Data uploading method, device and equipment, readable storage medium and vehicle

Abstract

The invention discloses a data uploading method, device and equipment, a readable storage medium and a vehicle, and the method comprises the steps: obtaining a target signal of the vehicle in a driving process, the target signal being used for representing a running state of the vehicle; performing feature extraction on the target signal under a plurality of different dimensions to obtain a plurality of target feature values corresponding to the plurality of different dimensions; determining that the target signal is abnormal under the condition that at least two target characteristic values in the plurality of target characteristic values are in abnormal deviation; according to the number of times of exception occurring in the preset time period, the probability that the target component breaks down is calculated; and under the condition that the probability is greater than a preset threshold value, uploading the target signal within a preset time period. According to the method, whether the target component is abnormal or not is judged according to the multiple target feature values, and the target signal is uploaded to the cloud platform only when the target component has the fault, so that the uploaded data volume can be effectively reduced, and communication resources are saved.

Description

Technical Field

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

[0002] In order to analyze the performance of the vehicle or the cause of the vehicle's abnormality, the vehicle data needs to be uploaded to the cloud platform, and the abnormality analysts will analyze the uploaded data to facilitate subsequent improvements to the vehicle.

[0003] Existing vehicle-mounted sensors mostly collect data in real time, and the amount of data is large. At present, when storing the collected data, most of them record the data periodically and then transmit the recorded data to the cloud platform, so as to facilitate the subsequent analysis of the vehicle's driving process based on the data uploaded to the cloud platform.

[0004] However, this data uploading method uploads a large amount of data. Summary of the invention

[0005] The present application provides a data uploading method, device, equipment, readable storage medium and vehicle to solve the problem of large amount of uploaded data in existing data uploading methods.

[0006] In order to solve the above problems, the first aspect of the present application provides a data uploading method, the method comprising:

[0007] Acquiring a target signal of a vehicle during driving; the target signal is used to characterize the running state of the vehicle;

[0008] Extracting features of the target signal in multiple dimensions to obtain multiple target feature values ​​corresponding to the multiple dimensions;

[0009] In the case where at least two target characteristic values ​​among the multiple target characteristic values ​​are in abnormal deviation, determining that the target signal is abnormal;

[0010] Calculating the probability of failure of the target component according to the number of abnormalities occurring within a preset time period;

[0011] When the probability is greater than a preset threshold, the target signal within the preset time period is uploaded.

[0012] A second aspect of the present application provides a data uploading device, the device comprising:

[0013] An acquisition module, used for acquiring a target signal of a vehicle during driving, wherein the target signal is used for representing a running state of the vehicle;

[0014] An extraction module is used to extract features of the target signal in multiple different dimensions to obtain multiple target feature values ​​corresponding to the multiple different dimensions;

[0015] A determination module, configured to determine that the target signal is abnormal if at least two target feature values ​​among the multiple target feature values ​​are in abnormal deviation;

[0016] A calculation module, used to calculate the probability of failure of the target component according to the number of abnormalities occurring within a preset time period;

[0017] The uploading module is used to upload the target signal within the preset time period when the probability is greater than a preset threshold.

[0018] A third aspect of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the data uploading method described in the first aspect are implemented.

[0019] A fourth aspect of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the data uploading method described in the first aspect are implemented.

[0020] A fifth aspect of the present application provides a vehicle, the vehicle comprising a vehicle-machine system, and the vehicle-machine system, when executed, is used to implement the steps of the data uploading method as described in the aspect.

