High-speed fault identification method based on internet of vehicles big data

Abstract

The present invention provides a high-speed fault identification method based on Internet of Vehicles big data, comprising the following steps: S1, acquiring vehicle status data, behavior data, and GPS data of an in-vehicle infotainment terminal, transmitting same to the cloud, and preprocessing the vehicle status data, the behavior data, and the GPS data to obtain vehicle speed, sharp acceleration, sharp deceleration, sharp turn, activation status of hazard warning lights, driver exit status, an anti-lock braking system (ABS) fault related trouble code, an engine malfunction indicator lamp related trouble code, a tire pressure anomaly related trouble code, a coolant temperature warning related trouble code, and GPS point positioning data. Thus, whether a vehicle has stopped on a highway due to a fault can be effectively and rapidly detected, and location information of the vehicle is acquired on the basis of the GPS point positioning data, without the need to mount an aftermarket sensor, thereby achieving the advantages of low costs and high accuracy. Multi-dimensional identification of whether the vehicle has stopped on the highway due to the fault provides a basis for an original equipment manufacturer to implement after-sale care and for ensuring driver safety.

Description

A High-Speed ​​Fault Identification Method Based on Vehicle Network Big Data Technical Field

[0001] This invention relates to the field of big data processing technology, and more specifically, to a high-speed fault identification method based on vehicle network big data. Background Technology

[0002] Vehicle malfunctions are becoming increasingly common. Serious vehicle malfunctions can render vehicles inoperable, negatively impacting road safety and traffic efficiency. Highways, being special road types, prohibit stopping unless the vehicle is completely immobilized. While manufacturers install certain common malfunction indicator sensors to assess vehicle conditions, relying solely on these sensors can lead to false alarms, and some malfunctions can occur while the vehicle is still drivable. For serious malfunctions, owners are forced to stop and attempt repairs or wait for roadside assistance.

[0003] Therefore, developing a method and device for identifying highway malfunctions and parking has become an important technological need today.

[0004] In existing technologies, some methods are used to identify vehicle breakdowns and stopping behaviors on highways, such as using onboard sensors and video analytics. However, these methods have some drawbacks, such as high installation costs and low recognition accuracy. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a high-speed fault identification method based on vehicle network big data that can quickly and accurately identify fault parking situations on highways, in order to address the shortcomings of the above-mentioned technical solutions.

[0006] This invention provides a high-speed fault identification method based on vehicle network big data, the method comprising the following steps:

[0007] S1 collects vehicle status data, behavior data, and GPS data from the vehicle's infotainment system and transmits them to the cloud. It preprocesses the vehicle status data, behavior data, and GPS data to obtain vehicle speed, rapid acceleration, rapid deceleration, sharp turns, hazard lights on / off status, whether the vehicle has been exited, ABS anti-lock braking system fault codes, engine malfunction light fault codes, tire pressure abnormality fault codes, coolant temperature alarm fault codes, and GPS location data.

[0008] S2, construct a highway fault stop judgment model trigger based on the vehicle speed and hazard lights being on; and determine whether the vehicle needs to trigger highway fault stop judgment based on the triggering conditions of the highway fault stop judgment model trigger.

[0009] S3. Based on the two-point-one-line method, a high-speed positioning judgment model is built, and for vehicles that meet the triggering conditions of the high-speed fault parking judgment model trigger, it is further judged whether the current vehicle has stopped due to vehicle abnormality and is not in the service area during the process of driving on the highway.

[0010] S4. Based on the high-speed positioning judgment model, a high-speed traffic jam behavior recognition model is constructed. When a vehicle has multiple similar stopping behaviors in its historical driving trajectory data on the highway and there is no data on returning to the factory for maintenance, and the current vehicle speed is less than the threshold a1, it is considered that the vehicle may have stopped due to high-speed traffic jam behavior, and such vehicle owner information is marked.

[0011] S5. Based on the highway traffic jam behavior recognition model, alarm fault codes and related signals corresponding to the alarm fault code types and the driver's exit behavior, construct a behavior discrimination and scene discrimination model, and further determine whether the vehicle that meets both step S2 and step S3 has stopped due to a fault on the highway.

[0012] S6. If step S5 is satisfied but step S4 is not satisfied, then the behavior discrimination and scenario discrimination model is used to determine that the vehicle has experienced a highway malfunction and stop behavior at that moment; otherwise, no malfunction and stop behavior has occurred.

