Vehicle signal data processing method, device, equipment and medium

Abstract

The application provides a vehicle signal data processing method, device, equipment and medium. The method comprises the following steps: obtaining a to-be-processed signal of a target vehicle through a cloud, determining a first signal heat value of the to-be-processed signal in the target vehicle according to a first signal heat model, determining a second signal heat value of the to-be-processed signal in a target vehicle type according to a second signal heat model, and determining the signal heat of the to-be-processed signal in combination with the first signal heat value and the second signal heat value. The signal heat of the to-be-processed signal in the target vehicle and the signal heat in the target vehicle type are comprehensively considered, the accuracy of the signal heat is improved, the signal data can be better classified, and finally the target vehicle classifies and processes the signal data of the to-be-processed signal according to the signal heat, thereby improving the efficiency of the signal data processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a vehicle signal data processing method and device, equipment and medium. BACKGROUND

[0002] With the rapid development of the new energy automobile industry, the data generated by automobiles shows explosive growth. The number of signals of each new energy automobile has exceeded 5000, and these signals are usually collected every second and uploaded to a data center at a second-level frequency, which has become a consensus solution in the industry.

[0003] How to efficiently process these data has become a technical problem to be solved. SUMMARY

[0004] The present application provides a vehicle signal data processing method, device, equipment and medium to solve the technical problem of how to efficiently process these data in the prior art.

[0005] In a first aspect, the present application provides a vehicle signal data processing method, comprising:

[0006] obtaining a to-be-processed signal of a target vehicle;

[0007] predicting, according to a preset first signal heat model, a signal heat of the to-be-processed signal in the target vehicle to obtain a first signal heat value;

[0008] predicting, according to a preset second signal heat model, a signal heat of the to-be-processed signal in a target vehicle type to obtain a second signal heat value, the target vehicle type being a vehicle type of the target vehicle;

[0009] determining a signal heat of the to-be-processed signal according to the first signal heat value and the second signal heat value;

[0010] sending the signal heat to the target vehicle.

[0011] In the present application, the first signal heat value is obtained by predicting, according to a preset first signal heat model, a signal heat of the to-be-processed signal in the target vehicle, comprising:

[0012] determining a first access frequency and a first fault association frequency of the to-be-processed signal in a preset time period;

[0013] inputting the first access frequency and the first fault association frequency into the preset first signal heat model for prediction processing to obtain the first signal heat value of the to-be-processed signal.

[0014] In the present application, the signal heat of the to-be-processed signal in the target vehicle type is predicted according to a preset second signal heat model, and a second signal heat value is obtained, comprising:

[0015] According to the target vehicle type of the target vehicle, the number of vehicles in use of the target vehicle type in a preset time period is obtained, and the second access frequency and the second fault association frequency of the to-be-processed signal related to all vehicles in use in the preset time period are obtained;

[0016] The number of vehicles in use, the second access frequency and the second fault association frequency are input into the preset second signal heat model for prediction processing, and the second signal heat value of the to-be-processed signal is obtained.

[0017] In the present application, the signal heat of the to-be-processed signal is determined according to the first signal heat value and the second signal heat value, comprising:

[0018] The first weight of the first signal heat value and the second weight of the second signal heat value are obtained;

[0019] According to the first weight, the second weight, the first signal heat value and the second signal heat value, the signal heat of the to-be-processed signal is obtained.

[0020] In the present application, before obtaining the first weight of the first signal heat value and the second weight of the second signal heat value, the method further comprises:

[0021] Obtain the failure rate of the to-be-processed signal in a preset update time period;

[0022] According to the failure rate, the failure rating corresponding to the failure rate is determined;

[0023] According to the failure rating, the first weight and the second weight corresponding to the failure rating are determined.

[0024] In the present application, the method further comprises:

[0025] Receive the signal data uploaded by the target vehicle, wherein the signal data is obtained after being sent and processed according to the signal heat;

[0026] The signal data is stored and processed.

[0027] In the present application, when the signal heat is less than the first threshold, the signal data is stored and processed, comprising:

[0028] Receive the data file sent by the target vehicle using the offline task in the non-busy period, wherein the data file is generated by the target vehicle according to the preset data requirement, and the data requirement is used to indicate the collection time period and the file size of the data file;

[0029] The signal data is decrypted using an offline task in a non-busy period to obtain decrypted signal data.

[0030] The decrypted signal data is stored in a preset storage format.

[0031] In the present application, when the signal heat is greater than a second threshold value, and the second threshold value is greater than or equal to a first threshold value, the signal data is stored, including:

[0032] Receiving signal data uploaded by a target vehicle in real time;

[0033] Decoding the signal data and writing it into a data lake.

