Vehicle accident handling system, vehicle accident handling method, equipment and medium

Abstract

The invention provides a vehicle accident processing system, a vehicle accident processing method, equipment and a medium. The vehicle accident processing system comprises a vehicle-mounted terminal, a cloud processing module and a cloud response module, a vehicle-mounted terminal obtains multiple pieces of vehicle state data collected by multiple vehicle-mounted sensors, and when it is detected that a traffic accident happens to a vehicle based on the multiple pieces of vehicle state data, the multiple pieces of vehicle state data are sent to multiple theme partitions in a distributed cluster through a message production assembly; the cloud processing module obtains corresponding vehicle state data from the plurality of theme partitions through a message consumption component, and determines the severity level of the traffic accident based on the plurality of vehicle state data; and the cloud response module executes corresponding accident response measures according to the severity level. Through the system and the method, more accurate accident assessment and response decision are realized, dependence on manual intervention is reduced, and response speed and accuracy are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent vehicle technology, and more specifically, to a vehicle accident handling system, a vehicle accident handling method, a device and a medium. Background Art

[0002] In order to facilitate people's travel, the smooth flow of traffic roads has become increasingly important. However, in many cases, it is difficult to avoid vehicle accidents on the road. Vehicle accidents are sudden and destructive. Therefore, once a vehicle accident occurs, if rescue is not timely or on-site protection is not adequate, it is very easy to cause road paralysis or even secondary accidents, affecting people's safety and comfort. Therefore, timely detection of vehicle traffic accidents and timely response to vehicle traffic accidents are very important.

[0003] However, the vehicle accident handling system usually relies on the owner to manually call the police or trigger the emergency call button on the car, which is likely to result in a long response time, especially when the owner is injured or unable to operate. And with the development of vehicle networking technology, each vehicle will generate a large amount of status data and send it to the cloud so that the cloud can perform corresponding responses based on the status data, but traditional data processing systems are difficult to efficiently manage and analyze these huge data streams, which in turn leads to a longer time to provide assistance to users. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a vehicle accident handling system, a vehicle accident handling method, a device and a medium, which utilize Kafka's high-throughput message queue technology to achieve fast and reliable data transmission and processing, and can quickly and accurately process status data from a large number of vehicles, ensuring stable operation even under high concurrency conditions, significantly shortening the response time, achieving faster and more accurate accident assessment and response decisions, reducing dependence on manual intervention, improving response speed and accuracy, and improving rescue efficiency and road safety.

[0005] In a first aspect, an embodiment of the present application provides a vehicle accident handling system, the vehicle accident handling system comprising a vehicle terminal, a cloud processing module and a cloud response module;

[0006] The vehicle terminal is used to obtain multiple vehicle status data collected by multiple vehicle sensors. When a traffic accident is detected based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in the distributed cluster through the message production component; wherein each topic partition corresponds to a different type of vehicle status data;

[0007] The cloud processing module is used to obtain corresponding vehicle status data from the multiple subject partitions through the message consumption component, and determine the severity level of the traffic accident based on the multiple vehicle status data;

[0008] The cloud response module is used to execute corresponding accident response measures according to the severity level.

[0009] Furthermore, the plurality of vehicle status data includes vehicle acceleration, current vehicle location information, fault code status, airbag status, and vehicle surrounding images; when the cloud processing module is used to determine the severity level of the traffic accident based on the plurality of vehicle status data, the cloud processing module is also used to:

[0010] The plurality of vehicle status data are input into a pre-trained accident severity prediction model to determine the severity level of the traffic accident.

[0011] Furthermore, when the cloud processing module is used to determine the severity level of the traffic accident based on the multiple vehicle status data, the cloud processing module is also used to:

[0012] When it is detected that the duration of the vehicle acceleration being within the first acceleration interval is less than a first time threshold, it is considered that the severity level of the traffic accident is a minor accident;

[0013] When it is detected that the duration of the vehicle acceleration being in the second speed interval is greater than or equal to the first time threshold and less than the second time threshold, it is considered that the severity level of the traffic accident is a medium accident;

[0014] When it is detected that the duration of the vehicle acceleration being greater than the acceleration threshold is greater than or equal to the second time threshold, or when it is detected that the airbag state is a triggered state, the severity level of the traffic accident is considered to be a serious accident.

