Vehicle interaction data processing method, device, computer equipment, and storage medium

Abstract

The present application relates to the technical field of Internet of Things, and in particular to a vehicle interaction data processing method, device, computer equipment, and storage medium. The method comprises: receiving a vehicle interaction data evaluation request sent by a first vehicle terminal, the vehicle interaction data evaluation request carrying a first vehicle identification and a second vehicle identification; determining the temporal dependency relationship and / or the spatial dependency relationship based on the vehicle social network between the first vehicle terminal and the second vehicle terminal according to the first vehicle identification and the second vehicle identification; and calculating the evaluation index of the vehicle interaction data according to the determined dependency relationship. The present method can quickly and effectively predict the requests sent by the vehicle terminal.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a vehicle interaction data processing method, apparatus, computer equipment and storage medium. Background Art

[0002] Driven by the government and automobile industry manufacturers, Internet of Vehicles technology has received widespread attention. In a self-organizing vehicle network, vehicles can use the IEEE 802.11p communication protocol to conduct short-range communication between vehicles, realize the exchange of information such as traffic jams, road construction, accidents / collisions, road conditions, weather alerts, etc., and enable users to obtain real-time road traffic information more conveniently.

[0003] However, due to defects in vehicle sensors, cyber attacks, and intentional interference by malicious users, the information shared between vehicles may be unreliable or even malicious. For example, a driver may send false information that a public parking lot is full to other users to ensure that he has a place to park, or the vehicle system may send emergency stop or turn information to surrounding vehicles after being attacked by an adversary, causing terrible traffic accidents when other vehicles take emergency measures, which will seriously damage the user's property safety or even threaten the user's life safety. Therefore, it is crucial to enable vehicles to evaluate the trustworthiness of other vehicles in real time and receive messages from other vehicles on the premise of understanding the trustworthiness of the other vehicle.

[0004] When a vehicle broadcasts an emergency message, the existing message-oriented trust evaluation scheme still needs to spend time seeking information sent by other vehicles to verify the authenticity of the traffic incident. This delay seriously threatens the buffer time for the receiver to take countermeasures, which is fatal to the driver. Therefore, it is necessary to propose a faster and more effective vehicle trust evaluation scheme to ensure the sharing of trustworthy information in the Internet of Vehicles. Summary of the invention

[0005] Based on this, it is necessary to provide a vehicle interaction data processing method, device, computer equipment, computer-readable storage medium and computer program product that can quickly and effectively predict the requests sent by the vehicle terminal in order to solve the above technical problems.

[0006] In a first aspect, the present application provides a vehicle interaction data processing method applied to a server, the method comprising:

[0007] Receiving a vehicle interaction data evaluation request sent by the first vehicle terminal, the vehicle interaction data evaluation request carrying a first vehicle identifier and a second vehicle identifier;

[0008] Determining, according to the first vehicle identifier and the second vehicle identifier, a temporal dependency relationship between the first vehicle terminal and the second vehicle terminal and / or a spatial dependency relationship based on a vehicle social network;

[0009] According to the determined dependency relationship, the evaluation index of the vehicle interaction data is calculated.

[0010] In one embodiment, determining the temporal dependency relationship between the first vehicle terminal and the second vehicle terminal and / or the spatial dependency relationship based on the vehicle social network according to the first vehicle identifier and the second vehicle identifier includes:

[0011] In the case where there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, it is determined that there is a temporal dependency relationship between the first vehicle terminal and the second vehicle terminal;

[0012] In the case that there is no historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, the spatial dependency relationship between the first vehicle terminal and the second vehicle terminal is obtained based on the vehicle social network.

[0013] In one embodiment, the evaluation index of the vehicle interaction data is calculated based on the determined dependency relationship, and the evaluation index of the vehicle interaction data is calculated, including:

[0014] In the case where there is a temporal dependency between the first vehicle and the second vehicle, an evaluation index of the vehicle interaction data is predicted by the first prediction model;

[0015] In the case where there is a spatial dependency relationship between the first vehicle and the second vehicle, the evaluation index of the vehicle interaction data is predicted by the second prediction model.

[0016] In one embodiment, the evaluation index of the vehicle interaction data predicted by the first prediction model includes:

[0017] Analyze the stability of data of historical interactions between the first vehicle terminal and the second vehicle terminal;

[0018] In the case where the data of the historical interaction between the first vehicle terminal and the second vehicle terminal is determined to be non-stationary data, converting the non-stationary data into stationary data;

[0019] The stable data is input into the first prediction model to predict the evaluation index of the vehicle interaction data.

[0020] In one embodiment, before inputting the stationary data into the first prediction model to predict the evaluation index of the vehicle interaction data, the method further includes:

[0021] Obtain historical data and convert it into a stationary time series;

[0022] According to the Chichi Information Criterion, the stationary time series is processed to obtain the target class and order;

[0023] Parameters are estimated according to the target class, order and stationary time series to obtain a first prediction model.

[0024] In one embodiment, the evaluation index of the vehicle interaction data predicted by the second prediction model includes:

[0025] Obtain a first feature matrix through the vehicle social network; input the first feature matrix into a third prediction model to obtain the features of each vehicle terminal;

[0026] The features of any two vehicle terminals that interact are concatenated to obtain a second feature matrix, and the second feature matrix is ​​input into a second prediction model to obtain an evaluation index of vehicle interaction data between any two vehicle terminals.

[0027] In one embodiment, before determining the temporal dependency relationship between the first vehicle terminal and the second vehicle terminal and / or the spatial dependency relationship based on the vehicle social network according to the first vehicle identifier and the second vehicle identifier, the method further includes:

[0028] Acquire historical data during the interaction between the first vehicle and the second vehicle;

[0029] Use interpolation to fill in missing values ​​in historical data;

[0030] Generate vehicle social network based on populated historical data.