[0034] In a second aspect, the present application provides a vehicle signal data processing method, including:

[0035] Obtaining a signal heat of a signal to be processed from the cloud;

[0036] Processing signal data of the signal to be processed according to the signal heat.

[0037] In the present application, processing signal data of the signal to be processed according to the signal heat, including:

[0038] When the signal heat is less than a first threshold value, generating a data file according to a preset data requirement, the data requirement being used to indicate a collection time period and a file size of the data file;

[0039] Sending the data file to the cloud using an offline task in a non-busy period.

[0040] In the present application, the method further includes:

[0041] If the data file fails to be uploaded, buffering the data file locally and performing asynchronous retry until the data file is successfully uploaded.

[0042] In the present application, processing signal data of the signal to be processed according to the signal heat, including:

[0043] When the signal heat is greater than a second threshold value, and the second threshold value is greater than or equal to a first threshold value, sending the signal data to the cloud in real time.

[0044] In a third aspect, the present application provides a vehicle signal data processing device, including:

[0045] A first obtaining module is configured to obtain a signal to be processed of a target vehicle;

[0046] A first prediction module is configured to predict a signal heat of the signal to be processed in the target vehicle according to a preset first signal heat model, to obtain a first signal heat value.

[0047] The second prediction module is configured to predict, according to a preset second signal heat model, a signal heat of the to-be-processed signal in a target vehicle type, to obtain a second signal heat value, the target vehicle type being a vehicle type of the target vehicle.

[0048] The signal heat module is configured to determine, according to the first signal heat value and the second signal heat value, the signal heat of the to-be-processed signal.

[0049] The sending module is configured to send the signal heat to the target vehicle.

[0050] In a fourth aspect, the present application provides a vehicle signal data processing apparatus, comprising:

[0051] The second acquisition module is configured to acquire, from the cloud, the signal heat of the to-be-processed signal.

[0052] The data processing module is configured to process, according to the signal heat, signal data of the to-be-processed signal.

[0053] In a fifth aspect, the present application provides an electronic device, comprising a processor and a memory in communication connection with the processor;

[0054] The memory stores computer execution instructions;

[0055] The processor executes the computer execution instructions stored in the memory, to implement the method provided by the present application.

[0056] In a sixth aspect, the present application provides a computer readable storage medium, the computer readable storage medium storing computer execution instructions, the computer execution instructions being executed by the processor to implement the method provided by the present application.

[0057] The vehicle signal data processing method, apparatus, device and medium provided by the present application acquire, from the cloud, the to-be-processed signal of the target vehicle, determine, according to a first signal heat model, a first signal heat value of the to-be-processed signal in the target vehicle, determine, according to a second signal heat model, a second signal heat value of the to-be-processed signal in a target vehicle type, and then determine the signal heat of the to-be-processed signal in combination with the first signal heat value and the second signal heat value. The signal heat of the to-be-processed signal in the target vehicle and the signal heat in the target vehicle type are comprehensively considered, the accuracy of the signal heat is improved, the signal data can be better classified, and finally the target vehicle classifies and processes the signal data of the to-be-processed signal according to the signal heat, improving the efficiency of signal data processing. BRIEF DESCRIPTION OF DRAWINGS

[0058] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0059] Figure 1 A scene schematic diagram of vehicle signal data processing provided for an embodiment of the present application is provided.

[0060] Figure 2 A flow schematic diagram of a vehicle signal data processing method provided for an embodiment of the present application is provided.

[0061] Figure 3 A flow schematic diagram of another vehicle signal data processing method provided for an embodiment of the present application is provided.

[0062] Figure 4 A structure schematic diagram of a vehicle signal data processing device provided for an embodiment of the present application is provided.

[0063] Figure 5 A structure schematic diagram of another vehicle signal data processing device provided for an embodiment of the present application is provided.

[0064] Figure 6 A structure schematic diagram of an electronic device provided for an embodiment of the present application is provided.

[0065] Through the above-mentioned drawings, the specific embodiments of the present application have been shown, and will be described in more detail hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0066] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to indicate the same or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0067] In order to clearly understand the technical solutions of the present application, the prior art solutions are first described in detail.

[0068] With the rapid development of the new energy automobile industry, the amount of data generated by automobiles is showing explosive growth. The number of signals of each new energy automobile has exceeded 5000, and these signals are usually collected every second and uploaded to the data center at a second-level frequency, which has become a consensus solution in the industry. How to efficiently process these data has become a technical problem to be solved.

