Vehicle state monitoring and early warning method and system

Abstract

The invention belongs to the technical field of vehicle state detection and early warning, and particularly relates to a vehicle state monitoring and early warning method and system.The monitoring and early warning method comprises the steps that a sensor obtains real-time data, an anomaly detection algorithm is applied, and an abnormal event is marked; calculating an information priority according to the abnormal severity and the driving scene, and distributing the information priority to a high-priority queue; multi-mode early warning is generated, and high-frequency sound and vibration are used during high-speed driving; extracting a voice prompt, and generating voice waveform data through a voice synthesis module; voice input of a driver is recognized, intention is analyzed, and abnormal information feedback is provided; according to the scene and the abnormal state, interactive output is optimized, and detailed information is displayed during low-speed congestion; dynamically adjusting the interface of the instrument panel, and amplifying the key area in case of abnormal severity; and integrating the image data and the voice data, generating a multi-mode signal, and transmitting the multi-mode signal after rendering processing. The vehicle abnormal information can be timely and accurately transmitted to a driver, and the driving safety is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle status detection and warning, and particularly relates to a vehicle status monitoring and warning method and system. Background Art

[0002] Vehicle status monitoring and warning technology plays a crucial role in the modern automotive industry. It is directly related to driving safety, vehicle performance maintenance, and the improvement of user experience. With the rapid development of intelligent driving and vehicle networking technologies, higher expectations are placed on vehicle status monitoring systems. They not only need to perceive the vehicle's operating conditions in real time but also provide intuitive and timely feedback to the driver through a human-machine interface. However, many current solutions still have obvious deficiencies in practical applications, restricting the full play of their functions.

[0003] Existing vehicle status monitoring systems often have limitations in information presentation and interaction methods. Many systems only provide a single dashboard display, with complex and unclassified information, making it difficult for drivers to quickly obtain key abnormal information. In addition, some systems rely only on a single prompt method, such as lights or text, for abnormal warnings, which are easily overlooked. Especially in complex driving environments, it is difficult to effectively attract the driver's attention. At the same time, traditional systems lack flexibility in human-machine interaction. Drivers need to operate manually when querying status information, increasing the risk of driving distraction.

[0004] These limitations reflect the core technical challenges faced in this field. First, the dynamic hierarchical display of information is a difficult problem. How to dynamically adjust the display content according to the importance of the status, ensuring both the simplicity of daily driving and providing detailed feedback in case of abnormalities, has not been fully solved. Second, the integration of multi-modal warning mechanisms is difficult. A single prompt method is difficult to adapt to different driving scenarios, and multiple methods such as sound and images need to be combined to improve the warning effect. Finally, the intelligence level of voice interaction is insufficient. Existing systems perform poorly in the accuracy of voice recognition and the real-time response of commands, making it difficult to meet the driver's convenient query needs during driving.

[0005] Therefore, how to design a system that can dynamically hierarchically display vehicle status information, integrate a multi-modal warning mechanism, and support intelligent voice interaction to achieve efficient information transmission and low driver distraction operations has become a key issue in the field of vehicle status monitoring and warning. Summary of the Invention

[0006] Aiming at the deficiencies of the prior art, the present invention provides a vehicle status monitoring and warning method and system, which can timely and accurately transmit vehicle abnormal information to the driver, effectively improving driving safety.

[0007] To achieve the above object, the technical solution of the present invention is: A vehicle status monitoring and warning method, the method comprising: S1. Obtain real-time status data from vehicle sensors, and preliminarily screen the data through a preset anomaly detection algorithm. If a parameter exceeds a preset threshold, it is marked as an abnormal event to obtain an abnormal trend set; S2. For the abnormal trend set, use a dynamic grading display algorithm to calculate the information presentation priority according to the abnormal severity and driving scenario complexity. If the information presentation priority score is higher than a preset threshold, the abnormal information is assigned to a high-priority display queue to determine the dynamic grading display content; S3. Generate a multimodal warning signal according to the dynamic grading display content. If the driving scenario is high-speed driving, high-frequency sound and vibration feedback are preferentially used to obtain a multimodal warning combination; the multimodal warning signal includes sound prompts, dashboard images, and tactile feedback; S4. Extract the audio signal of the sound prompt part from the multimodal warning combination, and synthesize the extracted audio signal through a speech synthesis module to generate speech waveform data described in natural language; S5. Obtain the driver's voice input, semantically parse the input command through a speech recognition model. If the recognition result contains an intention to query the status, extract abnormal information from the abnormal trend set, generate speech interaction response content, and determine the interaction feedback information; S6. According to the interaction feedback information, combined with the current driving scenario and abnormal state, judge the scenario type. If the scenario is low-speed congestion, detailed feedback content is displayed through the dashboard, otherwise concise information is preferentially output through voice to obtain optimized interaction output; S7. Extract the display content from the optimized interaction output, and dynamically adjust the dashboard interface through an image processing module. If the abnormal feedback detail level is higher than a preset threshold, the key abnormal area is enlarged to generate a final display interface; S8. Obtain the image and voice data of the final display interface, integrate the image and voice data into a unified data stream to obtain a multimodal signal, perform rendering processing on the multimodal signal to generate an image and voice data stream adapted to the vehicle terminal, obtain a rendered transmission signal, transmit the rendered transmission signal to the vehicle terminal, and measure the transmission delay. If the transmission delay is lower than a preset threshold, it is determined that the signal transmission meets the requirements.

[0008] Preferably, the obtaining real-time status data from vehicle sensors, preliminarily screening the data through a preset anomaly detection algorithm, and if a parameter exceeds a preset threshold, marking it as an abnormal event to obtain an abnormal trend set includes: Obtain real-time data transmitted by vehicle sensors, including data on engine speed, brake pressure, and tire pressure, and remove noise through mean filtering to generate a standardized data set; Preliminarily screen the parameters in the standardized dataset through an anomaly detection algorithm. If any one of the parameters exceeds the preset threshold, mark it as an abnormal event using the fixed threshold judgment method, and classify the abnormal events using the K-Means algorithm to obtain an abnormal event set; For the abnormal event set, extract the timestamps and parameter values of each type of abnormal event to generate an abnormal feature dataset, and use a decision tree algorithm to predict the development trend of the abnormal events for the abnormal feature dataset to obtain an abnormal trend set.

[0009] Preferably, the abnormal severity includes the abnormal occurrence frequency, the influence range, and the potential risk level; the driving scenario complexity includes the current number of lanes, the distance to the vehicle ahead, and the weather visibility.