[0031] In one embodiment, a vehicle interaction data processing method applied to a first vehicle terminal is provided, the method comprising:

[0032] receiving an interaction request, the interaction request carrying a second vehicle identifier;

[0033] The first vehicle terminal generates a vehicle interaction data evaluation request and sends the vehicle interaction data evaluation request to the server;

[0034] Receiving an evaluation index of vehicle interaction data generated by the server based on the vehicle interaction data processing method in any one of the above embodiments;

[0035] Data is exchanged with the second vehicle terminal according to the evaluation index of the vehicle interaction data.

[0036] In one embodiment, the vehicle interaction data processing method in the vehicle social network further includes:

[0037] generating a direct trust assessment with a second vehicle terminal with a preset probability;

[0038] The direct trust evaluation is uploaded to the server periodically as vehicle history data.

[0039] In one embodiment, the generating of a direct trust assessment with the second vehicle terminal with a preset probability includes:

[0040] receiving an interaction request sent by the second vehicle terminal with a preset probability;

[0041] A direct trust evaluation between the current node and the second vehicle terminal is generated according to the direct trust evaluation between the previous node and the second vehicle terminal and the determination factor.

[0042] In a second aspect, the present application further provides a vehicle interaction data processing device, the device comprising:

[0043] A receiving module, configured to receive a vehicle interaction data evaluation request sent by a first vehicle terminal, wherein the vehicle interaction data evaluation request carries a first vehicle identifier and a second vehicle identifier;

[0044] A determination module, configured to determine, according to the first vehicle identifier and the second vehicle identifier, a dependency relationship between the first vehicle terminal and the second vehicle terminal in time and / or space based on a vehicle social network;

[0045] The evaluation module is used to calculate the evaluation index of the vehicle interaction data based on the dependency relationship between the first vehicle terminal and the second vehicle terminal in time and / or space based on the vehicle social network.

[0046] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the anti-debugging method provided in the embodiment of the first aspect are implemented.

[0047] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the anti-debugging method provided in the embodiment of the first aspect above.

[0048] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the anti-debugging method provided in the embodiment of the first aspect are implemented.

[0049] The above-mentioned vehicle interaction data processing method, device, computer equipment and storage medium respectively perform trust evaluation on vehicle interaction data through the temporal dependency between the first vehicle terminal and the second vehicle terminal and / or the spatial dependency based on the vehicle social network to quickly predict the trust with the second vehicle when the first vehicle sends a trust query request, so as to overcome the delay problem and realize fast and accurate trust evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A diagram showing an application environment of a vehicle interaction data processing method in one embodiment;

[0051] Figure 2 A schematic diagram of a process flow of a vehicle interaction data processing method in one embodiment;

[0052] Figure 3 A schematic diagram of a spatial dependency relationship between vehicle terminals in one embodiment;

[0053] Figure 4 A schematic flow chart of a vehicle interaction data processing method in another embodiment;

[0054] Figure 5 is a structural block diagram of a vehicle interaction data processing device in one embodiment;

[0055] Figure 6 is a structural block diagram of a vehicle interaction data processing device in another embodiment;

[0056] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] The vehicle interaction data processing method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the first vehicle terminal 102 communicates with the second vehicle terminal 106 through the IEEE 802.11p communication protocol, and the first vehicle terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 receives a vehicle interaction data evaluation request sent by the first vehicle terminal 102, and the vehicle interaction data evaluation request carries a first vehicle identifier and a second vehicle identifier; according to the first vehicle identifier and the second vehicle identifier, the time dependency relationship and / or the spatial dependency relationship based on the vehicle social network between the first vehicle terminal 102 and the second vehicle terminal 106 are determined; based on the time dependency relationship and / or the spatial dependency relationship based on the vehicle social network between the first vehicle terminal 102 and the second vehicle terminal 106, the evaluation index of the vehicle interaction data is calculated and sent to the first vehicle terminal 102, and the first vehicle terminal 102 interacts with the second vehicle terminal 106 according to the evaluation index of the vehicle interaction data. The first vehicle terminal 102 and the second vehicle terminal 106 are vehicle terminals, which may be in a vehicle. The server 104 may be implemented as an independent server or a server cluster composed of multiple servers.

[0059] In one embodiment, Figure 2 As shown, a vehicle interaction data processing method applied to a server is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0060] S202: Receive a vehicle interaction data evaluation request sent by the first vehicle terminal, where the vehicle interaction data evaluation request carries a first vehicle identifier and a second vehicle identifier.

[0061] Specifically, the first vehicle terminal refers to the vehicle that receives the vehicle interaction data evaluation request during the vehicle interaction process, and the second vehicle terminal refers to the vehicle that sends the vehicle interaction data evaluation request during the vehicle interaction process. The vehicle interaction data evaluation request refers to the request for message evaluation between the first vehicle terminal and the message sender vehicle sent to the server, that is, the message evaluation request between the first vehicle terminal and the second vehicle terminal sent to the server, and the message sent by the second vehicle can be subsequently performed trust evaluation, validity evaluation, etc.; the first vehicle identification and the second vehicle identification refer to the identity identification of the vehicles, which can be the license plate numbers of the first vehicle and the second vehicle, or any information that can represent the vehicle identity identification.

[0062] Specifically, the server receives a vehicle interaction data evaluation request sent by the first vehicle terminal, and the vehicle interaction data evaluation request carries a first vehicle identifier and a second vehicle identifier. Optionally, the server can determine the dependency relationship between the first vehicle and the second vehicle based on the first vehicle identifier and the second vehicle identifier carried in the vehicle interaction data evaluation request sent by the first vehicle to the server, and then use different processing methods according to different dependency relationships between the first vehicle and the second vehicle to calculate evaluation indicators of the vehicle interaction data.

