Vehicle remote monitoring method and system

Abstract

The present invention discloses a vehicle remote monitoring method and system, which relates to the field of vehicle network communication and data transmission optimization. It includes feature extraction of the first input data collected by the vehicle, and based on the correlation and sensitivity of the first input data, constructing a dynamic mapping relationship of the first processing data; hierarchical scheduling and transmission path selection of different transmission layer data according to the dynamic mapping relationship and the network status of the vehicle's environment; constructing a dynamic topology network based on the connection matrix and transmission layer data between vehicles, and synthesizing data at a target node with a stable connection; after the data is synthesized, the target node receives it and detects the receiving result. The present invention constructs a dynamic topology network based on the connection matrix and transmission layer information between vehicles, and uses asynchronous collaborative transmission to send and synthesize data in batches, which effectively improves the real-time, reliability and bandwidth utilization of data transmission.

Description

Technical Field

[0001] The present invention relates to the field of vehicle networking communication and data transmission optimization, and in particular to a vehicle remote monitoring method and system. Background Art

[0002] In recent years, with the rapid development of intelligent connected vehicles and autonomous driving technologies, vehicle remote monitoring has become an important research direction in the field of Internet of Vehicles (IoV). Vehicle remote monitoring provides strong support for traffic safety, intelligent scheduling and in-vehicle information services through real-time collection and transmission of multi-dimensional data such as vehicle status, driving environment and driving behavior.

[0003] At present, vehicle remote monitoring systems mainly rely on cellular networks (such as 4G, 5G) and vehicle networking communication technologies (such as V2V, V2I, V2X) to achieve information exchange between vehicles and cloud platforms, roadside equipment and other vehicles. Traditional vehicle remote monitoring methods usually adopt a strategy of timed collection and periodic transmission, and directly upload the collected vehicle status data to the cloud for unified processing and analysis.

[0004] However, with the increasing number and types of vehicle sensors, the dimensions of collected data are becoming increasingly complex, and the amount of data is growing explosively. The traditional periodic upload method can no longer meet the requirements of real-time and reliability. In addition, during vehicle driving, the network status will be affected by multiple factors such as geographical location, environmental occlusion, and communication interference, and there is a large volatility. Summary of the invention

[0005] In view of the problems of inflexible data transmission scheduling and poor adaptability to network fluctuations in the existing data transmission, a vehicle remote monitoring method and system are proposed in the present invention.

[0006] Therefore, the problem to be solved by the present invention is how to build an efficient hierarchical scheduling strategy based on data characteristics and network status, and improve transmission reliability and bandwidth utilization through dynamic topology and asynchronous collaborative transmission technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a vehicle remote monitoring method, comprising: extracting features from first input data collected from a vehicle, and constructing a dynamic mapping relationship for first processing data based on the relevance and sensitivity of the first input data; performing hierarchical scheduling and transmission path selection for data of different transmission layers according to the dynamic mapping relationship and the network status of the vehicle's environment; in a scenario where network coverage is insufficient, constructing a dynamic topology network based on a connection matrix between vehicles and transmission layer data, sending data of different transmission layers in batches, and synthesizing data at a target node with a stable connection; after the data is synthesized, the target node receives the data and detects the reception result.

[0009] As a preferred solution of the vehicle remote monitoring method described in the present invention, wherein: the dynamic mapping relationship of constructing the first processed data includes: prioritizing the transmission data according to the spatial dependency relationship; mapping the first input data to different transmission layers according to the priority, including a fast transmission layer, a periodic transmission layer and a low-frequency storage layer; the first processed data includes the data of each transmission layer allocated according to the dynamic mapping relationship.

[0010] As a preferred solution of the vehicle remote monitoring method of the present invention, the determination of the spatial dependency relationship includes the following steps: calculating the grey correlation degree between the data:

[0011]

[0012] in, For the Class data and The relevance of class data; and There are two types of data in time The value of is the adjustment coefficient, is the observation window size; calculate the spatial correlation weight:

[0013]

[0014] in, is the number of data categories; the higher the correlation, the stronger the spatial dependency.

[0015] As a preferred solution of the vehicle remote monitoring method described in the present invention, the hierarchical scheduling and transmission path selection of data in different transmission layers include: when a first network state is detected, the first processed data is transmitted using a parallel transmission method of a main link and an auxiliary link; wherein the main link uses a cellular network to transmit the data of the fast transmission layer, and the auxiliary link uses V2V / V2X communication to share the data of the periodic transmission layer; when a second network state is detected, switching to an adaptive compensation mode to optimize the transmission of the first processed data.