[0021] The method provided in the embodiment of the present application obtains the target signal of the vehicle during driving; the target signal is used to characterize the running state of the vehicle; the target signal is feature extracted in multiple different dimensions to obtain multiple target feature values ​​corresponding to the multiple different dimensions; when at least two of the multiple target feature values ​​are in abnormal deviation, the target signal is determined to be abnormal; the probability of failure of the target component is calculated according to the number of abnormalities in a preset time period; when the probability is greater than a preset threshold, the target signal within the preset time period is uploaded. In the above, by extracting the features of the target signal in multiple different dimensions to obtain multiple target feature values, determining whether the target component is abnormal according to the multiple target feature values, and uploading the target signal to the cloud platform only when the target component is faulty, the amount of uploaded data can be effectively reduced and communication resources can be saved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of a process of uploading data provided by an embodiment of the present application;

[0023] Figure 2Another schematic diagram of the data uploading method provided in the embodiment of the present application;

[0024] Figure 3 A structural diagram of a data uploading device provided in an embodiment of the present application;

[0025] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0028] like Figure 1 As shown, the embodiment of the present application provides a data uploading method, the method comprising the following steps 101 to 105, wherein:

[0029] Step 101 , obtaining a target signal of a vehicle during driving, wherein the target signal is used to characterize the running state of the vehicle.

[0030] The target signal may include an initial audio signal and an initial vibration signal, and may also include a controller area network (CAN) signal.

[0031] Exemplarily, step 101 may specifically include the following steps:

[0032] Collecting a first audio signal and a first vibration signal during the driving of the vehicle;

[0033] Based on a preset time length, intercepting the first audio signal to obtain the initial audio signal, wherein a starting time of the initial audio signal is the same as a starting time of the first audio signal;

[0034] Based on the time length, the first vibration signal is intercepted to obtain the initial vibration signal, and the starting time of the initial vibration signal is the same as the starting time of the first vibration signal.

[0035] For example, the first audio signal can be collected by a microphone sensor, and the first vibration signal can be collected by a vibration sensor. The time length can adopt a default value or can be determined based on user input. The first audio signal is intercepted according to the time length, and the starting time of the obtained initial audio signal is the same as the starting time of the first audio signal, and the duration of the initial audio signal is the duration of the time length. For example, if the first audio signal is a 10-second audio signal and the time length is 5 seconds, the initial audio signal is obtained by intercepting the first 5 seconds of the first audio signal. Correspondingly, the first vibration signal is also intercepted in the same way.

[0036] By collecting the first audio signal and the first vibration signal and intercepting the initial audio signal and the initial vibration signal therefrom, the amount of data processing for subsequent signal-based determination of whether a target component has an abnormality can be reduced, thereby improving processing efficiency.

[0037] Step 102: extract features of the target signal in multiple dimensions to obtain multiple target feature values ​​corresponding to the multiple dimensions.

[0038] The multiple dimensions may be sound dimensions, vibration dimensions, etc. If the target signal includes an audio signal, the target feature value includes at least one of a loudness value, a sound pressure level value, and a roughness value; if the target signal includes a vibration signal, the target feature value includes at least one of a vibration amplitude value and a vibration roughness value.

[0039] Step 103: When at least two target feature values ​​among the multiple target feature values ​​are in abnormal deviation, determine that the target signal is abnormal.

[0040] The target characteristic value being in an abnormal deviation can be understood as the target characteristic value not being in a pre-acquired reference interval. In the case where at least two target characteristic values ​​are not in a pre-acquired reference interval, it is determined that the target signal of the vehicle is abnormal.

[0041] The target feature value may include multiple feature values, each of which is pre-set with a reference interval. When performing a comparison, the feature value is compared with the reference interval corresponding to the feature value. If the feature value is located in the corresponding reference interval, it means that there is no abnormality. If the feature value is not located in the corresponding reference interval, it means that there is an abnormality.

[0042] Step 104, calculating the probability of failure of the target component according to the number of abnormalities occurring within a preset time period.

[0043] For example, the probability of a target component failing is determined based on the number of anomalies that occur within a preset time period.

[0044] The preset time period can be set according to the actual situation and is not limited here. The target component can be a range extender, a generator, a drive motor or an air compressor, etc., which require fault analysis and is not limited here.

[0045] Step 105 : when the probability is greater than a preset threshold, uploading the target signal within the preset time period.

[0046] In the case of a target component failure, the target signal within the preset time period is sent to the cloud platform for subsequent abnormal analysis based on the target signal. If the target component is not faulty, the target signal within the preset time period is not uploaded to save communication resources.