[0063] S204: Determine, according to the first vehicle identifier and the second vehicle identifier, a temporal dependency relationship between the first vehicle terminal and the second vehicle terminal and / or a spatial dependency relationship based on a vehicle social network.

[0064] Among them, the temporal dependency refers to the relationship of direct information interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, that is, the first vehicle terminal and the second vehicle terminal have historical interactions, which means that the first vehicle terminal directly sends information to the second vehicle terminal and / or receives information sent by the second vehicle terminal, and no information is transmitted through other vehicle terminals in the middle; the spatial dependency refers to the relationship of indirect information interaction between the first vehicle terminal and the second vehicle terminal in the spatial dimension, that is, information interaction can be carried out through other vehicle terminals.

[0065] The vehicle social network refers to a graph generated based on historical data between vehicle terminals, wherein the vehicle social network can optionally be represented by a directed graph, in which the points represent vehicle terminals and the directed edges between the points represent the message interaction process between vehicles, i.e., the interaction data mentioned above.

[0066] Specifically, the server determines the dependency relationship between the first vehicle terminal and the second vehicle terminal according to the first vehicle identification and the second vehicle identification. Optionally, the server can determine the relationship between the first vehicle terminal and the second vehicle terminal according to the license plate of the first vehicle and the license plate of the second vehicle. For example, the server can query whether there is a historical interaction between the first vehicle terminal and the second vehicle terminal according to the license plate of the first vehicle and the license plate of the second vehicle, and then determine whether there is a historical interaction between the two to determine the dependency relationship between the first vehicle terminal and the second vehicle terminal. Optionally, the dependency relationship between the first vehicle terminal and the second vehicle terminal can be one of the dependency relationship between the first vehicle terminal and the second vehicle terminal only in the time dimension, the dependency relationship between the first vehicle terminal and the second vehicle terminal at the same time, in the time dimension and the space of the vehicle social network, and the dependency relationship between the first vehicle terminal and the second vehicle terminal only in the space of the social network. The specific dependency relationship is determined based on the historical interaction records of the first vehicle terminal and the second vehicle terminal.

[0067] S206: Calculate and obtain evaluation indicators of the vehicle interaction data according to the determined dependency relationship.

[0068] The evaluation index of vehicle interaction data refers to an evaluation index generated by the server according to the vehicle interaction data evaluation request, which can quantitatively measure the credibility of the vehicle interaction data evaluation request. Optionally, the first vehicle terminal can choose to trust or distrust the vehicle interaction data evaluation request sent by the second vehicle terminal according to the evaluation index of the vehicle interaction data to avoid intentional interference by malicious users.

[0069] Specifically, after determining the dependency relationship between the first vehicle terminal and the second vehicle terminal, the server calculates an evaluation index of the vehicle interaction data according to the dependency relationship between the first vehicle terminal and the second vehicle terminal. Optionally, the server may use different models to calculate the evaluation index of the vehicle interaction data according to different dependency relationships between the first vehicle terminal and the second vehicle terminal. For example, when the server determines that the first vehicle terminal and the second vehicle terminal have a temporal dependency relationship, the first prediction model is used to calculate the evaluation index of the vehicle interaction data; when the server determines that the first vehicle terminal and the second vehicle terminal have a spatial dependency relationship in the vehicle social network, the second prediction model is used to calculate the evaluation index of the vehicle interaction data.

[0070] In the above embodiments, trust evaluation is performed on vehicle interaction data through different dependencies between the first vehicle terminal and the second vehicle terminal, namely, temporal dependencies and / or spatial dependencies based on vehicle social networks, so as to quickly predict trust with the second vehicle when the first vehicle sends a trust query request, thereby overcoming the delay problem and achieving fast and accurate trust evaluation.

[0071] In one embodiment, the temporal dependency and / or the spatial dependency based on the vehicle social network between the first vehicle terminal and the second vehicle terminal are determined based on the first vehicle identification and the second vehicle identification, including: when there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the temporal dimension, it is determined that there is a temporal dependency between the first vehicle terminal and the second vehicle terminal; when there is no historical interaction between the first vehicle terminal and the second vehicle terminal in the temporal dimension, the spatial dependency between the first vehicle terminal and the second vehicle terminal is obtained based on the vehicle social network.

[0072] Among them, the temporal dependency relationship between the first vehicle terminal and the second vehicle terminal refers to the existence of historical interactions between the first vehicle terminal and the second vehicle terminal, that is, the first vehicle terminal has message interactions with the second vehicle terminal at any time point before the current time point; obtaining the spatial dependency relationship between the first vehicle terminal and the second vehicle terminal based on the vehicle social network means that the first vehicle terminal and the second vehicle terminal can be indirectly interacted through the intermediate vehicle in the vehicle social network. At this time, the spatial dependency relationship between the first vehicle terminal and the second vehicle terminal can be obtained. Figure 3 As shown, Figure 3 The figure is a schematic diagram of the spatial dependency between vehicle terminals in an embodiment. If there is a historical interaction between vehicle A and vehicle B, and there is a direct historical interaction between vehicle A and vehicle C, then vehicle A is called an intermediate vehicle. Vehicle B and vehicle C can have an indirect interaction through vehicle A, and a direct spatial dependency between vehicle B and vehicle C can be obtained.