[0013] S7: Obtain all vehicle information that has been communicated and confirmed with the vehicle owner for all vehicles that have experienced highway breakdowns and stops, and build a multi-classification intelligent model based on all vehicle information that has been communicated and confirmed with the vehicle owner; classify the vehicles that have gone through steps S2, S3 and S4 through the multi-classification intelligent model, and identify the vehicles that have experienced highway breakdowns and stops and the corresponding breakdown and accident scenarios.

[0014] In the high-speed fault identification method based on vehicle network big data described in this invention; in step S2: the triggering conditions of the highway fault stop judgment model trigger include triggering conditions constructed based on the vehicle speed and triggering conditions constructed based on the hazard lights being on. When both the triggering conditions constructed based on the vehicle speed and the triggering conditions constructed based on the hazard lights being on are met simultaneously within a certain time period, the highway fault stop judgment is triggered; otherwise, the highway fault stop judgment is not triggered.

[0015] In the high-speed fault identification method based on vehicle network big data described in this invention, the triggering condition based on vehicle speed is that the vehicle is stationary for a continuous time interval (t1-t(N)), i.e., the vehicle speed is 0 at the current moment. The vehicle speed is expressed as... Among them, the Indicates t i The speed data is collected at the current moment. 0 indicates that the speed is 0 at the current moment, and t1 indicates the start time of the model trigger.

[0016] In the high-speed fault identification method based on vehicle network big data described in this invention, the triggering condition constructed based on the hazard light activation status is that the hazard lights are activated within a continuous time interval of (t1-t(N)), and the hazard light switching status is expressed as follows: Among them, the Indicates t i The data collected shows the status of the hazard lights switch at the moment of acquisition. 1 indicates that the hazard lights are on, and t1 indicates the start time of the model trigger.

[0017] In the high-speed fault identification method based on vehicle network big data described in this invention, step S3 further includes the following steps:

[0018] S31, using GPS point positioning data, quickly determine whether the vehicle is located on the highway based on the two-point-one-line method; obtain the GPS point positioning data corresponding to three points A, B, and C, where point B is the GPS point positioning data corresponding to time t0 in step S2, and point A is the GPS point positioning data corresponding to the N1 minutes before time t0. 0-N1 GPS location data at time t0, where point C is the location of point N minutes after time t0. 0+N The GPS location data at any time; the GPS location data of points A, B, and C are used to obtain addresses through reverse geocoding, and then fuzzy matching is used to obtain addresses on the highway. The addresses are used to exclude highway locations that are parked in highway service areas and parking areas. If points A, B, and C are all on the highway at the same time, the vehicle is considered to be on the highway if the triggering conditions are met.

[0019] In the high-speed fault identification method based on vehicle network big data described in this invention, step S5 includes the following parking behaviors:

[0020] A. Before and after the triggering condition in step S2 is triggered at time t, detect the vehicle exit detection period Δγ after time t to see if the driver has exited the vehicle, i.e., whether the driver has unbuckled the seat belt or the left front door of the vehicle has opened.

[0021] B. Before the triggering condition in step S2 is triggered at time t, check whether any alarm fault codes affecting driving safety occur before time t. The alarm fault codes include at least ABS anti-lock braking system fault codes, engine fault light illumination fault codes, tire pressure abnormality fault codes, and coolant temperature alarm fault codes.

[0022] C. Before the trigger condition of step S2 is triggered at time t, detect the hard acceleration, hard deceleration, sharp turn, acceleration, and vehicle speed detection period Δγ before time t. During the Δδ period, set the threshold for the number of fault codes related to the ABS anti-lock braking system failure to b1, and the threshold for the degree of the steering angle to b2. When the number of fault codes related to the ABS anti-lock braking system failure > b1, the degree of the steering angle > b2, and a sharp turn behavior occurs; during the Δγ period, set the threshold for the number of fault codes related to the engine failure to c1, and the threshold for the hood being opened to c2. When the number of fault codes related to the engine failure > c1, the hood being opened threshold > c2; during the Δγ period, set the threshold for the number of fault codes related to abnormal tire pressure to A1, the threshold for the tire pressure signal value corresponding to the four tires indicating abnormal tire pressure to A2, and the number of occurrences to m0. When the number of fault codes related to abnormal tire pressure > A1 and the vehicle speed is greater than s1, at least one of the four tires has a tire pressure signal value < A2; during the Δγ period, set the threshold for the number of fault codes related to abnormal water temperature to B1, the threshold for abnormal water temperature to B2, and the corresponding number of occurrences to m1. When the number of fault codes related to abnormal water temperature > B1, the number of occurrences where the corresponding water temperature > B2 is greater than or equal to m1; during the Δγ period, the engine state change state has M1 start behaviors; during the Δδ period, set the threshold for abnormal battery voltage to d1, and the number of occurrences to n1. When the number of occurrences where the battery voltage < d1 during multiple ignition is greater than or equal to n1.

