Network self-recovery method, device, equipment, medium and product

Abstract

The invention discloses a network self-recovery method, device and equipment, a medium and a product. The method comprises the following steps: acquiring initial state data of a global vehicle-mounted Ethernet network in a target vehicle; performing anomaly detection on the initial state data, and screening to obtain abnormal state data; and in response to the abnormal state data meeting an abnormal self-recovery condition, carrying out network self-recovery on the vehicle-mounted Ethernet. According to the invention, the problem that the network abnormity cannot be self-recovered in time in the prior art is solved, the effects of automatically monitoring and early warning the abnormal state data and automatically recovering the network of the vehicle-mounted Ethernet are realized, and the robustness of the system is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle monitoring, and in particular to a network self-recovery method, device, equipment, medium and product. BACKGROUND

[0002] With the increasing demand for multimedia and audio-video systems in the vehicle cabin, the network bandwidth and network performance are increasingly required, whether it is in-vehicle or out-of-vehicle network connection. Under this background, vehicle-mounted Ethernet emerges as the times require.

[0003] In the current vehicle network architecture, network anomalies cannot be recovered in time. SUMMARY

[0004] The present application provides a network self-recovery method, device, equipment, medium and product to solve the problem that network anomalies cannot be recovered in time in the prior art.

[0005] According to an aspect of the present application, a network self-recovery method is provided, comprising:

[0006] Obtaining initial state data of a global vehicle-mounted Ethernet network in a target vehicle;

[0007] Performing anomaly detection on the initial state data to obtain abnormal state data;

[0008] In response to the abnormal state data meeting an abnormal self-recovery condition, performing network self-recovery on the vehicle-mounted Ethernet.

[0009] According to another aspect of the present application, a network self-recovery device is provided, applied to a vehicle end of a target vehicle, comprising:

[0010] An obtaining module for obtaining initial state data of a global vehicle-mounted Ethernet network in a target vehicle;

[0011] An anomaly detection module for performing anomaly detection on the initial state data to obtain abnormal state data;

[0012] An abnormal self-recovery module for performing network self-recovery on the vehicle-mounted Ethernet in response to the abnormal state data meeting an abnormal self-recovery condition.

[0013] According to another aspect of the present application, an electronic device is provided, comprising:

[0014] At least one processor; and

[0015] A memory in communication connection with the at least one processor; wherein

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the network self-recovery method according to any one of the embodiments of the application.

[0017] According to another aspect of the application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the network self-recovery method according to any one of the embodiments of the application when executed by the processor.

[0018] According to another aspect of the application, a computer program product is provided, which comprises a computer program for implementing the network self-recovery method according to any one of the embodiments of the application when executed by a processor.

[0019] The technical solution of the embodiments of the application monitors the state of the global vehicle Ethernet network of the target vehicle, detects the abnormal state data from the initial state data, screens the abnormal state data, and automatically performs network self-recovery on the vehicle Ethernet network when the abnormal state data meets the abnormal self-recovery condition, thereby solving the problem that the network cannot be self-recovered in time in the prior art, achieving automatic monitoring and early warning of the abnormal state data, and achieving the effect of automatically performing network recovery on the vehicle Ethernet network, and improving the robustness of the system.

[0020] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the application, nor is it used to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort.

[0022] Figure 1 is a flowchart of a network self-recovery method provided by the embodiments of the application;

[0023] Figure 2 is a communication architecture diagram between a plurality of domain controllers provided by the embodiments of the application;

[0024] Figure 3 is a flowchart of another network self-recovery method provided by the embodiments of the application;

[0025] Figure 4This is a flowchart of another network self-recovery method provided in an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of a network self-recovery device provided in an embodiment of the present invention;

[0027] Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] In one embodiment, Figure 1 This is a flowchart of a network self-recovery method provided in an embodiment of the present invention. This embodiment is applicable to situations involving monitoring and self-recovery of the status of an in-vehicle Ethernet network. The method can be executed by a network self-recovery device, which can be implemented in hardware and / or software and can be configured in the vehicle. Figure 1 As shown, the method includes:

[0031] S110. Obtain the initial status data of the full-domain in-vehicle Ethernet network in the target vehicle.

