Collision identification method and device, equipment and medium

Abstract

The invention discloses a collision identification method, and the method comprises the steps: determining a communication connection state between a target vehicle and a cloud service platform when the target vehicle has a first collision risk; if the communication between the target vehicle and the cloud service platform is abnormal, determining that the vehicle is collided; if the communication between the target vehicle and the cloud service platform is normal, performing secondary detection on the collision risk of the target vehicle based on the vehicle driving speed information to determine whether the target vehicle has a second collision risk, and determining whether the target vehicle is collided according to the second collision risk; the vehicle collision is detected for the first time through the collision signal, when communication abnormity exists between the vehicle and the cloud service platform, it is determined that the vehicle collides, the collision warning information is generated, accident warning processing is effectively achieved, and the safety guarantee of a vehicle user is improved; and when communication abnormity does not exist between the vehicle and the cloud service platform, whether collision occurs is further determined through the AI algorithm, so that the accuracy of collision detection is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a collision identification method, device, equipment and medium. Background Art

[0002] In today's environment, road traffic accidents have become an increasingly serious public safety issue worldwide. They are the most common ground traffic accidents that cause the most casualties. Therefore, it is of great significance to study and master relevant treatment measures, optimize post-accident solutions, improve accident handling efficiency, and reduce casualties. After a major accident, if there is no mature background alarm solution and data storage solution, it will be impossible to deal with subsequent vehicle collisions and continue to optimize the treatment measures after the extreme collision of the entire vehicle.

[0003] In order to ensure the safety of users when riding or driving, the vehicle's onboard emergency call system (E-Call, emergency call) can automatically initiate an alarm when a traffic accident occurs. The emergency call (ECALL) system configured in the vehicle generally includes a communication box (telematics box, TBOX), which is also connected to the vehicle's airbag controller. The TBOX can automatically call the emergency rescue center for rescue after detecting the collision signal sent by the airbag controller. However, if the collision signal is not routed to the TBOX during a vehicle collision, the mobile communication function of the TBOX will be damaged, resulting in the cloud platform data being unable to alert the vehicle of an extreme collision for immediate rescue. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present application provides a collision identification method, device, equipment and medium to solve at least one defect in the prior art.

[0005] To achieve the above objectives and other objectives, the present application provides a collision identification method, which is applied to a cloud service platform. The method includes:

[0006] Monitor the collision signal of the target vehicle;

[0007] performing a first detection of a collision risk of the target vehicle based on the collision signal to determine whether the target vehicle has a first collision risk;

[0008] When the target vehicle has a first collision risk, determining a communication connection state between the target vehicle and the cloud service platform;

[0009] If the communication connection state between the target vehicle and the cloud service platform is abnormal, it is determined that the vehicle has collided;

[0010] If the communication connection status between the target vehicle and the cloud service platform is normal, the vehicle speed information from the first time to the second time is obtained, and the collision risk of the target vehicle is secondly detected based on the vehicle speed information to determine whether the target vehicle has a second collision risk, and whether the target vehicle collides is determined based on the second collision risk; wherein the first time is earlier than the second time.

[0011] In one embodiment of the present application, the step of determining the communication connection status between the target vehicle and the cloud service platform includes:

[0012] Obtaining vehicle status data corresponding to the target vehicle when it has a first collision risk in the cloud service platform;

[0013] Testing the integrity of the vehicle status data;

[0014] If there is data missing in the vehicle status data, determining that the communication connection status between the target vehicle and the cloud service platform is abnormal;

[0015] If there is no data missing in the vehicle status data, it is determined that the communication connection status between the target vehicle and the cloud service platform is normal.

[0016] In one embodiment of the present application, the collision signal includes: a collision signal sent by an ABM controller, and the step of first detecting the collision risk of the target vehicle based on the collision signal includes:

[0017] A collision signal emitted by a real-time ABM controller is obtained, and the collision signal emitted by the real-time ABM controller is input into a pre-trained collision risk identification model, and a first detection of the collision risk of the target vehicle is performed through the collision risk identification model to determine whether the target vehicle has a first collision risk; wherein the collision risk identification model is trained with the collision signal emitted by the historical ABM controller as input and the historical collision risk as output.

[0018] In one embodiment of the present application, the step of determining the collision risk of the target vehicle based on the vehicle speed information includes:

[0019] Inputting the vehicle speed information from the first time to the second time into a pre-trained LSTM-based collision risk classification model, and classifying the airbag status corresponding to the vehicle speed information through the collision risk classification model, wherein the airbag status includes airbag deployment and airbag non-deployment, and airbag deployment indicates that the vehicle has a collision risk;

[0020] The LSTM-based collision risk classification model is trained using vehicle speed information as training input data and airbag status as training output data.