[0023] In the high-speed fault identification method based on vehicle networking big data described in the present invention; in step S6, when at least one of the fault codes of A parking behavior and B parking behavior and one of the C parking behaviors are satisfied simultaneously, and the parking scenario corresponding to step S4 is not satisfied, it is determined that the vehicle has a high-speed fault parking behavior on the highway at time t, otherwise, there is no high-speed fault parking behavior.

[0024] In the high-speed fault identification method based on vehicle networking big data described in the present invention; step S7 further includes the following steps:

[0025] S71. Record and mark the historical communication information. When the number of high-speed fault parking vehicles in the historical communication reaches the ten-thousand level, identify various abnormal situations as multi-class labels; collect the historical driving information, alarm information, factory return information, and GPS information of the vehicle.

[0026] In the high-speed fault identification method based on vehicle networking big data described in the present invention; step S7 further includes the following steps:

[0027] S72 trains an intelligent multi-classification model based on multiple abnormal situations and classification labels, and collects historical driving information, alarm information, return-to-factory information and GPS information of the vehicle. By classifying the vehicles that have passed through steps S2 and S3, it identifies vehicles that have stopped due to highway breakdowns and the corresponding breakdown and accident scenarios, and provides timely care to the owners of vehicles that have stopped due to highway breakdowns.

[0028] This invention presents a high-speed fault identification method based on vehicle-to-everything (V2X) big data. This method effectively and quickly monitors whether a vehicle has stopped on a highway due to a malfunction. It obtains the vehicle's location information through GPS point positioning data, eliminating the need for aftermarket sensors. It features low cost and high accuracy, and identifies whether a vehicle has stopped due to a malfunction on a highway through multi-dimensional identification. This provides OEMs with a foundation for after-sales service, ensuring vehicle owner safety, and providing comprehensive after-sales support. Attached Figure Description

[0029] Figure 1 is a flowchart illustrating an embodiment of the high-speed fault identification method based on vehicle network big data of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Figure 1 is a flowchart illustrating an embodiment of the high-speed fault identification method based on vehicle-to-everything (V2X) big data according to the present invention. A high-speed fault identification method based on V2X big data is provided, comprising the following steps:

[0033] In step S1, vehicle status data, behavior data, and GPS data are collected from the vehicle terminal and transmitted to the cloud. The vehicle status data, behavior data, and GPS data are preprocessed to obtain vehicle speed, rapid acceleration, rapid deceleration, sharp turn, hazard light status, whether the vehicle has been exited, ABS anti-lock braking system fault codes, engine malfunction light fault codes, tire pressure abnormality fault codes, coolant temperature alarm fault codes, and GPS location data.

[0034] In step S2, a highway fault stop judgment model trigger is constructed based on the vehicle speed and hazard lights being on; and the triggering conditions of the highway fault stop judgment model trigger are used to determine whether the vehicle needs to trigger the highway fault stop judgment.

[0035] In step S3, a high-speed positioning judgment model is built based on the two-point-one-line method, and for vehicles that meet the triggering conditions of the high-speed fault parking judgment model trigger, it is further judged whether the current vehicle has stopped due to vehicle abnormality and is not in the service area during the current vehicle's driving on the highway.

[0036] In step S4, a high-speed traffic jam behavior recognition model is constructed based on the high-speed positioning judgment model. When a vehicle has multiple similar stopping behaviors in its historical driving trajectory data on the highway and there is no data on returning to the factory for maintenance, and the current vehicle speed is less than the threshold a1, it is considered that the vehicle may have stopped due to high-speed traffic jam behavior, and such vehicle owner information is marked.

[0037] In step S5, a behavior discrimination and scenario discrimination model is constructed based on the highway traffic jam behavior recognition model, alarm fault codes and related signals corresponding to alarm fault code types and driver getting out of the vehicle. For vehicles that meet both step S2 and step S3, it is further determined whether a fault has occurred and the vehicle has stopped on the highway.

