An integrated voice recognition-based method and system for analyzing vehicle driving behavior

Abstract

This application relates to the technical field, and in particular to an integrated voice recognition-based method and system for analyzing vehicle driving behavior. The method includes: obtaining voice input content, analyzing the voice input content, and identifying vehicle driving problems; determining the driving link according to the vehicle driving problems, and retrieving real-time driving data according to the driving link; analyzing the real-time driving data, determining the problem relevance, and determining a solution according to the problem relevance. By extracting the voice input content, the problem described by the user can be quickly located, providing a clear direction for diagnosis and analysis. Associating the voice input content with specific driving links, and by retrieving real-time driving data, the actual operating state of the vehicle can be provided when the vehicle driving problem occurs, and the root cause of the vehicle driving problem can be identified; combining the real-time driving data with factors such as environmental factors and vehicle component performance to improve the accuracy and comprehensiveness of diagnosis.

Description

Technical Field

[0001] This application relates to the technical field, and in particular to a method and system for analyzing automotive driving behavior integrated with speech recognition. Background Art

[0002] With the continuous development of modern automotive technologies, driving behavior analysis has gradually become an important tool for improving driving safety, comfort, and vehicle maintenance management. Automotive driving behavior analysis can not only help drivers discover potential vehicle problems but also provide real-time feedback and corrective suggestions when faults or abnormal driving behaviors occur.

[0003] Traditional driving behavior analysis methods usually rely on real-time data from various sensors in the vehicle, such as throttle pedal opening, braking frequency, vehicle speed, acceleration, etc. Therefore, how to efficiently and accurately identify vehicle problems and provide solutions in a timely manner remains a major challenge for current vehicle diagnostic systems. Summary of the Invention

[0004] This application provides a method and system for analyzing automotive driving behavior integrated with speech recognition to solve the above problems.

[0005] In a first aspect, this application provides a method for analyzing automotive driving behavior integrated with speech recognition, the method comprising:

[0006] Obtaining speech input content, analyzing the speech input content, and identifying vehicle driving problems;

[0007] Determining a driving segment according to the vehicle driving problem, and retrieving real-time driving data according to the driving segment;

[0008] Analyzing the real-time driving data, determining problem relevance, and determining a solution according to the problem relevance.

[0009] Through this solution, the speech input provides a convenient way for users to report vehicle problems without manual operation, thereby reducing distractions during driving and improving driving safety. Converting the speech input content into text content improves the efficiency and accuracy of information processing. Through content extraction, quickly locate the problems described by the user, providing a clear direction for diagnosis and analysis. Associating the speech input content with specific driving segments helps to more accurately analyze and solve problems in driving segments. By retrieving real-time driving data, the actual operating state of the vehicle is provided when a vehicle driving problem occurs, providing an important data basis for diagnosis. By analyzing the real-time driving data, abnormal patterns in vehicle operation are discovered, which helps to identify the root cause of vehicle driving problems. Combining the real-time driving data with factors such as environmental factors and vehicle component performance improves the accuracy and comprehensiveness of diagnosis.

[0010] Optionally, the obtaining of the voice input content includes:

[0011] In response to a voice dialogue instruction triggered by the user, obtaining a voice signal collected by an in-vehicle microphone array;

[0012] Performing noise reduction and endpoint detection on the voice signal to extract an effective voice segment;

[0013] Converting the effective voice segment into text content to obtain the voice input content.

[0014] Through this solution, a natural interface for the user to interact with the vehicle device is provided, allowing the user to trigger the device function through voice instructions without distraction, improving driving safety. The in-vehicle microphone array can capture the sounds inside and outside the vehicle, providing a sound source for the voice recognition device, enabling the user to issue voice instructions from any position. The noise reduction process can significantly reduce the interference of environmental noise and in-vehicle noise, improving the accuracy of the voice recognition device. Endpoint detection can accurately identify the start point and end point of the voice, extract the effective voice segment, and avoid processing invalid information. By extracting the effective voice segment, focusing on processing the sound data related to the voice instruction, reducing the computational amount and processing time, and improving the response speed. The voice recognition device converts the voice signal into text content, which helps to analyze and respond to the specific needs of the user. The finally obtained voice input content contains the vehicle driving problems described by the user, providing information for further analysis and diagnosis, and helping to provide a more personalized solution.

[0015] Optionally, the analyzing of the voice input content to identify vehicle driving problems includes:

[0016] Extracting a keyword set from the voice input content, the keyword set including abnormal description words, component name words, and driving scenario words;

[0017] Analyzing the component name words and the driving scenario words to determine the vehicle driving link;

[0018] Analyzing the abnormal description words to determine the link problem;

[0019] Taking the link problem and the vehicle driving link as the vehicle driving problem.

[0020] Through this solution, by using natural language processing technology, a set of keywords is extracted from the user's voice input, which helps to identify the user's problem. Extracting the set of keywords helps to quickly locate vehicle driving problems. Abnormal description words such as abnormal noise and vibration help to identify the nature of the vehicle driving problem; component name words such as engine and brake help to determine the vehicle components involved in the vehicle driving problem; driving scenario words such as when accelerating and when turning help to determine the driving link where the problem occurs. By analyzing the set of keywords, determining which driving link the problem described by the user occurs in, such as accelerating, decelerating, turning, etc., helps to narrow the scope of problem diagnosis and improve the diagnosis efficiency. By analyzing the abnormal description words, determining the type of abnormality described by the user, such as mechanical failure and performance degradation, helps to provide a more accurate solution. Combining the link problem with the vehicle driving link to form a complete vehicle driving problem helps to provide a basis for real-time driving data retrieval, problem relevance analysis, and solution determination.

[0021] Optionally, retrieving the real-time driving data according to the driving link includes:

[0022] Analyze the voice input content to determine the trigger timestamp;

[0023] According to the voice trigger timestamp, determine the time window when the problem occurs;

[0024] Extract the multi-dimensional data stream within the time window from the vehicle sensors and controllers as the real-time driving data.

[0025] Through this solution, by analyzing the user's voice input content, the user's intentions and needs are identified, thus providing more personalized services. By determining the trigger timestamp of the user's voice command and accurately recording the time window when the problem occurs, it helps in the diagnosis and analysis of vehicle driving problems. Determining the time window when the problem occurs according to the trigger timestamp helps to obtain sufficient multi-dimensional data for analysis, thereby improving the accuracy of diagnosis. Extracting the multi-dimensional data stream within the time window from the vehicle sensors and controllers provides an important data basis for problem diagnosis.

[0026] Optionally, the real-time driving data includes the vehicle body's own data, and analyzing the real-time driving data to determine problem relevance includes:

[0027] Obtain the driving environment data during driving;

[0028] Based on the driving environment data, analyze the vehicle driving problem to determine the type of abnormality;

[0029] Analyze the real-time driving data to determine the frequency domain characteristics;

[0030] Determine the vibration resonance peak position associated with the abnormal type according to the frequency domain characteristics;

[0031] Determine the candidate abnormal components according to the vibration resonance peak position;

[0032] Analyze the vehicle body's own data to determine the problem relevance between the candidate abnormal components and the vehicle driving problems.