[0021] In one embodiment of the present application, the vehicle speed information includes: an average value and a maximum change value of the vehicle speed from the first time to the second time, and the maximum change value represents the difference between the maximum value and the minimum value of the vehicle speed.

[0022] In one embodiment of the present application, before the step of performing a first detection on the collision risk of the target vehicle based on the collision signal, the method further includes:

[0023] Acquire first vehicle body state information, wherein the first vehicle body state information includes: high voltage information, gear position, and vehicle speed value of the vehicle;

[0024] When the vehicle is at high pressure, the gear is not the P gear, and the vehicle speed value is greater than zero, judging whether the vehicle speed value satisfies the first preset condition or / and the second preset condition; the first detection of the collision risk of the target vehicle is performed when the vehicle speed value satisfies the first preset condition or / and the second preset condition;

[0025] Among them, the first preset condition includes: there is a vehicle speed value at the first time and there is no vehicle speed value at the second time; the second preset condition includes: the first vehicle speed value corresponding to the first time is greater than the second vehicle speed value corresponding to the second time, and the difference between the first vehicle speed value and the second vehicle speed value is greater than the preset speed threshold.

[0026] In one embodiment of the present application, when the target vehicle has a first collision risk and the communication connection status between the target vehicle and the cloud service platform is normal, second vehicle body status information transmitted by T-BOX to the cloud service platform is obtained, and the second vehicle body status information includes at least one of the following: main driver's door signal, passenger driver's door signal, left rear door signal, right rear door signal, post-collision lower high-voltage signal, BMS battery temperature signal, gear signal, vehicle speed value, airbag signal, ECALL signal.

[0027] To achieve the above objectives and other related objectives, the present application provides a collision recognition device, the device comprising:

[0028] A data monitoring module, used to monitor the collision signal of the target vehicle;

[0029] A first collision risk detection module, configured to perform a first detection of a collision risk of a target vehicle based on the collision signal to determine whether the target vehicle has a first collision risk;

[0030] A connection status determination module, used to determine the communication connection status between the target vehicle and the cloud service platform when the target vehicle has a first collision risk;

[0031] A collision occurrence determination module, used to determine that a collision occurs with the target vehicle when the communication connection state between the target vehicle and the cloud service platform is abnormal;

[0032] The second collision determination module is used to obtain the vehicle speed information from the first time to the second time when the communication connection state between the target vehicle and the cloud service platform is normal, perform a second detection on the collision risk of the target vehicle based on the vehicle speed information to determine whether the target vehicle has a second collision risk, and determine whether the target vehicle collides according to the second collision risk; wherein the first time is earlier than the second time.

[0033] To achieve the above objectives and other related objectives, the present application provides a device, including:

[0034] one or more processors; and

[0035] The memory is used to store one or more programs. When the one or more programs are executed by the one or more processors, the memory implements the method described.

[0036] To achieve the above objectives and other related objectives, the present application provides one or more machine-readable media having instructions stored thereon, which, when executed by one or more processors, enable the processors to execute the described methods.

[0037] Beneficial effects of this application:

[0038] A collision identification method of the present application includes: monitoring a collision signal of a target vehicle; performing a first detection of the collision risk of the target vehicle based on the collision signal to determine whether the target vehicle has a first collision risk; when the target vehicle has the first collision risk, determining the communication connection state between the target vehicle and a cloud service platform; if the communication connection state between the target vehicle and the cloud service platform is an abnormal state, determining that the vehicle has collided; if the communication connection state between the target vehicle and the cloud service platform is a normal state, obtaining vehicle driving speed information from a first time to a second time, performing a second detection of the collision risk of the target vehicle based on the vehicle driving speed information to determine whether the target vehicle has a second collision risk, and determining whether the target vehicle has collided according to the second collision risk; wherein the first time is earlier than the second time; the present application performs a first detection of vehicle collision through a collision signal, directly determines that the vehicle has collided when there is a communication anomaly between the vehicle and the cloud service platform, that is, when data is missing, and generates collision warning information, effectively achieving accident alarm processing, and improving the safety of vehicle users; and when there is no communication anomaly between the vehicle and the cloud service platform, further determining whether the vehicle has collided through an AI algorithm, thereby improving the accuracy of collision detection.

[0039] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0041] Figure 1 A schematic diagram of an exemplary collision identification method implementation environment of the present application;

[0042] Figure 2 A flowchart of a collision identification method according to an embodiment of the present application;

[0043] Figure 3 The process of the method for performing the first detection of the collision risk of the vehicle according to the embodiment of the present application;

[0044] Figure 4 A flowchart of a method for determining a communication connection status between a target vehicle and a cloud service platform in an embodiment of the present application;

[0045] Figure 5A block diagram of a collision recognition device shown as an exemplary embodiment of the present application;

[0046] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the memory of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0047] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0048] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0049] Although the terms "first", "second", "A", and "B", etc. may be used herein to describe various elements, these elements should not be limited by these terms and are only used to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the following technology. The term "and / or" includes a combination of multiple related items or any of the multiple related items.