[0016] As a preferred solution of the vehicle remote monitoring method of the present invention, the calculation of the vehicle connection matrix is ​​as follows: define the vehicle connection matrix , whose elements are calculated as:

[0017]

[0018] in, For vehicles and The plane distance, is the benchmark distance parameter, corresponding to the typical interaction distance of the urban road network. is the distance attenuation index, obtained through actual vehicle test optimization. is the velocity direction vector, is the vehicle heading angle, For vehicles The instantaneous velocity modulus, is the density correction term, is the local density, is the density gain coefficient, when Above a critical density, positive correlations enhance associations.

[0019] As a preferred solution of the vehicle remote monitoring method described in the present invention, the construction of a dynamic topology network includes: based on the calculated connection matrix, selecting vehicles with connectivity and stability higher than a threshold as core nodes, responsible for topology management and data coordination; if a vehicle has connectivity with multiple adjacent vehicles higher than a threshold and is driving stably, it is set as a backbone node; if the vehicle has good transmission capability, it is given priority as a master node; if the vehicle is still within the coverage of the cellular network, the topology is mainly based on the cellular network, and V2V communication is used as a supplement; if the cellular signal is weak or unavailable, a V2V / V2X self-organizing network will be used between vehicles to form a grid topology structure; some vehicles remain connected to the cellular network, acting as gateway nodes to achieve integrated communication between cellular and V2V networks.

[0020] As a preferred solution of the vehicle remote monitoring method described in the present invention, the detection of the receiving result includes: detecting whether data is lost. If the data loss exceeds a set threshold, a data backtracking mechanism is triggered to request retransmission from the vehicle that last stored complete data.

[0021] In a second aspect, the present invention provides a vehicle remote monitoring system, which comprises:

[0022] A feature extraction and dynamic mapping module is used to extract features from the first input data collected by the vehicle, and to construct a dynamic mapping relationship for the first processed data based on the correlation and sensitivity of the first input data; a hierarchical scheduling and path selection module is used to perform hierarchical scheduling and transmission path selection for data of different transmission layers according to the dynamic mapping relationship and the network status of the vehicle's environment; a dynamic topology construction module is used to construct a dynamic topology network based on the connection matrix and transmission layer data between vehicles in a scenario with insufficient network coverage, send data of different transmission layers in batches, and synthesize data at a target node with a stable connection; a data reception and result detection module is used for receiving the data at the target node after the data is synthesized, and to detect the reception result.

[0023] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the vehicle remote monitoring method as described in the first aspect of the present invention are implemented.

[0024] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the vehicle remote monitoring method as described in the first aspect of the present invention are implemented.

[0025] The beneficial effects of the present invention are as follows: the present invention realizes hierarchical scheduling and adaptive transmission path selection of data in different transmission layers by extracting features of the first input data collected by the vehicle and constructing a dynamic mapping relationship based on the correlation and sensitivity of the data; at the same time, in the scenario of insufficient network coverage, a dynamic topology network is constructed based on the connection matrix and transmission layer information between vehicles, and an asynchronous collaborative transmission method is adopted to send and synthesize data in batches, thereby effectively improving the real-time, reliability and bandwidth utilization of data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 The diagram is a schematic diagram of the operation of the vehicle remote monitoring method.

[0028] Figure 2 A schematic diagram of the process of hierarchical scheduling and transmission path selection for data in different transmission layers.

[0029] Figure 3 This is the structural diagram of the vehicle remote monitoring system. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0032] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0033] Example 1

[0034] Reference Figure 1~Figure 3 , which is the first embodiment of the present invention, and provides a vehicle remote monitoring method, such as Figure 1 As shown, the following steps are included:

[0035] S1: extracting features from first input data collected from the vehicle, and constructing a dynamic mapping relationship for first processed data based on the relevance and sensitivity of the first input data.

[0036] In one embodiment of the present application, extracting features from first input data collected from the vehicle includes:

[0037] The first input data is preprocessed to obtain first cleaned data, and feature extraction is performed to obtain first feature data.

[0038] It should be noted that the first input data includes vehicle operating status data, environmental perception data, driver behavior data, etc.