[0033] Through this solution, collecting the driving environment data of the vehicle during driving helps to identify the external conditions of the vehicle operation and also helps to analyze the environmental impact on the vehicle problems. By analyzing the driving environment data, the potential association between environmental factors and vehicle problems is identified. For example, a slippery road condition leads to a longer braking distance, thus affecting the braking performance of the vehicle. According to the determined abnormal type, a preliminary diagnosis result is provided to offer corresponding solutions to the user. Extracting the vehicle body's own data from vehicle sensors and controllers, such as speed, acceleration, engine speed, throttle pedal opening, brake state, etc., helps to reflect the actual operation state of the vehicle and also helps to analyze vehicle problems. The frequency domain characteristics help to diagnose vehicle driving problems related to vibration. The resonance peak position helps to determine the abnormal components with faults. The abnormal components are candidate abnormal components for further diagnosis and inspection. Determine the relevance between the candidate abnormal components and the vehicle driving problems described by the user, so as to provide accurate diagnosis results and solutions to the user. Determining the problem relevance helps the user to identify the vehicle condition in a timely manner and take corresponding maintenance measures.

[0034] Optionally, the determining the solution according to the problem relevance includes:

[0035] Analyze the driving environment data to determine the road slope and air humidity during driving;

[0036] Analyze the road slope and the air humidity to determine the environmental interference impact;

[0037] Determine the collaborative abnormality degree of the candidate abnormal components during driving according to the problem relevance;

[0038] Determine the solution according to the environmental interference impact and the collaborative abnormality degree.

[0039] Through this solution, by analyzing the driving environment data, the specific environmental conditions encountered by the vehicle during driving are identified, such as road gradient and air humidity. The driving environment data helps to diagnose the environmental interference effects on vehicle problems. By analyzing the road gradient and air humidity, the environmental interference effects on vehicle performance are determined, such as the gradient affecting the acceleration and braking performance of the vehicle, and the humidity affecting the tire grip and braking of the vehicle. By analyzing the problem relevance, the possibility of simultaneous anomalies of candidate abnormal components under the influence of environmental interference is determined, which helps to narrow down the problem scope and improve the accuracy of diagnosis. Combining the environmental interference effects and the co-anomaly degree of candidate abnormal components, a solution is determined to provide corresponding repair suggestions or operation guides for users.

[0040] Optionally, the driving environment data includes a road bump index. Analyzing the vehicle body's own data to determine the problem relevance between the candidate abnormal components and the vehicle driving problem includes:

[0041] Analyze the candidate abnormal components to determine the mechanical characteristics of the candidate abnormal components;

[0042] According to the mechanical characteristics, retrieve the preset component feature database to obtain the standard vibration frequency range of the candidate abnormal components;

[0043] Analyze the vibration resonance peak position in the frequency domain characteristics and calculate the offset between the vibration resonance peak position and the standard vibration frequency range;

[0044] According to the offset and the road bump index, determine the component anomaly confidence level of each candidate abnormal component, and calculate using the following formula:

[0045] ;

[0046] Wherein, represents the component anomaly confidence level; represents the offset; represents the influence weight of the offset on the component to generate an anomaly; represents the influence weight of the road bump index on the component to generate an anomaly; represents the road bump index;

[0047] According to the preset component feature database, determine the current wear condition of each candidate abnormal component;

[0048] According to the current wear condition, determine the anomaly threshold;

[0049] Compare the component anomaly confidence level with the anomaly threshold of the corresponding candidate abnormal component;

[0050] If the anomaly confidence level of the component exceeds the anomaly threshold of the corresponding candidate anomalous component, it is determined that there is a correlation between the candidate anomalous component and the vehicle driving problem.

[0051] Through this solution, by analyzing the mechanical characteristics of the candidate anomalous component, the performance parameters and expected behaviors of the selected anomalous component are identified. By retrieving the preset component feature database, the standard vibration frequency range of the candidate anomalous component is obtained, providing a reference for frequency domain analysis. Through frequency domain analysis, the positions of the vibration resonance peaks are identified, and the offset from the standard vibration frequency range is calculated, which helps to determine whether there is an anomaly in the candidate anomalous component. The anomaly confidence level of the component is calculated by a formula to quantify the likelihood of anomaly for each candidate component, thus providing a more accurate basis for diagnosis. Through the preset component feature database, the current wear condition of the candidate anomalous component is obtained, which helps to evaluate the aging and wear condition of the candidate anomalous component. According to the current wear condition of the candidate anomalous component, the anomaly threshold is determined, which helps to judge whether the performance of the candidate anomalous component exceeds the normal range. By comparing the anomaly confidence level of the component with the anomaly threshold, it is determined which candidate anomalous components are anomalous, providing diagnostic suggestions for the user. If the anomaly confidence level of the component exceeds the anomaly threshold, it is confirmed that there is a correlation between the candidate anomalous component and the vehicle driving problem and it is the cause of the problem, thus providing repair suggestions or operation guidelines for the user.

[0052] Optionally, determining the co-anomaly degree of the candidate anomalous component during driving according to the problem correlation includes:

[0053] Obtaining the sensor data related to the candidate anomalous component within the time window;

[0054] Analyzing the sensor data to determine the phase synchronization of the candidate anomalous component;

[0055] Calculating the cross-correlation coefficient between each sensor signal and each candidate anomalous component according to the phase synchronization;

[0056] Determining the co-anomaly degree of the candidate anomalous component during driving according to the cross-correlation coefficient.

[0057] Through this solution, collecting sensor data related to candidate abnormal components within a time window helps to analyze the basis of the performance of candidate abnormal components. By preprocessing the sensor data, the real-time working state and performance indicators of candidate abnormal components are identified. Analyzing the phase relationship between different sensor signals helps to determine whether the candidate abnormal components are working under the correct timing, thereby identifying potential collaborative abnormality degrees. By calculating the cross-correlation coefficient, quantifying the similarity and timing relationship between different sensor signals helps to evaluate the collaborative working conditions of candidate abnormal components. According to the cross-correlation coefficient, determining the collaborative abnormality degree of each candidate abnormal component during driving helps to identify which candidate abnormal components jointly cause vehicle problems.

[0058] Optionally, the method further includes:

[0059] After outputting the solution, monitor the vehicle state in real time, and according to the monitoring result, determine whether the user has solved the vehicle driving problem;

[0060] If not solved, form a maintenance assistance data packet with the vehicle driving problem and the real-time driving data.

[0061] Through this solution, clearly convey the determined solution to the user, including maintenance suggestions, adjustment methods or further inspection steps, so that the user can identify and take corresponding measures. By continuously monitoring the running state and sensor data of the vehicle, monitor the performance changes of the vehicle in real time to ensure the effectiveness of the measures taken by the user. Collect real-time driving data, such as vibration, temperature, speed, etc., and compare and analyze it with the solution output to the user to evaluate the effectiveness of the solution. According to the real-time monitoring result and analysis result, judge whether the user has successfully solved the vehicle driving problem, so as to provide feedback or further guidance to the user. If the problem is not solved, collect and organize the vehicle driving problem and real-time driving data to form a maintenance assistance data packet to provide necessary diagnostic information for maintenance personnel.