[0069] In addition to this, the existing automobile big data processing system also faces the following technical problems:

[0070] 1. Unclear data classification: The amount of data generated by vehicles is huge and diverse. From a technical perspective, how to effectively classify data so as to facilitate targeted storage and processing is an important challenge.

[0071] 2. High storage cost: Due to the large amount of vehicle data and different data lifecycles, if all data is processed according to the same storage strategy without distinction, it will result in high storage cost.

[0072] 3. Low data processing efficiency: Traditional data processing methods often cannot efficiently process vehicle big data, especially in data collection, cleaning, analysis, etc.

[0073] 4. Lack of flexibility: Existing data processing systems often lack sufficient flexibility to adapt to changing data needs and application scenarios.

[0074] To solve at least one of the above technical problems in the prior art, the inventors have found that the signal data processing method provided by the present application can be used to obtain the target vehicle's to-be-processed signal, determine the signal heat of the to-be-processed signal according to the access times and fault association times of the to-be-processed signal, and provide a basis for signal data processing of the to-be-processed signal according to the signal heat.

[0075] The application scenario of the vehicle signal data processing method provided by the present application is introduced as follows.

[0076] Figure 1 A scene diagram of the vehicle signal data processing provided by the present application is shown in FIG. 1, which includes a target vehicle and a cloud, wherein the target vehicle includes multiple signals, the cloud predicts a first signal heat value of each signal in the target vehicle according to a first signal heat model, predicts a second signal heat value of each signal in the target vehicle type according to a second signal heat model, and then obtains a signal heat of each signal according to the first signal heat value and the second signal heat value, and processes signal data of each signal according to the signal heat of each signal. Figure 1

[0077] A flowchart of the vehicle signal data processing method provided by the present application is shown in FIG. 2, which is applied to a target vehicle and a cloud, and includes the following steps: Figure 2 Figure 2 S201, the cloud obtains the to-be-processed signal of the target vehicle.

[0078]

[0079] ​​In the embodiment, the cloud can refer to a server or an electronic device providing cloud computing services for the target vehicle. The to-be-processed signal can be any signal in the target vehicle, such as a power system signal, a vehicle state signal, an environment signal, a safety signal, a navigation and position signal, a diagnosis signal, a communication signal, or a vehicle comfort signal. The cloud can obtain the signal to be processed as the to-be-processed signal according to the state or configuration information of the target vehicle by communicating with the target vehicle.

[0080] In S202, the cloud predicts the signal heat of the to-be-processed signal in the target vehicle according to a preset first signal heat model, to obtain a first signal heat value.

[0081] The first signal heat model is used to predict the signal heat of the to-be-processed signal in the target vehicle. The first signal heat model can be obtained by obtaining a first training sample set of a plurality of signals in the target vehicle in a first training time period. The first training sample set includes a plurality of groups of first training samples corresponding to the plurality of signals. Each group of first training samples includes a first access frequency sample and a first fault association frequency sample of the signal related to the target vehicle in the first training time period, and a first signal heat label. The first signal heat model is obtained by training a first to-be-trained model according to the first training sample set. The first signal heat label can be obtained by manually judging the first access frequency sample and the first fault association frequency sample.

[0082] In a possible implementation, the prediction of the signal heat of the to-be-processed signal in the target vehicle according to the preset first signal heat model to obtain the first signal heat value can include:

[0083] determining a first access frequency and a first fault association frequency of the to-be-processed signal in a preset time period;

[0084] inputting the first access frequency and the first fault association frequency into the preset first signal heat model for prediction processing to obtain the first signal heat value of the to-be-processed signal.

[0085] In the embodiment, the data processing of the to-be-processed signal often needs to be clear about a specific time period, for example, processing signal data in a certain time period. Therefore, the time period in which signal data processing is needed can be determined first, which can be referred to as a preset time period. Then, the access frequency and the fault association frequency of the to-be-processed signal related to the target vehicle in the preset time period are counted, which are referred to as a first access frequency and a first fault association frequency. Then, the first access frequency and the first fault association frequency can be input into the preset first signal heat model for prediction to obtain the first signal heat value.

[0086] Specifically, the cloud can divide the to-be-processed signal into fields, then count the access times and the failure association times of each field, and then aggregate the access times and the failure association times of each field, remove the repeated times of the same access or failure corresponding to multiple fields, and obtain the access times and the failure association times of the to-be-processed signal.

[0087] S203, according to the preset second signal heat model, the signal heat of the to-be-processed signal in the target vehicle type is predicted to obtain a second signal heat value, and the target vehicle type is the vehicle type of the target vehicle.