[0039] Data preprocessing includes outlier filtering and noise removal.

[0040] For example, when the first input data includes tire pressure data, if the fluctuation exceeds ±10% in a short period of time and there is no drastic change in ambient temperature, the data is considered abnormal and is eliminated after outlier filtering; for acceleration data, Kalman filtering is used to eliminate high-frequency jitter caused by road bumps to obtain a smooth acceleration curve.

[0041] Preferably, the first characteristic data includes time sensitivity and spatial correlation.

[0042] S1.1: Calculate sensitivity weights based on the extracted features, obtain a sensitivity matrix, and determine dynamic sensitivity.

[0043] Preferably, the calculation of the sensitivity matrix includes:

[0044] Based on the improved entropy method, the time sensitivity weight is calculated; based on the correlation analysis model, the spatial correlation weight is calculated; and the time sensitivity weight and the spatial correlation weight are normalized to obtain the sensitivity matrix.

[0045] Specifically, the calculation process of the time sensitivity weight includes:

[0046] First, calculate the time volatility (rate of data change):

[0047]

[0048] in, For the The volatility of class data in time 𝑇, For the Class data in time The numerical value of is the observation window size.

[0049] Calculating entropy :

[0050]

[0051] in, is the normalization coefficient, is the normalized time volatility, is the number of data categories.

[0052] Calculate the time sensitivity weight:

[0053]

[0054] Among them, the entropy value The larger the value, the smaller the data fluctuation (higher stability), the lower the time sensitivity and the smaller the weight. Conversely, data with large fluctuations (such as emergency failure data) has higher sensitivity and a larger weight.

[0055] The calculation process of spatial association weight includes:

[0056] Calculate the grey correlation between data:

[0057]

[0058] in, For the Class data and The relevance of class data; and There are two types of data in time The value of is the adjustment coefficient, is the observation window size.

[0059] Calculate spatial association weights:

[0060]

[0061] It should be noted that the higher the correlation, the stronger the spatial dependence of data between different sensors, while data with low spatial correlation (such as independently measured data) have a lower weight.

[0062] S1.2: Prioritize the transmission nodes, and construct a dynamic mapping relationship for the first processed data based on the dynamic sensitivity and priority ranking.

[0063] The transmission data can be prioritized according to the spatial dependencies.

[0064] It should be noted that data with higher dynamic sensitivity and strong spatial correlation (such as emergency fault alarms and real-time video streams) will be given higher priority; data with lower spatial correlation but higher time sensitivity (such as independent sensor data) will be given a medium priority; data with both lower dynamic sensitivity and spatial correlation (such as historical records) will be given the lowest priority.

[0065] Preferably, the dynamic mapping relationship includes:

[0066] The dynamic mapping relationship maps the first input data to different transmission layers according to priorities, including a fast transmission layer, a periodic transmission layer and a low-frequency storage layer.

[0067] It should be noted that the fast transmission layer is used to transmit data with high dynamic sensitivity and high spatial correlation, the periodic transmission layer is used to transmit data with medium dynamic sensitivity, and the low-frequency storage layer is used for redundant data with low dynamic sensitivity, so as to reduce network congestion during transmission.

[0068] Exemplarily, emergency fault alarm data is mapped to a fast transmission layer to ensure minimum delay; tire pressure data is mapped to a periodic transmission layer to reduce transmission frequency; and video recording data is mapped to a low-frequency storage layer to reduce network congestion.

[0069] The first processed data includes data of each transport layer allocated according to a dynamic mapping relationship.

[0070] Optionally, based on real-time changes in the first input data, the dynamic mapping relationship is periodically updated, and adaptively adjusted when the correlation or sensitivity fluctuates, so as to dynamically adapt to the network status.

[0071] S2: Perform hierarchical scheduling and transmission path selection for data at different transmission layers according to the dynamic mapping relationship and the network status of the vehicle's environment.

[0072] like Figure 2 As shown, hierarchical scheduling and transmission path selection for data in different transmission layers include:

[0073] S2.1: When a first network state is detected, the first processed data is transmitted using a parallel transmission method of a main link and an auxiliary link.

[0074] The main link uses a cellular network to transmit the data of the fast transmission layer, and the auxiliary link uses V2V / V2X communication to share the data of the periodic transmission layer.

