Disaster recovery data backup method and system based on motorcycle vehicle networking

Abstract

The present invention provides a disaster recovery data backup method and system based on a motorcycle Internet of Vehicles. The method: first, a cloud server backs up a backup data file sent by a motorcycle on-board terminal, and after the backup is completed, extracts the current situation awareness data of the motorcycle from the backup data file, and then performs situation prediction based on the current situation awareness data to determine whether there is a security risk in the future situation; if there is a security risk in the future situation data, a security risk record is generated, and the security risk record and the backup data file are backed up as new backup data files to the disaster recovery site of the motorcycle manufacturer; otherwise, the original backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer; in this way, the present invention realizes disaster recovery data backup of the motorcycle Internet of Vehicles system by combining the cloud server and the disaster recovery site, which can not only effectively ensure data security and recoverability, but also use the backup data as an important basis for supporting motorcycle safety responsibility tracing.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster recovery data security, and in particular to a disaster recovery data backup method and system based on a motorcycle vehicle network. Background Art

[0002] To stand out in the fiercely competitive market, motorcycle manufacturers and related companies are increasing their R&D and investment in connected vehicle technology. By launching motorcycles with connected vehicle functionality, they are enhancing their product's added value and competitiveness, attracting more consumers. Furthermore, connected vehicles provide companies with more opportunities for interaction and communication with users, helping them better understand user needs and improve their products and services.

[0003] The connected vehicle system collects and analyzes various motorcycle data to provide users with services such as navigation, vehicle condition monitoring, safety warnings, and personalized customization. However, motorcycles may encounter various unexpected situations during driving, such as collisions, failures, and network outages. These situations may cause data loss or corruption in the connected vehicle system, affecting the user experience and vehicle safety. Furthermore, motorcycles are more prone to accidents than cars, causing greater damage to both people and vehicles. Furthermore, the prevalence of motorcycle modifications increases the potential risk of vehicle failure or accidents.

[0004] Therefore, establishing an effective disaster recovery data backup method is crucial for motorcycle Internet of Vehicles systems and motorcycle safety responsibility tracing. Summary of the Invention

[0005] In view of the deficiencies of the prior art mentioned above, the purpose of the present invention is to provide a disaster recovery data backup method based on the motorcycle Internet of Vehicles, which extracts situation perception data from the backup data files provided by the motorcycle on-board terminal through a cloud server, and performs situation prediction to determine whether there are security risks in the future situation; moreover, the cloud server not only backs up the original backup data files, but also backs up the security risk records to the disaster recovery center; in this way, not only the data security and recoverability of the motorcycle Internet of Vehicles system can be guaranteed, but also the traceability of motorcycle safety responsibilities can be ensured.

[0006] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0007] The method for disaster recovery data backup based on motorcycle vehicle networking includes the following steps:

[0008] The motorcycle onboard terminal sends the backup data file to the cloud server;

[0009] After receiving the backup data file, the cloud server backs it up, and after the backup is complete, extracts data from the backup data file to obtain current situation awareness data of the motorcycle, and performs situation prediction based on the current situation awareness data to determine whether there is a safety risk in the future situation; wherein the situation awareness data is used to characterize the driving state, system state, and driving behavior state of the motorcycle;

[0010] If there is a security risk in the future situation data, the cloud server generates a security risk record and backs up the security risk record and the backup data file as a new backup data file to the disaster recovery site of the motorcycle manufacturer; otherwise, the backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer.

[0011] According to a specific embodiment, in the disaster recovery data backup method based on the motorcycle Internet of Vehicles provided by the present invention, the cloud server extracts data from the data file to be backed up in the following manner:

[0012] Parsing the data file to be backed up to obtain data collected by the motorcycle sensor layer;

[0013] According to the data identifiers of the data collected by the motorcycle sensor layer, the driving state associated data, the system state associated data and the driving behavior state associated data are extracted as the situation awareness data.