[0047] In this embodiment, a target signal of a vehicle during driving is obtained; the target signal is used to characterize the running state of the vehicle; the target signal is feature extracted in multiple different dimensions to obtain multiple target feature values ​​corresponding to the multiple different dimensions; when at least two of the multiple target feature values ​​are in abnormal deviation, the target signal is determined to be abnormal; the probability of failure of the target component is calculated according to the number of abnormalities in a preset time period; when the probability is greater than a preset threshold, the target signal within the preset time period is uploaded. In the above, by extracting the target signal in multiple different dimensions to obtain multiple target feature values, determining whether the target component is abnormal based on the multiple target feature values, and uploading the target signal to the cloud platform only when the target component fails, the amount of uploaded data can be effectively reduced and communication resources can be saved.

[0048] In one embodiment of the present application, the target signal includes an initial audio signal and an initial vibration signal;

[0049] Feature extraction is performed on the target signal in multiple different dimensions to obtain multiple target feature values ​​corresponding to the multiple different dimensions, including:

[0050] Performing signal processing on the initial audio signal to obtain a target audio signal corresponding to the target component of the vehicle;

[0051] Performing signal processing on the initial vibration signal to obtain a target vibration signal corresponding to the target component;

[0052] Signal feature extraction is performed on the target audio signal and the target vibration signal to obtain a plurality of target feature values ​​corresponding to a plurality of different dimensions.

[0053] In the above, signal feature extraction is performed based on the initial audio signal and the initial vibration signal, and the characteristic values ​​of the audio signal and the vibration signal of the target component are fully considered, so that the subsequent abnormality determination can be more accurate.

[0054] Specifically, performing signal processing on the initial audio signal may be to filter the initial audio signal and extract the target audio signal corresponding to the target component. Exemplarily, performing signal processing on the initial audio signal to obtain the target audio signal corresponding to the target component of the vehicle may specifically include:

[0055] Performing time-frequency conversion on the initial audio signal to obtain a first frequency signal corresponding to the initial audio signal;

[0056] Extracting signals with amplitudes greater than a first threshold from the first frequency signal to obtain a first filtered signal;

[0057] Performing frequency domain order analysis on the target component through a control signal representing vehicle working information to obtain a sound frequency segment corresponding to each order of the target component under multiple orders;

[0058] Signals corresponding to a plurality of the sound frequency bands are intercepted from the first filtered signal to obtain the target audio signal.

[0059] In the above, the signal corresponding to the target component is intercepted from the initial audio signal to obtain the target audio signal, which can make the feature value subsequently determined based on the target audio signal more accurate, thereby improving the accuracy of abnormality determination of the target component.

[0060] In the above, the control signal representing the vehicle working information can be a CAN signal, and the first threshold can be set according to the actual situation and is not limited here. The rotation speed of the target component can be obtained from the CAN signal, and the order frequency is calculated as: rotation speed*order / 60. The calculated order frequency is used as the center of the sound frequency segment, and the frequency segments of the preset range are intercepted to the left and right. The preset range can be set according to the actual situation and is not limited here.

[0061] Calculate the sound frequency segments corresponding to the target component at multiple orders, for example, calculate the sound frequency segments corresponding to each order of the target component at multiple orders such as 1st order, 2nd order, 4th order, 6th order and 8th order. Intercept the signals corresponding to the multiple sound frequency segments from the first filtered signal to obtain the target audio signal.

[0062] The signal processing of the initial vibration signal may be to filter the initial vibration signal and extract the target vibration signal corresponding to the target component. Exemplarily, the signal processing of the initial vibration signal to obtain the target vibration signal corresponding to the target component may specifically include:

[0063] Performing time-frequency conversion on the initial vibration signal to obtain a second frequency signal corresponding to the initial vibration signal;

[0064] Extracting a signal having an amplitude greater than a second threshold value from the second frequency signal to obtain a second filtered signal;

[0065] Performing frequency domain order analysis on the target component through a control signal representing vehicle working information to obtain vibration frequency segments corresponding to each order of the target component under multiple orders;

[0066] Signals corresponding to a plurality of the vibration frequency bands are intercepted from the second filtered signal to obtain the target vibration signal.