[0015] Furthermore, the cloud processing module includes a model training unit, and the model training unit is used to train the accident severity prediction model through the following steps:

[0016] Acquire multiple training samples; wherein each training sample includes vehicle status historical data and historical accident severity levels corresponding to the vehicle status historical data;

[0017] Inputting a plurality of the training samples into the original prediction model of accident severity level, and determining the severity level prediction value corresponding to the vehicle status historical data in each training sample;

[0018] Compare the historical accident severity level corresponding to the historical vehicle status data in each training sample with the severity level prediction value, and calculate the loss function of the original prediction model of the accident severity level in the current state;

[0019] Based on the loss function of the original prediction model of the accident severity level, the model parameters of the original prediction model of the accident severity level are continuously adjusted until the original prediction model of the accident severity level reaches a convergence state, thereby obtaining the accident severity level prediction model.

[0020] Furthermore, when the cloud response module is used to execute corresponding accident response measures according to the severity level, the cloud response module is also used to:

[0021] When the severity level is a minor accident or a moderate accident, corresponding accident notification information is generated based on the severity level, and the accident notification information is sent to the user terminal; wherein the accident notification information includes the time, location, severity level of the traffic accident, and recommended emergency measures corresponding to the severity level;

[0022] When the severity level is a serious accident, a call request is sent to the user terminal. When it is detected that the call request is accepted, a smart voice assistant is used to communicate with the user by voice to provide the user with accident assistance.

[0023] Furthermore, when the cloud response module is used to communicate with the user by voice using the intelligent voice assistant to provide accident assistance to the user, the cloud response module is also used to:

[0024] When the user's current emergency needs are determined based on the intelligent voice assistant, corresponding emergency measures are executed based on the current emergency needs, and the execution status of the emergency measures is recorded.

[0025] Furthermore, after the cloud response module executes corresponding accident response measures according to the severity level, the cloud response module is also used to:

[0026] A corresponding accident report is generated according to the multiple vehicle status data, the time of occurrence of the traffic accident, the location of occurrence of the traffic accident, the severity level of the traffic accident and the accident response measures.

[0027] In a second aspect, an embodiment of the present application further provides a vehicle accident handling method, which is applied to a vehicle accident handling system, wherein the vehicle accident handling system includes a vehicle-mounted terminal, a cloud processing module, and a cloud response module; the vehicle accident handling method includes:

[0028] The vehicle terminal obtains multiple vehicle status data collected by multiple vehicle sensors, and when a traffic accident is detected based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in the distributed cluster through the message production component; wherein each topic partition corresponds to a different type of vehicle status data;

[0029] The cloud processing module obtains corresponding vehicle status data from the multiple subject partitions through the message consumption component, and determines the severity level of the traffic accident based on the multiple vehicle status data;

[0030] The cloud response module executes corresponding accident response measures according to the severity level.

[0031] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the vehicle accident handling method as described above are performed.

[0032] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the vehicle accident handling method as described above are executed.

[0033] The embodiments of the present application provide a vehicle accident handling system, a vehicle accident handling method, a device and a medium, wherein the vehicle accident handling system includes a vehicle-mounted terminal, a cloud processing module and a cloud response module; the vehicle-mounted terminal obtains multiple vehicle status data collected by multiple vehicle-mounted sensors, and when a traffic accident is detected in the vehicle based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in a distributed cluster through a message production component; wherein each topic partition corresponds to a different type of vehicle status data; the cloud processing module obtains corresponding vehicle status data from the multiple topic partitions through a message consumption component, and determines the severity level of the traffic accident based on the multiple vehicle status data; the cloud response module executes corresponding accident response measures according to the severity level.

[0034] This application can quickly identify and judge the severity of an accident at the moment of the accident by collecting and analyzing vehicle status information in real time, so as to immediately initiate corresponding emergency measures to achieve more accurate accident assessment and response decisions, reduce reliance on manual intervention, and improve response speed and accuracy. At the same time, Kafka's high-throughput message queue technology is used to achieve fast and reliable data transmission and processing, which can quickly and accurately process status data from a large number of vehicles, ensuring stable operation even in high-concurrency situations, significantly shortening response time, and improving rescue efficiency and road safety.

[0035] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 One of the structural schematic diagrams of a vehicle accident handling system provided in an embodiment of the present application;

[0038] Figure 2 The second structural diagram of a vehicle accident handling system provided in an embodiment of the present application;

[0039] Figure 3 A flow chart of a vehicle accident handling method provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0042] First, the application scenarios to which the present application is applicable are introduced. The present application can be applied in the field of intelligent vehicle technology.

[0043] In order to facilitate people's travel, the smooth flow of traffic roads has become increasingly important. However, in many cases, it is difficult to avoid vehicle accidents on the road. Vehicle accidents are sudden and destructive. Therefore, once a vehicle accident occurs, if rescue is not timely or on-site protection is not adequate, it is very easy to cause road paralysis or even secondary accidents, affecting people's safety and comfort. Therefore, timely detection of vehicle traffic accidents and timely response to vehicle traffic accidents are very important.