[0050] As used herein, unless the context indicates otherwise, the singular form is intended to include the plural form, and it will be understood that the term "comprising" means the presence of stated features, quantities, steps, operations, elements, or combinations thereof, but does not exclude the presence or addition of one or more other features, quantities, steps, operations, elements, components, or combinations thereof.

[0051] Before the detailed description, it is intended to clarify that the division of components in this specification is divided only by the main function of each component. That is, two or more components to be described below can be combined into one component, or can be divided into two or more components according to more detailed functions. In addition to the main function of the component, each component to be described below can also perform some or all of the functions of other components, and some of the main functions of each component can be exclusively performed by other components.

[0052] In order to more clearly describe the solution of the present application, some knowledge related to the solution is first introduced below.

[0053] In-vehicle information terminal (Telematics BOX, T-Box):

[0054] Generally, a T-Box is installed in the vehicle. The T-Box is equipped with a mobile communication module, which can report the vehicle's driving status data to the vehicle's manufacturer platform, and then report it to the national vehicle platform through the manufacturer's platform, so that the national vehicle management department can realize real-time monitoring of the vehicle's operating status.

[0055] Generally, after a vehicle with T-Box installed is started, T-Box is triggered to periodically report vehicle data to the cloud service platform of the vehicle until the vehicle is turned off, and T-Box stops reporting vehicle data to the cloud service platform of the vehicle. Understandably, in some special cases, T-Box may not report vehicle data. For example, a serious accident occurs in the vehicle, causing serious damage to the T-Box controller, that is, the vehicle control unit (ECU). Although the T-Box is not damaged, after the vehicle control unit fails, the vehicle control unit cannot control the communication between the vehicle and the cloud service platform, causing T-Box to be unable to continue reporting vehicle data.

[0056] The present application is further described below in conjunction with the accompanying drawings.

[0057] See also Figure 1 , the implementation environment includes a terminal device 110 and a server 120, and the terminal device 110 and the server 120 communicate with each other through a wireless network. The server 120 monitors the collision signal of the target vehicle; based on the collision signal, the collision risk of the target vehicle is first detected to determine whether the target vehicle has a first collision risk; when the target vehicle has a first collision risk, the communication connection state between the target vehicle and the cloud service platform is determined; if the communication connection state between the target vehicle and the cloud service platform is abnormal, it is determined that the vehicle has collided; if the communication connection state between the target vehicle and the cloud service platform is normal, the vehicle driving speed information from the first time to the second time is obtained, and the collision risk of the target vehicle is second detected based on the vehicle driving speed information to determine whether the target vehicle has a second collision risk, and whether the target vehicle has collided according to the second collision risk; wherein the first time is earlier than the second time. After determining that the target vehicle has collided, a collision warning message can be generated to facilitate rescue personnel to carry out on-site rescue in the first time.

[0058] It should be understood that Figure 1The number of terminal devices 110 and servers 120 in the embodiment is only for illustration. Any number of terminal devices 110 and servers 120 may be provided according to actual needs.

[0059] The terminal device 110 is a T-BOX, which is installed on the target vehicle.

[0060] Among them, the server 110 corresponds to the service end, which can be a server that provides various services, which can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, etc. This is not limited here. In this embodiment, the server provides cloud services.

[0061] The terminal device 110 can communicate with the server 120 through wireless networks such as 3G (third generation mobile information technology), 4G (fourth generation mobile information technology), and 5G (fifth generation mobile information technology), and this is not restricted here.

[0062] The server, i.e., the cloud service platform, stores the device information of the target vehicle, such as the vehicle identification, vehicle type, and license plate number of the target vehicle. The cloud service platform also stores the contact information of the owner of the target vehicle.

[0063] When the target vehicle is started, the T-BOX in the target vehicle will periodically report vehicle data to the cloud service platform. The cloud service platform can monitor the target vehicle based on the vehicle data uploaded by the T-BOX. When the cloud service platform determines that the target vehicle has collided based on the vehicle data, it can generate a collision alarm message to prompt the corresponding monitoring personnel. The monitoring personnel respond to the collision alarm message and, based on the contact information of the target vehicle, can confirm whether the target vehicle needs rescue by calling the contact information (telephone number) of the owner of the target vehicle. When it is determined that rescue is needed, on-site rescue will be carried out as soon as possible.

[0064] See also Figure 2 , Figure 2 This is a flow chart of a collision identification method according to an embodiment of the present application. Figure 2 As shown, the collision identification method at least includes steps S210 to S240:

[0065] Step S210: monitoring the collision signal of the target vehicle.