[0075] Specifically, continuously monitor the network signal strength, stability, and bandwidth availability of the vehicle's current environment to determine whether the vehicle complies with the first network status (i.e., the cellular network is stable and V2V / V2X communication is available);

[0076] The main link transmission uses cellular networks (such as 4G / 5G) to upload data from the fast transmission layer to a remote server or cloud to ensure low-latency transmission of critical data;

[0077] Auxiliary link transmission uses V2V / V2X communication (such as DSRC, C-V2X) to share periodic transmission layer data between surrounding vehicles or roadside equipment, realize local redundant data sharing, and reduce cellular network bandwidth occupancy.

[0078] Preferably, a time synchronization algorithm is used to ensure that data transmission of the main link and the auxiliary link is completed within a suitable time window, thereby avoiding information lag problems caused by data asynchrony.

[0079] S2.2: When a second network state is detected, switch to an adaptive compensation mode to optimize transmission of the first processed data.

[0080] In an embodiment of the present application, when the second network state is detected, the operation includes:

[0081] Monitor whether the current network state enters the second network state (such as unstable cellular network signal, limited bandwidth, or unavailable V2X communication);

[0082] When a network state degradation is detected, switching to an adaptive compensation mode and optimizing the transmission of the first processed data based on a dynamic mapping relationship;

[0083] Use wavelet transform or autoencoder to compress redundant data to reduce the amount of transmitted data;

[0084] For data with strong continuity (such as environmental sensor data), a downsampling strategy is used to reduce the data update frequency and improve bandwidth utilization;

[0085] Adaptive QoS scheduling algorithm is used to ensure that critical data is transmitted first, while low-priority data is delayed or transmitted in batches.

[0086] In the scheme of the present invention, redundant data refers to the data redundancy caused by repeated measurements of sensors, small data changes, repeated information uploading, etc. during the vehicle remote monitoring data transmission process.

[0087] S2.3: Perform trend prediction based on historical data to reduce the transmission of redundant data.

[0088] Use time series analysis methods (such as ARIMA, LSTM, etc.) to model historical data and predict future data change trends;

[0089] If the change trend of the predicted data is stable, the transmission of redundant data is reduced, and real-time updates are triggered only when abnormal changes occur in the data;

[0090] If the forecast data fluctuates greatly, maintain high-frequency data updates to ensure the real-time nature of the data.

[0091] Optionally, based on the prediction model, an adaptive anomaly detection algorithm is combined to identify data anomalies. When the deviation between the transmitted data and the predicted data exceeds a set threshold, a data compensation mechanism is triggered to ensure data accuracy.

[0092] Indicatively, if data is lost or abnormal, it can be filled with historical trend data to avoid system misjudgment; when the network is restored, the time period of the abnormal data is stored, and the server is requested to compensate for the data after the network is restored.

[0093] S3: In scenarios with insufficient network coverage, a dynamic topology network is constructed based on the connection matrix and transport layer data between vehicles. Data from different transport layers are sent in batches and data is synthesized at target nodes with stable connections.

[0094] Preferably, the calculation of the vehicle connection matrix includes:

[0095] First, define the vehicle-to-vehicle connection matrix , whose elements are calculated as:

[0096]

[0097] in, For vehicles and The plane distance, is the benchmark distance parameter, corresponding to the typical interaction distance of the urban road network. is the distance attenuation index, obtained through actual vehicle test optimization. is the velocity direction vector, is the vehicle heading angle, For vehicles The instantaneous velocity modulus, is the density correction term, is the local density, is the density gain coefficient, when Above a critical density, positive correlations enhance associations.

[0098] For example, car A: (x=100m, y=200m), v=10m / s, =30°; Car B: (x=120m, y=180m), v=9m / s, =25°, local density =45 vehicles / km;

[0099] Calculated =28.28m, distance term= ;

[0100] Direction similarity: , ;

[0101] Then based on the density correction and correction coefficient, the final correlation is obtained = ; If the connection threshold is set to 0.5, a stable V2V link is established.

[0102] In an embodiment of the present application, constructing a dynamic topology network includes:

[0103] Based on the calculated connection matrix, vehicles with connectivity and stability higher than the threshold are selected as core nodes, responsible for topology management and data coordination; if a vehicle has connectivity with multiple adjacent vehicles higher than the threshold and its driving is stable, it is set as a backbone node; if the vehicle has good transmission capabilities (such as a high bandwidth of the on-board communication module), it is given priority as the main node.