[0010] Preferably, the specific method for determining the dynamically graded display content includes: S201. According to the abnormal occurrence frequency, the influence range, and the potential risk level, calculate the abnormal severity score using the weighted scoring method. When calculating the abnormal severity score, set the weight of the abnormal occurrence frequency to 0.4, the weight of the influence range to 0.3, and the weight of the potential risk level to 0.3. The calculation formula for the abnormal severity score is: , where represents the abnormal severity score, represents the abnormal occurrence frequency score, represents the influence range score, represents the potential risk level score; S202. According to the factors of the current number of lanes, the distance to the vehicle ahead, and the weather visibility, calculate the driving scenario complexity score. The calculation formula is as follows:

[0011] where C represents the driving scenario complexity score, represents the number of evaluation factors, represents the weight of the th factor, represents the th factor score value; S203. According to the abnormal severity score and the driving scenario complexity score, calculate the information presentation priority score using the linear weighted method. When calculating, set the weight of the abnormal severity score to 0.6 and the weight of the driving scenario complexity score to 0.4. The calculation formula is expressed as: , where represents the information presentation priority score, represents the abnormal severity score, and C represents the driving scenario complexity score; S204. If the information presentation priority score is higher than the preset threshold, then allocate the abnormal information to the high-priority display queue, and use the sliding window algorithm to update the high-priority display queue in real time to ensure that high-priority information can be presented in a timely manner.

[0012] Preferably, the method for generating the multi-modal warning signal is as follows: Obtain driving scenario data from the vehicle-mounted millimeter-wave radar and camera, including three features: vehicle speed, acceleration, and lane line curvature. Use a random forest classifier to determine whether the current scenario is a high-speed driving scenario. When the classification confidence is greater than the preset threshold, it is determined as a high-speed scenario. In a high-speed scenario, set the sound signal frequency to 3000 - 5000 Hz and the vibration intensity to 0.5 - 1.2 G as the priority signal parameters, and generate an initial warning signal set according to the priority configuration, including three parameters: sound frequency, vibration intensity, and duration. Extract the sound frequency and duration parameters from the initial warning signal set and input them into the dashboard display module to generate an image signal with a flashing red border. Use the weighted average fusion algorithm to integrate the sound signal, vibration signal, and image signal. When calculating, set the sound weight to 0.4, the vibration weight to 0.3, and the image weight to 0.3. The weighted average fusion algorithm is expressed as: , where represents the fused signal, represents the sound signal, represents the vibration signal, represents the image signal; Encode the fused signal into the CAN bus protocol format and output it to the speaker, vibration motor, and display screen through the vehicle control unit to generate a multi-modal warning signal.

[0013] Preferably, extract the audio signal of the sound prompt part from the multi-modal warning combination, and synthesize the extracted audio signal through the speech synthesis module to generate speech waveform data described in natural language, including: Intercept the audio signal in the 20 Hz - 20 kHz frequency band from the multi-modal warning combination to obtain the sound prompt signal, and calculate the Mel-frequency cepstral coefficients of the sound prompt signal to obtain the audio feature vector. Input the audio feature vector into a pre-trained support vector machine classifier to output the abnormal type label and abnormal severity score. If the abnormal type label is an emergency brake failure, read and parse the vehicle fault code through the OBD-II interface to obtain the fault location code. Input the abnormal type label, abnormal severity score, and fault location code into the speech synthesis module to generate speech waveform data described in natural language.

[0014] Preferably, based on the interactive feedback information, combined with the current driving scenario and abnormal state, the scenario type is judged. If the scenario is low-speed congestion, detailed feedback content is displayed through the instrument panel; otherwise, concise information is preferentially output through voice to obtain an optimized interactive output, including: Obtain real-time data from vehicle sensors and user interaction interfaces, analyze the driving environment and interactive feedback information, and determine the feature description of the current state; According to the feature description of the current state, combined with the pre-established scenario classification model, use the support vector machine algorithm to classify the driving environment and abnormal state, and judge whether it belongs to the low-speed congestion scenario; If the classification result is a low-speed congestion scenario, generate detailed feedback content through the instrument panel display module, including the specific description of the current state and recommended operations, to obtain a visual output result; The specific description of the current state includes the current vehicle speed and the length of the congestion ahead, and the recommended operations include suggesting that the driver be patient or choose a detour route; If the classification result does not belong to the low-speed congestion scenario, generate concise information through the speech synthesis module, including the key tips of the current state, to obtain the voice output content; For the generated detailed feedback content or concise information, obtain the response data of the user interaction interface, analyze the acceptance degree of the user for the output method, and determine the adjustment direction of the optimization plan; According to the analysis result of the user response data, adjust the priority and content form of the output method, generate an updated interactive plan, and complete the optimization process of scenario adaptation.

[0015] Preferably, extract the display content from the optimized interactive output, dynamically adjust the instrument panel interface through the image processing module. If the detailed degree of abnormal feedback is higher than the preset threshold, enlarge the key abnormal information area to generate the final display interface, including: Obtain the original display content in JSON format from the interactive output, and extract the digital scale and pointer angle of the instrument panel interface through the image processing module to generate structured display data including values and coordinates; According to the value range in the structured display data, adjust the color contrast and scale line width of the instrument panel, output the preliminary adjusted interface in bitmap format, calculate the abnormal score of each pixel block in the preliminary adjusted interface, and mark it as an abnormal area when the abnormal score of the pixel block exceeds the preset threshold; Extract the area larger than 50 pixels from the abnormal area, record its center coordinates and bounding box size as key abnormal data, enlarge the display ratio of the key abnormal area by 2 times to generate an enlarged bitmap of the abnormal area, and superimpose the enlarged bitmap of the abnormal area on the corresponding coordinates of the preliminary adjusted interface to output the final display interface.

[0016] A vehicle status monitoring and warning system, the system comprising: Data acquisition and processing module: used to obtain real-time status data from vehicle sensors, preliminarily screen the data, and if the parameters exceed the preset threshold, mark it as an abnormal event and generate an abnormal trend set; Priority calculation and allocation module: used to calculate the information presentation priority according to the abnormal severity and driving scenario complexity. If the information presentation priority score is higher than the preset threshold, allocate the abnormal information to the high-priority display queue and determine the dynamic hierarchical display content; Multi-modal warning generation module: used to generate multi-modal warning signals according to the dynamic hierarchical display content. If the driving scenario is high-speed driving, high-frequency sound and vibration feedback are preferred to obtain a multi-modal warning combination; the multi-modal warning signal includes sound prompts, dashboard images, and tactile feedback; Voice synthesis and interaction module: used to extract the audio signal of the sound prompt part from the multi-modal warning combination, generate speech waveform data described in natural language through the voice synthesis module; obtain the driver's voice input, parse the semantics through the voice recognition model. If the recognition result contains the intention of status query, extract the abnormal information from the abnormal trend set, generate voice interaction response content, and determine the interaction feedback information; Interaction optimization and display module: used to judge the scenario type according to the interaction feedback information, combined with the current driving scenario and abnormal status. If the scenario is low-speed congestion, display detailed feedback content through the dashboard, otherwise, preferentially output concise information through voice to obtain optimized interaction output; Interface dynamic adjustment module: used to extract the display content from the optimized interaction output, dynamically adjust the dashboard interface through the image processing module. If the abnormal feedback detail level is higher than the preset threshold, zoom in on the key abnormal area to generate the final display interface; Signal transmission and rendering module: used to obtain the image and voice data of the final display interface, integrate them into a unified data stream, generate an image and voice data stream adapted to the vehicle terminal, measure the transmission delay, and if the transmission delay is lower than the preset threshold, determine that the signal transmission meets the requirements.