[0067] In the above, the signal corresponding to the target component is intercepted from the initial vibration signal to obtain the target vibration signal, which can make the characteristic value subsequently determined based on the target vibration signal more accurate, thereby improving the accuracy of the abnormality judgment of the target component.

[0068] In the above, the second threshold can be set according to the actual situation and is not limited here. The rotation speed of the target component can be obtained from the CAN signal, and the order frequency is calculated as: rotation speed * order / 60. The calculated order frequency is used as the center of the vibration frequency segment, and the frequency segments of the preset range are intercepted to the left and right. The preset range can be set according to the actual situation and is not limited here.

[0069] The vibration frequency segments corresponding to the target component at multiple orders are calculated, for example, the vibration frequency segments corresponding to each order of the target component at multiple orders such as 1st order, 2nd order, 4th order, 6th order and 8th order are calculated. Signals corresponding to the multiple vibration frequency segments are intercepted from the second filtered signal to obtain a target vibration signal.

[0070] In one embodiment of the present application, the target feature value includes a first feature value and a second feature value;

[0071] Signal feature extraction is performed on the target audio signal and the target vibration signal to obtain a plurality of target feature values ​​corresponding to a plurality of different dimensions, including:

[0072] Extract signal features according to the target audio signal to obtain a first feature value, where the first feature value includes at least one of a loudness value, a sound pressure level value, and a roughness value;

[0073] Signal feature extraction is performed according to the target vibration signal to obtain a second feature value, where the second feature value includes at least one of a vibration amplitude and a vibration roughness value.

[0074] In the above, by extracting the first eigenvalue of the target audio signal and the second eigenvalue of the target vibration signal, it is convenient to subsequently determine whether the target component has an abnormality based on the first eigenvalue and the second eigenvalue, thereby improving the accuracy of the determination.

[0075] In one embodiment of the present application, when at least two target feature values ​​among the multiple target feature values ​​are in abnormal deviation, determining that the target signal is abnormal includes:

[0076] Comparing the first characteristic value with a reference interval corresponding to the first characteristic value to obtain a first comparison result;

[0077] Comparing the second eigenvalue with a reference interval corresponding to the second eigenvalue to obtain a second comparison result;

[0078] If at least two characteristic values ​​in the first comparison result and the second comparison result are not located in the corresponding reference interval, it is determined that the target signal is abnormal.

[0079] In the above, the first comparison result and the second comparison result are comprehensively considered, and only when at least two characteristic values ​​in the two comparison results are not located in the corresponding reference interval, it is determined that the target component has an abnormality, which can improve the accuracy of the determination.

[0080] In the above, the first eigenvalue is the eigenvalue of the target audio signal, including at least one of the loudness value, the sound pressure level value and the roughness value; the second eigenvalue is the eigenvalue of the target vibration signal, including at least one of the vibration amplitude value and the vibration roughness value. Each eigenvalue is pre-set with a reference interval. When comparing, the eigenvalue is compared with the reference interval corresponding to the eigenvalue. If the eigenvalue is in the corresponding reference interval, it means that there is no abnormality. If the eigenvalue is not in the corresponding reference interval, it means that there is an abnormality. The first comparison result can be a determination result of whether the eigenvalue falls in the corresponding reference interval.

[0081] Exemplarily, if at least two characteristic values ​​in the first comparison result and the second comparison result are not located in the corresponding reference interval, it is determined that the target component is abnormal during the time period of collecting the target signal. For example, if the loudness value in the first comparison result is not located in the reference interval corresponding to the loudness value, the sound pressure level value is located in the reference interval corresponding to the sound pressure level value, and the vibration amplitude in the second comparison result is not located in the reference interval corresponding to the vibration amplitude, and the vibration roughness value is located in the reference interval corresponding to the vibration roughness value, it is determined that the target component is abnormal during the time period of collecting the target signal.

