1 = b), the current driving state (D i，2 ) of the second vehicle (V2) is the abnormal state (b) (D i，2 = b), and the driving result is the abnormal state in which the accident event does not occur, the probability can be P b，b(b)

[0110] Furthermore, in the current driving state (D) of the first vehicle (V1) i，1 (b)(D) is an abnormal state. i，1 =b), the current driving state of the second vehicle (V2) (D) i，2 (b)(D) is an abnormal state. i，2 =b), in the case where the driving outcome is an abnormal state resulting in an accident event, the probability can be P. b，b (d)

[0111] The probability of accident risk (P) in each situation k，l In (x)), the overall accident hazard rate (Γ) related to the accident event k，l ) can be accessed via "Γ" k，l =P a，a (c)+P a，b (c)+P a，b (d)+P b，b The mathematical expression for (d) is determined.

[0112] The driving event prediction device 100, located in either the first vehicle (V1) or the second vehicle (V2), determines the overall accident risk rate (Γ). k，L Whether the overall accident risk rate (Γ) is greater than the threshold (φ), if so, k，l If the value is greater than the threshold (φ), a warning signal can be provided to either the first vehicle (V1) or the second vehicle (V2).

[0113] According to an embodiment, when a vehicle accident occurs, the comprehensive accident risk rate (Γ) under the corresponding circumstances is collected. k,l The data pool can be used to generate a threshold value (φ), and candidate values ​​that can become the threshold can be added to the data pool. The threshold (φ) can then be derived by analyzing the data pool (similar to how the meteorological bureau defines "rainfall" as starting with a probability of -%).

[0114] According to another embodiment, the accident rate of a vehicle is extracted by characteristics, "labeling" is performed based on driving data, and an appropriate threshold (φ) is derived by analyzing the data pool.

[0115] Figure 7 Provided for illustration Figure 6 The flowchart shows the situation of the warning signal.

[0116] Reference Figures 1 to 7 The driving event prediction device 100 can collect vehicle data (step S710).

[0117] The driving event prediction device 100 can grasp the current driving state (D) of the first vehicle, including the driving event prediction device 100. i，1The current driving status of the second vehicle located around the first vehicle (D) i，2 (Step S720).

[0118] The driving event prediction device 100 can predict the driving event based on the current driving state (D) of the first vehicle. i，1 ) and the current driving status of the second vehicle (D i，2 The probability (P) of each outcome is calculated by comparing it with past data. k，l (x))(Step S730).

[0119] The driving event prediction device 100 can predict the probability (P) of each situation. k，l (x) calculates the overall accident risk rate (Γ) related to the accident event. k,l (Step S740).

[0120] The driving event prediction device 100 can determine the overall accident risk rate (Γ). k,l Is the overall accident risk rate (Γ) greater than the threshold (φ) (step S750)? k,l If the value is greater than the threshold (φ), the driving event prediction device 100 can provide a warning signal to the vehicle (step S760).

[0121] Figure 8 The diagram illustrates a scenario where a warning signal is provided to a vehicle according to another embodiment of the present invention.

[0122] Figure 6 In the middle, there is a surrounding vehicle (V2) near the first vehicle (V1), and conversely, Figure 8 In the middle, there are multiple surrounding vehicles (V2, V3, V4...V) near the first vehicle (V1). n ).

[0123] Reference Figure 1 , Figure 2 and Figure 8 In the first vehicle (V1) or the nth vehicle (V n The driving event prediction device 100 embodied within the device is based on the current driving state (D) of the first vehicle (V1). i，1 The current driving state (D) of vehicle n (Vn) and vehicle n. i，n It can calculate the probability of accident risk (P) for each situation. k，l (x)).

[0124] In addition, the driving event prediction device 100 can estimate the probability of accident risk (P) in various situations. k，l In (x)), calculate the comprehensive accident hazard rate (Γ) related to the accident event. k,l ).

[0125] Figure 8 In the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D n ) of the nth vehicle (V i，n ) is the normal state (a) (D i，2 = a), and the driving result is the normal state in which no accident event has occurred, the probability can be P a，a (a).

[0126] Also, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D n ) of the nth vehicle (V i，n ) is the normal state (a) (D i，2 = a), and the driving result is the normal state in which an accident event has occurred, the probability can be P a，a (c).

[0127] Also, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D n ) of the nth vehicle (V i，n ) is the abnormal state (b) (D i，2 = b), and the driving result is the normal state in which no accident event has occurred, the probability can be P a，b (a).

[0128] Also, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D n ) of the nth vehicle (V i，n ) is the abnormal state (b) (D i，2 = b), and the driving result is the abnormal state in which no accident event has occurred, the probability can be P a，b (b).

[0129] Also, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 = a), the current driving state (D n ) of the nth vehicle (V i，n ) is the abnormal state (b) (D i，2 = b), and the driving result is the normal state in which an accident event has occurred, the probability can be P a，b (c).