[0017] Preferably, the priority calculation and allocation module includes: Abnormal severity assessment unit: used to calculate the abnormal severity score by using the weighted scoring method according to the abnormal occurrence frequency, influence range, and potential risk level. The weight of the abnormal occurrence frequency is 0.4, the weight of the influence range is 0.3, and the weight of the potential risk level is 0.3; the calculation formula of the abnormal severity score is: , where, represents the abnormal severity score, represents the normal occurrence frequency score, Indicates the influence range score, Indicates the potential risk level score; Driving scenario complexity evaluation unit: Used to calculate the driving scenario complexity score based on the current number of lanes, the distance to the vehicle ahead, and the weather visibility. The calculation formula is as follows:

[0018] Where C represents the driving scenario complexity score, Indicates the number of evaluation factors, Indicates the weight of the th factor, Indicates the score value of the th factor; Priority calculation unit: Used to calculate the information presentation priority score using the linear weighted method based on the abnormal severity score and the driving scenario complexity score. The weight of the abnormal severity score is 0.6, and the weight of the driving scenario complexity score is 0.4; The calculation formula is expressed as: Where, Indicates the information presentation priority score, Indicates the abnormal severity score, and C represents the driving scenario complexity score; High-priority queue management unit: Used to assign abnormal information to the high-priority display queue if the information presentation priority score is higher than the preset threshold, and use the sliding window algorithm to update the display queue in real time to ensure the timely presentation of high-priority information; The multi-modal warning generation module includes: Driving scenario recognition unit: Used to obtain driving scenario data from the in-vehicle millimeter-wave radar and camera, and use a random forest classifier to determine whether the current scenario is high-speed driving; Warning signal configuration unit: Used to set the sound signal frequency to 3000 - 5000Hz and the vibration intensity to 0.5 - 1.2G in the high-speed scenario to generate an initial warning signal set; Signal fusion unit: Used to integrate the sound signal, vibration signal, and image signal using the weighted average fusion algorithm to generate a multi-modal warning signal; The interface dynamic adjustment module includes: Abnormal area extraction unit: Used to extract the abnormal area from the dashboard interface and record its center coordinates and bounding box size; Area magnification unit: Used to double the display ratio of the key abnormal area, generate an enlarged bitmap of the abnormal area, and overlay it on the preliminary adjusted interface to generate the final display interface.

[0019] The technical effects and advantages of the present invention: 1. A vehicle status monitoring and warning method provided by the present invention can obtain status data in real time through vehicle sensors and use a preset anomaly detection algorithm to preliminarily screen the data, quickly and accurately mark anomaly events, and generate an anomaly trend set, which helps to timely discover potential vehicle problems and take measures in advance to ensure driving safety; adopt a dynamic grading display algorithm to calculate the information presentation priority according to the anomaly severity and driving scenario complexity, ensuring that high-priority information can be presented in a timely manner. This grading display method can avoid information overload for drivers in complex driving scenarios and improve the efficiency and accuracy of information transmission; generate multimodal warning signals including sound prompts, dashboard images, and tactile feedback, and adjust the warning method according to the driving scenario. When driving at high speed, high-frequency sounds and vibration feedback are preferred, which can more effectively attract the driver's attention, enhance the perception effect, and improve driving safety; synthesize the extracted audio signal through a speech synthesis module to generate speech waveform data described in natural language. This natural language interaction method is more intuitive and easy to understand, can improve the driver's interaction experience, and reduce the possibility of misoperation; use a speech recognition model to semantically analyze the driver's speech input, quickly recognize the driver's intention, and extract relevant information from the anomaly trend set to generate speech interaction response content. This intelligent speech interaction method can improve the response speed and enable the driver to more conveniently obtain the required information during driving; judge the scenario type according to the current driving scenario and anomaly status, and accordingly adjust the information presentation method. In a low-speed congestion scenario, detailed feedback content is displayed through the dashboard, and in other scenarios, concise information is preferentially output through speech. This scenario adaptation optimization method can improve the quality of information presentation and enable the driver to obtain clear and accurate information in different scenarios; dynamically adjust the dashboard interface through an image processing module, enlarge the key anomaly information area, and generate the final display interface. This dynamic interface adjustment method can enhance the readability of information and enable the driver to obtain key information more quickly and make correct decisions; render the integrated multimodal signal and measure the transmission delay to ensure that the rendered transmission signal can be transmitted to the vehicle terminal in a timely and accurate manner. This low-latency transmission method can ensure the real-time nature of information and enable the driver to timely obtain the latest vehicle status information. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is the flowchart of the vehicle status monitoring and warning of the present invention;

[0021] Figure 2 is the structural diagram of the vehicle status monitoring and warning system of the present invention; Figure 3 is the structural schematic diagram of the priority calculation and distribution module of the vehicle status monitoring and warning system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0022] The following embodiments given in conjunction with the accompanying drawings further describe the present invention in detail.

[0023] Refer to Figure 1 As shown, a vehicle status monitoring and warning method, the method includes: S1. Obtain real-time status data from vehicle sensors, and preliminarily screen the data through a preset anomaly detection algorithm. If a parameter exceeds the preset threshold, it is marked as an abnormal event to obtain an abnormal trend set; when this step is specifically implemented, it includes: Obtain real-time data transmitted by vehicle sensors, including data on engine speed, brake pressure, and tire pressure, and remove noise through mean filtering to generate a standardized data set; Preliminarily screen the parameters in the standardized data set through an anomaly detection algorithm. If any one of the parameters exceeds the preset threshold, use the fixed threshold judgment method to mark it as an abnormal event, and use the K-Means algorithm to classify the abnormal events to obtain an abnormal event set; For the abnormal event set, extract the timestamps and parameter values of each type of abnormal event to generate an abnormal feature data set, and use the decision tree algorithm to predict the development trend of the abnormal events for the abnormal feature data set to obtain an abnormal trend set.