[0032] Here, the target vehicle refers to any vehicle with an arbitrarily configured terminal; initial state data refers to unprocessed network state information obtained from the global Ethernet network. In one embodiment, the state data of the vehicular Ethernet network includes at least one of the following: inter-node connectivity, network port traffic of Ethernet switches or the Ethernet physical layer, network port bandwidth, time delay, data packet loss rate, signal quality, cyclic redundancy check (CRC), and error frames. Inter-node connectivity refers to the connectivity between nodes within a domain controller, and the connectivity between multiple domain controllers; network port traffic refers to the amount of data transmitted through a network port, typically measured in bits per second; network port bandwidth refers to the maximum data transmission rate that a network port can support, such as 100 Mbps or 1 Gbps; time delay refers to the time required to transmit data from one network node to another; data packet loss rate refers to the ratio between the number of data packets lost during data transmission and the total number of data packets; signal quality characterizes the signal strength and noise level in the Ethernet physical layer; CRC is used to detect errors during data transmission; and error frames refer to frames in Ethernet transmission that do not conform to protocol specifications or contain errors.

[0033] In actual operation, the target vehicle may include one or more domain controllers. Figure 2 This is a communication architecture diagram between multiple domain controllers provided in an embodiment of the present invention. Figure 2As shown, a target vehicle contains n domain controllers, namely domain controller 1, domain controller 2, ..., domain controller n. In one example, each domain controller in the target vehicle can establish a communication connection with the cloud server; alternatively, one domain controller in the target vehicle is used as the master device, and the other domain controllers are used as slave devices, and the domain controller acting as the master device establishes a communication connection with the cloud server. Assuming that domain controller 1 is used as the master device, and domain controller 2, domain controller 3, ..., domain controller n are used as slave devices, the System-on-Chip (SOC) in the master domain controller 1 communicates with other nodes within the domain (Ethernet switches, Ethernet physical layers (PHYs), 5G, microcontroller units (MCUs), virtual machines, etc.) and SOCs in other domain controllers outside the domain to confirm Ethernet connectivity with other nodes. Communication protocols and methods between nodes within the domain and domain controllers outside the domain include, but are not limited to, Internet Control Message Protocol (ICMP), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), and Quick UDP Internet Connections (QUIC). Data such as network port traffic, network port bandwidth, time delay, packet loss rate, signal quality, cyclic redundancy check (CRC), and error frames are obtained from Ethernet switches or the Ethernet physical layer. In one example, initial state data of the entire Ethernet network can be obtained by reading hardware register values ​​and data packet frames. In this embodiment, the vehicle-side device can use Universal Flash Storage (UFS) to store the read initial state data in a pre-configured local file storage system or file storage space to record the network status of the Ethernet network for subsequent analysis and optimization. Simultaneously, the data is periodically reported to a cloud server for observation and recording.

[0034] S120. Perform anomaly detection on the initial state data and filter out the abnormal state data.

[0035] Here, abnormal state data refers to data related to abnormalities in the Ethernet network status. In this embodiment, a pre-created anomaly detection model can be used to evaluate the initial state data to determine whether there are any anomalies in the network status. If anomalies are found, the corresponding abnormal state data is obtained through filtering.

[0036] S130. In response to abnormal state data meeting the abnormal self-recovery conditions, perform network self-recovery on the vehicle Ethernet.

[0037] The abnormal self-recovery condition characterizes whether the Ethernet network can be restored by performing a self-recovery operation. In one example, the criterion for setting the abnormal self-recovery condition is that the self-recovery operation will not seriously affect the driving experience of the vehicle. For example, if a self-recovery operation performed while the vehicle is in motion causes the vehicle's main control screen to suddenly turn off, causing psychological stress to the driver, then the self-recovery operation does not meet the abnormal self-recovery condition.

[0038] In one embodiment, the process of determining whether abnormal state data meets the abnormal self-recovery conditions includes: constructing a corresponding abnormal judgment vector based on the abnormal state data; inputting the abnormal judgment vector into a pre-created abnormal self-recovery model to obtain the corresponding abnormal root cause; and determining whether the abnormal self-recovery conditions are met based on the abnormal root cause. The abnormal judgment vector can be a one-dimensional vector, which can be understood as a set of values ​​arranged in order for multiple abnormal state data; of course, the abnormal judgment vector can also be a multi-dimensional vector, which can be understood as an ordered pair of values ​​composed of multiple abnormal state data.