[0088] The second signal heat model is used to predict the signal heat of the to-be-processed signal in all vehicles in use, and can be obtained by obtaining a second training sample set of a plurality of signals of the target vehicle type in a second training time period. The second training sample set includes a plurality of sets of second training samples corresponding to the plurality of signals. Each set of second training samples includes a number of vehicle samples of the target vehicle type in use in the second training time period, a second access times sample and a second failure association times sample related to all vehicle samples in use in the second training time period, and a second signal heat label. According to the second training sample set, a pre-obtained second to-be-trained model is trained to obtain the second signal heat model.

[0089] In one possible implementation, according to the preset second signal heat model, the signal heat of the to-be-processed signal in the target vehicle type is predicted to obtain a second signal heat value, which can include:

[0090] According to the target vehicle type of the target vehicle, the number of vehicles in use of the target vehicle type in a preset time period and the second access times and the second failure association times of the to-be-processed signal related to all vehicles in use in the preset time period are obtained.

[0091] The number of vehicles in use, the second access times and the second failure association times are input into the preset second signal heat model for prediction processing to obtain the second signal heat value of the to-be-processed signal.

[0092] In the embodiment, the signal heat value of the to-be-processed signal in the same type of vehicle can be obtained according to the accessed times and the fault association times of the to-be-processed signal in the same type of vehicle, so that the signal heat of the to-be-processed signal is comprehensively judged according to the two signal heat values, and the accuracy of the signal heat judgment is improved. Moreover, since the signal types in the same type of vehicle are the same, it is more convenient to obtain the condition of each signal of the target vehicle. Therefore, the in-service vehicles of the target vehicle in a preset time period can be obtained based on the target vehicle type of the target vehicle. The in-service vehicle can refer to a vehicle used in the preset time period, for example, the preset time period is 1 month, and the in-service vehicle can be a vehicle that has traveled on the road or a vehicle that has been in the power-on state during the 1 month. The second accessed times and the second fault association times of the to-be-processed signal related to all in-service vehicles in the preset time period are counted, and then the number of in-service vehicles, the second accessed times and the second fault association times are input into a preset second signal heat model for prediction processing to obtain a second signal heat value of the to-be-processed signal.

[0093] The first to-be-trained model and the second to-be-trained model can include an AI large model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, or a generative adversarial network (GAN) model, etc. When the first to-be-trained model and the second to-be-trained model both use an AI large model, compared with other models, they can handle more complex data relationships and patterns, and improve the accuracy and robustness of prediction.

[0094] The first to-be-trained model and the second to-be-trained model can also be fine-tuned periodically using lora according to the recent accessed times and the fault association times of each signal to adapt to the change trend of the signal heat and provide more accurate prediction results.

[0095] S204, determining the signal heat of the to-be-processed signal according to the first signal heat value and the second signal heat value.

[0096] In the present application, after obtaining the first signal heat value and the second signal heat value, the signal heat of the to-be-processed signal can be obtained by comprehensively considering the two signal heat values.

[0097] Specifically, determining the signal heat of the to-be-processed signal according to the first signal heat value and the second signal heat value can include:

[0098] obtaining a first weight of the first signal heat value and a second weight of the second signal heat value;

[0099] According to the first weight, the second weight, the first signal heat value and the second signal heat value, a signal heat of the to-be-processed signal is obtained.

[0100] In the embodiment, the sum of the first weight and the second weight can be 1, so after the first weight is determined, the second weight can be obtained.

[0101] Further, before the first weight of the first signal heat value and the second weight of the second signal heat value are obtained, the method can further include:

[0102] Obtaining a failure rate of the to-be-processed signal in a preset update time period;

[0103] According to the failure rate, a failure classification corresponding to the failure rate is determined.

[0104] According to the failure classification, a first weight and a second weight corresponding to the failure classification are determined.

[0105] In the present application, the first weight and the second weight can be updated periodically through the failure rate, so that the signal heat of the to-be-processed signal is dynamically adjusted according to the dynamic failure rate of the target vehicle type, so as to better process the signal data of the to-be-processed signal according to the failure condition of the target vehicle type.

[0106] The preset update time period is, for example, 1 month.

[0107] The failure rate can refer to the failure rate of the to-be-processed signal in all vehicles corresponding to the target vehicle type.

[0108] The failure classification can refer to a classification according to the failure rate, which is used to classify the failure rate, for example, the failure rate of 0-0.5% is a first failure classification, the failure rate of 0.5%-0.8% is a second failure classification, and the failure rate greater than 0.8% is a third failure classification.