[0024] In one embodiment, vehicle sensors collect operation parameters such as engine speed, brake pressure, and tire pressure in real time. The normal range of engine speed is 800 to 3000 revolutions per minute, the normal range of brake pressure is 10 to 20 MPa, and the normal range of tire pressure is 2.2 to 2.8 Kpa. Through a preset anomaly detection algorithm, such as the 3σ principle based on statistical process control (SPC), the data is preliminarily screened; if the engine speed exceeds 3000 revolutions per minute or is lower than 800 revolutions per minute, the brake pressure is lower than 10 MPa or higher than 20 MPa, and the tire pressure is lower than 2.2 Kpa or higher than 2.8 Kpa, it is marked as an abnormal event.

[0025] For example, when the detected engine speed is 3500 revolutions per minute, the system automatically marks it as abnormal and records the relevant timestamp and parameter value. This abnormal event is summarized into the abnormal information set for subsequent analysis.

[0026] Furthermore, if the brake pressure is detected to be lower than 10 MPa multiple times, the system may predict a leakage risk in the brake system and generate a warning message. The entire process realizes the automated processing from data collection to anomaly detection and then to fault prediction, ensuring the safe operation of the vehicle.

[0027] S2. For the abnormal trend set, use the dynamic hierarchical display algorithm to calculate the information presentation priority according to the severity of the abnormality and the complexity of the driving scenario. If the information presentation priority score is higher than the preset threshold, assign the abnormal information to the high-priority display queue and determine the dynamic hierarchical display content.

[0028] Specifically, the severity of the abnormality includes the frequency of occurrence of the abnormality, the scope of influence, and the potential risk level; the complexity of the driving scenario includes the current number of lanes, the distance to the vehicle ahead, and the weather visibility.

[0029] In one embodiment, the specific method for determining the dynamic hierarchical display content includes: S201. According to the frequency of occurrence of the abnormality, the scope of influence, and the potential risk level, use the weighted scoring method to calculate the severity score of the abnormality. When calculating the severity score of the abnormality, set the weight of the frequency of occurrence of the abnormality to 0.4, the weight of the scope of influence to 0.3, and the weight of the potential risk level to 0.3. The calculation formula for the severity score of the abnormality is: , where represents the severity score of the abnormality, represents the score of the frequency of occurrence, represents the score of the scope of influence, represents the score of the potential risk level; through this formula, the frequency of occurrence, the scope of influence, and the potential risk level of the abnormality can be comprehensively considered to obtain a comprehensive severity assessment score.

[0030] S202. According to the factors of the current number of lanes, the distance to the vehicle ahead, and the weather visibility, calculate the complexity score of the driving scenario. The calculation formula is as follows:

[0031] where C represents the complexity score of the driving scenario, represents the number of evaluation factors, represents the weight of the th factor, represents the score value of the th factor; S203. According to the severity score of the abnormality and the complexity score of the driving scenario, use the linear weighted method to calculate the information presentation priority score. When calculating, set the weight of the severity score of the abnormality to 0.6 and the weight of the complexity score of the driving scenario to 0.4. The calculation formula is expressed as: , where represents the information presentation priority score, represents the severity score of the abnormality, and C represents the complexity score of the driving scenario; S204. If the information presentation priority score is higher than the preset threshold, then allocate the abnormal information to the high-priority display queue, and use the sliding window algorithm to update the high-priority display queue in real time to ensure that high-priority information can be presented in a timely manner.

[0032] For example, set the preset threshold to 80 points. When it is detected that the information presentation priority score of a certain abnormal information is 85 points and there are already 3 high-priority information in the current display queue, the system will automatically remove the information with the lowest score from the queue to ensure that the new information can be displayed in a timely manner. Through this dynamic hierarchical display algorithm, the driving safety and information processing efficiency can be effectively improved.

[0033] S3. Generate multi-modal warning signals according to the dynamically hierarchical display content. If the driving scenario is high-speed driving, then preferentially use high-frequency sound and vibration feedback to obtain a multi-modal warning combination; the multi-modal warning signals include sound prompts, dashboard images, and tactile feedback.

[0034] Specifically, the method for generating multi-modal warning signals is as follows: Obtain driving scenario data from on-vehicle millimeter-wave radar and cameras, including three features: vehicle speed, acceleration, and lane line curvature. Use a random forest classifier to determine whether the current scenario is high-speed driving. When the classification confidence is greater than the preset threshold, it is determined as a high-speed scenario; For example, set the classification confidence to , and set the preset threshold to . When > , it is determined as a high-speed scenario. Specifically, set the preset threshold to 0.85. When the classification confidence is greater than the preset threshold of 0.85, it is determined as a high-speed scenario.

[0035] In a high-speed scenario, set the sound signal frequency to 3000 - 5000 Hz and the vibration intensity to 0.5 - 1.2 G as the priority signal parameters. Generate an initial warning signal set according to the priority configuration, including three parameters: sound frequency, vibration intensity, and duration; Extract the sound frequency and duration parameters from the initial warning signal set and input them into the dashboard display module to generate an image signal with a flashing red border; Use the weighted average fusion algorithm to integrate the sound signal, vibration signal, and image signal. When calculating, set the sound weight to 0.4, the vibration weight to 0.3, and the image weight to 0.3; the weighted average fusion algorithm is expressed as: , where represents the fused signal, represents the sound signal, represents the vibration signal, represents the image signal; Encode the fused signal into the CAN bus protocol format and output it to the speaker, vibration motor, and display screen through the vehicle control unit to generate a multimodal warning signal.

[0036] S4. Extract the audio signal of the voice prompt part from the multimodal warning combination, and synthesize the extracted audio signal through the speech synthesis module to generate speech waveform data described in natural language; the specific implementation of this step includes: Intercept the audio signal in the 20Hz - 20kHz frequency band from the multimodal warning combination to obtain the voice prompt signal, and calculate the Mel-frequency cepstral coefficients of the voice prompt signal to obtain the audio feature vector; When intercepting the audio signal, extract the features of the audio signal through the Mel-frequency cepstral coefficients (MFCC) algorithm, set the frame length to 25 milliseconds, the frame shift to 10 milliseconds, and extract 13-dimensional MFCC coefficients as the voice features; Input the audio feature vector into a pre-trained support vector machine classifier, output the abnormal type label and the abnormal severity score. If the abnormal type label is an emergency brake failure, read and analyze the vehicle fault code through the OBD-II interface to obtain the fault location code; Input the abnormal type label, the abnormal severity score, and the fault location code into the speech synthesis module to generate speech waveform data described in natural language; the speech synthesis module can adopt the Tacotron2 model.