[0038] In step S6, if step S5 is satisfied but step S4 is not satisfied, then the behavior discrimination and scene discrimination model is used to determine that the vehicle has experienced a highway malfunction and stop behavior at that moment; otherwise, no malfunction and stop behavior has occurred.

[0039] In step S7, all vehicle information that has been communicated and confirmed with the vehicle owner for all vehicles that have experienced highway breakdowns and stops is obtained, and a multi-classification intelligent model is constructed based on all vehicle information that has been communicated and confirmed with the vehicle owner. The multi-classification intelligent model is used to classify the vehicles that have gone through steps S2, S3 and S4, and to separate the vehicles that have experienced highway breakdowns and stops and the corresponding breakdown and accident scenarios.

[0040] In this embodiment, in step S2: the triggering conditions of the highway fault parking judgment model trigger include triggering conditions based on the vehicle speed and triggering conditions based on the hazard lights being on. When both the triggering conditions based on the vehicle speed and the triggering conditions based on the hazard lights being on are met simultaneously within a certain time period, the highway fault parking judgment is triggered; otherwise, the highway fault parking judgment is not triggered.

[0041] In this embodiment, the triggering condition based on vehicle speed is that the vehicle is stationary for a continuous time interval (t1-t(N)), i.e., the vehicle speed is 0 at the current moment. The vehicle speed is expressed as... Among them, the Indicates t i The speed data is collected at the current moment. 0 indicates that the speed is 0 at the current moment, and t1 indicates the start time of the model trigger.

[0042] In this embodiment, the triggering condition based on the double flash on status is that the double flash is on within a continuous time interval of (t1-t(N)), and the double flash on / off status is represented as follows: Among them, the Indicates t i The data collected shows the status of the hazard lights switch at the moment of acquisition. 1 indicates that the hazard lights are on, and t1 indicates the start time of the model trigger.

[0043] In this embodiment, step S3 further includes the following steps:

[0044] S31, using GPS point positioning data, quickly determine whether the vehicle is located on the highway based on the two-point-one-line method; obtain the GPS point positioning data corresponding to three points A, B, and C, where point B is the GPS point positioning data corresponding to time t0 in step S2, and point A is the GPS point positioning data corresponding to the N1 minutes before time t0. 0-N1 GPS location data at time t0, where point C is the location of point N minutes after time t0. 0+N The GPS location data at any time; the GPS location data of points A, B, and C are used to obtain addresses through reverse geocoding, and then fuzzy matching is used to obtain addresses on the highway. The addresses are used to exclude highway locations that are parked in highway service areas and parking areas. If points A, B, and C are all on the highway at the same time, the vehicle is considered to be on the highway if the triggering conditions are met.

[0045] In this embodiment, step S5 includes the following parking behavior:

[0046] A. Before and after the trigger time t when the trigger condition of step S2 is triggered, detect the alighting detection period Δγ after time t to determine whether the driver has an alighting behavior, that is, there is a signal indicating that the driver in the driver's seat unbuckles the seat belt or the left front door of the vehicle is opened.

[0047] B. Before the trigger time t when the trigger condition of step S2 is triggered, detect whether there is an alarm fault code that affects driving safety before time t. The alarm fault codes at least include fault codes related to the anti-lock braking system (ABS) fault, fault codes related to the engine fault light being on, fault codes related to abnormal tire pressure, and fault codes related to water temperature alarm.

[0048] C. Before the trigger time t when the trigger condition of step S2 is triggered, detect rapid acceleration, rapid deceleration, sharp turns, acceleration, and vehicle speed detection period Δγ before time t. During the Δγ period, set the threshold number of fault codes related to the anti-lock braking system (ABS) fault as b1, and the threshold degree of the steering angle as b2. When the number of fault codes related to the anti-lock braking system (ABS) fault > b1, the degree of the steering angle > b2, and a sharp turn behavior occurs; during the Δγ period, set the threshold number of fault codes related to the engine fault as c1, and the threshold for the engine hood to be opened as c2. When the number of fault codes related to the engine fault > c1, the threshold for the engine hood to be opened > c2; during the Δδ period, set the threshold number of fault codes related to abnormal tire pressure as A1, and the threshold for the tire pressure signal value corresponding to the four tires to indicate abnormal tire pressure as A2, and the number of occurrences is m0. When the number of fault codes related to abnormal tire pressure > A1 and the vehicle speed is greater than s1, at least one of the four tires has a tire pressure signal value < A2; during the Δγ period, set the threshold number of fault codes related to abnormal water temperature as B1, the threshold for abnormal water temperature as B2, and the corresponding number of occurrences as m1. When the number of fault codes related to abnormal water temperature > B1, the number of occurrences where the corresponding water temperature > B2 is greater than or equal to m1; during the Δγ period, the engine state change state has M1 startup behaviors; during the Δγ period, set the threshold for abnormal battery voltage as d1, and the number of occurrences is n1. When the number of occurrences where the battery voltage < d1 during multiple ignition is greater than or equal to n1.