[0066] The cloud service platform monitors and identifies collision signals based on vehicle data reported by T-BOX, and then performs a first detection of the vehicle's collision risk based on the collision signals to predict whether the target vehicle will collide.

[0067] Step S220, performing a first detection on the collision risk of the target vehicle based on the collision signal to determine whether the target vehicle has a first collision risk;

[0068] After identifying the collision signal, the cloud service platform detects whether the target vehicle has collided based on the collision signal, that is, determines whether the target vehicle has a first collision risk.

[0069] In an embodiment of the present application, the collision signal includes a collision signal issued by an ABM controller, and the collision signal issued by the ABM controller includes: a pre-collision flag and / or an airbag pop-up flag, wherein in the vehicle data, the pre-collision flag can be represented by pre_crash_flag, and the airbag pop-up flag can be represented by ABM_CRASH.

[0070] See also Figure 3 , Figure 3 This is the process of the method for performing the first detection of the collision risk of a vehicle according to an embodiment of the present application. Figure 3 As shown, the steps of first detecting the collision risk of the target vehicle based on the collision signal include:

[0071] Step S310, obtaining a collision signal sent by a real-time ABM controller;

[0072] It should be noted that the cloud service platform identifies the pre-collision flag and the airbag deployment flag in the vehicle data, and then determines the status of the pre-collision flag and / or the airbag deployment flag.

[0073] Step S320, inputting the collision signal emitted by the real-time ABM controller into a pre-trained collision risk identification model, and performing a first detection on the collision risk of the target vehicle through the collision risk identification model to determine whether the target vehicle has a first collision risk; wherein the collision risk identification model is trained with the collision signal emitted by the historical ABM controller as input and the historical collision risk as output.

[0074] The training process of the collision risk identification model includes:

[0075] S1. Obtain a historical data sample set and divide it into a training sample set and a test sample set;

[0076] S2. Use the training sample set to train the preset deep learning model;

[0077] Specifically, during training, 70% of the training samples in the training sample set can be used to train the deep learning model, and 30% of the training samples can be used to test the deep learning model.

[0078] S3. Use the test sample set to test the trained deep learning model. When the test result meets the preset conditions, determine that the neural network model is a trained collision risk identification model.

[0079] Step S230, when the target vehicle has a first collision risk, determining the communication connection state between the target vehicle and the cloud service platform.

[0080] It should be noted that the communication connection status between the target vehicle and the cloud service platform includes a normal state and an abnormal state, and the communication connection between the target vehicle and the cloud service platform includes the communication connection between the vehicle controller ECU and the T-BOX and the communication connection between the T-BOX and the cloud service platform. To determine the communication connection status between the target vehicle and the cloud service platform, it is necessary to make corresponding judgments on the communication connection status between the vehicle controller ECU and the T-BOX and the communication connection status between the T-BOX and the cloud service platform.

[0081] Step S240, if the communication connection state between the target vehicle and the cloud service platform is abnormal, it is determined that the vehicle has collided;

[0082] After a vehicle collision, especially a collision at high speed, such as when the target vehicle collides at a high speed greater than 80km / h, the front cabin of the vehicle will collapse rapidly, causing the entire vehicle wiring harness in the front cabin to fail, resulting in abnormal communication between the vehicle and the cloud service platform. Therefore, whether the vehicle has collided can be determined based on whether the communication connection status between the target vehicle and the cloud service platform is normal.

[0083] If the communication connection status between the vehicle controller ECU and T-BOX and between T-BOX and the cloud service platform is abnormal, the communication connection status between the target vehicle and the cloud service platform is considered to be abnormal. For example, if the communication connection status between the vehicle controller and T-BOX is normal, and the communication connection status between T-BOX and the cloud service platform is abnormal, the communication connection status between the target vehicle and the cloud service platform is abnormal; if the communication connection status between the vehicle controller and T-BOX is abnormal, and the communication connection status between T-BOX and the cloud service platform is normal, the communication connection status between the target vehicle and the cloud service platform is abnormal; if the communication connection status between the vehicle controller and T-BOX is abnormal, and the communication connection status between T-BOX and the cloud service platform is abnormal, the communication connection status between the target vehicle and the cloud service platform is abnormal. If the communication connection status between the vehicle controller ECU and T-BOX and the communication connection status between T-BOX and the cloud service platform are both normal, the communication connection status between the target vehicle and the cloud service platform is considered to be normal.

[0084] It should be noted that if the vehicle is in an abnormal network area such as a tunnel or garage, the communication connection status between the target vehicle and the cloud service platform may also be abnormal. Therefore, it is necessary to identify the area where the target vehicle is located. When the target vehicle is in an abnormal network area, it will not be immediately determined that the target vehicle has collided. In this way, the false alarm rate of vehicle collision identification can be reduced.