[0073] Specifically, the server determines the dependency relationship between the first vehicle terminal and the second vehicle terminal, and determines that the first vehicle terminal and the second vehicle terminal have a time dependency relationship when there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension; when there is no historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, the server obtains the spatial dependency relationship between the first vehicle terminal and the second vehicle terminal based on the vehicle social network, wherein optionally, the server first determines whether there is an interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, that is, whether there is a historical interaction between the first vehicle terminal and the second vehicle terminal, and when there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, the server determines that the first vehicle terminal and the second vehicle terminal have a time dependency relationship, otherwise the spatial dependency relationship between the first vehicle terminal and the second vehicle terminal is obtained based on the vehicle social network.

[0074] In the above embodiment, the server can determine the dependency relationship between the first vehicle terminal and the second vehicle terminal by whether there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, and then use a suitable model to predict the first vehicle terminal and the second vehicle terminal with different dependencies.

[0075] In one embodiment, based on the determined dependency relationship, an evaluation index of the vehicle interaction data is calculated, and the evaluation index of the vehicle interaction data is calculated, including: when there is a temporal dependency between the first vehicle and the second vehicle, the evaluation index of the vehicle interaction data is predicted by a first prediction model; when there is a spatial dependency between the first vehicle and the second vehicle, the evaluation index of the vehicle interaction data is predicted by a second prediction model.

[0076] The first prediction model refers to a model that can predict the interaction between vehicle terminals that have a temporal dependency, and the second prediction model refers to a model that can predict the interaction between vehicle terminals that have a spatial dependency.

[0077] Specifically, after determining the dependency relationship between the first vehicle terminal and the second vehicle terminal, the server uses different prediction models to calculate the evaluation index of the vehicle interaction data according to the dependency relationship between the first vehicle terminal and the second vehicle terminal. When the server determines that the first vehicle terminal and the second vehicle terminal have a temporal dependency relationship, the server uses the first prediction model to predict the evaluation index of the interaction data sent by the first vehicle terminal and the second vehicle terminal, wherein the first prediction model may optionally be an ARIMA model or other model that can predict time series; when the server determines that there is a spatial dependency relationship between the first vehicle terminal and the second vehicle terminal, the server uses the second prediction model to predict the evaluation index of the interaction data sent by the first vehicle terminal and the second vehicle terminal, wherein the second prediction model may optionally be an MLP (Multiayer Perceptron) or other model that can make predictions based on spatial dependencies.

[0078] In the above embodiment, different prediction models are used to perform predictions for the first vehicle terminal and the second vehicle terminal having different dependencies, so that evaluation indicators of vehicle interaction data can be obtained more quickly and accurately.

[0079] In one embodiment, the evaluation index of the vehicle interaction data is predicted by the first prediction model, including: analyzing the stability of the data of the historical interaction between the first vehicle terminal and the second vehicle terminal; when the data of the historical interaction between the first vehicle terminal and the second vehicle terminal is determined to be non-stationary data, converting the non-stationary data into stationary data; inputting the stationary data into the first prediction model to predict the evaluation index of the vehicle interaction data.

[0080] Among them, data stationarity refers to an indicator used to judge whether the data is stationary, which can be judged by the fluctuation around a constant and the fluctuation range. If the data fluctuates around a constant and the fluctuation range is limited, that is, there is a constant mean and a constant variance, then the data is called stationary data, otherwise it is non-stationary data.

[0081] Specifically, firstly, the stability of the data of the historical interaction between the first vehicle terminal and the second vehicle terminal is analyzed. If the data of the historical interaction between the first vehicle terminal and the second vehicle terminal is determined to be non-stationary data, the non-stationary data is processed and converted into stable data. Optionally, the non-stationary data can be differentially processed, that is, the value at the next time point minus the current time point, that is, y t -y t-1, until the non-stationary data is converted into stationary data. After the non-stationary data is converted into stationary data, the stationary data is input into the first prediction model to predict the historical interaction data between the first vehicle terminal and the second vehicle terminal to obtain the evaluation index of the vehicle interaction data.

[0082] In the above embodiment, by analyzing the stability of the data of the historical interaction between the first vehicle terminal and the second vehicle terminal and converting the non-stationary data into stationary data, it is possible to ensure that the data input to the model meets the requirements of the first model.

[0083] In one embodiment, before inputting the stationary data into the first prediction model and predicting the evaluation index of the vehicle interaction data, it also includes: obtaining historical data and converting the historical data into a stationary time series; processing the stationary time series according to the Chi Chi information criterion to obtain the target class and order; and estimating parameters according to the target class, order and stationary time series to obtain the first prediction model.

[0084] The target level refers to the target level used when the first prediction model is used to predict the evaluation index of vehicle interaction data in the time dimension. Historical data refers to the data that the vehicle terminal records the direct trust evaluation results of the first vehicle terminal on each second vehicle terminal in a distributed manner in the time dimension and uploads to the server periodically, wherein the direct trust evaluation is generated by the first vehicle terminal evaluating the interaction message sent by the second vehicle terminal according to the prediction rule.

[0085] Specifically, before the server inputs the stationary data into the first prediction model to predict and obtain the evaluation index of the vehicle interaction data, it needs to calculate the parameters of the first prediction model and then obtain the first prediction model. Specifically, first obtain the historical data, and convert the historical data into a stationary time series, and then process the stationary time series according to the Akaike information criterion to obtain the target hierarchy and order. In other embodiments, the target hierarchy p and order q are obtained by using the Akaike information criterion (AIC) order determination method. The AIC criterion order determination method is as follows:

[0086] AIC = nlogδ 2 +2(p+q+2)

[0087] Among them, n is the number of samples of the stationary sequence, δ 2 is the sum of squares of the fitting residuals. The AIC criterion order determination method is transformed into solving the following problem:

[0088] AIC(p,q)=min k,l AIC(k,l)…0≤k≤M,0≤l≤N

[0089] Among them, M and N are the upper limits of the ARIMA model order, which are generally taken as or In practical applications, p and q do not exceed 2; k and l are parameters to be determined.