[0014] According to a specific embodiment, in the disaster recovery data backup method based on the motorcycle Internet of Vehicles provided by the present invention, after configuring the cloud server to establish a situation prediction model, the situation prediction model is used to predict the future situation based on the current situation perception data, and to determine whether the prediction data that plays a dominant role in the future situation has a security risk; wherein, if the prediction data that plays a dominant role in the future situation deviates from the corresponding safety control range, then the future situation has a security risk; otherwise, the future situation does not have a security risk.

[0015] According to a specific embodiment, in the disaster recovery data backup method based on the motorcycle Internet of Vehicles provided by the present invention, the situation prediction model is configured as a vector autoregression model, and after the situation perception data is input into the vector autoregression model, the prediction output is a future situation represented by driving state prediction data, system state prediction data and driving behavior state prediction data, and based on the pulse response analysis, the degree of influence of the driving state prediction data, system state prediction data and driving behavior state prediction data on the other two variables is determined respectively, and the prediction data with the highest comprehensive influence on the other two variables is used as the prediction data that plays a dominant role in the future situation; wherein, the comprehensive influence on the other two variables is the weighted average of the influence on the other two variables.

[0016] According to a specific embodiment, in the disaster recovery data backup method based on the motorcycle Internet of Vehicles provided by the present invention, if there is a security risk in the future situation, the predicted output future situation will be compared with the next situation perception data; wherein, if the error index exceeds the set range, the lag order of the vector autoregressive model will be updated according to the error index.

[0017] Based on the same inventive concept, the present invention also provides a disaster recovery data backup system based on a motorcycle vehicle network, which includes:

[0018] Motorcycle onboard terminal, used to send backup data files to the cloud server;

[0019] The cloud server is configured to back up the backup data file after receiving it, and after the backup is completed, extract data from the backup data file to obtain current situation awareness data of the motorcycle, and perform situation prediction based on the current situation awareness data to determine whether there is a safety risk in the future situation; wherein the situation awareness data is used to characterize the driving state, system state, and driving behavior state of the motorcycle;

[0020] If there is a security risk in the future situation data, the cloud server generates a security risk record and backs up the security risk record and the backup data file as a new backup data file to the disaster recovery site of the motorcycle manufacturer; otherwise, the backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer;

[0021] The disaster recovery site is used to back up the backup data files sent by the cloud server.

[0022] According to a specific embodiment, in the disaster recovery data backup system based on the motorcycle Internet of Vehicles provided by the present invention, the cloud server is configured to extract data from the data file to be backed up in the following manner:

[0023] Parsing the data file to be backed up to obtain data collected by the motorcycle sensor layer;

[0024] According to the data identifiers of the data collected by the motorcycle sensor layer, the driving state associated data, the system state associated data and the driving behavior state associated data are extracted as the situation awareness data.

[0025] According to a specific embodiment, in the disaster recovery data backup system based on the motorcycle Internet of Vehicles provided by the present invention, the cloud server is configured to establish a situation prediction model, and after establishing the situation prediction model, the situation prediction model is used to predict the future situation based on the current situation perception data, and to determine whether the prediction data that plays a dominant role in the future situation has a security risk; wherein, if the prediction data that plays a dominant role in the future situation deviates from the corresponding safety control range, then the future situation has a security risk; otherwise, the future situation does not have a security risk.

[0026] According to a specific embodiment, in the disaster recovery data backup system based on the motorcycle Internet of Vehicles provided by the present invention, the cloud server is configured to establish the situation prediction model based on a vector autoregression model, and after the situation perception data is input into the vector autoregression model, the cloud server is configured to predict and output the future situation represented by driving state prediction data, system state prediction data and driving behavior state prediction data, and based on the pulse response analysis, determine the degree of influence of the driving state prediction data, system state prediction data and driving behavior state prediction data on the other two variables respectively, and use the prediction data with the highest comprehensive influence on the other two variables as the prediction data that plays a dominant role in the future situation; wherein, the comprehensive influence on the other two variables is the weighted average of the influence on the other two variables.