[0037] For example, the input text is "The left rear wheel brake pressure sensor fails and needs to be repaired immediately", the acoustic feature dimension is 80-dimensional Mel spectrum, the sampling rate is 16kHz, and the speech waveform data described in natural language is generated through the WaveNet vocoder.

[0038] This application can also sort the speech waveform data described in natural language in descending order according to the abnormal severity score to obtain a priority queue, and sequentially play the speech waveform data in the priority queue through the in-vehicle speaker; use the microphone to collect the played speech signal, and use the dynamic time warping algorithm to calculate its similarity with the original speech waveform data. If the similarity is lower than 95%, regenerate the speech waveform data.

[0039] S5. Obtain the driver's voice input, semantically parse the input instruction through the speech recognition model. If the recognition result contains the intention of status query, extract the abnormal information from the abnormal trend set, generate the speech interaction response content, and determine the interaction feedback information; In specific implementation, first, when obtaining the driver's voice input, the driver's voice can be captured through a four-channel circular microphone array at a sampling rate of 16 kHz to generate an original audio signal, and the NS module in WebRTC is used to perform noise reduction processing on the original audio signal, and clear voice data in 16-bit PCM format is output; then, when performing semantic parsing, the clear voice data is input into the Kaldi speech recognition tool, and an instruction text string encoded in UTF-8 is output. Rasa NLU is used to classify the intent of the instruction text. When the status query intent is recognized, information including vehicle speed, fuel quantity, and tire pressure is extracted. For example, when the driver says "Check tire pressure", the speech recognition model can use the BERT pre-trained model to classify the intent, and the output query intent probability is 0.87. If it exceeds the threshold of 0.65, it is determined as the status query intent; finally, according to the vehicle speed, fuel quantity, and tire pressure information, the matching fault code records within the last 24 hours are queried from the abnormal trend set, and the fault code records are filled into a preset Jinja2 text template to generate a response text string. The response text is converted into an audio stream in MP3 format with a sampling rate of 48 kHz through Google TTS, and the audio stream is played through the in-vehicle speaker at a sound pressure level of 80 dB. For example, when the current left front tire pressure is 210 kPa (normal range 220 - 250 kPa), the abnormal judgment rule is triggered, and the text of "The left front tire pressure is low, the current value is 210 kPa, and it is recommended to supplement it to 230 kPa" is converted into speech output through the Tacotron2 vocoder using the template filling technology.

[0040] It should be noted that the entire voice processing flow of this application can be completed within 800 ms, meeting the requirements of in-vehicle real-time performance. Among them, the speech recognition takes 300 ms, the semantic parsing takes 150 ms, the data query takes 50 ms, and the speech synthesis takes 300 ms.

[0041] S6. According to the interaction feedback information, combined with the current driving scenario and abnormal state, judge the scenario type. If the scenario is low-speed congestion, detailed feedback content is displayed through the instrument panel, otherwise, concise information is preferentially output through voice to obtain an optimized interaction output; the specific implementation of this step includes: By obtaining real-time data from vehicle sensors and user interaction interfaces, analyzing the driving environment and interaction feedback information, and determining the feature description of the current state. Furthermore, the vehicle sensors include a speed sensor, a distance sensor, a camera, etc., which are used to obtain vehicle speed, vehicle distance, and surrounding environment information. For example, assume that the current vehicle speed is 5 kilometers per hour, the distance to the vehicle in front is only 2 meters, and the camera captures that the vehicles in front are densely arranged. These data will be transmitted to the system for analysis, and it is initially judged that it may be in a congested state. Such a data collection method can ensure that the system's perception of the driving environment has high precision and real-time performance, providing a reliable basis for subsequent classification.

[0042] According to the feature description of the current state, combined with the pre-established scenario classification model, the support vector machine algorithm is used to classify the driving environment and abnormal states to determine whether it belongs to the low-speed congestion scenario; If the classification result is the low-speed congestion scenario, the detailed feedback content is generated through the dashboard display module, including the specific description of the current state and the recommended operations, to obtain the visual output result; The specific description of the current state includes the current vehicle speed and the length of the congestion ahead, and the recommended operations include suggesting that the driver be patient or choose a detour route; for example, when the current vehicle speed is 5 kilometers per hour and the length of the congestion ahead is about 200 meters, at this time, suggesting that the driver be patient or choose a detour route, this kind of visual output is intuitive and clear, which helps the driver quickly understand the situation and take reasonable measures, thus improving driving safety and comfort.

[0043] If the classification result does not belong to the low-speed congestion scenario, the concise information is generated through the speech synthesis module, including the key prompts of the current state, to obtain the voice output content; for example, when the vehicle speed is 60 kilometers per hour and the vehicle distance is greater than 50 meters, the system will generate a concise prompt through the speech synthesis module, such as "The current road is clear, please pay attention to maintaining a safe vehicle distance". This kind of voice output method is concise and efficient, avoiding distracting the driver's attention, while ensuring that the key information is conveyed in time and enhancing the interaction experience.

[0044] For the generated detailed feedback content or concise information, obtain the response data of the user interaction interface, analyze the acceptance degree of the user for the output method, and determine the adjustment direction of the optimization plan; According to the analysis result of the user response data, adjust the priority and content form of the output method, generate the updated interaction plan, and complete the optimization process of scenario adaptation. For example, in the low-speed congestion scenario, the detailed feedback displayed on the dashboard is frequently viewed by the driver, while the voice prompt has a higher response rate in the non-congestion scenario, and the system will adjust the output priority accordingly, giving priority to the method that the user accepts more.

[0045] S7. Extract the display content from the optimized interactive output, dynamically adjust the dashboard interface through the image processing module. If the detailed degree of the abnormal feedback is higher than the preset threshold, magnify the key abnormal area to generate the final display interface; the specific implementation of this step includes: Obtain the original display content in JSON format from the interactive output, and extract the digital scale and pointer angle of the dashboard interface through the image processing module to generate the structured display data containing the values and coordinates; It should be noted that the image processing module adopted can be the Canny edge detection algorithm of the OpenCV image parsing module.

[0046] Adjust the color contrast and scale line width of the dashboard according to the numerical range in the structured display data, output the preliminary adjusted interface in bitmap format, calculate the anomaly scores of each pixel block in the preliminary adjusted interface, and mark it as an abnormal area when the anomaly score of the pixel block exceeds the preset threshold; It should be noted that when adjusting the color contrast and scale line width of the dashboard, the Pillow library can be called for adjustment. When calculating the anomaly scores of each pixel block in the preliminary adjusted interface, the Isolation Forest algorithm can be used for calculation.