[0049] In this embodiment, in step S6, when at least one of the fault codes in A parking behavior and B parking behavior and one of the behaviors in C parking behavior are satisfied simultaneously, and the parking scenario corresponding to step S4 is not satisfied, it is determined that the vehicle has a high-speed fault parking behavior on the highway at time t, otherwise, there is no high-speed fault parking behavior.

[0050] In this embodiment, step S7 further includes the following steps:

[0051] In step S71, historical communication information is recorded and marked. When the number of vehicles with highway breakdowns and stops reaches tens of thousands, various abnormal situations will be identified as multi-classification labels. Historical driving information, alarm information, return-to-work information, and GPS information of the vehicles are collected. Among them, historical driving information includes driving speed, hazard lights, water temperature, emergency braking, acceleration, etc., and alarm information includes fault alarm signals issued by the vehicle while driving. All of these are obtained from the vehicle's data transmission. Historical return-to-work information is obtained from the dealership's return-to-work records.

[0052] In this embodiment, step S7 further includes the following steps:

[0053] In step S72, an intelligent multi-classification model is trained based on multi-abnormal situation multi-classification labels and collected historical driving information, alarm information, return-to-factory information, and GPS information of the vehicles. This model classifies vehicles that have experienced highway breakdowns and corresponding fault and accident scenarios, and provides timely care to the owners of these vehicles. Highway breakdowns and corresponding faults and scenarios include abnormal water temperature, tire blowout, and difficulty starting.

[0054] Specifically, the vehicle's infotainment system transmits vehicle status data, behavior data, and GPS data to the cloud via CAN bus, selecting key data such as vehicle speed, rapid acceleration, rapid deceleration, sharp turns, hazard light status, whether the driver has exited the vehicle, and GPS data. Step S1 also includes data filtering to remove abnormal data where the vehicle speed exceeds a threshold. The threshold is the maximum value that the CAN bus transmits.

[0055] The trigger condition for the highway fault-based parking judgment model is that the vehicle is stationary within a certain time period if both of the following conditions are met simultaneously; otherwise, it is not triggered. Specifically, the vehicle must be stationary for the entire BC time period and its hazard lights must be on. When the data collection interval is n minutes, and the BC segment is a time interval (t1-t(N)) arranged sequentially, the specific trigger conditions are: 1) The vehicle is stationary within the consecutive BC time intervals, represented as [value missing]. 2) The hazard lights are on within the consecutive BC time intervals, represented as [value missing]. Among them, parameters Indicates t i The speed at which data is collected, where 0 indicates that the speed is 0 at the current moment. Indicates t i The data represents the status of the dual flash on / off state at specific times. 1 indicates dual flash is on. t1 represents the start time of the model trigger, i.e., time B. t(N) represents the end time of the model trigger, i.e., time C.

[0056] Specifically, for vehicles meeting the trigger conditions, further determination is made as to whether the vehicle stopped after a breakdown while driving on the highway. However, directly using GPS positioning data at each moment to determine highway location results in excessive data, slowing down real-time processing. Furthermore, relying on a single GPS address can lead to GPS positioning inaccuracies. Therefore, a method balancing speed and accuracy is proposed: utilizing GPS point positioning data, a two-point-one-line method is used to quickly determine if the vehicle is located on the highway. This involves applying two two-point-one-line logics, such as obtaining GPS point positioning data corresponding to points A, B, and C. Point B is the GPS point positioning data corresponding to time t0 in step S2, and point A is the GPS point positioning data corresponding to the N1 minutes prior to time t0. 0-N1 GPS location data corresponding to time t0, where point C is the location of point N minutes after time t0. 0+N The GPS location data corresponds to the given time. Reverse geocoding is performed on the GPS location data of the three points to obtain addresses. Fuzzy matching is then used to obtain addresses on the highway, and addresses are used to exclude vehicles parked in highway service areas or rest areas. If points A, B, and C are all on the highway simultaneously, the vehicle is considered to meet the triggering condition and is on the highway. For example, point A represents the Changge toll station on the G4 Beijing-Hong Kong-Macau Expressway in Laocheng Town, Changge City, Xuchang City, Henan Province; point B represents the Xuchang service area on the G4 Beijing-Hong Kong-Macau Expressway in Foerhu Town, Changge City, Xuchang City, Henan Province; and point C represents the Xuchang service area on the G4 Beijing-Hong Kong-Macau Expressway in Foerhu Town, Changge City, Xuchang City, Henan Province. In this case, the vehicle triggering the condition is excluded.