[0027] According to a specific embodiment, in the disaster recovery data backup system based on the motorcycle Internet of Vehicles provided by the present invention, the cloud server is configured to compare the predicted output future situation with the next situation perception data if there is a security risk in the future situation; wherein, if the error index exceeds the set range, the lag order of the vector autoregression model is updated according to the error index.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] In the disaster recovery data backup method based on the motorcycle Internet of Vehicles provided by the present invention, after the cloud server receives the backup data file sent by the motorcycle on-board terminal, it backs it up, and after the backup is completed, it extracts data from the backup data file to obtain the current situation awareness data of the motorcycle, and performs situation prediction based on the current situation awareness data to determine whether there is a security risk in the future situation; if there is a security risk in the future situation data, the cloud server generates a security risk record, and backs up the security risk record and the backup data file as a new backup data file to the disaster recovery site of the motorcycle manufacturer; otherwise, the backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer. In this way, the present invention realizes disaster recovery data backup of the motorcycle Internet of Vehicles system by combining the cloud server and the disaster recovery site, which can not only effectively ensure data security and recoverability, but also use the backup data as an important basis for supporting motorcycle safety responsibility tracing. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 Schematic diagram of the process of the present invention;

[0031] Figure 2 Schematic diagram of the workflow of the situation prediction model in the method of the present invention;

[0032] Figure 3 Schematic diagram of the structure of the system of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments. However, this should not be construed as limiting the scope of the present invention to the following embodiments, as all technologies implemented based on the present invention fall within the scope of the present invention.

[0034] like Figure 1 As shown, the present invention provides a disaster recovery data backup method based on a motorcycle vehicle network, which includes the following steps:

[0035] First, the motorcycle onboard terminal establishes a communication connection with the cloud server. Then, the motorcycle onboard terminal generates a backup data file through the data collected by its sensor layer, and then sends the backup data file to the cloud server.

[0036] Next, after receiving the backup data file, the cloud server backs it up and, after the backup is complete, extracts data from the backup data file to obtain the current situation awareness data of the motorcycle. Then, based on the current situation awareness data, a situation prediction is performed to determine whether a future situation poses a safety risk; wherein the situation awareness data is used to characterize the motorcycle's driving state, system state, and driving behavior state;

[0037] If there is a security risk in the future situation data, the cloud server generates a security risk record and backs up the security risk record and the backup data file as a new backup data file to the disaster recovery site of the motorcycle manufacturer; otherwise, the backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer.

[0038] Specifically, the cloud server extracts data from the data file to be backed up in the following manner:

[0039] Parsing the data file to be backed up to obtain data collected by the motorcycle sensor layer;

[0040] According to the data identifiers of the data collected by the motorcycle sensor layer, the driving state associated data, the system state associated data and the driving behavior state associated data are extracted as the situation awareness data.

[0041] Specifically, the driving state, system state and driving behavior state of a motorcycle are correlated. During implementation, the driving state-related data include: transmission gear data, wheel speed, tire pressure and temperature, brake fluid level, brake pressure, instantaneous speed, average speed, acceleration, deceleration, tilt angle, vehicle head direction and steering angle, latitude and longitude coordinates, and altitude; the system state-related data include: engine speed, throttle opening, fuel pressure, intake air temperature and pressure, battery voltage, generator output voltage and current, spark plug ignition time and energy, clutch state, transmission gear data, chain or belt tension, tire pressure and temperature, brake pressure, brake fluid level, and other data; the driving behavior-related data include: throttle operation data, brake operation data, gear operation data, clutch operation data, body tilt angle, head and hand position data, etc.

[0042] Specifically, in the disaster recovery data backup method based on the motorcycle Internet of Vehicles provided by the present invention, after configuring the cloud server to establish a situation prediction model, the situation prediction model is used to predict the future situation based on the current situation perception data, and to determine whether the prediction data that plays a dominant role in the future situation has a security risk; wherein, if the prediction data that plays a dominant role in the future situation deviates from the corresponding safety control range, then the future situation has a security risk; otherwise, the future situation does not have a security risk.