[0085] Communication anomalies between the target vehicle and the cloud service platform will affect data transmission, and data loss will occur during the transmission process, resulting in incomplete data. Therefore, the communication connection status between the target vehicle and the cloud service platform can be determined by the integrity of the data.

[0086] See also Figure 4 , Figure 4 This is a flow chart of a method for determining the communication connection status between a target vehicle and a cloud service platform in an embodiment of the present application. Figure 4 In the step of determining the communication connection status between the target vehicle and the cloud service platform, the step includes:

[0087] Step S410, obtaining vehicle status data corresponding to the target vehicle when there is a first collision risk in the cloud service platform;

[0088] Step S420, checking the integrity of the vehicle status data;

[0089] Step S430: if there is data missing in the vehicle status data, determining that the communication connection status between the target vehicle and the cloud service platform is abnormal;

[0090] Step S440: If there is no missing data in the vehicle status data, it is determined that the communication connection status between the target vehicle and the cloud service platform is normal.

[0091] It should be noted that the missing of vehicle status data includes two situations: partial missing and empty data.

[0092] Step S250, if the communication connection status between the target vehicle and the cloud service platform is normal, obtain the vehicle speed information from the first time to the second time, perform a second detection of the collision risk of the target vehicle based on the vehicle speed information to determine whether the target vehicle has a second collision risk, and determine whether the target vehicle collides based on the second collision risk; wherein the first time is earlier than the second time.

[0093] When the communication connection status between the target vehicle and the cloud service platform is normal, the collision risk of the vehicle is further predicted through the vehicle speed information to improve the accuracy of determining the vehicle collision.

[0094] It should be noted that the first time and the second time are both preset vehicle data reporting times. The vehicle speed information includes: the average value and the maximum change value of the vehicle speed from the first time to the second time, and the maximum change value represents the difference between the maximum value and the minimum value of the vehicle speed. The time period between the first time and the second time can be set according to actual conditions. For example, the time period between the first time and the second time is 3s, or the time period between the first time and the second time is 5s, or the time period between the first time and the second time is 10s, or the time period between the first time and the second time is 30s, etc. Of course, in other embodiments, the time period between the first time and the second time can be set to other times, which is not limited here.

[0095] In an embodiment of the present application, the steps of determining the collision risk of the target vehicle based on the vehicle speed information include:

[0096] The vehicle speed information from the first time to the second time is input into a pre-trained collision risk classification model based on LSTM (Long Short-Term Memory). The airbag status corresponding to the vehicle speed information is classified by the collision risk classification model. The airbag status includes airbag deployment and airbag non-deployment. Airbag deployment indicates that the vehicle has a collision risk. The LSTM-based collision risk classification model is trained using the vehicle speed information as training input data and the airbag status as training output data.

[0097] The vehicle speed information in different time periods is input into the pre-trained LSTM-based collision risk classification model, and then the vehicle speed information in different time periods is processed separately by the LSTM model. After multi-layer abstract extraction by LSTM, the extracted information is spliced ​​together, and then goes through batch normalization and multiple fully connected layers. The last fully connected layer has two nodes, and the weights of the two classifications are calculated by softmax, corresponding to the airbag deployment and airbag non-deployment, respectively.

[0098] Among them, for the training of the collision risk classification model, as much collision data as possible including vehicle speed information and airbag status (indicating that the airbag is deployed) when the vehicle collides, and non-collision data including vehicle speed information and airbag status (indicating that the airbag is not deployed) when the vehicle does not collide are obtained as training data. The training data is normalized and the missing data is interpolated; then the collision data and non-collision data are combined into a data set in a ratio close to 1:1; then the training set, validation set, and test set are separated from the data set in a ratio of 8:1:1, wherein the vehicle speed information is used as input data and the airbag status is used as a training label. The model is trained using the training set, the hyperparameters are adjusted to train the model multiple times, the model is selected using the validation set, the training results with higher accuracy on the validation set are selected, and the model performance is tested again on the test set. During the model training process, the LSTM (Long Short-Term Memory Network) block that can process time series information is used to process the vehicle speed information in different time periods respectively. After multi-layer abstract extraction by LSTM, the extracted information is spliced ​​together and then goes through batch normalization and multiple fully connected layers. The last fully connected layer has two nodes, and the weights of the two classifications are calculated through softmax, corresponding to the airbag deployment and non-deployment, respectively.

[0099] Among them, the LSTM model is expressed as:

[0100] i t =σ(W xi x t +W hi h t-1 +b i )

[0101] f t =σ(W xf x t +W hf h t-1 +b f )

[0102] o t =σ(W xo x t +W ho h t-1 +bo )

[0103]

[0104] h t =o t ☉tanh(C t )

[0105] Among them, i t represents the input gate, f t represents the forget gate, o t represents the output gate, C t Indicates the cell state, represents the candidate cell state, W and b represent the corresponding weight matrix and bias term, and ☉ represents element-wise multiplication.