[0047] Extract the areas with an area greater than 50 pixels from the abnormal areas, record their center coordinates and bounding box sizes as key abnormal data, expand the display ratio of the key abnormal areas by 2 times, generate the enlarged bitmap of the abnormal areas, and overlay the enlarged bitmap of the abnormal areas on the corresponding coordinates of the preliminary adjusted interface to output the final display interface.

[0048] It should be noted that when expanding the display ratio of the key abnormal areas by 2 times, the bilinear interpolation algorithm can be used.

[0049] S8. Obtain the image and voice data of the final display interface, integrate the image and voice data into a unified data stream to obtain a multimodal signal, perform rendering processing on the multimodal signal to generate an image and voice data stream adapted to the vehicle terminal, obtain the rendered transmission signal, transmit the rendered transmission signal to the vehicle terminal, and measure the transmission delay. If the transmission delay is lower than the preset threshold, it is determined that the signal transmission meets the requirements.

[0050] It should be noted that when performing rendering processing on the multimodal signal, the OpenGL rendering engine can be used. When obtaining the image, the image signal is collected at a rate of 30 frames per second, and the H.265 encoding algorithm is used to compress the image, with a compression ratio of 1:50; when obtaining the voice data, the sound signal is captured at a sampling rate of 44.1 kHz, and the AAC encoding is used to compress the sound signal, with a compression ratio of 1:10.

[0051] The present invention first obtains the real-time operating parameters from the vehicle sensors, uses a preset algorithm to detect abnormal events, and generates an abnormal trend set; secondly, calculates the information presentation priority according to the abnormal severity and driving scenario complexity, and determines the dynamic hierarchical display content; thirdly, generates multimodal warning signals according to the dynamic hierarchical display content, including sound, image and tactile feedback, and optimizes the combination according to the driving scenario; finally, it also supports voice interaction and can provide corresponding abnormal status feedback according to the driver's voice commands. Through the above technical solutions, the present invention can timely and accurately transmit vehicle abnormal information to the driver, effectively improving driving safety.

[0052] See Figures 2 - 3As shown in the figure, the present application also proposes a vehicle status monitoring and warning system, which includes: Data acquisition and processing module: used to obtain real-time status data from vehicle sensors, preliminarily screen the data, if the parameters exceed the preset threshold, mark it as an abnormal event, and generate an abnormal trend set.

[0053] Priority calculation and allocation module: used to calculate the information presentation priority according to the abnormal severity and driving scenario complexity. If the information presentation priority score is higher than the preset threshold, the abnormal information is allocated to the high-priority display queue to determine the dynamic hierarchical display content; this module also includes: Abnormal severity assessment unit: used to calculate the abnormal severity score by using the weighted scoring method according to the abnormal occurrence frequency, influence range and potential risk level, where the weight of the abnormal occurrence frequency is 0.4, the weight of the influence range is 0.3, and the weight of the potential risk level is 0.3; the calculation formula of the abnormal severity score is: , where, represents the abnormal severity score, represents the normal occurrence frequency score, represents the influence range score, represents the potential risk level score; Driving scenario complexity assessment unit: used to calculate the driving scenario complexity score according to the current number of lanes, the distance to the vehicle ahead and the weather visibility. The calculation formula is as follows:

[0054] where C represents the driving scenario complexity score, represents the number of evaluation factors, represents the th factor's weight, represents the th factor's score value; Priority calculation unit: used to calculate the information presentation priority score by using the linear weighted method according to the abnormal severity score and the driving scenario complexity score, where the weight of the abnormal severity score is 0.6 and the weight of the driving scenario complexity score is 0.4; the calculation formula is expressed as: , where, represents the information presentation priority score, represents the abnormal severity score, and C represents the driving scenario complexity score; High-priority queue management unit: used to allocate the abnormal information to the high-priority display queue if the information presentation priority score is higher than the preset threshold, and use the sliding window algorithm to update the display queue in real time to ensure the timely presentation of high-priority information.

[0055] Multi-modal Warning Generation Module: It is used to generate multi-modal warning signals according to the dynamically graded display content. If the driving scenario is high-speed driving, high-frequency sound and vibration feedback are preferentially adopted to obtain a multi-modal warning combination; the multi-modal warning signals include sound prompts, dashboard images, and tactile feedback; this module also includes: Driving Scenario Recognition Unit: It is used to obtain driving scenario data from in-vehicle millimeter-wave radars and cameras, and use a random forest classifier to determine whether the current scenario is high-speed driving; Warning Signal Configuration Unit: It is used to set the sound signal frequency to 3000 - 5000 Hz and the vibration intensity to 0.5 - 1.2 G in a high-speed scenario to generate an initial warning signal set; Signal Fusion Unit: It is used to integrate sound signals, vibration signals, and image signals using a weighted average fusion algorithm to generate multi-modal warning signals.

[0056] Voice Synthesis and Interaction Module: It is used to extract the audio signal of the sound prompt part from the multi-modal warning combination, generate speech waveform data described in natural language through a voice synthesis module; obtain the driver's voice input, parse the semantics through a voice recognition model. If the recognition result contains an intention of status query, extract abnormal information from the abnormal trend set, generate voice interaction response content, and determine the interaction feedback information.

[0057] Interaction Optimization and Display Module: It is used to judge the scenario type according to the interaction feedback information, combined with the current driving scenario and abnormal state. If the scenario is low-speed congestion, detailed feedback content is displayed through the dashboard, otherwise concise information is preferentially output through voice to obtain optimized interaction output.

[0058] Interface Dynamic Adjustment Module: It is used to extract the display content from the optimized interaction output, and dynamically adjust the dashboard interface through an image processing module. If the abnormal feedback detail level is higher than the preset threshold, the key abnormal area is enlarged to generate the final display interface; this module also includes: Abnormal Area Extraction Unit: It is used to extract the abnormal area from the dashboard interface and record its center coordinates and bounding box dimensions; Area Enlargement Unit: It is used to double the display ratio of the key abnormal area, generate an enlarged bitmap of the abnormal area, and overlay it on the preliminary adjusted interface to generate the final display interface.

[0059] Signal Transmission and Rendering Module: It is used to obtain the image and voice data of the final display interface, integrate them into a unified data stream, generate an image and voice data stream adapted to the vehicle terminal, measure the transmission delay, and if the transmission delay is lower than the preset threshold, it is determined that the signal transmission meets the requirements.

[0060] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the inventive concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention.