[0090] Specifically, after determining the target hierarchy and order of the first prediction model, the parameters in the first prediction model are determined. The first prediction model can be obtained according to the target hierarchy, order and parameters. In other embodiments, after determining the order of the model, the constrained least squares method is used to estimate the parameters in the ARIMA model. Let the direct trust sequence be represented by X t :

[0091]

[0092] Among them, ε t is a mean of 0 and a variance of is a stationary white noise, θ j Assume that X is the parameter to be determined. t Reversible, with:

[0093]

[0094] Among them, I j is the j-th trust sequence.

[0095] The above model sequence can be transformed into the following form:

[0096]

[0097]

[0098] Among them, B i is the delay operator.

[0099] According to the above formula, we can get the operator identity:

[0100]

[0101] Comparing the same power of B on both sides of the equation, we can get:

[0102]

[0103]

[0104]

[0105] …

[0106]

[0107] When j>q, let θj =0,i>p, Rewrite the above formula as:

[0108]

[0109]

[0110]

[0111] …

[0112]

[0113] I j It can be obtained from the above formula that the conditional least squares estimation method minimizes the following residual sum of squares:

[0114]

[0115] It stipulates that: when t≤0, X t = 0. Since I j yes and θ, so the residual sum of squares is also and θ, that is:

[0116]

[0117] Minimizing the above equation requires the use of nonlinear least squares methods, which can be used to find and So that:

[0118]

[0119] and become The conditional least square method of and θ is used to obtain the parameters of the ARIMA prediction model. The obtained parameters are used to predict the direct trust of the time series, and finally the direct trust of the first vehicle terminal to the second vehicle terminal during the vehicle interaction is obtained.

[0120] In the above embodiment, the target hierarchy, order and parameters of the first prediction model can be obtained by processing the historical data, and then the first prediction model can be obtained.

[0121] In one embodiment, the evaluation index of vehicle interaction data is predicted by the second prediction model, including: obtaining a first feature matrix through a vehicle social network; inputting the first feature matrix into a third prediction model to obtain the features of each vehicle terminal; concatenating the features of any two vehicle terminals that interact to obtain a second feature matrix, and inputting the second feature matrix into the second prediction model to obtain the evaluation index of vehicle interaction data between any two vehicle terminals.

[0122] The first feature matrix is ​​a matrix obtained according to the vehicle social network, which may be an adjacency matrix; the second feature matrix is ​​a matrix obtained by inputting the first matrix into the third prediction model to obtain the features of each vehicle terminal and then performing feature concatenation; the third prediction model is a first deep learning model that is pre-trained to obtain the features of the vehicle terminal, for example, a graph neural network, etc.;

[0123] Specifically, firstly, a first feature matrix is ​​obtained through the vehicle social network, and then the first feature matrix is ​​input into the third model, and the features of each vehicle terminal can be obtained through the third model, and then the features of any two vehicle terminals that have interaction are spliced ​​to obtain a second feature matrix, and finally the second feature matrix is ​​input into the third prediction model to obtain the evaluation index of the vehicle interaction data between any two vehicle terminals. In other embodiments, the information interaction between nodes in the vehicle social network is realized through a pre-trained graph neural network model (a node in the vehicle social network refers to any vehicle terminal), so as to model the spatial dependency relationship between sites, and the calculation formula is as follows:

[0124]

[0125] in, A represents the adjacency matrix of the vehicle social network. In this embodiment, edge weights are considered when calculating the adjacency matrix. I is the unit matrix. Normalize the matrix; H (l) represents the node signal of the layer of the graph convolution neural network, H (0) That is, the input of the neural network; W (l) is the parameter of the lth layer, and the parameter of W is learned by back propagation during the training process of the neural network; φ is the activation function, and the Relu activation function is selected in this embodiment. After the neural network training is completed, the neural network can be used to calculate the features between any two vehicle terminals. Then the features of any two vehicle terminals that have interaction are spliced ​​and input into the MLP to complete the indirect trust prediction.

[0126] In the above embodiment, the indirect trust prediction between any two vehicle terminals in the vehicle social network can be obtained by calculating the vehicle social network.

[0127] In one embodiment, before determining the temporal dependency and / or spatial dependency between the first vehicle terminal and the second vehicle terminal based on the first vehicle identification and the second vehicle identification, it also includes: obtaining historical data during the interaction between the first vehicle and the second vehicle; filling the missing values ​​of the historical data using an interpolation method; and generating a vehicle social network based on the filled historical data.

[0128] Specifically, before determining the temporal dependency between the first vehicle terminal and the second vehicle terminal and / or the spatial dependency based on the vehicle social network, the server needs to obtain historical data during the interaction between the first vehicle terminal and the second vehicle terminal. Optionally, when the first vehicle terminal does not respond to the vehicle interaction data evaluation request issued by the second vehicle terminal to determine whether it is credible or there is a storage error in the server, the historical data will be missing. In this case, the server will use interpolation to fill in the corresponding missing values. Optionally, linear interpolation can be used to fill in the missing values. The linear interpolation method assumes that a continuous sequence containing missing values ​​satisfies a linear change relationship, and a linear function is used to fit the data change. The calculation formula of the linear interpolation method is as follows:

[0129]

[0130] in, is the direct trust from i to j at the tth time, and the corresponding They are the direct trust from i to j at the t-1 and t+1 times respectively.