[0062] In a second aspect, the present application provides an integrated voice recognition-based vehicle driving behavior analysis system, the system includes:

[0063] A content analysis module, configured to obtain voice input content, analyze the voice input content, and identify vehicle driving problems;

[0064] A data retrieval module, configured to determine a driving link according to the vehicle driving problem, and retrieve real-time driving data according to the driving link;

[0065] A solution determination module, configured to analyze the real-time driving data, determine problem relevance, and determine a solution according to the problem relevance.

[0066] Optionally, when the content analysis module obtains the voice input content, it is used for:

[0067] In response to a voice dialogue instruction triggered by the user, obtain the voice signal collected by the vehicle-mounted microphone array;

[0068] Perform noise reduction and endpoint detection on the voice signal, and extract the effective voice segment;

[0069] Convert the effective voice segment into text content to obtain the voice input content.

[0070] Optionally, when the content analysis module analyzes the voice input content and identifies vehicle driving problems, it is used for:

[0071] Extract the keyword set in the voice input content, where the keyword set includes abnormal description words, component name words, and driving scenario words;

[0072] Analyze the component name words and the driving scenario words to determine the vehicle driving link;

[0073] Analyze the abnormal description words to determine the link problem;

[0074] Use the link problem and the vehicle driving link as the vehicle driving problem.

[0075] Optionally, when the data retrieval module retrieves real-time driving data according to the driving link, it is used for:

[0076] Analyze the voice input content to determine the trigger timestamp;

[0077] Determine the time window when the problem occurs according to the voice trigger timestamp;

[0078] Extract the multi-dimensional data stream within the time window from the vehicle sensors and controllers as the real-time driving data.

[0079] Optionally, the real-time driving data includes the vehicle body's own data. When the solution determination module analyzes the real-time driving data to determine the problem relevance, it is used for:

[0080] Obtain the driving environment data during driving;

[0081] Based on the driving environment data, analyze the vehicle driving problem to determine the abnormal type;

[0082] Analyze the real-time driving data to determine the frequency domain characteristics;

[0083] According to the frequency domain characteristics, determine the position of the vibration resonance peak associated with the abnormal type;

[0084] Determine candidate abnormal components according to the vibration resonance peak positions;

[0085] Analyze the vehicle body's own data to determine the problem relevance between the candidate abnormal components and the vehicle driving problems.

[0086] Optionally, when determining a solution according to the problem relevance, the solution determination module is used for:

[0087] Analyze the driving environment data to determine the road gradient and air humidity during driving;

[0088] Analyze the road gradient and the air humidity to determine the environmental interference impact;

[0089] Determine the collaborative abnormality degree of the candidate abnormal components during driving according to the problem relevance;

[0090] Determine a solution according to the environmental interference impact and the collaborative abnormality degree.

[0091] Optionally, the driving environment data includes a road bump index. When analyzing the vehicle body's own data to determine the problem relevance between the candidate abnormal components and the vehicle driving problems, the solution determination module is used for:

[0092] Analyze the candidate abnormal components to determine the mechanical characteristics of the candidate abnormal components;

[0093] According to the mechanical characteristics, retrieve a preset component feature database to obtain the standard vibration frequency range of the candidate abnormal components;

[0094] Analyze the vibration resonance peak positions in the frequency domain characteristics and calculate the offset between the vibration resonance peak positions and the standard vibration frequency range;

[0095] Determine the component abnormality confidence level of each candidate abnormal component according to the offset and the road bump index, and calculate using the following formula:

[0096] ;

[0097] Wherein, represents the component abnormality confidence level; represents the offset; represents the influence weight of the offset on the component to generate an abnormality; represents the influence weight of the road bump index on the component to generate an abnormality; represents the road bump index;

[0098] Determine the current wear condition of each candidate abnormal component according to the preset component feature database;

[0099] Determine an anomaly threshold according to the current wear condition;

[0100] Compare the component anomaly confidence level with the anomaly thresholds of the corresponding candidate anomaly components;

[0101] If the component anomaly confidence level exceeds the anomaly threshold of the corresponding candidate anomaly component, determine that there is a correlation between the candidate anomaly component and the vehicle driving problem.

[0102] Optionally, when the solution determination module determines the collaborative anomaly degree of the candidate anomaly component during driving according to the problem correlation, it is used for:

[0103] Obtain the sensor data related to the candidate anomaly component within the time window;

[0104] Analyze the sensor data to determine the phase synchronization of the candidate anomaly component;

[0105] Calculate the cross-correlation coefficient between each sensor signal and each candidate anomaly component according to the phase synchronization;

[0106] Determine the collaborative anomaly degree of the candidate anomaly component during driving according to the cross-correlation coefficient.

[0107] Optionally, the integrated voice recognition-based vehicle driving behavior analysis system further includes a data formation module, which is used for:

[0108] After outputting the solution, monitor the vehicle state in real time, and determine whether the user has solved the vehicle driving problem according to the monitoring result;

[0109] If not solved, form a maintenance assistance data packet with the vehicle driving problem and the real-time driving data. Brief Description of the Drawings

[0110] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0111] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0112] Figure 2 It is a flowchart of a method for analyzing vehicle driving behavior with integrated voice recognition provided by an embodiment of the present application;

[0113] Figure 3Schematic structural diagram of an in-vehicle driving behavior analysis system integrating speech recognition provided by an embodiment of the present application. Detailed implementation manners

[0114] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0115] In addition, the term "and / or" in this article is only an associative relationship describing associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, both A and B exist simultaneously, and B exists alone. These three situations. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0116] The embodiments of the present application will be further described in detail below with reference to the accompanying drawings of the specification.

[0117] Traditional driving behavior analysis methods usually rely on real-time data from various sensors in the vehicle, such as throttle pedal opening, braking frequency, vehicle speed, acceleration, etc. Therefore, how to efficiently and accurately identify vehicle problems and provide solutions in a timely manner remains a major challenge for current vehicle diagnostic systems.

[0118] Based on this, the present application provides an in-vehicle driving behavior analysis method and system integrating speech recognition, which obtains speech input content, analyzes the speech input content, and identifies vehicle driving problems; according to the vehicle driving problems, determines the driving link, and according to the driving link, retrieves real-time driving data; analyzes the real-time driving data, determines the problem relevance, and according to the problem relevance, determines the solution. The speech input provides a convenient way for users to report vehicle problems without manual operation, thereby reducing distractions during driving and improving driving safety. Converting the speech input content into text content improves the efficiency and accuracy of information processing. Through content extraction, quickly locate the problems described by the user, providing a clear direction for diagnosis and analysis. Associating the speech input content with specific driving links helps to more accurately analyze and solve problems in the driving links. By retrieving real-time driving data, the actual operating state of the vehicle is provided when a vehicle driving problem occurs, providing an important data basis for diagnosis. By analyzing the real-time driving data, abnormal patterns in vehicle operation are discovered, which helps to identify the root causes of vehicle driving problems. Combining the real-time driving data with environmental factors, vehicle component performance and other factors improves the accuracy and comprehensiveness of diagnosis.