[0082] In one embodiment of the present application, the probability of failure of the target component is calculated according to the number of abnormalities occurring within a preset time period, including:

[0083] Counting the number of occurrences of the abnormality within a preset time period, the number of abnormalities may be the number of consecutive abnormalities or the number of discontinuous abnormalities;

[0084] The probability of a target component of the vehicle failing is calculated based on the number of target signals acquired within a preset time period and the number of abnormalities occurring.

[0085] The number of target signals obtained within a preset time period is N, where N is an integer greater than 1. The ratio of the number of abnormality occurrences to N is used as the probability of a target component failure, or the probability of a target component failure is determined based on the ratio of the number of abnormality occurrences to N, which is not limited here.

[0086] or,

[0087] Acquire N target signals obtained successively within a preset time period, where N is an integer greater than 1;

[0088] Determine the number of times that N target signals have abnormalities, which may be the number of consecutive abnormalities or the number of discontinuous abnormalities;

[0089] The ratio of the number to N is taken as the probability of failure of the target component.

[0090] In this embodiment, when an abnormality is detected in the target component, the target signal is not uploaded to the cloud platform immediately. Instead, N comparison results within a preset time period are counted, and based on these N comparison results, it is determined whether the target component has an abnormality. This can effectively avoid uploading data to the cloud platform in the event of a single or a few abnormalities in sporadic or inaccurate detections, which can further reduce the amount of data uploaded to the cloud platform and save communication resources.

[0091] The preset time period can be set according to the actual situation, such as 1 hour, or 2 hours, which is not limited here. The vehicle-mounted sensor can collect target data once every preset time, for example, collect target signals once every 5 minutes. In this way, multiple collections can be made within the preset time period to obtain multiple target signals. For each target signal, the above method is used to obtain the corresponding comparison result, and then based on these multiple comparison results, it is determined whether the target component is abnormal within the preset time period. That is, the number of times the target component is judged to be abnormal in N comparison results is counted. If the ratio of this number to N is greater than the preset threshold, it is determined that the target component is faulty, and the N target signals are sent to the cloud platform to facilitate subsequent fault analysis based on these N target signals.

[0092] Figure 2 The figure shows a flow chart of the data uploading method provided by the present application. Figure 2 As shown, the implementation process is as follows:

[0093] The vehicle collects real-time data about the vehicle status during driving through on-board sensors, mainly collecting the vehicle's sound and vibration signals;

[0094] The sound signal and vibration signal are respectively converted into frequency domain signals through fast Fourier transform.

[0095] After being converted into frequency domain signals, the signals are analyzed on the spectrum graph;

[0096] Separate the signals with amplitude greater than a certain threshold, analyze the order of each component of the vehicle according to the signal on the vehicle CAN communication, and extract the signal of the corresponding order. The order frequency calculation method is: speed * order / 60.

[0097] Calculate characteristic values ​​such as vibration amplitude and sound pressure level based on the separated spectrum signal;

[0098] Compare the calculated real-time characteristic value with the reference range value of a normal device;

[0099] The single-point data is judged for faults and recorded in the model's cache space.

[0100] The method for judging single-point data failure is as follows:

[0101] The first audio signal collected from this moment is input into the model, and the bandwidth length w is input, where w is the time length. The audio signal with the bandwidth length starting from this moment is intercepted to obtain the initial audio signal at the single point. Similarly, the first vibration signal collected from this moment is input into the model, and the vibration signal with the bandwidth length starting from this moment is intercepted to obtain the initial vibration signal at the single point.

[0102] By using the method of fast Fourier transform and feature calculation, the characteristic values ​​of the initial audio signal (including loudness value, sound pressure level value and roughness value) and the characteristic values ​​of the initial vibration signal (including roughness value, vibration amplitude and vibration roughness value) at the start time are calculated;

[0103] The characteristic value is compared with the normal characteristic standard value obtained in advance based on big data statistics for a single point judgment. When at least two characteristic values ​​show abnormal deviations, the data at that point is judged to be abnormal, the data of the abnormal point is recorded, and the record of that moment is added to the number of abnormalities.