[0043] Through the above approach, when a safety incident occurs, the specific prediction data from the previously predicted future situation plays a leading role, clearly clarifying safety responsibilities. For example, if the driving behavior prediction data plays a leading role, it can indirectly indicate that the user engaged in certain dangerous driving behaviors while driving the motorcycle. If the system status prediction data plays a leading role, it can indirectly indicate that the motorcycle experienced some faults that affected the normal operation of the motorcycle during the user's driving. This fault information can help motorcycle manufacturers improve their products and protect the rights of vehicle owners. If the driving status data plays a leading role, it not only involves the vehicle owner's driving form and road conditions, but also the working dynamics of the motorcycle system during driving, thus involving the responsibilities of both the vehicle owner and the manufacturer. In one specific embodiment, the cloud server can be jointly established by regulatory agencies and motorcycle manufacturers to better achieve effective supervision of motorcycle traffic safety.

[0044] like Figure 2 As shown, the situation prediction model is configured as a vector autoregression model, and after the situation perception data is input into the vector autoregression model, the prediction output is a future situation represented by the driving state prediction data, the system state prediction data and the driving behavior state prediction data, and based on the impulse response analysis, the influence of the driving state prediction data, the system state prediction data and the driving behavior state prediction data on the other two variables is determined, and the prediction data with the highest comprehensive influence on the other two variables is used as the prediction data that plays a dominant role in the future situation; wherein, the comprehensive influence on the other two variables is the weighted average of the influence on the other two variables.

[0045] In implementation, for a vector autoregressive model (VAR model) containing k variables, the variable vector is denoted as Y t =(Y 1t ,Y 2t ,···,Y kt ) T , where t represents time, Y kt is the value of the kth variable at time t, and T represents the transpose. The general form of the VAR model can be expressed as: Where c=(c1,c2,···,c k ) T is a k-dimensional constant vector representing the intercept term; p is the lag order of the model, which determines the time span of the influence of the past value of the variable on the current value; A i is a coefficient matrix that represents the lag relationship between variables, for example, A i Element a in ij Indicates the degree of influence of the i-th variable on the j-th variable at the first lag order; ε t =(ε1,ε2,···,εk ) T is a k-dimensional white noise vector, also called a random error term, with a mean of zero and a covariance matrix of Ω, and the error terms at different times are independent of each other.

[0046] Among them, the choice of lag order is crucial for the VAR model. If it is too small, important lag relationships between variables may be omitted, resulting in model setting errors; if it is too large, the number of parameters of the model will increase, the degrees of freedom will be reduced, and the model may be overfitted. Commonly used methods for determining the lag order include information criteria, such as Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and Hannan-Quinn Information Criterion (HQIC). These criteria weigh the goodness of model fit and model complexity. In the present invention, Akaike Information Criterion (AIC) is adopted, and its calculation formula is AIC=-2Ln(L)+2k, where is the likelihood function value of the L model and k is the number of parameters of the model. The lag order that minimizes the AIC value is selected as the optimal lag order.

[0047] Among them, the parameters of the VAR model are usually estimated using the multivariate extension of the least squares method (OLS). The goal is to find the intercept term c, coefficient matrix A i and the covariance matrix Ω, minimizing the residual sum of squares. Specifically, the VAR model is written in matrix form: Y = Xβ + E, where Y is a T × k matrix containing the observed values ​​of all variables; X is a matrix consisting of constant terms and lagged values ​​of the variables; E is a T × k matrix consisting of all parameters to be estimated; and E is a residual matrix. The parameter estimates are then obtained using the least squares method.

[0048] After initially establishing a situation forecasting model based on the principles of the aforementioned VAR model, the first step is to identify the time series data related to the situation and perform data cleaning and preprocessing on the identified relevant data. Then, using actual historical observations, the residuals of the situation forecasting model are calculated, and statistical indicators such as the root mean square error (RMSE) and mean absolute error (MAE) are used to evaluate the model's goodness of fit. At the same time, information criteria such as the Akaike Information Criterion (AIC), the Bayesian Information Criterion (BIC), and the Hannan-Quinn Information Criterion (HQIC) are used to consider model complexity and goodness of fit in model selection. Models with smaller AIC and BIC values ​​are generally preferred. Once the situation forecasting model achieves the appropriate goodness of fit, it can begin operation.