[0044] Research has found that vehicle accident handling systems usually rely on the owner to manually call the police or trigger the emergency call button on the vehicle, which is likely to result in a long response time, especially when the owner is injured or unable to operate. And with the development of Internet of Vehicles technology, each vehicle will generate a large amount of status data and send it to the cloud so that the cloud can perform corresponding responses based on the status data. However, traditional data processing systems are difficult to efficiently manage and analyze these huge data streams, which in turn leads to a longer time to provide assistance to users.

[0045] Based on this, the embodiment of the present application provides a vehicle accident handling system to achieve faster and more accurate accident assessment and response decisions, reduce reliance on manual intervention, improve response speed and accuracy, and improve rescue efficiency and road safety.

[0046] See also Figure 1 , Figure 1 This is one of the structural diagrams of a vehicle accident handling system provided in an embodiment of the present application. Figure 1 As shown in , the vehicle accident handling system 100 provided in the embodiment of the present application includes a vehicle-mounted terminal 110 , a cloud processing module 120 and a cloud response module 130 .

[0047] The vehicle terminal 110 is used to obtain multiple vehicle status data collected by multiple vehicle sensors. When a traffic accident is detected based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in the distributed cluster through the message production component.

[0048] Here, the vehicle-mounted sensors may include an acceleration sensor, a GPS module, an OBD-II interface, an airbag sensor, and a camera installed on the vehicle. Specifically, according to the embodiment provided by the present application, the multiple vehicle status data include vehicle acceleration, current vehicle positioning information, fault code status, airbag status, and images around the vehicle. Among them, the acceleration sensor is used to detect the acceleration change of the vehicle, the GPS module is used to collect the current location information of the vehicle, the OBD-II interface is used to detect the fault code status of the vehicle, the airbag sensor is used to detect whether the vehicle's airbag is popped out and obtain the airbag status, and the camera is used to collect video data around the vehicle and obtain the impact around the vehicle.

[0049] Here, the distributed cluster refers to the Kafka cluster. Apache Kafka is a powerful and flexible distributed stream processing platform suitable for a variety of scenarios, including log collection, messaging, event-driven architecture, and real-time data analysis. Its high throughput, low latency, reliability, and scalability make it a key component in modern data architecture. Through reasonable design and configuration, Kafka can help organizations build efficient and reliable real-time data processing systems. The message production component refers to the Kafka Producer in the Kafka ecosystem, which is responsible for publishing messages to the client application of the Kafka cluster. The Producer is able to send messages to a specific Topic in the Kafka cluster, and the Producer supports asynchronous sending mode, allowing the producer to send messages to Kafka without waiting for confirmation, thereby improving throughput. Specifically, in the vehicle terminal 110, the Kafka Producer is configured using a Kafka client library (such as the Java Kafka Producer API) to set parameters such as the Broker address and Topic name. By configuring multiple Broker nodes, a high-availability Kafka cluster is formed. Topic partitions are Topic partitions in Kafka. In Kafka, Topic Partitions are the basic units for distributing data to Kafka clusters. Create multiple Topics. Specifically, each Topic partition corresponds to different types of vehicle status data. By setting a reasonable number of partitions and replicas, high concurrent processing capabilities and fault tolerance can be supported. The vehicle terminal sends the collected vehicle status data to the specified Topic through KafkaProducer.

[0050] Here, in the specific implementation, when the vehicle-mounted terminal 110 is started, each vehicle-mounted sensor connected to the vehicle-mounted terminal 110 is initialized. The vehicle-mounted terminal 110 reads the vehicle status data collected by each vehicle-mounted sensor through the I / O interface, and converts the collected vehicle status data into a unified data structure, such as into a JSON format. Then, the vehicle-mounted terminal 110 determines whether the vehicle is currently in a traffic accident based on the collected vehicle status data. Here, for example, when the vehicle acceleration is in the picture, or the airbag status is in the triggered state, or the fault code status is a fault, it is considered that the vehicle has been in a traffic accident. At this time, the data upload mechanism is immediately triggered, and the formatted vehicle status data is sent to the specified topic partition through the Kafka Producer.

[0051] The cloud processing module 120 is used to obtain corresponding vehicle status data from the multiple subject partitions through a message consumption component, and determine the severity level of the traffic accident based on the multiple vehicle status data.