[0104] After all target signals acquired in a preset time period are calculated, the probability of abnormality is statistically calculated, for example, signal feature extraction is performed on all single point data in the time series;

[0105] The points determined to be abnormal are recorded in the abnormal point data, and the non-abnormal points are recorded in the non-abnormal point data, where the probability of abnormality is the total number of samples in the abnormal point data / (the total number of samples in the abnormal point data + the total number of samples in the non-abnormal point data);

[0106] The statistical probability and threshold are judged to determine whether the vehicle has a fault.

[0107] If there is a fault, the data collected by multiple sensors in the data storage space are packaged and uploaded to the cloud platform for fault cause analysis and troubleshooting;

[0108] If there is no fault, the data is stored in a rolling manner (queue storage, first-in-first-out principle). When the storage capacity reaches the maximum storage time limit, the earliest stored data is deleted first, and the newly collected data is stored.

[0109] In the above method, the vehicle-mounted sensors are used to sense the vehicle's operating status in real time and detect whether the vehicle has any faults. At the same time, the original signal data within a certain period of time is stored, so that when a fault is found, the original signal data can be uploaded to the cloud platform, reducing the amount of uploaded data. By storing the fault-related data on the cloud platform, it can assist diagnostic personnel in diagnosing the fault and improve work efficiency.

[0110] like Figure 3 As shown, the embodiment of the present application further provides a data uploading device 300, the device comprising:

[0111] The acquisition module 301 is used to acquire a target signal of the vehicle during driving; the target signal is used to represent the running state of the vehicle;

[0112] An extraction module 302 is used to extract features of the target signal in multiple different dimensions to obtain multiple target feature values ​​corresponding to the multiple different dimensions;

[0113] A determination module 303, configured to determine that the target signal is abnormal when at least two target feature values ​​among the multiple target feature values ​​are in abnormal deviation;

[0114] A calculation module 304 is used to calculate the probability of failure of the target component according to the number of abnormalities occurring within a preset time period;

[0115] The uploading module 305 is configured to upload the target signal within the preset time period when the probability is greater than a preset threshold.

[0116] Optionally, the target signal includes an initial audio signal and an initial vibration signal;

[0117] The extraction module 302 includes:

[0118] A first processing submodule, configured to perform signal processing on the initial audio signal to obtain a target audio signal corresponding to the target component of the vehicle;

[0119] A second processing submodule is used to perform signal processing on the initial vibration signal to obtain a target vibration signal corresponding to the target component;

[0120] The extraction submodule is used to extract signal features from the target audio signal and the target vibration signal to obtain the target feature value.

[0121] Optionally, the target signal also includes a CAN signal;

[0122] The first processing submodule includes:

[0123] A first conversion unit, configured to perform time-frequency conversion on the initial audio signal to obtain a first frequency signal corresponding to the initial audio signal;

[0124] A first extraction unit, configured to extract a signal having an amplitude greater than a first threshold from the first frequency signal to obtain a first filtered signal;

[0125] A first analysis unit is used to perform frequency domain order analysis on the target component through a control signal representing vehicle working information, so as to obtain a sound frequency segment corresponding to each order of the target component under multiple orders;

[0126] The first acquisition unit is used to intercept signals corresponding to the plurality of sound frequency bands from the first filtered signal to obtain the target audio signal.

[0127] Optionally, the second processing submodule includes:

[0128] A second conversion unit, configured to perform time-frequency conversion on the initial vibration signal to obtain a second frequency signal corresponding to the initial vibration signal;

[0129] A second extraction unit, used to extract a signal having an amplitude greater than a second threshold in the second frequency signal to obtain a second filtered signal;

[0130] A second analysis unit is used to perform frequency domain order analysis on the target component through a control signal representing vehicle working information, so as to obtain a vibration frequency segment corresponding to each order of the target component under multiple orders;

[0131] The second acquisition unit is used to intercept signals corresponding to the multiple vibration frequency bands from the second filtered signal to obtain the target vibration signal.