[0119] Figure 1 A schematic diagram of an application scenario provided for this application. When analyzing driving behavior, the method provided by this application is applied. Specifically, the method provided by this application is applied to any in-vehicle chip. The in-vehicle chip interacts with the user. The voice input provides a convenient way for the user to report vehicle problems without manual operation, thereby reducing distractions during driving and improving driving safety. Convert the voice input content into text content to improve the efficiency and accuracy of information processing. Through content extraction, quickly locate the problems described by the user and provide a clear direction for diagnosis and analysis. Associate the voice input content with specific driving links, which helps to more accurately analyze and solve problems in driving links. By retrieving real-time driving data, provide the actual operating status of the vehicle when a vehicle driving problem occurs, providing an important data basis for diagnosis. By analyzing real-time driving data, discover abnormal patterns in vehicle operation, which helps to identify the root causes of vehicle driving problems. Combine real-time driving data with environmental factors, vehicle component performance and other factors to improve the accuracy and comprehensiveness of diagnosis.

[0120] For the specific implementation method, reference can be made to the following embodiments.

[0121] Figure 2 A flowchart of a method for analyzing automotive driving behavior with integrated speech recognition provided for an embodiment of this application. The method of this embodiment can be applied to the in-vehicle chip in the above scenario. As Figure 2 shown, the method includes:

[0122] S201. Obtain the voice input content, analyze the voice input content, and identify vehicle driving problems;

[0123] The voice input content can be a description collected by the in-vehicle microphone array and converted into text content through a voice dialogue command by the user.

[0124] Vehicle driving problems can be various problems encountered during driving, such as vehicle performance, driving experience, safety warnings, etc.

[0125] Specifically, the user triggers the voice recognition device by pressing a button or saying a specific wake-up word. The in-vehicle microphone array captures the user's voice signal. Perform preprocessing such as noise reduction and endpoint detection on the collected voice signal. Convert the processed voice signal into text content. Perform semantic analysis on the converted text content to extract a keyword set such as abnormal description words, component name words, and driving scenario words. According to the extracted keyword set, identify vehicle driving problems described by the user, such as abnormal engine noise and abnormal feeling of the brake pedal.

[0126] S202. Determine the driving link according to the vehicle driving problem, and retrieve real-time driving data according to the driving link;

[0127] The driving operations can be driving behaviors or operations such as acceleration, deceleration, turning, and gear shifting encountered during driving.

[0128] The real-time driving data can be real-time data extracted from vehicle sensors and controllers, reflecting the current operating state of the vehicle.

[0129] Specifically, according to the vehicle driving problem, analyze the driving operations where the vehicle driving problem occurs. Using natural language processing technology, extract content such as acceleration, turning, and braking related to the driving operations from the voice input content. According to the determined driving operations, determine the time window when the problem occurs. Extract the multi-dimensional data stream within the time window from the vehicle sensors and controllers, that is, the real-time driving data.

[0130] S203. Analyze the real-time driving data, determine the problem relevance, and based on the problem relevance, determine the solution.

[0131] The problem relevance can be to determine the relevance between the vehicle driving problem and abnormal components or driving behaviors through the analysis of the real-time driving data.

[0132] The solution can be a processing solution provided for the user according to the analysis result of the problem relevance.

[0133] Specifically, perform preprocessing such as data cleaning and normalization on the extracted data. Analyze the vehicle body data such as the change rate of the throttle pedal opening, braking frequency, gear shifting operation, engine speed, steering wheel angle, and tire pressure. Use Fourier transform signal processing technology to perform frequency domain analysis on the real-time driving data to identify frequency domain features such as vibration resonance peaks and frequency mutations. Based on the driving environment data and the vehicle body data, analyze the vehicle driving problem and determine the abnormal type. Analyze the frequency domain features of the real-time driving data to identify the vibration resonance peak positions related to the abnormal type. According to the resonance peak positions, determine the candidate abnormal components. Analyze the driving environment data to determine environmental factors such as road slope and air humidity during driving. Analyze the influence of environmental interference. According to the problem relevance, determine the collaborative abnormality degree of the candidate abnormal components during driving. Integrate the influence of environmental interference and the collaborative abnormality degree to determine the final solution.

[0134] Through this solution, voice input provides a convenient way for users to report vehicle problems without manual operation, thereby reducing distractions during driving and improving driving safety. Convert the voice input content into text content to improve the efficiency and accuracy of information processing. Through content extraction, quickly locate the problems described by the user, providing a clear direction for diagnosis and analysis. Associate the voice input content with specific driving scenarios, which helps to more accurately analyze and solve problems in driving scenarios. By retrieving real-time driving data, provide the actual operating status of the vehicle when a vehicle driving problem occurs, providing an important data basis for diagnosis. By analyzing real-time driving data, discover abnormal patterns in vehicle operation, which helps to identify the root causes of vehicle driving problems. Combine real-time driving data with environmental factors, vehicle component performance and other factors to improve the accuracy and comprehensiveness of diagnosis.

[0135] In some embodiments, in response to a voice dialogue instruction triggered by the user, obtain a voice signal collected by an in-vehicle microphone array; perform noise reduction and endpoint detection on the voice signal, and extract an effective voice segment; convert the effective voice segment into text content to obtain the voice input content.

[0136] The voice dialogue instruction can be an instruction issued by the user to the in-vehicle device in a voice manner.

[0137] The in-vehicle microphone array can be an array composed of multiple microphones installed in the vehicle for capturing sounds inside and outside the vehicle.

[0138] The voice signal can be a sound wave emitted by the user through the in-vehicle microphone array. The sound wave is converted into an electrical signal by the microphone and then transmitted to a voice recognition device for processing.

[0139] The effective voice segment can be the part of the voice signal that is confirmed to contain useful information after endpoint detection and noise reduction processing.

[0140] The text content can be the content in text form converted from the effective voice segment by the voice recognition device.

[0141] Specifically, preset a wake word and use a wake word detection algorithm to identify the user's voice dialogue instruction. Once the wake word is detected, the voice recognition device is activated and ready to receive and process the user's voice dialogue instruction. Capture the voice signal emitted by the user through the in-vehicle microphone array. Perform noise reduction processing on the collected voice signal, and at the same time use an endpoint detection algorithm to determine the start point and end point of the voice signal, thereby extracting the effective voice segment. Input the extracted effective voice segment into the voice recognition device, and through the voice recognition engine, convert the voice signal into text content to generate the voice input content.

[0142] Through this solution, a natural interface for user-vehicle device interaction is provided, allowing users to trigger device functions through voice commands without distraction, thereby enhancing driving safety. The in-vehicle microphone array can capture sounds inside and outside the vehicle, providing a sound source for the voice recognition device, enabling users to issue voice commands from any position. Noise reduction processing can significantly reduce the interference of environmental noise and in-vehicle noise, improving the accuracy of the voice recognition device. Endpoint detection can accurately identify the start and end points of speech, extract valid speech segments, and avoid processing invalid information. By extracting valid speech segments, focusing on processing the sound data related to voice commands, the computational load and processing time are reduced, and the response speed is increased. The voice recognition device converts the voice signal into text content, facilitating the analysis and response to the specific needs of users. The finally obtained voice input content contains the vehicle driving problems described by users, providing information for further analysis and diagnosis, and helping to provide more personalized solutions.