[0131] Specifically, generating a vehicle social network based on historical data and filled historical data means that the server constructs a global social network based on historical data and filled missing values, combining Figure 3 As shown, the nodes in the global social network represent vehicle terminals, the directed edges represent the interactions between vehicle terminals, and the weights on the directed edges represent the latest direct trust between vehicle terminals. When the server determines that there is an interaction between the first vehicle terminal and the second vehicle terminal based on historical data, it generates a directed edge from the first vehicle terminal to the second vehicle terminal, and uses the latest direct trust between the first vehicle terminal and the second vehicle terminal as the weight of the directed edge. In one embodiment, the vehicle social network constructed by the trust evaluation system is represented by G(N,E), where N represents the set of all vehicle nodes participating in information interaction, E represents the set of edges between nodes, and the edge e∈E between node i and node j is represented by a triple e(i,j,w ij ).

[0132] In the above embodiment, a vehicle social network is generated by filling the historical data, and the dependency relationship between vehicle terminals and the prediction of evaluation indicators for subsequent vehicle interaction data between vehicle terminals with spatial dependencies can be determined based on the vehicle social network.

[0133] In one embodiment, Figure 4 As shown, a vehicle interaction data processing method applied to a first vehicle terminal is provided, comprising the following steps:

[0134] S402: receiving an interaction request, where the interaction request carries a second vehicle identifier.

[0135] Among them, the interaction request refers to the vehicle interaction data evaluation request sent by the second vehicle terminal to the first vehicle terminal, which may be information about traffic congestion, road construction, accidents / collisions, road conditions and weather alerts sent by the second terminal to the first vehicle terminal, wherein the interaction request carries information that can represent the vehicle identity.

[0136] Specifically, the first vehicle terminal receives an interaction request sent by the second vehicle terminal and the interaction request carries a second vehicle identification, and then generates a vehicle interaction data evaluation request based on the interaction request and the second vehicle identification and sends it to the server. The server generates an evaluation index of the vehicle interaction data for the vehicle interaction data evaluation request and returns it, and then the first vehicle terminal performs data interaction based on the evaluation index of the vehicle interaction data.

[0137] S404: The first vehicle terminal generates a vehicle interaction data evaluation request, and sends the vehicle interaction data evaluation request to the server.

[0138] Specifically, the first vehicle terminal generates a vehicle interaction data evaluation request based on the interaction request sent by the second vehicle terminal and the second vehicle identifier carried in the interaction request, and sends the vehicle interaction data evaluation request to the server, which processes the vehicle interaction data evaluation request and generates corresponding vehicle interaction data evaluation indicators.

[0139] S406: Receive evaluation indicators of vehicle interaction data generated by the server based on the vehicle interaction data processing method in any one of the above implementations.

[0140] Specifically, after receiving the vehicle interaction data evaluation request, the server first determines the dependency relationship between the second vehicle terminal and the first vehicle terminal. If the first vehicle terminal and the second vehicle terminal have a temporal dependency, the first prediction model is used to predict the evaluation index of the vehicle interaction data; if the first vehicle terminal and the second vehicle terminal have a spatial dependency, the second prediction model is used to predict the evaluation index of the vehicle interaction data, and then the evaluation index of the vehicle interaction data is returned to the first vehicle terminal.

[0141] S408: Performing data interaction with the second vehicle terminal according to the evaluation index of the vehicle interaction data.

[0142] Specifically, after receiving the evaluation index of vehicle interaction data sent by the server, the first vehicle terminal interacts with the second vehicle terminal based on the evaluation index of the vehicle interaction data. For example, if the evaluation index of the vehicle interaction data is to perform a trust evaluation on the interaction request of the second vehicle terminal, then after receiving the evaluation index of vehicle interaction data regarding vehicle trust sent by the server, the first vehicle terminal chooses to trust or not trust the interaction request issued by the second vehicle terminal based on the evaluation index of the vehicle interaction data regarding vehicle trust.

[0143] In the above embodiment, by evaluating the interaction request sent by the second vehicle terminal through the first prediction model and / or the second prediction model, the first vehicle terminal can quickly judge the vehicle interaction data evaluation request sent by the second vehicle terminal, and then make adjustments to the real-time road traffic information, route, whether to travel, etc.

[0144] In one embodiment, the method for processing vehicle interaction data in a vehicle social network further includes: generating a direct trust evaluation with a second vehicle terminal with a preset probability; and periodically uploading the direct trust evaluation as vehicle history data to a server.

[0145] Among them, direct trust evaluation refers to the calculation performed by the first vehicle terminal according to preset rules after receiving the vehicle interaction data evaluation request sent by the second vehicle terminal.

[0146] Specifically, the first vehicle terminal generates a direct trust evaluation with the second vehicle terminal with a preset probability, wherein the preset probability can be optionally set according to the actual usage scenario; in one embodiment, the first vehicle terminal can generate a direct trust evaluation between the current node and the second vehicle terminal based on the direct trust evaluation between the previous node and the second vehicle terminal and the determination factor. The generated direct trust evaluation is then uploaded to the server regularly as vehicle historical data, and the server further processes the historical data.

[0147] In the above embodiment, the first vehicle terminal generates a direct trust evaluation with the second vehicle terminal with a preset probability and regularly uploads the direct trust evaluation as vehicle historical data to the server, so that the server processes the historical data to obtain evaluation indicators of the vehicle interaction data between the first vehicle terminal and the second vehicle terminal.

[0148] In one embodiment, generating a direct trust evaluation with a second vehicle terminal with a preset probability includes: receiving an interaction request sent by the second vehicle terminal with a preset probability; generating a direct trust evaluation between the current node and the second vehicle terminal based on the direct trust evaluation between the previous node and the second vehicle terminal and a determination factor.