[0039] In one embodiment, constructing a corresponding anomaly judgment vector based on abnormal state data includes: forming a data set of abnormal state data corresponding to each network indicator; arranging the data set of each network indicator according to a predetermined arrangement rule to obtain the corresponding anomaly judgment vector. The data set of abnormal state data can be understood as a set of one or more related abnormal state data for a network indicator. In one example, the predetermined arrangement order may include, but is not limited to, one of the following: chronological order; random sorting. Chronological order refers to the order in which the abnormal state data of each network indicator is detected. For example, the data set of each network indicator can be sorted according to chronological order to obtain the corresponding anomaly judgment vector. For instance, if the abnormal state data of network indicators 1, 2, 3, and 4 are detected at times 1, 2, 3, and 4 respectively, then the data set of each network indicator can be sorted according to the chronological order of time 1, 2, 3, and 4 to obtain the corresponding anomaly judgment vector.

[0040] For example, suppose the anomaly detection vector is a one-dimensional vector composed of anomaly status data for four network metrics, which can be represented in the form (a1, a2, a3, a4, ...). Here, a1 is the set of connectivity verification statistics with the IP to be checked; a2 is the set of changes in network interface card (NIC) packet transmission and reception data; a3 is the set of error data; and a4 is the set of changes in interruption data. In one example, when the anomaly detection vector is a multi-dimensional vector, one row of the vector can represent the anomaly status data of one metric. For example, the first row could be the connectivity verification statistics, the second row the NIC packet transmission and reception data changes, the third row the error data, and the fourth row the interruption data changes. The IP to be checked refers to the IP of a cloud server, the IP of a WiFi module, or the IP of a domain controller or ECU node to be checked, etc. Connectivity verification data can be represented using 0 and 1, for example, 0 represents disconnection and 1 represents connectivity. The set of data changes for network interface card (NIC) packet transmission and reception can include, but is not limited to, one of the following: packet loss rate, the difference between the relative values ​​of the number of packets sent last time and the number of packets sent this time (representing uplink / downlink rates or bandwidth), the difference between the relative values ​​of the number of packets received last time and the number of packets received this time, and traffic per unit time. The set of error data can include, but is not limited to, one of the following: receive length error, receive overflow error, receive cyclic redundancy check error, receive frame error, receive FIFO queue error, receive missing error, transmit abort error, transmit carrier error, transmit FIFO queue error, transmit heartbeat error, transmit window error, excessively long frame error, circular buffer overflow error, cyclic redundancy check error, frame synchronization error, FIFO overflow, and missing packets, etc. The set of data changes for interrupts refers to both software interrupts and hardware interrupts. Hardware interrupts are implemented in hardware, such as disks, NICs, keyboards, clocks, etc. Each device or set of devices has its own IRQ interrupt request. When a hardware interrupt occurs, the Central Processing Unit (CPU) interrupts the currently running task to handle the interrupt. In a multi-core system, an interrupt typically only interrupts one CPU. A hardware interrupt can directly interrupt the CPU, triggering relevant code in the kernel. For processes that require some processing time, the interrupt code itself can also be interrupted by other hardware interrupts. Hardware interrupt handling is usually handled by hardware drivers; the handler only processes critical tasks that can be completed quickly, while the remaining time-consuming tasks are postponed and handled by software interrupts. Software interrupts are implemented in several ways: they are generated by the currently running process, typically requesting input / output (I / O). These requests invoke kernel programs that can schedule I / O.For some devices, I / O requests can be queued and processed later. Depending on the I / O model, a process may be suspended until the I / O is complete, at which point the kernel scheduler will select another process to run. The handling of soft interrupts is similar to that of hard interrupts, but they are generated by the currently running process. Soft interrupts can be generated by the interrupt handler of a hard interrupt or triggered by an application. Soft interrupts are implemented in advance in the code and are not random.