[0109] Each failure classification corresponds to a different weight value, for example, the weight value corresponding to the first failure classification is 50%, the weight value corresponding to the second failure classification is 60%, and the weight value corresponding to the third failure classification is 70%.

[0110] The method of determining the first weight and the second weight according to the failure classification can include: since the failure rate reflects the failure condition of the target vehicle type, the second weight can be directly adjusted through the failure rate, the weight value corresponding to the failure classification is taken as the second weight, and the difference between the second weight and 100% is taken as the first weight.

[0111] When the failure corresponding to the to-be-processed signal has multiple failure types, the value of the failure rate of the failure type with the maximum failure rate is selected.

[0112] S205: The cloud sends the signal heat to the target vehicle.

[0113] In this application, after the cloud calculates the signal heat of the signal to be processed, it needs to send the signal heat to the target vehicle so that the target vehicle can perform corresponding processing on the signal data of the signal to be processed according to the signal heat of the signal to be processed.

[0114] S206: The target vehicle processes the signal data of the signal to be processed according to the signal heat.

[0115] In this embodiment, after calculating the signal heat of the signal to be processed, the cloud can construct a configuration file in JSON format. When the target vehicle is powered on, the target vehicle can pull the configuration file from the cloud and process the signal data of the signal to be processed based on the signal heat of the signal to be processed. Furthermore, signal data can be automatically classified according to signal heat, which helps optimize data storage strategies, improve storage efficiency, and reduce costs.

[0116] A vehicle signal data processing method provided in an embodiment of the present application obtains a signal to be processed of a target vehicle through the cloud, and determines a first signal heat value of the signal to be processed in the target vehicle according to a first signal heat model, and determines a second signal heat value of the signal to be processed in the target vehicle type according to a second signal heat model, and then determines the signal heat of the signal to be processed in combination with the first signal heat value and the second signal heat value. This method comprehensively considers the signal heat of the signal to be processed in the target vehicle and the signal heat in the target vehicle type, improves the accuracy of the signal heat, and thus can better classify the signal data. Finally, the target vehicle classifies and processes the signal data of the signal to be processed according to the signal heat, thereby improving the efficiency of signal data processing.

[0117] Figure 3 A flow chart of another vehicle signal data processing method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method is applied to the cloud and the target vehicle, and the method includes:

[0118] S301. The cloud obtains the signal to be processed of the target vehicle.

[0119] S302: Predict the signal heat of the signal to be processed in the target vehicle according to a preset first signal heat model to obtain a first signal heat value.

[0120] S303 : Predict the signal heat of the signal to be processed in the target vehicle type according to a preset second signal heat model to obtain a second signal heat value, where the target vehicle type is the vehicle type of the target vehicle.

[0121] S304, determining the signal heat of the to-be-processed signal according to the first signal heat value and the second signal heat value.

[0122] S305, the cloud sends the signal heat to the target vehicle.

[0123] S306, the target vehicle performs uploading processing on the signal data of the to-be-processed signal according to the signal heat.

[0124] In the embodiment, after the target vehicle obtains the signal heat of the to-be-processed signal, the uploading manner of the signal data of the to-be-processed signal is determined according to the signal heat, so that the signal data with low signal heat is uploaded offline, and the signal data with high signal heat is uploaded in real time, thereby avoiding the signal data with low signal heat from occupying the real-time uploading resources, and improving the uploading processing efficiency of the signal data.

[0125] In an implementation, the uploading processing on the signal data of the to-be-processed signal by the target vehicle according to the signal heat can include:

[0126] When the signal heat is less than a first threshold value, the signal data is assembled into a data file according to a preset data requirement, and the data requirement is used to indicate the collection time period and the file size of the data file.

[0127] The data file is sent to the cloud using an offline task in a non-busy period.

[0128] In the embodiment, the first threshold value can be a parameter used to distinguish different signal heat types. When the signal heat is less than the first threshold value, it indicates that the signal heat of the to-be-processed signal is low, and the signal data can be assembled according to the preset data requirement on the target vehicle side to obtain a plurality of data files. For example, the signal data is assembled into a data file every 30 minutes in the target vehicle, and the size of each data file is fixed at 4 MB. When the target vehicle is in a non-busy state, the data file is sent to the cloud using an offline task. If the data file fails to be uploaded, the data file is buffered locally and asynchronously retried until the uploading is successful.