[0049] Furthermore, when the situation prediction model is working, if there is a safety risk in the future situation, the predicted future situation will be compared with the next situation perception data; if the error index exceeds the set range, the lag order of the vector autoregressive model will be updated according to the error index.

[0050] Specifically, the impulse response function (IRF) is an important analytical tool for the VAR model, which is used to describe the dynamic response of an endogenous variable to a unit shock (pulse) from other endogenous variables. Calculating the impulse response function requires orthogonalizing the VAR model to separate the impact of different shocks. Orthogonalization is usually achieved using Cholesky decomposition, which converts shocks into an orthogonal form, allowing the impact of each shock to be analyzed independently. In this way, through the above method, the user's trend prediction model can be continuously optimized based on the trend perception data actually generated by different users, making the prediction more accurate.

[0051] like Figure 3 As shown, the present invention also provides a disaster recovery data backup system based on motorcycle vehicle networking, which includes:

[0052] Motorcycle onboard terminal, used to send backup data files to the cloud server;

[0053] The cloud server is configured to back up the backup data file after receiving it, and after the backup is completed, extract data from the backup data file to obtain current situation awareness data of the motorcycle, and perform situation prediction based on the current situation awareness data to determine whether there is a safety risk in the future situation; wherein the situation awareness data is used to characterize the driving state, system state, and driving behavior state of the motorcycle;

[0054] If there is a security risk in the future situation data, the cloud server generates a security risk record and backs up the security risk record and the backup data file as a new backup data file to the disaster recovery site of the motorcycle manufacturer; otherwise, the backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer;

[0055] The disaster recovery site is used to back up the backup data files sent by the cloud server.

[0056] Specifically, the cloud server is configured to have a data extraction module, and the data extraction module extracts data from the data file to be backed up in the following manner:

[0057] Parsing the data file to be backed up to obtain data collected by the motorcycle sensor layer;

[0058] According to the data identifiers of the data collected by the motorcycle sensor layer, the driving state associated data, the system state associated data and the driving behavior state associated data are extracted as the situation awareness data.

[0059] Specifically, the cloud server is configured to establish a situation prediction model, and after establishing the situation prediction model, predict the future situation based on the current situation perception data through the situation prediction model, and determine whether the prediction data that plays a dominant role in the future situation has a security risk; wherein, if the prediction data that plays a dominant role in the future situation deviates from the corresponding security control range, then the future situation has a security risk; otherwise, the future situation does not have a security risk.

[0060] Specifically, the cloud server is configured to establish the situation prediction model based on a vector autoregression model, and after the situation perception data is input into the vector autoregression model, predict and output the future situation represented by driving state prediction data, system state prediction data and driving behavior state prediction data, and based on the pulse response analysis, determine the degree of influence of the driving state prediction data, system state prediction data and driving behavior state prediction data on the other two variables respectively, and use the prediction data with the highest comprehensive influence on the other two variables as the prediction data that plays a dominant role in the future situation; wherein, the comprehensive influence on the other two variables is the weighted average of the influence on the other two variables.

[0061] Furthermore, the cloud server is configured to compare the predicted output future situation with the next situation perception data if there is a security risk in the future situation; wherein, if the error index exceeds the set range, the lag order of the vector autoregression model is updated according to the error index.

[0062] It should be understood that the system disclosed herein can be implemented in other ways. For example, the module division described above is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, the communication connections between modules can be through interfaces, indirect coupling or communication connections between devices or units, and can be electrical or otherwise.