[0149] Specifically, the first vehicle terminal receives the vehicle interaction data evaluation request from the second vehicle terminal with a preset probability, wherein the preset probability is preferably 50%, because the first vehicle terminal may or may not receive the vehicle interaction data evaluation request sent by the second vehicle terminal during driving. At the same time, the first vehicle terminal generates a direct trust evaluation between the current node and the second vehicle terminal based on the direct trust evaluation between the previous node and the second vehicle terminal and the determination factor. In one embodiment, each vehicle terminal of the vehicle social network initialization node receives the message from the second vehicle terminal with a probability of 50%. At the same time, the first vehicle terminal performs a simple direct trust evaluation on the second vehicle terminal based on the message quality of the message sent by the second vehicle terminal. The evaluation method is as follows:

[0150]

[0151] The first vehicle terminal is represented by i, the second vehicle terminal is represented by j, is the direct trust from i to j for the tth time, its initial value is 0.5, α is the determination factor, when the vehicle interaction data evaluation request of the second vehicle terminal is verified to be credible by the message of the first vehicle terminal, α=1, otherwise α=-1.

[0152] In the above embodiment, the first vehicle terminal can generate a direct trust evaluation between the current node and the second vehicle terminal through the direct trust evaluation between the previous node and the second vehicle terminal and the determination factor, so that the server can predict the evaluation index of the vehicle interaction data based on the direct trust evaluation.

[0153] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0154] Based on the same inventive concept, the embodiment of the present application also provides a vehicle interaction data processing device for implementing the vehicle interaction data processing method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more vehicle interaction data processing device embodiments provided below can refer to the limitations of the vehicle interaction data processing method above, and will not be repeated here.

[0155] In one embodiment, Figure 5 As shown, a vehicle interaction data processing device applied to a server is provided, comprising: a receiving module 100, a judging module 200 and an evaluating module 300, wherein:

[0156] The receiving module 100 is used to receive a vehicle interaction data evaluation request sent by the first vehicle terminal, where the vehicle interaction data evaluation request carries a first vehicle identifier and a second vehicle identifier.

[0157] The judgment module 200 is used to determine the temporal dependency relationship between the first vehicle terminal and the second vehicle terminal and / or the spatial dependency relationship based on the vehicle social network according to the first vehicle identification and the second vehicle identification.

[0158] The evaluation module 300 is used to calculate the evaluation index of the vehicle interaction data according to the determined dependency relationship.

[0159] In one embodiment, the determination module 200 further includes:

[0160] The time dependency judgment unit is used to determine whether the first vehicle terminal and the second vehicle terminal have a time dependency relationship when there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension.

[0161] The spatial dependency judgment unit is used to obtain the spatial dependency between the first vehicle terminal and the second vehicle terminal based on the vehicle social network when there is no historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension.

[0162] In one embodiment, the evaluation module 300 further includes:

[0163] The first evaluation index calculation unit is used to predict the evaluation index of the vehicle interaction data through the first prediction model when there is a time dependency relationship between the first vehicle and the second vehicle.

[0164] The second evaluation index calculation unit is used to predict the evaluation index of the vehicle interaction data through the second prediction model when there is a spatial dependency relationship between the first vehicle and the second vehicle.

[0165] In one embodiment, the first evaluation index calculation unit further includes:

[0166] The data stability analysis subunit is used to analyze the data stability of the historical interaction between the first vehicle terminal and the second vehicle terminal.

[0167] The data stationarity conversion subunit is used to convert the non-stationary data into stationary data when the historical interaction data between the first vehicle terminal and the second vehicle terminal is determined to be non-stationary data.

[0168] The first evaluation index prediction subunit is used to input the stable data into the first prediction model to predict the evaluation index of the vehicle interaction data.

[0169] In one embodiment, the first evaluation index calculation unit further includes:

[0170] The data acquisition subunit is used to acquire historical data and convert the historical data into a stationary time series.

[0171] The parameter calculation subunit is used to process the stationary time series according to the red and late information criterion to obtain the target hierarchy and order.

[0172] The model acquisition unit is used to perform parameter estimation according to the target hierarchy, order and stationary time series to obtain a first prediction model.

[0173] In one embodiment, the second evaluation index calculation unit further includes:

[0174] The feature acquisition subunit is used to obtain a first feature matrix through the vehicle social network; and input the first feature matrix into the third prediction model to obtain the features of each vehicle terminal.

[0175] The second evaluation index prediction subunit is used to splice the features of any two vehicle terminals that interact to obtain a second feature matrix, input the second feature matrix into the second prediction model, and obtain the evaluation index of the vehicle interaction data between any two vehicle terminals.

[0176] In one embodiment, the vehicle interaction data processing device further includes:

[0177] The historical data acquisition module is used to acquire historical data during the interaction between the first vehicle and the second vehicle.

[0178] The data filling module is used to fill the missing values ​​of historical data using interpolation method.

[0179] The vehicle social network generation module is used to generate a vehicle social network based on the filled historical data.

[0180] In one embodiment, Figure 6 As shown, a vehicle interaction data processing device applied to a vehicle terminal is provided, comprising: a request receiving module 400, an evaluation request sending module 500, an evaluation module 600 and a data interaction module 700, wherein:

[0181] The request receiving module 400 is used to receive an interaction request, where the interaction request carries a second vehicle identifier.

[0182] The evaluation request sending module 500 is used for the first vehicle terminal to generate a vehicle interaction data evaluation request and send the vehicle interaction data evaluation request to the server.

[0183] The evaluation module 600 is used to receive evaluation indicators of vehicle interaction data generated by the server based on the vehicle interaction data processing method in any one of the above embodiments.

[0184] The data interaction module 700 is used to perform data interaction with the second vehicle terminal according to the evaluation index of the vehicle interaction data.

[0185] In one embodiment, the vehicle interaction data processing device applied to the vehicle terminal further includes:

[0186] A direct trust assessment generation module is used to generate a direct trust assessment with a second vehicle terminal with a preset probability.