[0132] Optionally, the target eigenvalue includes a first eigenvalue and a second eigenvalue;

[0133] The extraction module 302 includes:

[0134] A first calculation submodule is used to extract signal features according to the target audio signal to obtain a first feature value, where the first feature value includes at least one of a loudness value, a sound pressure level value, and a roughness value;

[0135] The second calculation submodule is used to extract signal features according to the target vibration signal to obtain a second eigenvalue, wherein the second eigenvalue includes at least one of a vibration amplitude and a vibration roughness value.

[0136] Optionally, the determination module 303 includes:

[0137] A first comparison submodule, used to compare the first characteristic value with a reference interval corresponding to the first characteristic value to obtain a first comparison result;

[0138] A second comparison submodule, used to compare the second characteristic value with a reference interval corresponding to the second characteristic value to obtain a second comparison result;

[0139] The third analysis submodule is used to determine that an abnormality exists in the target component during the time period of collecting the target signal if at least two characteristic values ​​in the first comparison result and the second comparison result are not located in the corresponding reference interval.

[0140] Optionally, the calculation module 304 includes:

[0141] A statistics submodule, used to count the number of times the anomaly occurs within a preset time period;

[0142] The third calculation submodule is used to calculate the probability of failure of the target component of the vehicle according to the number of target signals obtained within a preset time period and the number of times the abnormality occurs.

[0143] Optionally, the acquisition module 301 includes:

[0144] A collection submodule, used for collecting a first audio signal and a first vibration signal of the vehicle during driving;

[0145] A first interception submodule, configured to intercept the first audio signal based on a preset time length to obtain the initial audio signal, wherein the starting time of the initial audio signal is the same as the starting time of the first audio signal;

[0146] The second interception submodule is used to intercept the first vibration signal based on the time length to obtain the initial vibration signal, and the starting time of the initial vibration signal is the same as the starting time of the first vibration signal.

[0147] The data upload device 300 provided in the embodiment of the present application can realize the aforementioned Figure 1Each process implemented by the illustrated method embodiment can also achieve the same technical effect, and will not be described again here to avoid repetition.

[0148] like Figure 4 As shown, the present application also provides an electronic device 400, the electronic device 400 includes a processor 401, a memory 402 and a communication interface 403, the memory 402 stores programs or instructions that can be run on the processor 401,

[0149] The program or instruction is implemented when the processor 401 executes it Figure 1 Each process implemented by the illustrated method embodiment can also achieve the same technical effect, and will not be described again here to avoid repetition.

[0150] The present application also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the following is implemented: Figure 1 Steps of the data uploading method in the illustrated embodiment.

[0151] The present application also provides a vehicle, the vehicle comprising a vehicle system, the vehicle system when executed to achieve Figure 1 Each process implemented by the illustrated method embodiment can also achieve the same technical effect, and will not be described again here to avoid repetition.

[0152] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

[0153] It should be noted that, in this article, relational terms such as "" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprises a..." do not exclude the existence of other identical elements in the process, method, article or device that includes the elements.

[0154] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0155] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0156] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A data uploading method, characterized in that: The method comprises: Acquiring a target signal of a vehicle during driving; the target signal is used to characterize the running state of the vehicle; Extracting features of the target signal in multiple dimensions to obtain multiple target feature values ​​corresponding to the multiple dimensions; In the case where at least two target characteristic values ​​among the multiple target characteristic values ​​are in abnormal deviation, determining that the target signal is abnormal; Calculating the probability of failure of the target component according to the number of abnormalities occurring within a preset time period; When the probability is greater than a preset threshold, the target signal within the preset time period is uploaded.

2. The method according to claim 1, characterized in that The target signal includes an initial audio signal and an initial vibration signal; The step of obtaining a target signal of a vehicle during driving includes: Collecting a first audio signal and a first vibration signal during the driving of the vehicle; Based on a preset time length, intercepting the first audio signal to obtain the initial audio signal, wherein a starting time of the initial audio signal is the same as a starting time of the first audio signal; Based on the time length, the first vibration signal is intercepted to obtain the initial vibration signal, and the starting time of the initial vibration signal is the same as the starting time of the first vibration signal.