[0106] In one embodiment, different time periods may be 3s, 5s, 10s, and 30s; 3 seconds, 5 seconds, 10 seconds, and 30 seconds are respectively used as a time window, and the vehicle speed information in different time windows is used as input, that is, 3 seconds is used as a time window, and the average value and maximum change value of the vehicle speed within 3 seconds are used as an input; 5 seconds is used as a time window, and the average value and maximum change value of the vehicle speed within 5 seconds are used as an input; 10 seconds is used as a time window, and the average value and maximum change value of the vehicle speed within 10 seconds are used as an input; 30 seconds is used as a time window, and the average value and maximum change value of the vehicle speed within 30 seconds are used as an input.

[0107] In one embodiment of the present application, before the step of performing a first detection on the collision risk of the target vehicle based on the collision signal, the method further includes:

[0108] Acquire first vehicle body state information, wherein the first vehicle body state information includes: high voltage information, gear position, and vehicle speed value of the vehicle;

[0109] When the vehicle is at high pressure, the gear is not the P gear, and the vehicle speed value is greater than zero, judging whether the vehicle speed value satisfies the first preset condition or / and the second preset condition; the first detection of the collision risk of the target vehicle is performed when the vehicle speed value satisfies the first preset condition or / and the second preset condition;

[0110] Among them, the first preset condition includes: there is a vehicle speed value at the first time and there is no vehicle speed value at the second time; the second preset condition includes: the first vehicle speed value corresponding to the first time is greater than the second vehicle speed value corresponding to the second time, and the difference between the first vehicle speed value and the second vehicle speed value is greater than the preset speed threshold.

[0111] The high pressure on the whole vehicle, the gear position being non-P gear, and the vehicle speed value being greater than zero are taken as preconditions, and subsequent processing is performed after screening through the preconditions. Then, screening is performed again through the first preset conditions and the second preset conditions, which can reduce the false alarm rate of the whole vehicle collision judgment.

[0112] It should be noted that the preset speed threshold can be set according to actual conditions, for example, the preset speed threshold is 60km / h. If the difference between the first speed value and the second speed value is greater than 60km / h, the speed suddenly changes, and it can be considered that the vehicle may collide, and the collision risk of the target vehicle is detected; if there is a speed value at the first time and no speed value at the second time, the speed signal is suddenly interrupted, and it can also be considered that the vehicle may collide, and the collision risk of the target vehicle needs to be detected.

[0113] In one embodiment of the present application, when the target vehicle has a first collision risk and the communication connection state between the target vehicle and the cloud service platform is normal, the second vehicle body state information transmitted by T-BOX to the cloud service platform is obtained, and the second vehicle body state information includes at least one of the following: main driver's door signal, passenger door signal, left rear door signal, right rear door signal, post-collision lower high voltage signal, BMS battery temperature signal, gear signal, vehicle speed value, airbag signal, ECALL signal. Of course, the second vehicle body state information can also be quickly stored in the IVI register (Interchangeable Virtual Instrument).

[0114] This application immediately and quickly stores the signals of the main driver's seat, co-driver's seat, left rear door and right rear door, the high-voltage signal after the collision, the BMS battery temperature signal, the gear signal, the vehicle speed signal, the airbag signal and the ECALL signal in the IVI register and the cloud platform, which is conducive to identifying market sentiment, immediately issuing background alarms, and assisting in effective and rapid rescue and handling at the scene of the accident.

[0115] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0116] Figure 5 is a block diagram of a collision recognition device shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown in FIG. 1 is specifically configured in the cloud service platform. The device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applied. Figure 5 As shown, a collision recognition device includes:

[0117] A data monitoring module 510 is used to monitor the collision signal of the target vehicle;

[0118] A first collision risk detection module 520, configured to perform a first detection of the collision risk of the target vehicle based on the collision signal to determine whether the target vehicle has a first collision risk;

[0119] A connection status determination module 530, configured to determine a communication connection status between the target vehicle and the cloud service platform when the target vehicle has a first collision risk;

[0120] A collision occurrence determination module 540, configured to determine that a collision occurs with the target vehicle when the communication connection state between the target vehicle and the cloud service platform is abnormal;

[0121] The second collision determination module 550 is used to obtain the vehicle speed information from the first time to the second time when the communication connection state between the target vehicle and the cloud service platform is normal, perform a second detection on the collision risk of the target vehicle based on the vehicle speed information to determine whether the target vehicle has a second collision risk, and determine whether the target vehicle collides according to the second collision risk; wherein the first time is earlier than the second time.