[0187] Direct trust evaluation upload module: used to upload direct trust evaluation as vehicle history data to the server periodically.

[0188] In one embodiment, the direct trust assessment generation module includes:

[0189] The interaction request receiving unit is used to receive the interaction request sent by the second vehicle terminal with a preset probability. The trust evaluation generating unit is used to generate a direct trust evaluation between the current node and the second vehicle terminal according to the direct trust evaluation between the previous node and the second vehicle terminal and the determination factor.

[0190] Each module in the above-mentioned vehicle interaction data processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0191] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store vehicle interaction data evaluation request data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle interaction data processing method is implemented.

[0192] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0193] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0194] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0195] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0196] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0197] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0198] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle interaction data processing method, characterized in that: Applied to a server, the vehicle interaction data processing method includes: Receiving a vehicle interaction data evaluation request sent by a first vehicle terminal, wherein the vehicle interaction data evaluation request carries a first vehicle identifier and a second vehicle identifier; In the case where there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, determining that there is a temporal dependency relationship between the first vehicle terminal and the second vehicle terminal; in the case where there is no historical interaction between the first vehicle terminal and the second vehicle terminal in the time dimension, acquiring a spatial dependency relationship between the first vehicle terminal and the second vehicle terminal based on the vehicle social network; According to the determined dependency relationship, the evaluation index of the vehicle interaction data is calculated.

2. The vehicle interaction data processing method according to claim 1, characterized in that: The step of calculating the evaluation index of the vehicle interaction data according to the determined dependency relationship includes: In the case where there is a temporal dependency between the first vehicle and the second vehicle, obtaining an evaluation index of the vehicle interaction data by predicting using a first prediction model; In the case where there is a spatial dependency relationship between the first vehicle and the second vehicle, an evaluation index of the vehicle interaction data is predicted by a second prediction model.

3. The vehicle interaction data processing method according to claim 2, characterized in that: The evaluation index of the vehicle interaction data predicted by the first prediction model includes: Analyzing the stability of historical interaction data between the first vehicle terminal and the second vehicle terminal; In the case where the data of the historical interaction between the first vehicle terminal and the second vehicle terminal is determined to be non-stationary data, converting the non-stationary data into stationary data; The stable data is input into the first prediction model to predict the evaluation index of the vehicle interaction data.

4. The vehicle interaction data processing method according to claim 3, characterized in that: Before inputting the stationary data into the first prediction model to predict the evaluation index of the vehicle interaction data, the method further includes: Acquire historical data and convert the historical data into a stationary time series; Processing the stationary time series according to the Chichi Information Criterion to obtain the target hierarchy and order; Parameter estimation is performed according to the target class, order and the stationary time series to obtain the first prediction model.

5. The vehicle interaction data processing method according to claim 2, characterized in that: The evaluation index of the vehicle interaction data predicted by the second prediction model includes: Obtain a first feature matrix through the vehicle social network; input the first feature matrix into a third prediction model to obtain features of each vehicle terminal; The features of any two of the vehicle terminals that interact are concatenated to obtain a second feature matrix, and the second feature matrix is ​​input into a second prediction model to obtain an evaluation index of the vehicle interaction data between the any two vehicle terminals.

6. The vehicle interaction data processing method according to claim 1, characterized in that: Before determining the temporal dependency relationship between the first vehicle terminal and the second vehicle terminal and / or the spatial dependency relationship based on the vehicle social network according to the first vehicle identifier and the second vehicle identifier, the method further includes: Acquire historical data during the interaction between the first vehicle and the second vehicle; Filling missing values ​​of the historical data using an interpolation method; The vehicle social network is generated according to the filled historical data.

7. A method for processing vehicle interaction data in a vehicle social network, characterized in that: Applied to a first vehicle terminal, the vehicle interaction data processing method in the vehicle social network includes: receiving an interaction request, wherein the interaction request carries a second vehicle identifier; The first vehicle terminal generates a vehicle interaction data evaluation request, and sends the vehicle interaction data evaluation request to the server; Receiving evaluation indicators of vehicle interaction data generated by the server based on the vehicle interaction data processing method according to any one of claims 1 to 6; Data is exchanged with the second vehicle terminal according to the evaluation index of the vehicle interaction data.

8. The vehicle interaction data processing method according to claim 7, characterized in that: The vehicle interaction data processing method in the vehicle social network also includes: generating a direct trust assessment with the second vehicle terminal with a preset probability; The direct trust evaluation is periodically uploaded to a server as vehicle history data.

9. The vehicle interaction data processing method according to claim 8, characterized in that: Generating a direct trust assessment with the second vehicle terminal with a preset probability includes: receiving the interaction request sent by the second vehicle terminal with a preset probability; A direct trust evaluation between the current node and the second vehicle terminal is generated according to the direct trust evaluation between the previous node and the second vehicle terminal and a determination factor.

10. A vehicle interaction data processing device, characterized in that: The device comprises: A receiving module, configured to receive a vehicle interaction data evaluation request sent by a first vehicle terminal, wherein the vehicle interaction data evaluation request carries a first vehicle identifier and a second vehicle identifier; a judgment module, configured to determine whether the first vehicle terminal and the second vehicle terminal have a temporal dependency relationship when there is a historical interaction between the first vehicle terminal and the second vehicle terminal in the temporal dimension; and to obtain a spatial dependency relationship between the first vehicle terminal and the second vehicle terminal based on the vehicle social network when there is no historical interaction between the first vehicle terminal and the second vehicle terminal in the temporal dimension; An evaluation module is used to calculate an evaluation index of vehicle interaction data based on a dependency relationship between the first vehicle terminal and the second vehicle terminal in time and / or space based on a vehicle social network.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images