[0143] In some embodiments, a set of keywords is extracted from the voice input content; the component name words and driving scenario words are analyzed to determine the vehicle driving links; the abnormal description words are analyzed to determine the problems in the links; the problems in the links and the vehicle driving links are used as the vehicle driving problems.

[0144] The set of keywords can be a set of key information extracted from the voice input content, and the set of keywords includes abnormal description words, component name words, and driving scenario words.

[0145] The abnormal description words can be words such as abnormal noise, vibration, and jamming used to describe abnormal vehicle phenomena.

[0146] The component name words can be the names of vehicle components such as the engine, brakes, and tires mentioned when describing problems.

[0147] The driving scenario words can be driving environments such as when accelerating, when turning, and when driving at high speed mentioned when describing problems.

[0148] The problems in the links can be specific problems such as lack of power during acceleration and abnormal feeling of the brake pedal that occur in the driving links.

[0149] Specifically, natural language processing technology is used to perform semantic analysis on the user's voice input content to identify a keyword set containing abnormal description words, component name words, and driving scenario words. Based on the identified component name words, the vehicle components mentioned by the user are determined. Based on the identified driving scenario words, the driving stage where the problem occurs is determined. The identified component name words are associated with the driving scenario words, and according to the association result, the vehicle driving stage is determined. The abnormal description words are analyzed to determine the nature of the vehicle driving problem. Combining the abnormal description words with the determined vehicle driving stage, the stage problem is thus determined. Combining the determined stage problem with the vehicle driving stage forms a complete vehicle driving problem.

[0150] Through this solution, by using natural language processing technology, a keyword set is extracted from the user's voice input, which helps to identify the user's problem. Extracting the keyword set helps to quickly locate the vehicle driving problem. Abnormal description words such as abnormal noise and vibration help to identify the nature of the vehicle driving problem; component name words such as engine and brake help to determine the vehicle components involved in the vehicle driving problem; driving scenario words such as when accelerating and when turning help to determine the driving stage where the problem occurs. By analyzing the keyword set, determining in which driving stage the problem described by the user occurs, such as accelerating, decelerating, turning, etc., helps to narrow down the scope of problem diagnosis and improve the diagnosis efficiency. By analyzing the abnormal description words, determining the type of abnormality described by the user, such as mechanical failure and performance degradation, helps to provide a more accurate solution. Combining the stage problem with the vehicle driving stage to form a complete vehicle driving problem helps to provide a basis for real-time driving data retrieval, problem relevance analysis, and solution determination.

[0151] In some embodiments, the voice input content is analyzed to determine the trigger timestamp; according to the voice trigger timestamp, the time window when the problem occurs is determined; and multi-dimensional data streams within the time window are extracted from vehicle sensors and controllers as real-time driving data.

[0152] The trigger timestamp can be the exact time point when the user issues a voice command and can be represented in the format of date and time.

[0153] The time window can be a time period before and after the trigger timestamp and can be represented in the form of a time range.

[0154] The multi-dimensional data streams can be real-time driving data such as speed, acceleration, throttle pedal opening, brake state, and engine speed extracted from vehicle sensors and controllers.

[0155] Specifically, natural language processing technology is used to perform semantic analysis on the user's voice input content. Through the voice input content, the exact time point when the user issues a voice command, that is, the trigger timestamp, is determined. According to the trigger timestamp, the time window when the problem occurs is determined. Multidimensional data streams such as speed, acceleration, throttle pedal opening, brake state, engine speed, etc. within the time window are extracted from vehicle sensors and controllers, and the multidimensional data streams are used as real-time driving data.

[0156] Through this solution, by analyzing the user's voice input content, the user's intentions and needs are identified, thereby providing more personalized services. By determining the trigger timestamp of the user's voice command and accurately recording the time window when the problem occurs, it helps in diagnosing and analyzing vehicle driving problems. Determining the time window when the problem occurs according to the trigger timestamp helps in obtaining sufficient multidimensional data for analysis, thereby improving the accuracy of diagnosis. Extracting multidimensional data streams within the time window from vehicle sensors and controllers provides an important data basis for problem diagnosis.

[0157] In some embodiments, driving environment data during driving is obtained; based on the driving environment data, vehicle driving problems are analyzed to determine the abnormal type; the real-time driving data is analyzed to determine the frequency domain characteristics; according to the frequency domain characteristics, the vibration resonance peak positions associated with the abnormal type are determined; according to the vibration resonance peak positions, candidate abnormal components are determined; the vehicle body's own data is analyzed to determine the problem relevance between the candidate abnormal components and the vehicle driving problems.

[0158] The driving environment data can be external environment information such as road gradient, road surface condition, air humidity, temperature, light condition, etc. collected by the vehicle during driving.

[0159] The abnormal type can be the classification of abnormal phenomena that occur during vehicle driving.

[0160] The frequency domain characteristics can be the characteristics obtained after performing frequency domain analysis on the vehicle body vibration signal.

[0161] The vibration resonance peak position can be the frequency position related to the vehicle body vibration in the frequency domain analysis result.

[0162] The candidate abnormal components can be a list of components that malfunction according to the frequency domain characteristics and the abnormal type.

[0163] The vehicle body's own data can be data such as speed, acceleration, engine speed, throttle pedal opening, brake state, etc. collected by the vehicle during driving and reflecting the vehicle's own operating state.

[0164] Specifically, driving environment data such as road gradient, road surface condition, air humidity, and temperature are obtained from vehicle sensors. The driving environment data is analyzed to analyze the impact of environmental factors on vehicle performance. Based on the analysis results, the abnormal type of vehicle driving problems is determined. Body self - data is extracted from vehicle sensors and controllers. The fast Fourier transform technique is used to perform frequency - domain analysis on the body self - data to identify frequency - domain features such as vibration modes and resonance frequencies. According to the frequency - domain features, the vibration resonance peak positions related to vehicle body vibration are identified. According to the vibration resonance peak positions, the faulty components are matched with the preset component feature database to determine candidate abnormal components. Based on the vehicle's own data, the standard vibration frequency range of the candidate abnormal components is analyzed and compared with the actually measured vibration frequency. According to the analysis results, the problem relevance between the candidate abnormal components and the vehicle driving problems is determined.

[0165] Through this solution, collecting driving environment data during vehicle driving helps to identify the external conditions of vehicle operation and also helps to analyze the environmental impact on vehicle problems. By analyzing the driving environment data, the potential association between environmental factors and vehicle problems is identified. For example, a slippery road condition leads to a longer braking distance, thus affecting the braking performance of the vehicle. According to the determined abnormal type, a preliminary diagnosis result is provided to offer corresponding solutions for users. Extracting body self - data such as speed, acceleration, engine speed, throttle pedal opening, and braking state from vehicle sensors and controllers helps to reflect the actual operating state of the vehicle and also helps to analyze vehicle problems. Frequency - domain features help to diagnose vehicle driving problems related to vibration. The resonance peak position helps to determine the abnormal components with faults. The abnormal components are candidate abnormal components for further diagnosis and inspection. Determining the relevance between the candidate abnormal components and the vehicle driving problems described by the user provides accurate diagnosis results and solutions for the user. Determining the problem relevance helps users to promptly identify the vehicle condition and take corresponding maintenance measures.