[0104] Furthermore, if the vehicle is still within the coverage of the cellular network, the topology is mainly based on the cellular network, and V2V communication is used as a supplement;

[0105] If the cellular signal is weak or unavailable, the vehicles will use V2V / V2X self-organizing networks to form a mesh topology;

[0106] Some vehicles remain connected to the cellular network, acting as gateway nodes to achieve integrated communication between cellular and V2V networks.

[0107] Optionally, if a vehicle's speed changes suddenly (such as sudden acceleration or lane change), it may affect its stability with neighboring vehicles, and the topology needs to be reconstructed. If the vehicle drives out of the communication range, its node role will automatically downgrade or exit the topology.

[0108] In addition, if the quality of a V2V link decreases (e.g., signal attenuation), it will automatically switch to a better path or enable additional relay nodes;

[0109] By adopting a load balancing strategy, if the data flow of a certain node is too high, part of the data can be allocated to other paths for transmission.

[0110] Furthermore, a relay node is selected to perform asynchronous collaborative transmission.

[0111] In this embodiment, the optimal relay node is dynamically selected based on the following indicators:

[0112] For some vehicles with low correlation but still within the network coverage, they can be set as relay nodes to expand the communication range and enhance data forwarding capabilities.

[0113] Vehicles with lower relevance or weaker signal coverage act as auxiliary nodes and participate in data forwarding only when necessary.

[0114] Furthermore, asynchronous collaborative transmission includes:

[0115] If the amount of data is large, data sharding is used to split the data into multiple small blocks, which are transmitted asynchronously by different relay nodes. A data integrity check is also set to ensure that the target node can fully restore the data.

[0116] Optionally, after receiving the data transmitted in batches, the target vehicle or infrastructure (such as the roadside unit RSU) synthesizes the data according to the data index; and uses hash check (MD5 / SHA-256) to verify the data integrity to ensure that there is no loss or tampering.

[0117] It can be seen that the present invention effectively improves the stability and adaptability of V2V communication by constructing a dynamic topology network based on the connection matrix, ensures communication efficiency through reasonable topology management and role division, and combines adaptive topology adjustment with asynchronous collaborative transmission strategy to improve data transmission quality and network robustness.

[0118] S4: After the data is synthesized, the target node receives it and detects the receiving result.

[0119] When the target vehicle receives the synthesized data, it detects whether the data is lost. If the data loss exceeds the set threshold, the data backtracking mechanism is triggered and a retransmission is requested from the vehicle that last stored the complete data.

[0120] If the amount of lost data is small, an intelligent data compensation algorithm is used to reduce the remote retransmission burden and improve the stability of the remote monitoring system based on historical trends and sensor data interpolation compensation.

[0121] Figure 3 A block diagram of a vehicle remote monitoring system according to an embodiment of the present application is shown.

[0122] Reference Figure 3 As shown, a vehicle remote monitoring system according to an embodiment of the present application includes:

[0123] A feature extraction and dynamic mapping module, used to extract features from first input data collected by the vehicle, and to construct a dynamic mapping relationship of first processed data based on the relevance and sensitivity of the first input data;

[0124] A hierarchical scheduling and path selection module, used to perform hierarchical scheduling and transmission path selection for data of different transmission layers according to the dynamic mapping relationship and the network status of the vehicle environment;

[0125] The dynamic topology building module builds a dynamic topology network based on the connection matrix and transmission layer data between vehicles in scenarios with insufficient network coverage, sends data from different transmission layers in batches, and synthesizes data at target nodes with stable connections;

[0126] The data receiving and result detection module is used for receiving the data after the data is synthesized, and detecting the receiving result.

[0127] This embodiment also provides a computer device suitable for the vehicle remote monitoring method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the vehicle remote monitoring method proposed in the above embodiment.

[0128] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0129] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the vehicle remote monitoring method proposed in the above embodiment is implemented.

[0130] In summary, the present invention realizes hierarchical scheduling and adaptive transmission path selection of data in different transmission layers by extracting features from the first input data collected by the vehicle and constructing a dynamic mapping relationship based on the correlation and sensitivity of the data; at the same time, in the scenario of insufficient network coverage, a dynamic topology network is constructed based on the connection matrix and transmission layer information between vehicles, and an asynchronous collaborative transmission method is adopted to send and synthesize data in batches, thereby effectively improving the real-time, reliability and bandwidth utilization of data transmission.