[0063] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each module may exist physically separately, or two or more modules may be integrated into a single processing unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0064] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0065] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A disaster recovery data backup method based on motorcycle vehicle networking, characterized in that: The following steps are involved: The motorcycle onboard terminal sends the backup data file to the cloud server; After receiving the backup data file, the cloud server backs it up, and after the backup is complete, extracts data from the backup data file to obtain current situation awareness data of the motorcycle, and performs situation prediction based on the current situation awareness data to determine whether there is a safety risk in the future situation; wherein the situation awareness data is used to characterize the driving state, system state, and driving behavior state of the motorcycle; If there is a security risk in the future situation data, the cloud server generates a security risk record and backs up the security risk record and the backup data file as a new backup data file to the disaster recovery site of the motorcycle manufacturer; otherwise, the backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer; The cloud server extracts data from the backup data file in the following manner: Parsing the backup data file to obtain data collected by the motorcycle sensor layer; Extracting driving state related data, system state related data, and driving behavior state related data as the situation awareness data based on data identifiers of data collected by the motorcycle sensor layer; After configuring the cloud server to establish a situation prediction model, the situation prediction model is used to predict a future situation based on the current situation awareness data, and to determine whether the prediction data that plays a dominant role in the future situation poses a security risk; if the prediction data that plays a dominant role in the future situation deviates from a corresponding security control range, then the future situation poses a security risk; otherwise, the future situation does not pose a security risk; Moreover, the situation prediction model is configured as a vector autoregression model, and after the situation perception data is input into the vector autoregression model, the prediction output is a future situation represented by the driving state prediction data, the system state prediction data and the driving behavior state prediction data, and based on the pulse response analysis, the influence of the driving state prediction data, the system state prediction data and the driving behavior state prediction data on the other two variables is determined respectively, and the prediction data with the highest comprehensive influence on the other two variables is used as the prediction data that plays a dominant role in the future situation; wherein, the comprehensive influence on the other two variables is the weighted average of the influence on the other two variables.

2. The method for disaster recovery data backup based on motorcycle vehicle networking according to claim 1, characterized in that: If there is a security risk in the future situation, the predicted future situation is compared with the next situation awareness data; if the error index exceeds the set range, the lag order of the vector autoregressive model is updated according to the error index.

3. A disaster recovery data backup system based on motorcycle vehicle networking, characterized in that: include: Motorcycle onboard terminal, used to send backup data files to the cloud server; The cloud server is configured to back up the backup data file after receiving it, and after the backup is completed, extract data from the backup data file to obtain current situation awareness data of the motorcycle, and perform situation prediction based on the current situation awareness data to determine whether there is a safety risk in the future situation; wherein the situation awareness data is used to characterize the driving state, system state, and driving behavior state of the motorcycle; If there is a security risk in the future situation data, the cloud server generates a security risk record and backs up the security risk record and the backup data file as a new backup data file to the disaster recovery site of the motorcycle manufacturer; otherwise, the backup data file continues to be backed up to the disaster recovery site of the motorcycle manufacturer; The disaster recovery site is used to back up the backup data files sent by the cloud server; The cloud server is configured to extract data from the backup data file in the following manner: Parsing the backup data file to obtain data collected by the motorcycle sensor layer; Extracting driving state related data, system state related data, and driving behavior state related data as the situation awareness data based on data identifiers of data collected by the motorcycle sensor layer; The cloud server is configured to establish a situation prediction model, and after establishing the situation prediction model, predict a future situation based on the current situation awareness data using the situation prediction model, and determine whether the prediction data that plays a dominant role in the future situation has a security risk; wherein, if the prediction data that plays a dominant role in the future situation deviates from a corresponding security control range, then the future situation has a security risk; otherwise, the future situation does not have a security risk; Moreover, the cloud server is configured to establish the situation prediction model based on a vector autoregression model, and after the situation perception data is input into the vector autoregression model, predict and output the future situation represented by the driving state prediction data, the system state prediction data and the driving behavior state prediction data, and based on the pulse response analysis, determine the degree of influence of the driving state prediction data, the system state prediction data and the driving behavior state prediction data on the other two variables respectively, and use the prediction data with the highest comprehensive influence on the other two variables as the prediction data that plays a dominant role in the future situation; wherein, the comprehensive influence on the other two variables is the weighted average of the influence on the other two variables.

4. The disaster recovery data backup system based on the motorcycle vehicle network according to claim 3, characterized in that: The cloud server is configured to compare the predicted future situation with the next situation awareness data if there is a security risk in the future situation; if the error index exceeds the set range, the lag order of the vector autoregression model is updated according to the error index.

Images