[0166] In some embodiments, the driving environment data is analyzed to determine the road gradient and air humidity during driving; the road gradient and air humidity are analyzed to determine the environmental interference impact; according to the problem relevance, the co - abnormal degree of the candidate abnormal components during driving is determined; based on the environmental interference impact and the co - abnormal degree, a solution is determined.

[0167] The road gradient can be the inclination degree of the road surface, which can be expressed in angles.

[0168] The air humidity can be the amount of water vapor in the atmosphere, which can be expressed in relative humidity (%).

[0169] The environmental interference impact can be the potential negative impact of driving environment data on vehicle performance and driving experience.

[0170] The collaborative anomaly degree can be the possibility that candidate abnormal components simultaneously exhibit anomalies under the influence of environmental interference.

[0171] Specifically, collect driving environment data such as road gradient and air humidity. Analyze the environmental interference effects of road gradient and air humidity on vehicle performance. Use speech recognition technology to analyze vehicle driving problems in the voice input content, combine the vehicle driving problems with the environmental interference effects and real-time driving data, and analyze the problem relevance. Based on the problem relevance, determine candidate abnormal components that may malfunction. Analyze the collaborative anomaly degree of the candidate abnormal components during driving, that is, the possibility that the candidate abnormal components simultaneously exhibit anomalies under the influence of environmental interference. Combine the environmental interference effects and the collaborative anomaly degree of the candidate abnormal components to determine a solution.

[0172] Through this solution, by analyzing driving environment data, identify the specific environmental conditions encountered by the vehicle during driving, such as road gradient and air humidity. The driving environment data helps diagnose the environmental interference effects on vehicle problems. By analyzing the road gradient and air humidity, determine the environmental interference effects of the road gradient and air humidity on vehicle performance, such as the gradient affecting the acceleration and braking performance of the vehicle, and the humidity affecting the tire grip and braking of the vehicle. By analyzing the problem relevance, determine the possibility that candidate abnormal components simultaneously exhibit anomalies under the influence of environmental interference, which helps narrow down the problem scope and improve the accuracy of diagnosis. Combine the environmental interference effects and the collaborative anomaly degree of the candidate abnormal components to determine a solution and provide corresponding maintenance suggestions or operation guides for users.

[0173] In some embodiments, analyze the candidate abnormal components to determine their mechanical characteristics; according to the mechanical characteristics, retrieve the preset component feature database to obtain the standard vibration frequency range of the candidate abnormal components; analyze the position of the vibration resonance peak in the frequency domain characteristics, and calculate the offset between the position of the vibration resonance peak and the standard vibration frequency range; according to the offset and the road surface bump index, determine the component anomaly confidence level of each candidate abnormal component, and calculate using the following formula:

[0174] (1)

[0175] Where, represents the component anomaly confidence level; represents the offset; represents the influence weight of the offset on the component generating anomalies; represents the influence weight of the road surface bump index on the component generating anomalies; Indicates the road surface bump index; determine the current wear condition of each candidate abnormal component according to the preset component feature database; determine the abnormal threshold according to the current wear condition; compare the component abnormal confidence level with the abnormal threshold of the corresponding candidate abnormal component; if the component abnormal confidence level exceeds the abnormal threshold of the corresponding candidate abnormal component, determine that there is a correlation between the candidate abnormal component and the vehicle driving problem.

[0176] The mechanical characteristics can be the physical and mechanical performance parameters of each component of the vehicle.

[0177] The preset component feature database can be a pre-set database containing the characteristic parameters of each component of the vehicle under normal working conditions. It is pre-stored in the vehicle-mounted chip and called when in use.

[0178] The standard vibration frequency range can be the vibration frequency range expected for each component of the vehicle under normal working conditions.

[0179] The offset can be the difference between the actual measurement data and the standard value in the preset component feature database.

[0180] The road surface bump index can be a quantitative index of the road surface bump degree.

[0181] The component abnormal confidence level can be the confidence level of the device's judgment on component abnormality.

[0182] The influence weight can be the relative importance of different factors such as environmental factors, driving behavior, and component status on vehicle performance.

[0183] The current wear condition can be the current wear degree of each component of the vehicle.

[0184] The abnormal threshold can be the critical value of component performance abnormality defined in the preset component feature database.

[0185] Specifically, conduct a detailed mechanical characteristic analysis on the candidate abnormal component, such as hardness, elastic modulus, strength, etc. According to the mechanical characteristics of the candidate abnormal component, obtain the standard vibration frequency range of the candidate abnormal component under normal working conditions from the preset component feature database. Conduct a frequency domain analysis on the vehicle body vibration signal, identify the position of the vibration resonance peak, and compare it with the standard vibration frequency range to calculate the offset ( )). Obtain the road surface bump index according to the measurement of the vehicle's suspension device sensor. Use formula (1) to calculate the component abnormal confidence level ( ). Obtain the current wear conditions of the candidate abnormal components, such as the degree of wear and service life, from the preset component feature database. Determine the critical value of component performance abnormality, i.e., the abnormality threshold, based on the current wear conditions of the candidate abnormal components. Compare the calculated component abnormality confidence level with the abnormality threshold to determine whether the component is beyond the normal range. If the component abnormality confidence level exceeds the abnormality threshold, there is a correlation between the candidate abnormal component and the vehicle driving problem.

[0186] Through this solution, by analyzing the mechanical characteristics of the candidate abnormal components, identify the performance parameters and expected behaviors of the selected abnormal components. By retrieving the preset component feature database, obtain the standard vibration frequency range of the candidate abnormal components to provide a reference for frequency-domain analysis. Through frequency-domain analysis, identify the positions of vibration resonance peaks and calculate the offset from the standard vibration frequency range, which helps to determine whether there are abnormalities in the candidate abnormal components. Calculate the component abnormality confidence level through a formula to quantify the possibility of abnormality for each candidate component, thus providing a more accurate basis for diagnosis. Through the preset component feature database, obtain the current wear conditions of the candidate abnormal components, which helps to evaluate the aging and wear conditions of the candidate abnormal components. Determine the abnormality threshold based on the current wear conditions of the candidate abnormal components, which helps to judge whether the performance of the candidate abnormal components exceeds the normal range. By comparing the component abnormality confidence level and the abnormality threshold, determine which candidate abnormal components are abnormal and provide diagnostic suggestions for users. If the component abnormality confidence level exceeds the abnormality threshold, confirm that there is a correlation between the candidate abnormal component and the vehicle driving problem and it is the cause of the problem, thus providing maintenance suggestions or operation guides for users.

[0187] In some embodiments, obtain the sensor data related to the candidate abnormal components within a time window; analyze the sensor data to determine the phase synchronization of the candidate abnormal components; calculate the cross-correlation coefficient between each sensor signal and each candidate abnormal component according to the phase synchronization; determine the collaborative abnormality degree of the candidate abnormal components during driving according to the cross-correlation coefficient.