[0130] And, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the normal state (a) (D i，1 =a), the current driving state (D n ) of the nth vehicle (V i，n ) is the abnormal state (b) (D i，2 =b), and the driving result is the abnormal state where the accident event occurs, the probability can be P a，b (d).

[0131] And, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the abnormal state (b) (D i，1 =b), the current driving state (D n ) of the nth vehicle (V i，n ) is the abnormal state (b) (D i，2 =b), and the driving result is the abnormal state where the accident event does not occur, the probability can be P b，b (b).

[0132] And, in the case where the current driving state (D i，1 ) of the first vehicle (V1) is the abnormal state (b) (D i，1 =b), the current driving state (D n ) of the nth vehicle (V i，n ) is the abnormal state (b) (D i，2 =b), and the driving result is the abnormal state where the accident event occurs, the probability can be P b，b (d).

[0133] In the above accident risk probability (P k，l (x)), the comprehensive accident risk rate (P ) related to the accident event can be determined by the mathematical formula of .

[0134] After that, in the case where the accident event occurs between the first vehicle (V1) and the plurality of surrounding vehicles (V2, V3, V4...V n ), the highest comprehensive accident risk rate (P ) can be determined.

[0135] The driving event prediction device 100 embodied in the first vehicle (V1) determines whether the highest comprehensive accident risk rate (P ) is greater than a threshold value (φ), and if the highest comprehensive accident risk rate (P ) is greater than the threshold value (φ), warning information can be provided to the first vehicle (V1).

[0136] Figure 9 Provided for illustration Figure 8 The flowchart shows the situation of the warning signal.

[0137] Reference Figures 1 to 9 The driving event prediction device 100 can collect vehicle data (step S910).

[0138] The driving event prediction device 100 can grasp the current driving state (D) of the vehicle including the driving event prediction device 100. i，1 ) and the current driving status of multiple surrounding vehicles located around the aforementioned vehicle (D i，j (Step S920).

[0139] The driving event prediction device 100 can predict the driving event based on the vehicle's current driving state (D). i，1 ) and several surrounding vehicles Current driving status (D) i，j This allows for comparison with past data, enabling the calculation of the probability (P) of each scenario. k，l (x))(Step S930).

[0140] The driving event prediction device 100 can predict the probability (P) of each situation. k，l In (x)), the comprehensive accident hazard rate related to the accident event can be calculated. (Step S940).

[0141] The driving event prediction device 100 can determine the highest overall accident risk rate in the event that occurs. (Step S950).

[0142] Driving event prediction device 100 assesses overall accident risk rate Is it greater than the highest threshold (φ) (step S960)? If the highest comprehensive accident risk rate... If the value exceeds the threshold (φ), the driving event prediction device 100 can provide a warning signal to the vehicle (step S970).

[0143] The methods described in the above embodiments can be formulated by a computer-executable program and utilize a computer-readable recording medium. When the program operates, the key can be embodied in a general-purpose digital computer. Furthermore, the data structures, program instructions, or data files that can be used in the embodiments of the present invention can be recorded in a computer-readable recording medium using various units. The computer-readable recording medium may include all types of storage devices that store data readable by a computer system.

[0144] As examples of the computer-readable recording medium, there can be included a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hard disk device specially configured to store and execute program instructions in the form of a ROM, a RAM, a flash memory, and the like. Also, the computer-readable recording medium can be a transmission medium that transmits a signal in which a program instruction, a data structure, and the like are specified. As examples of the program instruction, there can be included a machine code formed by a compiler and a high-level language code that is executed in a computer using an interpreter and the like.

[0145] The embodiments disclosed in the present specification and drawings disclose specific examples in order to simply explain the gist of the present application and help understanding the present application, and the scope of the present application is not limited thereto. Therefore, the scope of the present application includes all modified or altered forms derived on the basis of the technical idea of the present application in addition to the embodiments disclosed herein.

Claims

1. An operation method of a travel event prediction device, characterized by, The method comprises: a step of acquiring vehicle data of a first vehicle using a transceiver for wireless communication and at least one sensor; a step of determining whether the first vehicle is in an abnormal state and whether the first vehicle has an accident event based on the vehicle data; a step of determining the first vehicle as being in a crisis state in a case where the first vehicle is in the abnormal state and the first vehicle has no accident event; a step of predicting a driving event of the first vehicle based on information related to the crisis state; a step of determining first driving state information of the first vehicle based on the vehicle data; a step of receiving second driving state information of a second vehicle located in a periphery of the first vehicle; a step of determining a plurality of accident risk rate values related to each of a plurality of driving scenarios of the first vehicle based on the first driving state information and the second driving state information; a step of adding the plurality of accident risk rate values to determine a comprehensive accident risk rate value; a step of determining whether the comprehensive accident risk rate value is greater than a threshold value; and a step of providing a warning signal to the first vehicle or the second vehicle if the comprehensive accident risk rate value is greater than the threshold value, wherein the comprehensive accident risk rate value is a sum of the following accident risk rate values: an accident risk rate value when a current driving state of the first vehicle is a normal state, a current driving state of the second vehicle is a normal state, and a driving result is a normal state in which an accident event occurs; an accident risk rate value when the current driving state of the first vehicle is the normal state, the current driving state of the second vehicle is an abnormal state, and the driving result is the normal state in which the accident event occurs; an accident risk rate value when the current driving state of the first vehicle is the normal state, the current driving state of the second vehicle is the abnormal state, and a driving result is an abnormal state in which an accident event occurs; and an accident risk rate value when the current driving state of the first vehicle is the abnormal state, the current driving state of the second vehicle is the abnormal state, and the driving result is the abnormal state in which the accident event occurs.