[0131] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A vehicle remote monitoring method, characterized in that: include: Extracting features from first input data collected from the vehicle, and constructing a dynamic mapping relationship for first processed data based on the relevance and sensitivity of the first input data; According to the dynamic mapping relationship and the network status of the vehicle environment, hierarchical scheduling and transmission path selection are performed for data of different transmission layers; In scenarios where network coverage is insufficient, a dynamic topology network is constructed based on the connection matrix and transport layer data between vehicles, data from different transport layers are sent in batches, and data is synthesized at target nodes with stable connections. After the data is synthesized, the target node receives it and detects the receiving result; The constructing of the dynamic mapping relationship of the first processing data includes: Prioritize transmission data based on spatial dependencies; Mapping the first input data to different transmission layers according to priorities, including a fast transmission layer, a periodic transmission layer, and a low-frequency storage layer; The first processed data includes data of each transport layer allocated according to the dynamic mapping relationship; The hierarchical scheduling and transmission path selection of data in different transmission layers includes: When the first network state is detected, the first processed data is transmitted using a parallel transmission mode of a main link and an auxiliary link; The main link uses a cellular network to transmit the data of the fast transmission layer, and the auxiliary link uses V2V / V2X communication to share the data of the periodic transmission layer; When the second network state is detected, the adaptive compensation mode is switched to optimize the transmission of the first processed data; the connection matrix between the vehicles is calculated as: Define the inter-vehicle connectivity matrix , whose elements are calculated as: in, For vehicles and The plane distance, is the benchmark distance parameter, corresponding to the typical interaction distance of the urban road network. is the distance attenuation index, obtained through actual vehicle test optimization. is the velocity direction vector, is the vehicle heading angle, For vehicles The instantaneous velocity modulus, is the density correction term, is the local density, is the density gain coefficient, when Above a critical density, positive correlations enhance associations.

2. The vehicle remote monitoring method according to claim 1, characterized in that: The determination of the spatial dependency relationship comprises the following steps: Calculate the grey correlation between data: in, For the Class data and The relevance of class data; and There are two types of data in time The value of is the adjustment coefficient, is the observation window size; Calculate spatial association weights: in, is the number of data categories; The higher the correlation degree is, the stronger the spatial dependency is.

3. The vehicle remote monitoring method according to claim 2, characterized in that: The construction of a dynamic topology network includes: Based on the calculated connection matrix, vehicles with connectivity and stability above the threshold are selected as core nodes to be responsible for topology management and data coordination. If a vehicle’s connectivity with multiple adjacent vehicles is higher than the threshold and its driving is stable, it will be set as a backbone node; If the vehicle has good transmission capabilities, it will be given priority as the master node; If the vehicle is still within the coverage of the cellular network, the topology is mainly based on the cellular network, and V2V communication is supplemented; If the cellular signal is weak or unavailable, the vehicles will use V2V / V2X self-organizing networks to form a mesh topology; Some vehicles remain connected to the cellular network, acting as gateway nodes to achieve integrated communication between cellular and V2V networks.

4. The vehicle remote monitoring method according to claim 3, characterized in that: The detecting of the receiving result comprises: The system detects whether data is lost. If the data loss exceeds the set threshold, the data backtracking mechanism is triggered to request retransmission from the vehicle that last stored complete data.

5. A vehicle remote monitoring system, based on the vehicle remote monitoring method according to any one of claims 1 to 4, characterized in that: Also includes: A feature extraction and dynamic mapping module, used to extract features from first input data collected by the vehicle, and to construct a dynamic mapping relationship of first processed data based on the relevance and sensitivity of the first input data; A hierarchical scheduling and path selection module, used to perform hierarchical scheduling and transmission path selection for data of different transmission layers according to the dynamic mapping relationship and the network status of the vehicle environment; The dynamic topology building module builds a dynamic topology network based on the connection matrix and transmission layer data between vehicles in scenarios with insufficient network coverage, sends data from different transmission layers in batches, and synthesizes data at target nodes with stable connections; The data receiving and result detection module is used for receiving the data after the data is synthesized, and detecting the receiving result.

6. 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 vehicle remote monitoring method described in any one of claims 1 to 4 are implemented.

7. 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 vehicle remote monitoring method according to any one of claims 1 to 4 are implemented.

Images