[0129] In another implementation, the uploading processing on the signal data of the to-be-processed signal by the target vehicle according to the signal heat can further include:

[0130] When the signal heat is greater than a second threshold value and the second threshold value is greater than or equal to the first threshold value, the signal data is sent to the cloud in real time.

[0131] In this embodiment, when the signal heat is greater than the second threshold value, and the second threshold value is greater than or equal to the first threshold value, it indicates that the signal heat of the to-be-processed signal is high, and the signal data needs to be sent to the cloud in real time, so as to facilitate the cloud to obtain the signal data in time for subsequent data analysis. For example, the target vehicle can transmit the signal data to the cloud through MQTT (Message Queuing Telemetry Transport, a lightweight publish / subscribe message transmission protocol).

[0132] S307, the cloud receives the signal data uploaded by the target vehicle.

[0133] S308, the cloud stores and processes the signal data.

[0134] In this embodiment, when the cloud receives the signal data uploaded by the target vehicle, different storage methods are used for storage according to the uploading method of the target vehicle, so as to improve the storage efficiency of the data.

[0135] Specifically, when the signal heat is less than the first threshold value, the signal data is stored and processed, including:

[0136] Receiving the data file sent by the target vehicle using the offline task in the non-busy period, the data file being generated by the target vehicle according to the preset data requirement, the data requirement being used to indicate the collection time period and the file size of the data file;

[0137] Decrypting the signal data using the offline task in the non-busy period to obtain decrypted signal data;

[0138] Storing the decrypted signal data according to the preset storage format.

[0139] In this embodiment, in order to avoid data leakage, the target vehicle encrypts the signal data when uploading the signal data. After the cloud receives the signal data uploaded by the target vehicle, the signal data is decrypted by the OSS (Object Storage Service) file, and is stored in the OSS storage cluster through the Parquet file format (a columnar storage file format). Not only the storage space is saved, but also the efficient query operation is supported, which is convenient for subsequent data analysis and business processing.

[0140] Specifically, when the signal heat is greater than the second threshold value, and the second threshold value is greater than or equal to the first threshold value, the signal data is stored and processed, including:

[0141] Receiving the signal data uploaded by the target vehicle in real time;

[0142] Decoding the signal data and writing into the data lake.

[0143] In the embodiment, the Flink MQTT Connector can be used to decode the signal data to obtain decoded signal data, and then the decoded signal data is written into a data lake, which can be a Paimon data lake, so that fast response and efficient business processing can be achieved. The Flink MQTT Connector is used to integrate Flink (an open source stream processing framework) with the MQTT protocol, so as to use MQTT as a data source or a data receiver in a stream processing application.

[0144] Another vehicle signal data processing method provided by the embodiment of the application obtains the to-be-processed signal of the target vehicle through the cloud, and the cloud determines the signal heat of the to-be-processed signal according to the first signal heat model and the second signal heat model. The target vehicle uploads and processes the signal data of the to-be-processed signal according to the signal heat, and the cloud stores the signal data after receiving the signal data uploaded by the target vehicle, thereby improving the uploading efficiency and storage efficiency of the vehicle signal data.

[0145] Figure 4 A structural schematic diagram of a vehicle signal data processing device provided by the embodiment of the application is shown in FIG. 4, which includes: Figure 4

[0146] The first obtaining module 401 is configured to obtain the to-be-processed signal of the target vehicle.

[0147] The first prediction module 402 is configured to predict the signal heat of the to-be-processed signal in the target vehicle according to a preset first signal heat model, to obtain a first signal heat value.

[0148] The second prediction module 403 is configured to predict the signal heat of the to-be-processed signal in the target vehicle type according to a preset second signal heat model, to obtain a second signal heat value, the target vehicle type being the vehicle type of the target vehicle.

[0149] The signal heat module 404 is configured to determine the signal heat of the to-be-processed signal according to the first signal heat value and the second signal heat value.

[0150] The sending module 405 is configured to send the signal heat to the target vehicle.

[0151] In some embodiments, the first prediction module 402 is further configured to:

[0152] determine the first access frequency and the first fault association frequency of the to-be-processed signal in the preset time period;

[0153] input the first access frequency and the first fault association frequency into the preset first signal heat model for prediction processing, to obtain the first signal heat value of the to-be-processed signal. ​

[0154] In some embodiments, the second prediction module 403 is further configured to:

[0155] According to the target vehicle type of the target vehicle, obtain the number of vehicles in use of the target vehicle type in a preset time period, and the second number of visits and the second number of failure associations of the to-be-processed signal related to all vehicles in use in the preset time period;

[0156] Input the number of vehicles in use, the second number of visits and the second number of failure associations into a preset second signal heat model for prediction processing, to obtain a second signal heat value of the to-be-processed signal.