[0052] Here, the cloud processing module 120 uses Apache Flink, which is a powerful distributed processing engine suitable for real-time data stream processing and batch processing. Its core features include low latency, high throughput, fault tolerance, and state management. Through reasonable architecture design and flexible APIs, Flink can help organizations build high-performance, reliable real-time data processing systems. Whether it is real-time data analysis, event-driven applications or ETL processing, Flink can provide strong support. Specifically, Apache Flink is used for real-time data processing and accident assessment. And Kafka Consumer is configured on the cloud processing module 120. Kafka Consumer is a client application responsible for consuming messages from the Kafka cluster. Consumer subscribes to one or more Topics and reads messages from the partitions of these Topics. The Kafka message consumption component is responsible for reading data from the specified Topic. Configure multiple consumer groups to realize parallel processing of data and improve the processing power of the system.

[0053] Here, in the specific implementation, the cloud processing module 120 obtains the corresponding vehicle status data from multiple Topic partitions through the Kafka message consumption component, and analyzes the data through preset algorithms and rules to determine the severity of the traffic accident. In this way, Kafka can handle large-scale data streams, support the processing of hundreds of thousands of messages per second, and is suitable for real-time processing of large-scale vehicle data. The Kafka cluster can be easily expanded to increase the processing power and storage capacity of the system by adding nodes to meet the future growth demand of data volume. As a high-performance message queue system, Kafka can achieve millisecond-level data transmission delays to ensure that vehicle status data can be uploaded to the cloud processing module 120 in real time. By integrating the real-time data processing framework Apache Flink, the cloud processing module 120 can process and analyze the data immediately after it arrives.

[0054] As an optional embodiment, when the cloud processing module 120 is used to determine the severity level of the traffic accident based on the multiple vehicle status data, the cloud processing module 120 is also used to:

[0055] The plurality of vehicle status data are input into a pre-trained accident severity prediction model to determine the severity level of the traffic accident.

[0056] Here, the accident severity level prediction model refers to a pre-trained model used to evaluate the severity level of the current traffic accident. As an example, the accident severity level prediction model can select a machine learning model, such as a random forest, a support vector machine, a neural network, etc., which is not specifically limited in this application.

[0057] Here, in the specific implementation, the cloud processing module 120 inputs the acquired multiple vehicle status data into a pre-trained accident severity prediction model, performs a comprehensive evaluation in combination with multiple sensor data, and determines the severity level of the traffic accident.

[0058] See also Figure 2 , Figure 2 This is a second structural diagram of a vehicle accident handling system provided in an embodiment of the present application. Figure 2 As shown, the cloud processing module 120 includes a model training unit 121. Specifically, the model training unit 121 is used to train the accident severity prediction model through the following steps:

[0059] A: Get multiple training samples.

[0060] Each training sample includes historical vehicle status data and historical accident severity levels corresponding to the historical vehicle status data.

[0061] B: Inputting the plurality of training samples into the original prediction model of accident severity level, and determining the severity level prediction value corresponding to the vehicle status historical data in each training sample.

[0062] Here, the severity level prediction value refers to the accident severity level corresponding to the vehicle status historical data predicted by the original accident severity level prediction model.

[0063] In the specific implementation of the above steps A-B, firstly, a plurality of training samples are obtained, each of which includes historical vehicle status data and historical accident severity levels corresponding to the historical vehicle status data. Then, the plurality of training samples are input into the original accident severity level prediction model to determine the severity level prediction value corresponding to the historical vehicle status data in each training sample.

[0064] C: Compare the historical accident severity level corresponding to the historical vehicle status data in each training sample with the severity level prediction value, and calculate the loss function of the original prediction model of the accident severity level under the current state.

[0065] D: Based on the loss function of the original prediction model of the accident severity level, the model parameters of the original prediction model of the accident severity level are continuously adjusted until the original prediction model of the accident severity level reaches a convergence state, thereby obtaining the accident severity level prediction model.

[0066] It should be noted that the loss function is a function that maps the value of a random event or its related random variables to a non-negative real number to represent the "risk" or "loss" of the random event. In applications, the loss function is usually associated with the optimization problem as a learning criterion, that is, the model is solved and evaluated by minimizing the loss function.

[0067] With respect to the above steps (3) to (4), in the specific implementation, for each training sample, the historical accident severity level corresponding to the historical data of the vehicle status in the training sample is compared with the predicted value of the severity level. By comparing the historical accident severity level with the predicted value of the severity level, it is determined whether the prediction of the original prediction model of the accident severity level is accurate. When the historical accident severity level corresponding to the historical data of the vehicle status is different from the predicted value of the severity level, it is considered that the prediction of the original prediction model of the accident severity level is inaccurate. At this time, it is necessary to calculate the loss function of the original prediction model of the accident severity level in the current state. The method of calculating the loss function is described in detail in the prior art and will not be described in detail here. Then, the model parameters of the original prediction model of the accident severity level are continuously adjusted. The original prediction model of the accident severity level will continuously minimize the loss through iteration. At each step of the iteration, the loss value of the original prediction model of the accident severity level will be calculated. When the loss value of the original prediction model of the accident severity level cannot reach the loss threshold, the model parameters of the original prediction model of the accident severity level are continuously updated, and the new parameters will calculate a new loss value, so that the loss value shows a fluctuating downward trend during the iteration process. Finally, when the loss value reaches smoothness, that is, when the loss value of the trained accident severity level original prediction model is not greater than the loss threshold, that is, when the loss value does not drop significantly compared with the loss value calculated last time, it is considered that the accident severity level original prediction model has reached a convergence state, and the prediction of the accident severity level original prediction model at this time is relatively accurate. At this time, the training is terminated and the accident severity level prediction model is obtained. In this way, the historical data is analyzed and learned through the accident severity level original prediction model, so as to achieve accurate prediction of traffic accident severity levels and provide users with a better service experience.