2. The method of claim 1, wherein, The threshold value is derived from a data pool configured to collect the comprehensive accident risk rate value when the first vehicle or the second vehicle has the accident event. 3.The method of claim 1, wherein the first driving state information includes past driving information of the first vehicle and current driving information of the first vehicle, the second driving state information includes past driving information of the second vehicle and current driving information of the second vehicle.

4. The method of claim 1, wherein, The first driving state information and the second driving state information each include at least one of information about whether an accident prevention system of a vehicle is activated, information about a sharp turn of the vehicle, information about a sharp braking of the vehicle, heart rate change information of an occupant in the vehicle, breathing information of the occupant, body temperature information of the occupant, noise information of the vehicle, sweating information of the occupant, and state information of the occupant. 5.The method of claim 1, wherein The transceiver is embodied in a telematics-based communication device or a car-to-x communication device, The at least one sensor includes at least one of a living body sensor and an optical sensor in the first vehicle.

6. The method of claim 1, wherein, Further comprising a step of determining, for determining the crisis state of the first vehicle, driving conditions of the first vehicle classified as the crisis state based on the vehicle data and machine learning.

7. A travel event prediction apparatus characterized by comprising: The device includes: a data acquisition unit that acquires vehicle data of a first vehicle using a transceiver for wireless communication and at least one sensor; a vehicle state determination unit that determines, based on the vehicle data, whether the first vehicle is in an abnormal state and whether the first vehicle has an accident event, or determines the first vehicle as a crisis state in a case where the first vehicle is in the abnormal state and the first vehicle has no accident event; and a vehicle driving prediction unit that predicts a driving event of the first vehicle based on information related to the crisis state, wherein the vehicle state determination unit determines first driving state information of the first vehicle based on the vehicle data, wherein the data acquisition unit receives second driving state information of a second vehicle located in a periphery of the first vehicle, wherein the vehicle driving prediction unit determines, based on the first driving state information and the second driving state information, a plurality of accident risk rate values related to each of a plurality of driving scenarios of the first vehicle; adds the plurality of accident risk rate values to determine a comprehensive accident risk rate value; and provides a warning signal to the first vehicle or the second vehicle when the comprehensive accident risk rate value is greater than a threshold value, wherein the comprehensive accident risk rate value is a sum of the following accident risk rate values: an accident risk rate value when a current driving state of the first vehicle is a normal state, a current driving state of the second vehicle is a normal state, and a driving result is a normal state in which an accident event occurs; an accident risk rate value when the current driving state of the first vehicle is the normal state, the current driving state of the second vehicle is an abnormal state, and the driving result is the normal state in which the accident event occurs; an accident risk rate value when the current driving state of the first vehicle is the normal state, the current driving state of the second vehicle is the abnormal state, and the driving result is an abnormal state in which an accident event occurs; and an accident risk rate value when the current driving state of the first vehicle is the abnormal state, the current driving state of the second vehicle is the abnormal state, and the driving result is the abnormal state in which the accident event occurs.

8. The apparatus of claim 7, wherein, The threshold value is derived from a data pool configured to collect the comprehensive accident risk rate value when the first vehicle or the second vehicle has an accident event.

9. The device according to claim 7, wherein the first driving state information includes past driving information of the first vehicle and current driving information of the first vehicle, the second driving state information includes past driving information of the second vehicle and current driving information of the second vehicle.

10. The apparatus of claim 7, wherein, The first and second driving state information includes at least one of information about whether an accident prevention system of a vehicle is activated, information about a sharp turn of the vehicle, information about a sharp braking of the vehicle, heart rate change information of an occupant in the vehicle, breathing information of the occupant, body temperature information of the occupant, noise information of the vehicle, sweating information of the occupant, and state information of the occupant.

11. The apparatus according to claim 7, wherein the transceiver is embodied in a telematics-based communication device or a car-to-anything communication device, the at least one sensor includes at least one of a living body sensor and an optical sensor in the first vehicle.

12. The apparatus of claim 7, wherein, To determine the crisis state of the first vehicle, the vehicle state determination section determines a driving condition of the first vehicle classified as the crisis state based on the vehicle data and machine learning.

Images