Claims

1. A vehicle status monitoring and warning method, characterized in that, The method includes: S1. Obtain real-time status data from vehicle sensors, preliminarily screen the data. If a parameter exceeds a preset threshold, mark it as an abnormal event to obtain an abnormal trend set; S2. For the abnormal trend set, calculate the information presentation priority according to the abnormal severity and driving scenario complexity. If the information presentation priority score is higher than the preset threshold, assign the abnormal information to the high-priority display queue to determine the dynamic hierarchical display content; S3. Generate a multimodal warning signal according to the dynamic hierarchical display content. If the driving scenario is high-speed driving, preferentially use high-frequency sound and vibration feedback to obtain a multimodal warning combination; the multimodal warning signal includes sound prompts, dashboard images, and tactile feedback; S4. Extract the audio signal of the sound prompt part from the multimodal warning combination, and synthesize the extracted audio signal through a speech synthesis module to generate speech waveform data described in natural language; S5. Obtain the driver's voice input, semantically parse the input command through a speech recognition model. If the recognition result contains the intention of status query, extract the abnormal information from the abnormal trend set to generate speech interaction response content and determine the interaction feedback information; S6. According to the interaction feedback information, combined with the current driving scenario and abnormal status, judge the scenario type. If the scenario is low-speed congestion, display detailed feedback content through the dashboard, otherwise preferentially output concise information through voice to obtain the optimized interaction output; S7. Extract the display content from the optimized interaction output, dynamically adjust the dashboard interface through an image processing module. If the abnormal feedback detail level is higher than the preset threshold, magnify the key abnormal area to generate the final display interface; S8. Obtain the image and voice data of the final display interface, integrate the image and voice data into a unified data stream to obtain a multimodal signal, perform rendering processing on the multimodal signal to generate an image and voice data stream adapted to the vehicle terminal to obtain a rendered transmission signal, transmit the rendered transmission signal to the vehicle terminal, and measure the transmission delay. If the transmission delay is lower than the preset threshold, determine that the signal transmission meets the requirements.

2. The vehicle state monitoring and warning method according to claim 1, characterized in that, The obtaining real-time status data from vehicle sensors, preliminarily screening the data. If a parameter exceeds a preset threshold, mark it as an abnormal event to obtain an abnormal trend set includes: Obtain the real-time data transmitted by vehicle sensors, including data such as engine speed, brake pressure, and tire pressure, and remove noise through mean filtering to generate a standardized data set; Preliminarily screen the parameters in the standardized data set through an anomaly detection algorithm. If any one of the parameters exceeds the preset threshold, mark it as an abnormal event using the fixed threshold judgment method, and classify the abnormal events using the K-Means algorithm to obtain an abnormal event set; For the abnormal event set, extract the timestamp and parameter value of each type of abnormal event to generate an abnormal feature data set, and use a decision tree algorithm to predict the development trend of the abnormal event for the abnormal feature data set to obtain an abnormal trend set.

3. A vehicle status monitoring and warning method according to claim 2, characterized in that, The abnormal severity includes the abnormal occurrence frequency, influence range, and potential risk level; The driving scenario complexity includes the current number of lanes, the distance to the vehicle ahead, and the weather visibility.

4. A vehicle status monitoring and warning method according to claim 3, characterized in that, The specific method for determining the dynamic hierarchical display content includes: S201. Calculate the severity score of the anomaly using the weighted scoring method based on the anomaly occurrence frequency, impact scope, and potential risk level. When calculating the severity score of the anomaly, set the weight of the anomaly occurrence frequency to 0.4, the weight of the impact scope to 0.3, and the weight of the potential risk level to 0.

3. The calculation formula for the severity score of the anomaly is: , where represents the severity score of the anomaly, represents the occurrence frequency score of the anomaly, represents the impact scope score, represents the potential risk level score; S202. Calculate the driving scenario complexity score based on factors such as the current number of lanes, the distance to the vehicle ahead, and the weather visibility. The calculation formula is as follows: Among them, C represents the driving scenario complexity score, represents the number of evaluation factors, represents the weight of the th factor, and represents the score value of the S203. According to the abnormal severity score and the driving scenario complexity score, use the linear weighting method to calculate the information presentation priority score. When calculating, set the weight of the abnormal severity score to 0.6 and the weight of the driving scenario complexity score to 0.

4. The calculation formula is expressed as: , where represents the information presentation priority score, represents the abnormal severity score, and C represents the driving scenario complexity score; S204. If the information presentation priority score is higher than the preset threshold, assign the abnormal information to the high-priority display queue, and use the sliding window algorithm to update the high-priority display queue in real time to ensure that high-priority information can be presented in a timely manner.

5. A vehicle state monitoring and warning method according to claim 1, characterized in that, The method for generating the multimodal warning signal is: Obtain driving scenario data from the in-vehicle millimeter-wave radar and camera, including three features: vehicle speed, acceleration, and lane line curvature. Use a random forest classifier to determine whether the current scenario is a high-speed driving scenario. When the classification confidence is greater than the preset threshold, it is determined as a high-speed scenario; In the high-speed scenario, set the sound signal frequency to 3000 - 5000 Hz and the vibration intensity to 0.5 - 1.2 G as the priority signal parameters, and generate an initial warning signal set according to the priority configuration, including three parameters: sound frequency, vibration intensity, and duration; Extract the sound frequency and duration parameters from the initial warning signal set and input them into the dashboard display module to generate an image signal with a flashing red border; Integrate the sound signal, vibration signal and image signal using the weighted average fusion algorithm. When calculating, set the sound weight to 0.4, the vibration weight to 0.3, and the image weight to 0.3; the weighted average fusion algorithm is expressed as: , where represents the fused signal, represents the sound signal, represents the vibration signal, represents the image signal; Encode the fused signal into the CAN bus protocol format and output it to the speaker, vibration motor, and display screen through the vehicle control unit to generate a multimodal warning signal.

6. The vehicle state monitoring and warning method according to claim 5, characterized in that, The method for extracting the audio signal of the sound prompt part from the multimodal warning combination and synthesizing the extracted audio signal through the speech synthesis module to generate speech waveform data described in natural language includes: Intercept the audio signal in the 20 Hz - 20 kHz frequency band from the multimodal warning combination to obtain the sound prompt signal, and calculate the Mel-frequency cepstral coefficients of the sound prompt signal to obtain the audio feature vector; Input the audio feature vector into a pre-trained support vector machine classifier to output the abnormal type label and the abnormal severity score. If the abnormal type label is an emergency brake failure, read and analyze the vehicle fault code through the OBD-II interface to obtain the fault location code; Input the abnormal type label, the abnormal severity score, and the fault location code into the speech synthesis module to generate speech waveform data described in natural language.