[0068] As an optional embodiment, when the cloud processing module 120 is used to determine the severity level of the traffic accident based on the multiple vehicle status data, the cloud processing module 120 is also used to:

[0069] I: When it is detected that the duration of the vehicle acceleration being within the first acceleration interval is less than a first time threshold, it is considered that the severity level of the traffic accident is a minor accident.

[0070] Here, when the vehicle is driving normally, the acceleration passes through -0.5m / s 2 ~0.5m / s 2 As an example, the first acceleration interval can be set to 0.5 m / s 2 ~2m / s 2 , the acceleration is slightly higher than the normal range, but does not reach the serious threshold, which can be considered a minor accident. The first time threshold can be set to 1 second. This application does not make specific restrictions on this.

[0071] Regarding the above step I, in the specific implementation, when it is detected that the vehicle acceleration is within the first acceleration interval and the duration is short, for example, the duration is less than 1 second, the severity level of the traffic accident is considered to be a minor accident.

[0072] II: When it is detected that the duration of the vehicle acceleration being in the second speed interval is greater than or equal to the first time threshold and less than the second time threshold, it is considered that the severity level of the traffic accident is a medium accident.

[0073] Here, as an example, the second acceleration interval can be set to 2m / s 2 ~4m / s 2 The second time threshold can be set to 2 seconds, which is not specifically limited in this application.

[0074] For the above step II, when it is detected that the vehicle acceleration is within the second acceleration range and the duration is greater than or equal to the first time threshold and less than the second time threshold, for example, when the duration is greater than or equal to 1 second and less than 2 seconds, the severity level of the traffic accident is considered to be a medium accident.

[0075] III: When it is detected that the duration of the vehicle acceleration being greater than the acceleration threshold is greater than or equal to the second time threshold, or when it is detected that the airbag state is in a triggered state, the severity level of the traffic accident is considered to be a serious accident.

[0076] Here, as an example, the acceleration threshold can be set to 4 m / s 2 , this application does not make any specific limitation on this.

[0077] Airbag deployment is usually direct evidence of a serious collision. If the airbag sensor detects that the airbag is deployed, that is, the airbag is in a triggered state, it is further confirmed as a serious accident. Regarding the above step III, in the specific implementation, when it is detected that the vehicle acceleration is greater than the acceleration threshold and the duration is greater than or equal to the second time threshold, the severity level of the traffic accident is considered to be a serious accident. Alternatively, when it is detected that the airbag is in a triggered state, the severity level of the traffic accident is considered to be a serious accident.

[0078] The cloud response module 130 is used to execute corresponding accident response measures according to the severity level.

[0079] The system can set the priority of notifications based on the severity of the accident and the owner's preferences. For example, in the case of a serious accident, phone notifications are prioritized; in the case of a minor accident, SMS and APP push notifications can be used first.

[0080] Here, the cloud response module 130 is mainly used to execute corresponding response measures according to the determined severity level of the traffic accident. In specific implementation, the cloud response module 130 executes corresponding accident response measures according to the severity level of the traffic accident.

[0081] As an optional embodiment, when the cloud response module 130 is used to execute the corresponding accident response measures according to the severity level, the cloud response module 130 is further used to:

[0082] (1) When the severity level is a minor accident or a moderate accident, corresponding accident notification information is generated based on the severity level, and the accident notification information is sent to the user terminal.

[0083] Specifically, the accident notification information includes the time, location, severity level, and recommended emergency measures corresponding to the severity level of the traffic accident.