[0188] The sensor data can be the data collected from various sensors of the vehicle, including throttle opening, brake pressure, and engine speed.

[0189] The phase synchronization can be the phase relationship between different sensor signals, i.e., the relative positions of different sensor signals in time.

[0190] The sensor signal can be the electrical signal output by the sensor, which is the specific manifestation of the sensor data.

[0191] The cross-correlation coefficient can be a measure of the correlation degree between two sensor signals.

[0192] Specifically, sensor data such as vibration sensors and temperature sensors related to candidate abnormal components within a time window are collected from the vehicle's sensors. The collected sensor data is preprocessed, such as data cleaning and normalization. Hilbert transform is performed on the sensor data and the component vibration signal to calculate the standard deviation of the instantaneous phase difference. Based on the standard deviation, the phase synchronization of the sensor data is analyzed, that is, the phase relationship between different sensor signals is analyzed. According to the phase synchronization, the sensor signals are time-synchronized to ensure that different sensor signals are compared within the same time window. The cross-correlation function of each pair of sensor signals and the candidate abnormal component is calculated. The maximum value, that is, the cross-correlation coefficient, is extracted from the cross-correlation function. The calculated cross-correlation coefficient is analyzed to evaluate the collaborative working condition between the candidate abnormal component and other components. A weighted scoring model including the peak value of the cross-correlation coefficient, time delay, and signal energy ratio is established to output a normalized score in the range of 0-1. According to the evaluation and the normalized score, the collaborative abnormality degree of each candidate abnormal component is determined.

[0193] Through this solution, collecting sensor data related to candidate abnormal components within a time window helps to analyze the basis of the performance of candidate abnormal components. By preprocessing the sensor data, the real-time working state and performance indicators of candidate abnormal components are identified. Analyzing the phase relationship between different sensor signals helps to determine whether the candidate abnormal component is working under the correct timing sequence, thereby identifying potential collaborative abnormality degrees. By calculating the cross-correlation coefficient, quantifying the similarity and timing relationship between different sensor signals helps to evaluate the collaborative working condition between candidate abnormal components. According to the cross-correlation coefficient, determining the collaborative abnormality degree of each candidate abnormal component during vehicle driving helps to identify which candidate abnormal components jointly cause vehicle problems.

[0194] In some embodiments, after the solution is output, the vehicle state is monitored in real time. According to the monitoring result, it is determined whether the user has solved the vehicle driving problem; if not, the vehicle driving problem and real-time driving data are formed into a maintenance assistance data packet.

[0195] The vehicle state can be real-time operating states such as the engine speed, vehicle speed, accelerator pedal position, brake state, and suspension equipment working state during vehicle driving.

[0196] The monitoring result can be the output after real-time monitoring and analysis of the vehicle state.

[0197] The maintenance assistance data packet can be a file or information set containing the vehicle driving problem and real-time driving data collected and sorted when the user fails to solve the vehicle driving problem.

[0198] Specifically, solutions such as maintenance suggestions, adjustment methods, and further inspection steps are output to the user in the form of text or voice. After the user attempts to solve the vehicle driving problem, the running state of the vehicle and sensor data are continuously monitored in real time. Real-time driving data such as the running state of the vehicle and sensor data are collected and compared and analyzed with the solutions output to the user. According to the real-time monitoring results and analysis results, it is evaluated whether the user has successfully solved the vehicle driving problem. If the user fails to solve the vehicle driving problem, the collected and sorted vehicle driving problems and real-time driving data are formed into a maintenance assistance data packet.

[0199] Through this solution, a definite solution is clearly communicated to the user, including maintenance suggestions, adjustment methods, or further inspection steps, enabling the user to identify and take corresponding measures. By continuously monitoring the running state of the vehicle and sensor data, the performance changes of the vehicle are monitored in real time to ensure the effectiveness of the measures taken by the user. Real-time driving data such as vibration, temperature, and speed are collected and compared and analyzed with the solutions output to the user to evaluate the effectiveness of the solutions. According to the real-time monitoring results and analysis results, it is judged whether the user has successfully solved the vehicle driving problem, so as to provide feedback or further guidance to the user. If the problem is not solved, the vehicle driving problems and real-time driving data are collected and sorted to form a maintenance assistance data packet, providing necessary diagnostic information for maintenance personnel.

[0200] Figure 3 As shown in the following figure, it is a schematic structural diagram of an integrated voice recognition-based vehicle driving behavior analysis system provided by an embodiment of the present application. Figure 3 As shown, the integrated voice recognition-based vehicle driving behavior analysis system 300 of this embodiment includes: a content analysis module 301, a data retrieval module 302, and a solution determination module 303.

[0201] The content analysis module 301 is used to obtain the voice input content, analyze the voice input content, and identify vehicle driving problems;

[0202] The data retrieval module 302 is used to determine the driving link according to the vehicle driving problem, and retrieve real-time driving data according to the driving link;

[0203] The solution determination module 303 is used to analyze the real-time driving data, determine the problem relevance, and determine a solution according to the problem relevance.

[0204] Optionally, when the content analysis module 301 obtains the voice input content, it is used for:

[0205] In response to the voice dialogue instruction triggered by the user, obtain the voice signal collected by the in-vehicle microphone array;

[0206] Perform noise reduction and endpoint detection on the voice signal, and extract the effective voice segment;

[0207] Convert the effective voice segment into text content to obtain the voice input content.

[0208] Optionally, when the content analysis module 301 analyzes the voice input content and identifies a vehicle driving problem, it is used for:

[0209] Extract the keyword set from the voice input content, where the keyword set includes abnormal description words, component name words, and driving scenario words;

[0210] Analyze the component name words and the driving scenario words to determine the vehicle driving link;

[0211] Analyze the abnormal description words to determine the link problem;

[0212] Use the link problem and the vehicle driving link as the vehicle driving problem.

[0213] Optionally, when the data retrieval module 302 retrieves real-time driving data according to the driving link, it is used for:

[0214] Analyze the voice input content to determine the trigger timestamp;

[0215] Determine the time window when the problem occurs according to the voice trigger timestamp;

[0216] Extract the multi-dimensional data stream within the time window from the vehicle sensors and controllers as the real-time driving data.

[0217] Optionally, the real-time driving data includes the vehicle body's own data. When the solution determination module 303 analyzes the real-time driving data to determine the problem relevance, it is used for:

[0218] Obtain the driving environment data during driving;

[0219] Based on the driving environment data, analyze the vehicle driving problem to determine the abnormal type;

[0220] Analyze the real-time driving data to determine the frequency domain characteristics;

[0221] According to the frequency domain characteristics, determine the vibration resonance peak position associated with the abnormal type;

[0222] According to the vibration resonance peak position, determine the candidate abnormal component;

[0223] Analyze the vehicle body's own data to determine the problem relevance between the candidate abnormal component and the vehicle driving problem.

[0224] Optionally, when determining a solution according to the problem relevance, the solution determination module 303 is configured to:

[0225] Analyze the driving environment data to determine the road gradient and air humidity during driving;

[0226] Analyze the road gradient and the air humidity to determine the environmental interference impact;

[0227] According to the problem relevance, determine the collaborative anomaly degree of the candidate abnormal component during driving; according to the environmental interference impact and the collaborative anomaly degree, determine a solution.