[0057] By analyzing historical driving trajectory data of vehicles on highways, if a vehicle is found to have repeatedly exhibited similar stopping behavior along its historical trajectory without returning to a repair shop, and its current speed is less than a threshold a1, where a1 = (a11, a12, a13…a14), then it is considered that the vehicle may have stopped due to highway traffic congestion, and the owner's information for this type of vehicle is marked. Specifically, the speed threshold a1 is derived from a multi-layered median definition based on historical data (layers are based on speed, holidays / weekdays, weather, etc.).

[0058] Because directly using alarm fault codes for identification can lead to issues such as abnormal fault code transmission or minor fault severity, a combination of alarm fault codes, corresponding signals for each alarm fault code type, and driver exit behavior is used to improve judgment. For vehicles that meet the triggering conditions of step S2 and the address in step S3 is on a highway, further determination is made as to whether a fault occurred on the highway causing the vehicle to stop. This includes three stopping behaviors: A, B, and C. Here, Δγ needs to be determined based on the specific vehicle specifications.

[0059] It should be noted that in parking behavior C, before the trigger condition in step S2 is triggered at time t, the detection period Δγ of rapid acceleration, rapid deceleration, sharp turning, acceleration, and vehicle speed before time t is performed. During the Δγ period, based on the acquisition of relevant signals of the fault code type in B: such as ABS anti-lock braking system fault codes and auxiliary signals: steering angle signal, turn signal, sharp turn signal, etc.; engine fault codes and auxiliary signals: engine speed signal, hood signal, etc.; abnormal tire pressure fault codes and auxiliary signals: tire pressure signals of all four tires; coolant temperature warning fault codes and auxiliary signals: coolant temperature signal, engine speed signal, accelerator pedal signal, speed signal, etc.; and the resulting starting difficulties, battery depletion, weak acceleration, etc., will be discussed in various ways.

[0060] Vehicle malfunctions have always been a crucial research focus for all automakers and suppliers. Highways, being a special type of road, present unique challenges for automakers. They aim to provide rapid assistance and roadside aid to vehicle owners after a breakdown, ensuring their safety. Furthermore, the high frequency of towing requests on highways makes after-sales service highly efficient; therefore, timely contact with owners for towing and support significantly improves after-sales profitability. Automakers have accumulated substantial data on vehicle malfunctions and user behavior through connected vehicle networks. This data reflects not only the vehicle's condition at the time of malfunction but also the owner's actions afterward, typically involving immediate vehicle inspection or relocation to a safe area. This invention, based on vehicle status and owner behavior, combined with the owner's address, can quickly and accurately identify vehicle breakdowns on highways, improving highway driving safety. Therefore, this invention proposes a method and device for identifying highway vehicle malfunctions based on onboard malfunctions and user behavior. This invention relates to a method and device for identifying vehicle malfunctions and parking on highways. The method includes: firstly identifying a vehicle that may be abnormally parked due to a malfunction, such as parking with hazard lights on for more than N minutes; secondly, using the vehicle's trajectory and a two-point-to-one method, quickly determining the vehicle's location on the highway, ruling out parking in highway service areas and rest areas; thirdly, ruling out highway traffic congestion; and finally, based on a combination of the malfunction indicator light sensor and its related signals, and the driver's exit behavior, determining that an abnormal parking behavior has occurred, and notifying the dealership to await assistance. This invention can reduce the impact on highway traffic, improve highway driving safety, and has broad application prospects. It lays the foundation for after-sales care and rescue. This invention can be widely applied in highway management and traffic safety fields, and is of great significance for improving highway safety and smooth traffic flow. This invention also has high practicality and can provide drivers with a more convenient driving experience, improving their sense of security and confidence.