[0122] In one embodiment of the present application, the connection status determination module 530 is used to obtain the vehicle status data corresponding to the target vehicle in the cloud service platform when there is a first collision risk; detect the integrity of the vehicle status data; if there is data missing in the vehicle status data, determine that the communication connection status between the target vehicle and the cloud service platform is an abnormal state; if there is no data missing in the vehicle status data, determine that the communication connection status between the target vehicle and the cloud service platform is a normal state.

[0123] In one embodiment of the present application, the collision signal includes: a collision signal issued by an ABM controller, a first collision risk detection module obtains a collision signal issued by a real-time ABM controller; the collision signal issued by the real-time ABM controller is input into a pre-trained collision risk identification model, and the collision risk of the target vehicle is first detected by the collision risk identification model to determine whether the target vehicle has a first collision risk; wherein the collision risk identification model is trained with collision signals issued by historical ABM controllers as input and historical collision risks as output.

[0124] In one embodiment of the present application, the second collision determination module 550 is used to input the vehicle speed information from the first time to the second time into a pre-trained LSTM-based collision risk classification model, and classify the airbag status corresponding to the vehicle speed information through the collision risk classification model, the airbag status including the airbag being deployed and the airbag not being deployed, and the airbag being deployed indicates that the vehicle has a collision risk; wherein the LSTM-based collision risk classification model is trained using the vehicle speed information as training input data and the airbag status as training output data.

[0125] In one embodiment of the present application, the vehicle speed information includes: an average value and a maximum change value of the vehicle speed from the first time to the second time, and the maximum change value represents the difference between the maximum value and the minimum value of the vehicle speed.

[0126] In one embodiment of the present application, the device also includes a screening module for obtaining first vehicle body status information, the first vehicle body status information including: high voltage information, gear position, and vehicle speed value on the whole vehicle; when the high voltage is on the whole vehicle, the gear position is non-P gear, and the vehicle speed value is greater than zero, determine whether the vehicle speed value meets the first preset condition or the second preset condition; the first detection of the collision risk of the target vehicle is performed when the vehicle speed value meets the first preset condition or / and the second preset condition; wherein, the first preset condition includes: there is a vehicle speed value at the first time and there is no vehicle speed value at the second time; the second preset condition includes: the first vehicle speed value corresponding to the first time is greater than the second vehicle speed value corresponding to the second time, and the difference between the first vehicle speed value and the second vehicle speed value is greater than the preset speed threshold.

[0127] In one embodiment of the present application, when the target vehicle has a first collision risk and the communication connection status between the target vehicle and the cloud service platform is normal, second vehicle body status information transmitted by the T-BOX to the cloud service platform is obtained, and the second vehicle body status information includes at least one of the following: main driver's door signal, passenger driver's door signal, left rear door signal, right rear door signal, post-collision lower high-voltage signal, BMS battery temperature signal, gear signal, vehicle speed value, airbag signal, ECALL signal.

[0128] It should be noted that the collision recognition device provided in the above embodiment and the collision recognition method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the collision recognition device provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0129] An embodiment of the present application further provides a device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the memory implements the collision identification method in the above embodiment.

[0130] The embodiments of the present application further provide one or more machine-readable media on which instructions are stored, and when executed by one or more processors, the processors execute the collision identification method in the above embodiments.

[0131] Figure 6 The schematic diagram of the structure of a computer system suitable for implementing the memory of the embodiment of the present application is shown. It should be noted that: Figure 6 The computer system of the memory shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0132] like Figure 6 As shown, the computer system includes a central processing unit (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) or the program loaded from the storage part to the random access memory (RAM), such as the method in the above embodiment. In the RAM, various programs and data required for system operation are also stored. The CPU, ROM and RAM are connected to each other through a bus. The input / output (I / O) interface is also connected to the bus.

[0133] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., are installed on the drive as needed so that a computer program read therefrom is installed into the storage part as needed.

[0134] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the collision identification method implemented above. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), various functions defined in the system of the present application are executed.

[0135] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0136] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0137] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0138] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the collision identification method as described above. The computer-readable storage medium may be included in the memory described in the above embodiment, or may exist independently without being assembled into the memory.

[0139] Another aspect of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the collision identification method provided in each of the above embodiments.

[0140] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A collision identification method, applied to a cloud service platform, characterized in that: The method comprises: Monitor the collision signal of the target vehicle; performing a first detection of the collision risk of the target vehicle based on the collision signal to determine whether the target vehicle has a first collision risk; When the target vehicle has a first collision risk, determining a communication connection state between the target vehicle and a cloud service platform; If the communication connection state between the target vehicle and the cloud service platform is abnormal, it is determined that the target vehicle has collided; If the communication connection status between the target vehicle and the cloud service platform is normal, the vehicle speed information from the first time to the second time is obtained, and the collision risk of the target vehicle is secondly detected based on the vehicle speed information to determine whether the target vehicle has a second collision risk, and whether the target vehicle collides is determined according to the second collision risk; wherein the first time is earlier than the second time.