[0157] In some embodiments, the signal heat module 404 is further configured to:

[0158] Obtain a first weight of the first signal heat value and a second weight of the second signal heat value;

[0159] According to the first weight, the second weight, the first signal heat value and the second signal heat value, obtain a signal heat of the to-be-processed signal.

[0160] Figure 5 Another structure schematic diagram of a vehicle signal data processing apparatus provided by an embodiment of the present application is shown in FIG. 5. The apparatus 50 includes: Figure 5

[0161] The second acquisition module 501 is configured to acquire a signal heat of the to-be-processed signal from the cloud.

[0162] The data processing module 502 is configured to process signal data of the to-be-processed signal according to the signal heat.

[0163] In some embodiments, the data processing module 502 is further configured to:

[0164] When the signal heat is less than a first threshold value, generate a data file according to a preset data requirement, and the data requirement is used to indicate a collection time period and a file size of the data file;

[0165] Send the data file to the cloud using an offline task in a non-busy time period.

[0166] In some embodiments, the data processing module 502 is further configured to:

[0167] When the signal heat is greater than a second threshold value and the second threshold value is greater than or equal to the first threshold value, send the signal data to the cloud in real time.

[0168] Figure 6 A structure schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 6. The electronic device 60 includes: Figure 6 ​​

[0169] The electronic device 60 can include a processor 601 with one or more processing cores, a memory 602 with one or more computer-readable storage media, a communication component 603, and the like. The processor 601, the memory 602, and the communication component 603 are connected by a bus 604.

[0170] In the implementation process, the at least one processor 601 executes computer-executed instructions stored in the memory 602, so that the at least one processor 601 performs the vehicle signal data processing method as described above.

[0171] The specific implementation process of the processor 601 can refer to the method embodiments described above, which have similar implementation principles and technical effects, and will not be described here.

[0172] In the above Figure 6 In the embodiments shown in the above The processor can be a central processing unit (CPU) and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), and the like. The general-purpose processor can be a microprocessor or can also be any conventional processor. The steps of the method disclosed in the application can be directly embodied as hardware processor execution or executed by a combination of hardware and software modules in the processor.

[0173] The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk memory.

[0174] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, an extended industry standard architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0175] In some embodiments, a computer program product is also provided, including a computer program or instructions, which, when executed by a processor, implement the steps of any of the vehicle signal data processing methods described above.

[0176] The specific implementation of each operation above can refer to the previous embodiments, which will not be repeated here.

[0177] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by related hardware controlled by the instructions, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0178] To this end, an embodiment of the present application provides a computer readable storage medium, which stores a plurality of instructions, which can be loaded by a processor to execute the steps of any of the vehicle signal data processing methods provided by the embodiments of the present application.

[0179] The storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0180] According to an aspect of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium.

[0181] Since the instructions stored in the storage medium can execute the steps of any of the vehicle signal data processing methods provided by the embodiments of the present application, the beneficial effects of any of the vehicle signal data processing methods provided by the embodiments of the present application can be achieved, which are described in detail in the previous embodiments and will not be repeated here.

[0182] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The specification and examples given are exemplary only and the true scope and spirit of the application are indicated by the following claims. The true scope of the application is indicated by the following claims.

[0183] It should be understood that the present application is not limited to the precise construction that has been described above and illustrated in the accompanying drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the present application. The scope of the present application is limited only by the appended claims.

Claims

1. A vehicle signal data processing method, characterized by, The method comprises: obtaining a to-be-processed signal of a target vehicle; predicting, according to a preset first signal heat model, signal heat of the to-be-processed signal in the target vehicle, to obtain a first signal heat value; predicting, according to a preset second signal heat model, signal heat of the to-be-processed signal in a target vehicle type, to obtain a second signal heat value, the target vehicle type being a vehicle type of the target vehicle; obtaining a first weight of the first signal heat value and a second weight of the second signal heat value; determining signal heat of the to-be-processed signal according to the first weight, the second weight, the first signal heat value, and the second signal heat value; sending the signal heat to the target vehicle.

2. The method of claim 1, wherein, The method comprises: determining a first access frequency and a first fault association frequency of the to-be-processed signal in a preset time period; inputting the first access frequency and the first fault association frequency into a preset first signal heat model for prediction processing, to obtain the first signal heat value of the to-be-processed signal.