[0061] The beneficial effects of the high-speed fault identification method based on vehicle network big data provided in this embodiment of the invention are at least as follows:

[0062] 1. By using the timing of hazard lights to identify vehicles that may be parked abnormally, the likelihood of misjudgment is reduced.

[0063] 2. By using the two-point-one-line method twice to determine that the vehicle is located on the highway, vehicles parked in other places are excluded, thus improving the accuracy of identification.

[0064] 3. By eliminating factors such as highway traffic jams, the possibility of misjudgment has been reduced.

[0065] 4. By promptly sending notifications to authorized dealerships, we can quickly respond to abnormal parking incidents, ensuring smooth traffic flow and safety on highways.

[0066] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0068] Therefore, the above description is only a preferred embodiment of the present invention, and the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A high-speed fault identification method based on Internet of Vehicles big data, characterized in that, The method includes the following steps: S1 collects vehicle status data, behavior data, and GPS data from the vehicle's infotainment system and transmits them to the cloud. It preprocesses the vehicle status data, behavior data, and GPS data to obtain vehicle speed, rapid acceleration, rapid deceleration, sharp turns, hazard lights on / off status, whether the vehicle has been exited, ABS anti-lock braking system fault codes, engine malfunction light fault codes, tire pressure abnormality fault codes, coolant temperature alarm fault codes, and GPS location data. S2, construct a highway fault stop judgment model trigger based on the vehicle speed and hazard lights being on; and determine whether the vehicle needs to trigger highway fault stop judgment based on the triggering conditions of the highway fault stop judgment model trigger. S3. Based on the two-point-one-line method, a high-speed positioning judgment model is built, and for vehicles that meet the triggering conditions of the high-speed fault parking judgment model trigger, it is further judged whether the current vehicle has stopped due to vehicle abnormality and is not in the service area during the process of driving on the highway. S4. Based on the high-speed positioning judgment model, a high-speed traffic jam behavior recognition model is constructed. When a vehicle has multiple similar stopping behaviors in its historical driving trajectory data on the highway and there is no data on returning to the factory for maintenance, and the current vehicle speed is less than the threshold a1, it is considered that the vehicle may have stopped due to high-speed traffic jam behavior, and such vehicle owner information is marked. S5. Based on the highway traffic jam behavior recognition model, alarm fault codes and related signals corresponding to the alarm fault code types and the driver's exit behavior, construct a behavior discrimination and scene discrimination model, and further determine whether the vehicle that meets both step S2 and step S3 has stopped due to a fault on the highway. S6. If step S5 is satisfied but step S4 is not satisfied, then the behavior discrimination and scenario discrimination model is used to determine that the vehicle has experienced a highway malfunction and stop behavior at that moment; otherwise, no malfunction and stop behavior has occurred. S7: Obtain all vehicle information that has been communicated and confirmed with the vehicle owner for all vehicles that have experienced highway breakdowns and stops, and build a multi-classification intelligent model based on all vehicle information that has been communicated and confirmed with the vehicle owner; classify the vehicles that have gone through steps S2, S3 and S4 through the multi-classification intelligent model, and identify the vehicles that have experienced highway breakdowns and stops and the corresponding breakdown and accident scenarios. 2.The high-speed fault identification method based on big data of Internet of Vehicles according to claim 1, characterized in that, In step S2: the triggering conditions of the highway fault stop judgment model trigger include triggering conditions based on the vehicle speed and triggering conditions based on the hazard lights being on. When both the triggering conditions based on the vehicle speed and the triggering conditions based on the hazard lights being on are met simultaneously within a certain time period, the highway fault stop judgment is triggered; otherwise, the highway fault stop judgment is not triggered.

3. The high-speed fault identification method based on vehicle network big data according to claim 2, characterized in that, The trigger condition based on the vehicle speed is that the vehicle is in a stationary state in a continuous (t1-t(N)) time interval, i.e. the current time vehicle speed is 0, which is represented as Wherein, the Denotes t i The speed data at the collection time, 0 indicates that the current time speed is 0, and t1 indicates the start time of the model trigger.

4. The high-speed fault identification method based on vehicle network big data according to claim 3, characterized in that, The triggering condition based on the double flash on status is that the double flash is on within a continuous time interval of (t1-t(N)), and the double flash on / off status is expressed as follows: Among them, the Indicates t i The data collected shows the status of the hazard lights switch at the moment of acquisition. 1 indicates that the hazard lights are on, and t1 indicates the start time of the model trigger.