[0084] With respect to the above step (1), in the specific implementation, when the cloud response module 130 determines that the severity level of the traffic accident is a minor accident or a moderate accident, the corresponding accident notification information is generated based on the severity level, and the accident notification information is sent to the user terminal. Specifically, the accident notification information can be sent to the user terminal in the form of text messages or APP push. When the accident notification information is sent in the form of text messages, the cloud response module 130 can send text messages multiple times within a certain period of time to ensure that the car owner can receive the accident notification information. When the accident notification information is pushed to the user terminal via the APP, the car owner can view detailed accident information on the user terminal and obtain emergency guidance. The push notification can contain more multimedia content, such as pictures and videos. At the same time, the mobile application of the user terminal can provide one-click alarm, call ambulance and other functions, so that the car owner can take quick action. In addition, the application can also display nearby rescue resources and service information.

[0085] (2) When the severity level is a serious accident, a call request is sent to the user terminal. When it is detected that the call request is accepted, a smart voice assistant is used to communicate with the user by voice to provide the user with accident assistance.

[0086] Regarding the above step (2), in the specific implementation, when the cloud response module 130 determines that the severity of the traffic accident is a serious accident, the user is notified by phone. The cloud response module 130 sends a call request to the user terminal. When it is detected that the call request is accepted, the cloud response module 130 uses an intelligent voice assistant (such as Amazon Alexa, Google Assistant) to communicate with the user by voice, providing the user with accident assistance and providing a quick response in an emergency. If the user has not answered the call, the cloud response module 130 will try to call multiple times within a certain period of time until the call is connected.

[0087] As an optional embodiment, when the cloud response module 130 is used to communicate with the user by voice using the intelligent voice assistant to provide accident assistance to the user, the cloud response module 130 is also used to:

[0088] When the user's current emergency needs are determined based on the intelligent voice assistant, corresponding emergency measures are executed based on the current emergency needs, and the execution status of the emergency measures is recorded.

[0089] Here, specifically, the cloud response module also integrates an emergency service system, which can send out alarms through API calls or phone calls, and integrates a medical emergency system, which can dispatch an ambulance through API calls or phone calls.

[0090] With respect to the above steps, in the specific implementation, when the cloud response module 130 determines the user's current emergency needs based on the intelligent voice assistant, it executes corresponding emergency measures based on the current emergency needs and records the execution of the emergency measures. Here, the current emergency needs may include alarming and calling an ambulance. When it is determined that the user's current emergency need is to alarm, the cloud response module 130 issues an alarm through an API call or a phone call; when it is determined that the user's current emergency need is to call an ambulance, the cloud response module 130 dispatches an ambulance through an API call or a phone call.

[0091] As an optional embodiment, the cloud response module 130 also automatically forwards the notification message of the traffic accident to the customer service center. After receiving the notification, the customer service staff of the customer service center will immediately contact the car owner to inquire about his / her condition and suggest calling the police or an ambulance according to the situation. If the car owner cannot answer the call, the cloud response module 130 can continue to try to contact the car owner through SMS or APP push. The customer service staff will record the situation of each contact and follow up if necessary.

[0092] As an optional embodiment, after the cloud response module 130 executes the corresponding accident response measures according to the severity level, the cloud response module 130 is further configured to:

[0093] A corresponding accident report is generated according to the multiple vehicle status data, the time of occurrence of the traffic accident, the location of occurrence of the traffic accident, the severity level of the traffic accident and the accident response measures.

[0094] With respect to the above steps, in specific implementation, after executing the corresponding accident response measures according to the severity level, the cloud response module 130 generates a corresponding accident report according to multiple vehicle status data, the time of occurrence of the traffic accident, the location of the traffic accident, the severity level of the traffic accident, and the accident response measures, and uses HDFS or a relational database (such as MySQL) to store the processed data and accident report. In this way, the processed data and accident report are stored in a persistent storage system for easy subsequent query and analysis.

[0095] As an optional embodiment, the cloud response module 130 can also generate corresponding accident information according to the severity of the traffic accident, and send the accident information through the social media platform to remind other car owners and their relatives and friends to pay attention to safety. The car owner can also share the accident information to his or her social media account through the user terminal with one click to obtain more help and support.

[0096] The vehicle accident handling system provided in the embodiment of the present application includes a vehicle-mounted terminal, a cloud processing module and a cloud response module; the vehicle-mounted terminal obtains multiple vehicle status data collected by multiple vehicle-mounted sensors, and when a traffic accident is detected in the vehicle based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in the distributed cluster through a message production component; wherein each topic partition corresponds to a different type of vehicle status data; the cloud processing module obtains the corresponding vehicle status data from the multiple topic partitions through a message consumption component, and determines the severity level of the traffic accident based on the multiple vehicle status data; the cloud response module executes corresponding accident response measures according to the severity level.