2. The collision recognition method according to claim 1, characterized in that: The step of determining the communication connection status between the target vehicle and the cloud service platform includes: Acquire vehicle status data corresponding to the target vehicle in the cloud service platform when the target vehicle has a first collision risk; Testing the integrity of the vehicle status data; If there is data missing in the vehicle status data, determining that the communication connection status between the target vehicle and the cloud service platform is abnormal; If there is no data missing in the vehicle status data, it is determined that the communication connection status between the target vehicle and the cloud service platform is normal.

3. The collision recognition method according to claim 1, characterized in that: The collision signal includes: a collision signal sent by the ABM controller, and the step of first detecting the collision risk of the target vehicle based on the collision signal includes: Get the collision signal from the real-time ABM controller; The collision signal emitted by the real-time ABM controller is input into a pre-trained collision risk identification model, and the collision risk of the target vehicle is first detected by the collision risk identification model to determine whether the target vehicle has a first collision risk; wherein the collision risk identification model is trained with the collision signal emitted by the historical ABM controller as input and the historical collision risk as output.

4. The collision recognition method according to claim 1, characterized in that: The step of performing a second detection on the collision risk of the target vehicle based on the vehicle speed information comprises: Inputting the vehicle speed information from the first time to the second time into a pre-trained LSTM-based collision risk classification model, and classifying the airbag status corresponding to the vehicle speed information through the collision risk classification model, wherein the airbag status includes airbag deployment and airbag non-deployment, and airbag deployment indicates that the vehicle has a collision risk; The LSTM-based collision risk classification model is trained using vehicle speed information as training input data and airbag status as training output data.

5. The collision recognition method according to claim 1 or 4, characterized in that: The vehicle speed information includes: an average value and a maximum change value of the vehicle speed from the first time to the second time, and the maximum change value represents a difference between a maximum value and a minimum value of the vehicle speed.

6. The collision identification method according to claim 1, characterized in that: Before the step of first detecting the collision risk of the target vehicle based on the collision signal, the method further includes: Acquire first vehicle body state information, wherein the first vehicle body state information includes: high voltage information, gear position, and vehicle speed value of the vehicle; When the vehicle is at high pressure, the gear is not the P gear, and the vehicle speed value is greater than zero, judging whether the vehicle speed value satisfies the first preset condition or / and the second preset condition; the first detection of the collision risk of the target vehicle is performed when the vehicle speed value satisfies the first preset condition or / and the second preset condition; Among them, the first preset condition includes: there is a vehicle speed value at the first time and there is no vehicle speed value at the second time; the second preset condition includes: the first vehicle speed value corresponding to the first time is greater than the second vehicle speed value corresponding to the second time, and the difference between the first vehicle speed value and the second vehicle speed value is greater than the preset speed threshold.

7. The collision identification method according to claim 1, characterized in that: When the target vehicle has a first collision risk and the communication connection status between the target vehicle and the cloud service platform is normal, second vehicle body status information transmitted by T-BOX to the cloud service platform is obtained, and the second vehicle body status information includes at least one of the following: a main driver's door signal, a passenger driver's door signal, a left rear door signal, a right rear door signal, a post-collision lower high-voltage signal, a BMS battery temperature signal, a gear signal, a vehicle speed value, an airbag signal, and an ECALL signal.

8. A collision recognition device, characterized in that: The device comprises: A data monitoring module, used to monitor the collision signal of the target vehicle; A first collision risk detection module, configured to perform a first detection of the collision risk of the target vehicle based on the collision signal to determine whether the target vehicle has a first collision risk; A connection status determination module, used to determine the communication connection status between the target vehicle and the cloud service platform when the target vehicle has a first collision risk; A collision occurrence determination module, used to determine that a collision occurs with the target vehicle when the communication connection state between the target vehicle and the cloud service platform is abnormal; The second collision determination module is used to obtain the vehicle speed information from the first time to the second time when the communication connection state between the target vehicle and the cloud service platform is normal, perform a second detection on the collision risk of the target vehicle based on the vehicle speed information to determine whether the target vehicle has a second collision risk, and determine whether the target vehicle collides according to the second collision risk; wherein the first time is earlier than the second time, and the first time and the second time are both preset vehicle speed information reporting times.

9. A device, characterized in that include: one or more processors; and A memory, used to store one or more programs, when the one or more programs are executed by the one or more processors, the memory implements the method according to any one of claims 1 to 7.

10. A machine-readable medium, characterized in that Instructions are stored thereon, which, when executed by one or more processors, cause the processors to perform the method according to any one of claims 1 to 7.

Images