5. The high-speed fault identification method based on vehicle network big data according to claim 4, characterized in that, Step S3 further includes the following steps: S31, using GPS point positioning data, based on the method of two-point line quickly determine whether the vehicle is positioned on the highway; obtain the GPS point positioning data corresponding to three points A, B and C, wherein the B point is the GPS point positioning data corresponding to the t0 moment in step S2, the A point is the GPS point positioning data corresponding to the t 0-N1 moment of the previous N1 minutes, and the C point is the GPS point positioning data corresponding to the t 0+N moment of the next N minutes; obtain the address through inverse geocoding after obtaining the GPS point positioning data of the three points A, B and C, and then obtain the address on the highway through fuzzy matching, and exclude the high-speed position of stopping in the high-speed service area and parking area by using the address, if the three points A, B and C are on the highway at the same time, it is considered that the vehicle meeting the triggering condition is on the highway.

6. The high-speed fault identification method based on vehicle network big data according to claim 5, characterized in that, Step S5 includes the following parking actions: A. Before and after the triggering condition in step S2 is triggered at time t, detect the vehicle exit detection period Δγ after time t to see if the driver has exited the vehicle, i.e., whether the driver has unbuckled the seat belt or the left front door of the vehicle has opened. B. Before the trigger condition of step S2 is triggered at time t, detect whether there are warning fault codes that affect driving safety before time t. The warning fault codes at least include fault codes related to the anti-lock braking system (ABS) failure, fault codes related to the engine fault light being on, fault codes related to abnormal tire pressure, and fault codes related to water temperature warning. C. Before the trigger condition of step S2 is triggered at time t, detect hard acceleration, hard deceleration, sharp turns, acceleration, and the vehicle speed detection period Δδ before time t. During the Δδ period, set the threshold number of fault codes related to the anti-lock braking system (ABS) failure as b1, and the threshold degree of the steering angle as b2. When the number of fault codes related to the anti-lock braking system (ABS) failure > b1, the degree of the steering angle > b2, and a sharp turn behavior occurs. During the Δγ period, set the threshold number of fault codes related to engine failure as c1, and the threshold for the engine hood being opened as c2. When the number of fault codes related to engine failure > c1, the threshold for the engine hood being opened > c2. During the Δγ period, set the threshold number of fault codes related to abnormal tire pressure as A1, and the threshold for the tire pressure signal value of the four corresponding tires indicating abnormal tire pressure as A2, and the number of occurrences is m0. When the number of fault codes related to abnormal tire pressure > A1 and the vehicle speed is greater than s1, at least one of the tire pressure signal values of the four corresponding tires < A2. During the Δγ period, set the threshold number of fault codes related to abnormal water temperature as B1, and the threshold for abnormal water temperature as B2, and the corresponding number of occurrences is m1. When the number of fault codes related to abnormal water temperature > B1 and the number of corresponding water temperature values > B2 is greater than or equal to m1. During the Δγ period, the engine state change state shows M1 startup behaviors. During the Δγ period, set the threshold for abnormal battery voltage as d1, and the number of occurrences is n1. When the number of times the battery voltage < d1 during multiple ignition attempts is greater than or equal to n1.

7. The high-speed fault identification method based on vehicle network big data according to claim 6, characterized in that, In step S6, when at least one of the fault codes in A parking behavior and B parking behavior and one of the C parking behaviors are satisfied, and the corresponding parking scenario in step S4 is not satisfied, it is determined that the vehicle has had a high-speed fault parking behavior on the highway at time t; otherwise, no high-speed fault parking behavior has occurred.

8. The high-speed fault identification method based on vehicle network big data according to claim 7, characterized in that, Step S7 further includes the following steps: S71. Record and mark historical communication information. When the number of high-speed highway fault parking vehicles in historical communication reaches the ten-thousand level, identify multiple abnormal situations as multi-class labels; collect the vehicle's historical driving information, warning information, information upon returning to the factory, and GPS information.

9. The high-speed fault identification method based on vehicle network big data according to claim 8, characterized in that, Step S7 further includes the following steps: S72. Train an intelligent multi-class model based on the multi-abnormal situation multi-class labels and the collected vehicle's historical driving information, warning information, information upon returning to the factory, and GPS information. By classifying the vehicles that have passed through steps S2 and S3, identify the vehicles that have had high-speed highway fault parking and the corresponding fault and accident scenarios, and promptly provide care to the owners of vehicles that have had high-speed highway fault parking.

Images