[0228] Optionally, the driving environment data includes a road bump index. When analyzing the vehicle body itself data to determine the problem relevance between the candidate abnormal component and the vehicle driving problem, the solution determination module 303 is configured to:

[0229] Analyze the candidate abnormal component to determine the mechanical characteristics of the candidate abnormal component;

[0230] According to the mechanical characteristics, retrieve a preset component feature database to obtain the standard vibration frequency range of the candidate abnormal component;

[0231] Analyze the vibration resonance peak position in the frequency domain characteristics, and calculate the offset between the vibration resonance peak position and the standard vibration frequency range;

[0232] According to the offset and the road bump index, determine the component anomaly confidence of each candidate abnormal component, and calculate using the following formula:

[0233] ;

[0234] Wherein, represents the component anomaly confidence; represents the offset; represents the influence weight of the offset on the component to generate an anomaly; represents the influence weight of the road bump index on the component to generate an anomaly; represents the road bump index;

[0235] According to the preset component feature database, determine the current wear condition of each candidate abnormal component;

[0236] According to the current wear condition, determine an anomaly threshold;

[0237] Compare the component anomaly confidence with the anomaly threshold of the corresponding candidate abnormal component;

[0238] If the abnormal confidence level of the component exceeds the abnormal threshold of the corresponding candidate abnormal component, it is determined that there is a correlation between the candidate abnormal component and the vehicle driving problem.

[0239] Optionally, when determining the collaborative abnormality degree of the candidate abnormal component during driving according to the problem correlation by the solution determination module 303, it is used for:

[0240] Obtain the sensor data related to the candidate abnormal component within the time window;

[0241] Analyze the sensor data to determine the phase synchronization of the candidate abnormal component;

[0242] According to the phase synchronization, calculate the cross-correlation coefficient between each sensor signal and each candidate abnormal component;

[0243] According to the cross-correlation coefficient, determine the collaborative abnormality degree of the candidate abnormal component during driving.

[0244] Optionally, the vehicle driving behavior analysis system integrated with speech recognition further includes a data formation module 304, which is used for:

[0245] After outputting the solution, monitor the vehicle state in real time, and according to the monitoring result, determine whether the user has solved the vehicle driving problem;

[0246] If not solved, form a maintenance assistance data packet with the vehicle driving problem and the real-time driving data.

[0247] The system of this embodiment can be used to execute the method of any of the above embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here.

Claims

1. A method for analyzing automobile driving behavior with integrated speech recognition, characterized in that: include: Acquire voice input content, analyze the voice input content, and identify vehicle driving problems; Determine the driving link according to the vehicle driving problem, and retrieve real-time driving data according to the driving link; Analyze the real-time driving data to determine the relevance of the problem, and determine a solution based on the relevance of the problem; The step of retrieving real-time driving data according to the driving link includes: Analyze the voice input content to determine a trigger timestamp; Determine the time window when the problem occurred based on the voice trigger timestamp; Extracting the multi-dimensional data stream within the time window from the vehicle sensor and controller as the real-time driving data; The real-time driving data includes vehicle body data, and the analyzing the real-time driving data to determine the problem correlation includes: Acquire driving environment data during driving; Analyzing the vehicle driving problem based on the driving environment data to determine the abnormality type; Analyze the real-time driving data to determine frequency domain characteristics; Determining, based on the frequency domain characteristics, a vibration resonance peak position associated with the abnormal type; Determining a candidate abnormal component according to the vibration resonance peak position; Analyzing the vehicle body data to determine the problem correlation between the candidate abnormal component and the vehicle driving problem; The driving environment data includes a road bump index, and the analyzing the vehicle body data to determine the problem correlation between the candidate abnormal component and the vehicle driving problem includes: Analyzing the candidate abnormal component to determine the mechanical properties of the candidate abnormal component; According to the mechanical characteristics, a preset component feature database is retrieved to obtain a standard vibration frequency range of the candidate abnormal component; Analyzing the vibration resonance peak position in the frequency domain characteristics, and calculating the offset between the vibration resonance peak position and the standard vibration frequency range; According to the offset and the road bump index, the component abnormality confidence of each candidate abnormal component is determined and calculated using the following formula: ； in, Indicates the abnormal confidence level of the component; represents the offset; Indicates the influence weight of the offset on the abnormality of the component; Indicates the influence weight of the road bump index on the abnormality of the component; represents the road bumpiness index; Determining the current wear condition of each candidate abnormal component according to the preset component feature database; determining an abnormal threshold value according to the current wear condition; Comparing the component abnormality confidence with the abnormality threshold of the corresponding candidate abnormal component; If the component abnormality confidence exceeds the abnormality threshold of the corresponding candidate abnormal component, it is determined that the candidate abnormal component is associated with the vehicle driving problem.

2. The method according to claim 1, characterized in that The obtaining of voice input content includes: In response to a voice dialogue command triggered by a user, a voice signal collected by an onboard microphone array is acquired; Performing noise reduction and endpoint detection on the speech signal to extract valid speech segments; The valid voice segment is converted into text content to obtain the voice input content.

3. The method according to claim 1, characterized in that The analyzing the voice input content and identifying the vehicle driving problem includes: Extracting a keyword set from the voice input content, the keyword set including abnormal description words, component name words, and driving scene words; Analyze the component name words and the driving scene words to determine the vehicle driving link; Analyze the abnormal description words to determine the link problem; The link problem and the vehicle driving link are regarded as the vehicle driving problem.

4. The method according to claim 1, characterized in that: Determining a solution according to the correlation of the problems includes: Analyze the driving environment data to determine the road slope and air humidity during driving; Analyze the road slope and the air humidity to determine the impact of environmental interference; Determining the coordinated abnormality degree of the candidate abnormal components during driving according to the problem correlation; A solution is determined based on the environmental interference impact and the coordination abnormality degree.

5. The method according to claim 4, characterized in that Determining the coordinated abnormality degree of the candidate abnormal component during driving according to the problem correlation includes: Acquire sensor data related to the candidate abnormal component within the time window; analyzing the sensor data to determine phase synchronization of the candidate abnormal component; Calculating a mutual correlation coefficient between each sensor signal and each candidate abnormal component according to the phase synchronization; According to the mutual correlation coefficient, the coordinated abnormality degree of the candidate abnormal components during the driving process is determined.

6. The method according to claim 1, characterized in that The method further comprises: After the solution is output, the vehicle status is monitored in real time, and according to the monitoring result, it is determined whether the user has solved the vehicle driving problem; If the problem is not solved, the vehicle driving problem and the real-time driving data are formed into a maintenance auxiliary data package.

7. A vehicle driving behavior analysis system integrated with speech recognition, characterized in that: The method as claimed in any one of claims 1 to 6 comprises: A content analysis module, used to obtain voice input content, analyze the voice input content, and identify vehicle driving problems; A data retrieval module, used to determine the driving link according to the vehicle driving problem, and retrieve real-time driving data according to the driving link; The solution determination module is used to analyze the real-time driving data, determine the problem relevance, and determine the solution based on the problem relevance.

Images