3. The method according to claim 2, characterized in that The feature extraction of the target signal in multiple different dimensions to obtain multiple target feature values ​​corresponding to the multiple different dimensions includes: Performing signal processing on the initial audio signal to obtain a target audio signal corresponding to the target component of the vehicle; Performing signal processing on the initial vibration signal to obtain a target vibration signal corresponding to the target component; Signal feature extraction is performed on the target audio signal and the target vibration signal to obtain a plurality of target feature values ​​corresponding to a plurality of different dimensions.

4. The method according to claim 3, characterized in that The performing signal processing on the initial audio signal to obtain a target audio signal corresponding to the target component of the vehicle includes: Performing time-frequency conversion on the initial audio signal to obtain a first frequency signal corresponding to the initial audio signal; Extracting signals with amplitudes greater than a first threshold from the first frequency signal to obtain a first filtered signal; Performing frequency domain order analysis on the target component through a control signal representing vehicle working information to obtain a sound frequency segment corresponding to each order of the target component under multiple orders; Signals corresponding to a plurality of the sound frequency bands are intercepted from the first filtered signal to obtain the target audio signal.

5. The method according to claim 3, characterized in that The performing signal processing on the initial vibration signal to obtain a target vibration signal corresponding to the target component includes: Performing time-frequency conversion on the initial vibration signal to obtain a second frequency signal corresponding to the initial vibration signal; Extracting a signal having an amplitude greater than a second threshold value from the second frequency signal to obtain a second filtered signal; Performing frequency domain order analysis on the target component through a control signal representing vehicle working information to obtain vibration frequency segments corresponding to each order of the target component under multiple orders; Signals corresponding to a plurality of the vibration frequency bands are intercepted from the second filtered signal to obtain the target vibration signal.

6. The method according to claim 3, characterized in that The plurality of target feature values ​​include a first feature value and a second feature value; The signal feature extraction of the target audio signal and the target vibration signal to obtain a plurality of target feature values ​​corresponding to a plurality of different dimensions includes: Extract signal features according to the target audio signal to obtain the first feature value, where the first feature value includes at least one of a loudness value, a sound pressure level value, and a roughness value; Signal feature extraction is performed according to the target vibration signal to obtain the second feature value, where the second feature value includes at least one of a vibration amplitude and a vibration roughness value.

7. The method according to claim 6, characterized in that In a case where at least two target characteristic values ​​among the multiple target characteristic values ​​are in abnormal deviation, determining that the target signal is abnormal includes: Comparing the first characteristic value with a reference interval corresponding to the first characteristic value to obtain a first comparison result; Comparing the second eigenvalue with a reference interval corresponding to the second eigenvalue to obtain a second comparison result; If at least two target feature values ​​in the first comparison result and the second comparison result are not within the corresponding reference interval, it is determined that the target signal is abnormal.

8. The method according to claim 1, characterized in that The calculating the probability of failure of the target component of the vehicle according to the number of abnormalities occurring within a preset time period includes: Count the number of times the anomaly occurs within a preset time period; The probability of a target component of the vehicle failing is calculated based on the number of target signals acquired within a preset time period and the number of abnormalities occurring.

9. A data uploading device, characterized in that: The device comprises: An acquisition module, used for acquiring a target signal of a vehicle during driving, wherein the target signal is used for representing a running state of the vehicle; An extraction module is used to extract features of the target signal in multiple different dimensions to obtain multiple target feature values ​​corresponding to the multiple different dimensions; A determination module, configured to determine that the target signal is abnormal if at least two target feature values ​​among the multiple target feature values ​​are in abnormal deviation; A calculation module, used to calculate the probability of failure of the target component according to the number of abnormalities occurring within a preset time period; The uploading module is used to upload the target signal within the preset time period when the probability is greater than a preset threshold.

10. An electronic device, characterized in that: The device includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the data uploading method according to any one of claims 1 to 8 are implemented.

11. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the data uploading method according to any one of claims 1 to 8 are implemented.

12. A vehicle, characterized in that: The vehicle includes a vehicle computer system, and the vehicle computer system, when executed, implements the steps of the data uploading method according to any one of claims 1 to 8.

Images