3. The method of claim 2, wherein, The method comprises: obtaining, according to the target vehicle type of the target vehicle, an in-service vehicle of the target vehicle type in the preset time period, and a second access frequency and a second fault association frequency of the to-be-processed signal related to all in-service vehicles in the preset time period; inputting the number of in-service vehicles, the second access frequency, and the second fault association frequency into a preset second signal heat model for prediction processing, to obtain the second signal heat value of the to-be-processed signal.

4. The method of claim 1, wherein, Before the method comprises: obtaining a failure rate of the to-be-processed signal in a preset update time period; determining a fault classification corresponding to the failure rate according to the failure rate; determining a first weight and a second weight corresponding to the fault classification according to the fault classification.

5. The method according to any of claims 1 to 4, characterized in that, The method further comprises: receiving signal data uploaded by the target vehicle, the signal data being obtained after sending processing according to the signal heat; storing the signal data.

6. The method of claim 5, wherein, When the signal heat is less than a first threshold value, the storing processing of the signal data comprises: receiving a data file sent by the target vehicle using an offline task in a non-busy period, the data file being generated by the target vehicle according to a preset data requirement, the data requirement being used to indicate a collection time period and a file size of the data file; decrypting the signal data using an offline task in a non-busy period, to obtain decrypted signal data; storing the decrypted signal data according to a preset storage format.

7. The method of claim 5, wherein, When the signal heat is greater than a second threshold value, and the second threshold value is greater than or equal to the first threshold value, performing storage processing on the signal data, comprising: Receiving signal data uploaded by the target vehicle in real time; Decoding the signal data and writing into a data lake.

8. A vehicle signal data processing method characterized by, Comprising: Obtaining a signal heat of a to-be-processed signal from the cloud, wherein the signal heat of the to-be-processed signal is determined according to a first weight of a first signal heat value, a second weight of a second signal heat value, the first signal heat value and the second signal heat value, the first signal heat value is obtained by predicting a signal heat of the to-be-processed signal in the target vehicle according to a preset first signal heat model, and the second signal heat value is obtained by predicting a signal heat of the to-be-processed signal in a target vehicle type according to a preset second signal heat model, the target vehicle type being a vehicle type of the target vehicle; Processing signal data of the to-be-processed signal according to the signal heat.

9. The method of claim 8, wherein, The processing of the signal data of the to-be-processed signal according to the signal heat comprises: When the signal heat is less than a first threshold value, generating a data file according to a preset data requirement, the data requirement being used to indicate a collection time period and a file size of the data file; Sending the data file to the cloud using an offline task in a non-busy period.

10. The method of claim 9, wherein, The method further comprises: If the data file fails to be uploaded, buffering the data file locally and performing asynchronous retry until the data file is successfully uploaded.

11. The method of claim 8, wherein, The processing of the signal data of the to-be-processed signal according to the signal heat comprises: When the signal heat is greater than a second threshold value, and the second threshold value is greater than or equal to the first threshold value, sending the signal data to the cloud in real time.

12. A vehicle signal data processing apparatus characterized by comprising: Comprising: A first obtaining module, configured to obtain a to-be-processed signal of a target vehicle; A first predicting module, configured to predict a signal heat of the to-be-processed signal in the target vehicle according to a preset first signal heat model, to obtain a first signal heat value; A second predicting module, configured to predict a signal heat of the to-be-processed signal in a target vehicle type according to a preset second signal heat model, to obtain a second signal heat value, the target vehicle type being a vehicle type of the target vehicle; A signal heat module, configured to obtain a first weight of the first signal heat value and a second weight of the second signal heat value, and determine a signal heat of the to-be-processed signal according to the first weight, the second weight, the first signal heat value and the second signal heat value; A sending module, configured to send the signal heat to the target vehicle.

13. A vehicle signal data processing apparatus characterized by comprising: Comprising: The second acquisition module is configured to acquire a signal heat of the to-be-processed signal from the cloud, wherein the signal heat of the to-be-processed signal is determined according to a first weight of a first signal heat value, a second weight of a second signal heat value, the first signal heat value and the second signal heat value, the first signal heat value is obtained by predicting a signal heat of a to-be-processed signal of a target vehicle in the target vehicle according to a preset first signal heat model, and the second signal heat value is obtained by predicting a signal heat of the to-be-processed signal in a target vehicle type according to a preset second signal heat model, the target vehicle type being a vehicle type of the target vehicle. The data processing module is configured to process signal data of the to-be-processed signal according to the signal heat.

14. An electronic device, comprising: The method comprises the following steps: A processor and a memory connected with the processor in communication; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory to implement the method according to any one of claims 1-11.

15. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method according to any one of claims 1-11.

Images