[0097] This application can quickly identify and judge the severity of an accident at the moment of the accident by collecting and analyzing vehicle status information in real time, so as to immediately initiate corresponding emergency measures to achieve more accurate accident assessment and response decisions, reduce reliance on manual intervention, and improve response speed and accuracy. At the same time, Kafka's high-throughput message queue technology is used to achieve fast and reliable data transmission and processing, which can quickly and accurately process status data from a large number of vehicles, ensuring stable operation even in high-concurrency situations, significantly shortening response time, and improving rescue efficiency and road safety.

[0098] See also Figure 3 , Figure 3 A flow chart of a vehicle accident handling method provided in an embodiment of the present application. A vehicle accident handling method provided in an embodiment of the present application is applied to a vehicle accident handling system, wherein the vehicle accident handling system includes an on-board terminal, a cloud processing module, and a cloud response module; Figure 3 As shown, the vehicle accident handling method includes:

[0099] S301, the vehicle terminal obtains multiple vehicle status data collected by multiple vehicle sensors, and when a traffic accident is detected based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in the distributed cluster through a message production component; wherein each topic partition corresponds to a different type of vehicle status data;

[0100] S302, the cloud processing module obtains corresponding vehicle status data from the multiple subject partitions through the message consumption component, and determines the severity level of the traffic accident based on the multiple vehicle status data;

[0101] S303, the cloud response module executes corresponding accident response measures according to the severity level.

[0102] Furthermore, the plurality of vehicle status data includes vehicle acceleration, current vehicle location information, fault code status, airbag status, and vehicle surrounding images; the cloud processing module determines the severity level of the traffic accident based on the plurality of vehicle status data, including:

[0103] The plurality of vehicle status data are input into a pre-trained accident severity prediction model to determine the severity level of the traffic accident.

[0104] Furthermore, the cloud processing module determines the severity level of the traffic accident based on the multiple vehicle status data, including:

[0105] When it is detected that the duration of the vehicle acceleration being within the first acceleration interval is less than a first time threshold, it is considered that the severity level of the traffic accident is a minor accident;

[0106] When it is detected that the duration of the vehicle acceleration being in the second speed interval is greater than or equal to the first time threshold and less than the second time threshold, it is considered that the severity level of the traffic accident is a medium accident;

[0107] When it is detected that the duration of the vehicle acceleration being greater than the acceleration threshold is greater than or equal to the second time threshold, or when it is detected that the airbag state is a triggered state, the severity level of the traffic accident is considered to be a serious accident.

[0108] Furthermore, the cloud processing module includes a model training unit, and the model training unit trains the accident severity prediction model through the following steps:

[0109] Acquire multiple training samples; wherein each training sample includes vehicle status historical data and historical accident severity levels corresponding to the vehicle status historical data;

[0110] Inputting a plurality of the training samples into the original prediction model of accident severity level, and determining the severity level prediction value corresponding to the vehicle status historical data in each training sample;

[0111] Compare the historical accident severity level corresponding to the historical vehicle status data in each training sample with the severity level prediction value, and calculate the loss function of the original prediction model of the accident severity level in the current state;

[0112] Based on the loss function of the original prediction model of the accident severity level, the model parameters of the original prediction model of the accident severity level are continuously adjusted until the original prediction model of the accident severity level reaches a convergence state, thereby obtaining the accident severity level prediction model.

[0113] Furthermore, the cloud response module executes corresponding accident response measures according to the severity level, including:

[0114] When the severity level is a minor accident or a moderate accident, corresponding accident notification information is generated based on the severity level, and the accident notification information is sent to the user terminal; wherein the accident notification information includes the time, location, severity level of the traffic accident, and recommended emergency measures corresponding to the severity level;

[0115] When the severity level is a serious accident, a call request is sent to the user terminal. When it is detected that the call request is accepted, a smart voice assistant is used to communicate with the user by voice to provide the user with accident assistance.

[0116] Furthermore, the cloud response module uses an intelligent voice assistant to communicate with the user by voice to provide accident assistance to the user, including:

[0117] When the user's current emergency needs are determined based on the intelligent voice assistant, corresponding emergency measures are executed based on the current emergency needs, and the execution status of the emergency measures is recorded.

[0118] Furthermore, after the cloud response module executes corresponding accident response measures according to the severity level, the vehicle accident handling method further includes:

[0119] A corresponding accident report is generated according to the multiple vehicle status data, the time of occurrence of the traffic accident, the location of occurrence of the traffic accident, the severity level of the traffic accident and the accident response measures.

[0120] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4As shown in , the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .

[0121] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned Figure 3 The specific implementation of the steps of the vehicle accident handling method in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0122] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 3 The specific implementation of the steps of the vehicle accident handling method in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0127] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0128] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0129] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A vehicle accident handling system, characterized in that: The vehicle accident handling system includes a vehicle terminal, a cloud processing module and a cloud response module; The vehicle terminal is used to obtain multiple vehicle status data collected by multiple vehicle sensors. When a traffic accident is detected based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in the distributed cluster through the message production component; wherein each topic partition corresponds to a different type of vehicle status data; The cloud processing module is used to obtain corresponding vehicle status data from the multiple subject partitions through the message consumption component, and determine the severity level of the traffic accident based on the multiple vehicle status data; The cloud response module is used to execute corresponding accident response measures according to the severity level.

2. The vehicle accident handling system according to claim 1, characterized in that: The plurality of vehicle status data includes vehicle acceleration, current vehicle location information, fault code status, airbag status, and vehicle surrounding images; when the cloud processing module is used to determine the severity level of the traffic accident based on the plurality of vehicle status data, the cloud processing module is also used to: The plurality of vehicle status data are input into a pre-trained accident severity prediction model to determine the severity level of the traffic accident.

3. The vehicle accident handling system according to claim 2, characterized in that: When the cloud processing module is used to determine the severity level of the traffic accident based on the plurality of vehicle status data, the cloud processing module is further used to: When it is detected that the duration of the vehicle acceleration being within the first acceleration interval is less than a first time threshold, it is considered that the severity level of the traffic accident is a minor accident; When it is detected that the duration of the vehicle acceleration being in the second speed interval is greater than or equal to the first time threshold and less than the second time threshold, it is considered that the severity level of the traffic accident is a medium accident; When it is detected that the duration of the vehicle acceleration being greater than the acceleration threshold is greater than or equal to the second time threshold, or when it is detected that the airbag state is a triggered state, the severity level of the traffic accident is considered to be a serious accident.

4. The vehicle accident handling system according to claim 2, characterized in that: The cloud processing module includes a model training unit, which is used to train the accident severity prediction model through the following steps: Acquire multiple training samples; wherein each training sample includes vehicle status historical data and historical accident severity levels corresponding to the vehicle status historical data; Inputting a plurality of the training samples into the original prediction model of accident severity level, and determining the severity level prediction value corresponding to the vehicle status historical data in each training sample; Compare the historical accident severity level corresponding to the historical vehicle status data in each training sample with the severity level prediction value, and calculate the loss function of the original prediction model of the accident severity level in the current state; Based on the loss function of the original prediction model of the accident severity level, the model parameters of the original prediction model of the accident severity level are continuously adjusted until the original prediction model of the accident severity level reaches a convergence state, thereby obtaining the accident severity level prediction model.

5. The vehicle accident handling system according to claim 1, characterized in that: When the cloud response module is used to execute corresponding accident response measures according to the severity level, the cloud response module is also used to: When the severity level is a minor accident or a moderate accident, corresponding accident notification information is generated based on the severity level, and the accident notification information is sent to the user terminal; wherein the accident notification information includes the time, location, severity level of the traffic accident, and recommended emergency measures corresponding to the severity level; When the severity level is a serious accident, a call request is sent to the user terminal. When it is detected that the call request is accepted, a smart voice assistant is used to communicate with the user by voice to provide the user with accident assistance.

6. The vehicle accident handling system according to claim 5, characterized in that: When the cloud response module is used to communicate with the user by voice using the intelligent voice assistant to provide accident assistance to the user, the cloud response module is also used to: When the user's current emergency needs are determined based on the intelligent voice assistant, corresponding emergency measures are executed based on the current emergency needs, and the execution status of the emergency measures is recorded.

7. The vehicle accident handling system according to claim 1, characterized in that: After the cloud response module executes the corresponding accident response measures according to the severity level, the cloud response module is further used to: A corresponding accident report is generated according to the multiple vehicle status data, the time of occurrence of the traffic accident, the location of occurrence of the traffic accident, the severity level of the traffic accident and the accident response measures.

8. A vehicle accident handling method, characterized in that: The vehicle accident handling method is applied to the vehicle accident handling system as claimed in any one of claims 1 to 7, wherein the vehicle accident handling system comprises a vehicle-mounted terminal, a cloud processing module and a cloud response module; The vehicle accident handling method comprises: The vehicle terminal obtains multiple vehicle status data collected by multiple vehicle sensors, and when a traffic accident is detected based on the multiple vehicle status data, the multiple vehicle status data are sent to multiple topic partitions in the distributed cluster through the message production component; wherein each topic partition corresponds to a different type of vehicle status data; The cloud processing module obtains corresponding vehicle status data from the multiple subject partitions through the message consumption component, and determines the severity level of the traffic accident based on the multiple vehicle status data; The cloud response module executes corresponding accident response measures according to the severity level.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the vehicle accident handling method as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the vehicle accident handling method as claimed in claim 8 are executed.

Images