7. A vehicle state monitoring and warning method according to claim 6, characterized in that, According to the interaction feedback information, combined with the current driving scenario and abnormal state, judge the scenario type. If the scenario is a low-speed congestion, display the detailed feedback content through the dashboard, otherwise, give priority to outputting concise information through voice to obtain the optimized interaction output, including: Analyze the driving environment and interaction feedback information by obtaining real-time data from vehicle sensors and user interaction interfaces to determine the feature description of the current state; According to the feature description of the current state, combined with the pre-established scenario classification model, use the support vector machine algorithm to classify the driving environment and abnormal state to determine whether it belongs to the low-speed congestion scenario; If the classification result is a low-speed congestion scenario, generate detailed feedback content through the dashboard display module, including the specific description of the current state and the recommended operation, to obtain the visual output result; The specific description of the current state includes the current vehicle speed and the length of the congestion ahead, and the recommended operations include advising the driver to be patient or choose a detour route; If the classification result does not belong to the low-speed congestion scenario, a concise message is generated through the speech synthesis module, including key prompts of the current state, to obtain the speech output content; For the generated detailed feedback content or concise message, the response data of the user interaction interface is obtained, the acceptance degree of the user for the output method is analyzed, and the adjustment direction of the optimization plan is determined; According to the analysis result of the user response data, the priority and content form of the output method are adjusted, an updated interaction plan is generated, and the optimization process of the scenario adaptation is completed.

8. A vehicle status monitoring and warning method according to claim 7, characterized in that, The display content is extracted from the optimized interactive output, and the dashboard interface is dynamically adjusted through the image processing module. If the detailed degree of the abnormal feedback is higher than the preset threshold, the key abnormal information area is enlarged to generate the final display interface, including: The original display content in JSON format is obtained from the interactive output, and the digital scale and pointer angle of the dashboard interface are extracted through the image processing module to generate structured display data including values and coordinates; According to the value range in the structured display data, the color contrast of the dashboard and the width of the scale lines are adjusted, a preliminary adjusted interface in bitmap format is output, the abnormal score of each pixel block in the preliminary adjusted interface is calculated, and when the abnormal score of the pixel block exceeds the preset threshold, it is marked as an abnormal area; Regions with an area larger than 50 pixels are extracted from the abnormal areas, their central coordinates and bounding box sizes are recorded as key abnormal data, the display ratio of the key abnormal areas is enlarged by 2 times to generate an enlarged bitmap of the abnormal areas, and the enlarged bitmap of the abnormal areas is superimposed on the corresponding coordinates of the preliminary adjusted interface to output the final display interface.

9. A vehicle status monitoring and warning system, characterized in that, The system includes: Data acquisition and processing module: used to obtain real-time state data from vehicle sensors, perform preliminary screening on the data, and if the parameters exceed the preset threshold, mark them as abnormal events and generate an abnormal trend set; Priority calculation and allocation module: used to calculate the information presentation priority according to the abnormal severity and driving scenario complexity. If the information presentation priority score is higher than the preset threshold, the abnormal information is assigned to the high-priority display queue to determine the dynamically graded display content; Multi-modal warning generation module: used to generate multi-modal warning signals according to the dynamically graded display content. If the driving scenario is high-speed driving, high-frequency sound and vibration feedback are preferred to obtain a multi-modal warning combination; the multi-modal warning signal includes sound prompts, dashboard images, and tactile feedback; Speech synthesis and interaction module: used to extract the audio signal of the sound prompt part from the multi-modal warning combination, generate speech waveform data described in natural language through the speech synthesis module; obtain the driver's speech input, parse the semantics through the speech recognition model. If the recognition result contains the intention of querying the state, the abnormal information is extracted from the abnormal trend set to generate speech interaction response content and determine the interaction feedback information; Interaction Optimization and Display Module: It is used to determine the scene type according to the interaction feedback information, combined with the current driving scene and abnormal state. If the scene is low-speed congestion, detailed feedback content is displayed through the instrument panel. Otherwise, concise information is preferentially output through voice to obtain the optimized interaction output. Interface Dynamic Adjustment Module: It is used to extract the display content from the optimized interaction output and dynamically adjust the instrument panel interface through the image processing module. If the detailed degree of abnormal feedback is higher than the preset threshold, the key abnormal area is enlarged to generate the final display interface. Signal Transmission and Rendering Module: It is used to obtain the image and voice data of the final display interface, integrate them into a unified data stream, generate the image and voice data stream adapted to the vehicle terminal, measure the transmission delay. If the transmission delay is lower than the preset threshold, it is determined that the signal transmission meets the requirements.

10. A vehicle status monitoring and warning system according to claim 9, characterized in that, The Priority Calculation and Allocation Module includes: Abnormality severity assessment unit: It is used to calculate the abnormality severity score by using the weighted scoring method according to the abnormality occurrence frequency, influence range and potential risk level, where the weight of the abnormality occurrence frequency is 0.4, the weight of the influence range is 0.3, and the weight of the potential risk level is 0.3; the calculation formula of the abnormality severity score is: , where represents the abnormality severity score, represents the abnormality occurrence frequency score, represents the influence range score, represents the potential risk level score; Driving Scene Complexity Evaluation Unit: It is used to calculate the driving scene complexity score according to the current number of lanes, the distance to the vehicle ahead, and the weather visibility. The calculation formula is as follows: Among them, C represents the driving scenario complexity score, represents the number of evaluation factors, represents the weight of the th factor, and represents the score value of the Priority calculation unit: used to calculate the information presentation priority score by the linear weighting method according to the abnormal severity score and the driving scenario complexity score, where the weight of the abnormal severity score is 0.6 and the weight of the driving scenario complexity score is 0.4; the calculation formula is expressed as: , where represents the information presentation priority score, represents the abnormal severity score, and C represents the driving scenario complexity score; High-Priority Queue Management Unit: It is used to allocate abnormal information to the high-priority display queue if the information presentation priority score is higher than the preset threshold, and use the sliding window algorithm to update the display queue in real time to ensure the timely presentation of high-priority information. The Multimodal Warning Generation Module includes: Driving Scene Recognition Unit: It is used to obtain driving scene data from the in-vehicle millimeter-wave radar and camera, and use a random forest classifier to determine whether the current scene is high-speed driving. Warning Signal Configuration Unit: It is used to set the sound signal frequency to 3000 - 5000Hz and the vibration intensity to 0.5 - 1.2G in the high-speed scene to generate the initial warning signal set. Signal Fusion Unit: It is used to integrate the sound signal, vibration signal, and image signal using the weighted average fusion algorithm to generate the multimodal warning signal. The Interface Dynamic Adjustment Module includes: Abnormal Area Extraction Unit: It is used to extract the abnormal area from the instrument panel interface and record its center coordinates and bounding box size. Area Enlargement Unit: It is used to double the display ratio of the key abnormal area, generate the enlarged abnormal area bitmap, and overlay it on the preliminary adjusted interface to generate the final display interface.

Images