[0041] An anomaly self-recovery model can be understood as a pre-created model that selects appropriate self-recovery operations for network anomalies, and then restores the vehicle Ethernet network through appropriate self-recovery operations; the root cause of the anomaly refers to the fundamental reason for the anomaly. In the embodiment, the anomaly judgment vector constructed from the anomaly state data is input into the pre-created anomaly self-recovery model to obtain the corresponding root cause of the anomaly, and a determination is made based on the root cause of the anomaly to determine whether a self-recovery operation is required; if a self-recovery operation is required and the anomaly self-recovery conditions are met, then the vehicle Ethernet network is automatically restored.

[0042] In one embodiment, the self-recovery operation includes at least one of the following: restarting the virtual network interface card, restarting the Ethernet service, redialing, restarting the Ethernet switch, restarting a single chip, and restarting the entire system. Different self-recovery operations can be used when the Ethernet network experiences different degrees of anomalies. For example, if the SOC node of domain controller 1 communicates normally with the MCU node in the domain, but the Ethernet communication between the SOC node and the 5G node in the domain is abnormal, it can be assumed that the overall Ethernet network in the domain is fine, and only the 5G node is faulty. When detecting the power-on of a 5G device, since the 5G chip restart only affects the domain controller's external communication and is not easily perceived by the user, the network daemon (netd) process on the 5G is immediately restarted via other communication methods to first restart the software-level Ethernet service (Operation 1). If Operation 1 fails, the Ethernet port is restarted (Operation 2). If Operation 2 fails, all processes are notified that the system is about to restart, all important data is preserved, processes are immediately shut down, and the 5G device restart operation is performed after preparation (Operation 3). If Operation 3 still fails, the 5G device records the situation and communicates with the MCU via Remote Procedure Call (RPC) to report to the SOC for recording. For example, if the SOC node of domain controller 1 has abnormal communication with various nodes inside and outside the domain, it can be considered that there is a problem with the overall Ethernet in the domain. It may be that the switch in domain controller 1 is abnormal or the Ethernet service is abnormal. Based on the recorded Ethernet switch port traffic data, it is determined whether the switch is the problem. If so, the switch is restarted; otherwise, the Ethernet service is restarted. If all of the above fail, the board-level system is restarted when the vehicle is idle.

[0043] The technical solution of this embodiment monitors the status of the target vehicle's full-domain in-vehicle Ethernet network, performs anomaly detection on the initial status data, filters out abnormal status data, and performs network self-recovery of the in-vehicle Ethernet when the abnormal status data meets the abnormal self-recovery conditions. This solves the problem of the inability to perform timely self-recovery of network anomalies in the prior art, realizes the effect of automatic monitoring and early warning of abnormal status data, and automatic network recovery of the in-vehicle Ethernet, and improves the robustness of the system.

[0044] In one embodiment, Figure 3 This is a flowchart of another network self-recovery method provided by an embodiment of the present invention. This embodiment further explains the initial state data acquisition process, anomaly detection process, and network recovery process based on the above embodiments. In this embodiment, the vehicle-mounted Ethernet includes at least one domain controller. The on-chip system in the domain controller establishes communication connections with other nodes within the domain, and the on-chip system in the domain controller establishes communication connections with on-chip systems in other domain controllers outside the domain.Figure 3 As shown, the method includes:

[0045] S210: Read the hardware register values ​​and / or data packet frames of other nodes in the corresponding domain controller through the on-chip system in each domain controller.

[0046] The vehicular Ethernet network can include one or more domain controllers. Each domain controller includes a system-on-a-chip (SoC) and multiple nodes (e.g., 5G, MCU, PHY, and SWITCH). The SoC in each domain controller can read hardware register values ​​and / or data packets from other nodes within that domain controller. Hardware register values ​​refer to specific values ​​stored in registers of the hardware devices within the domain controller. For example, hardware register values ​​can be data retrieved from the registers of the PHY chip or from the registers of the SWITCH. Data packets are data structures used to encapsulate different data. A data packet can include a header, a data portion, and a trailer. The data portion carries the relevant status data for each vehicular Ethernet network. In practice, the relevant status data of each node at different points in time can be stored in data packet format; alternatively, the relevant status data of multiple nodes at the same point in time can also be stored in data packet format, without limitation.

[0047] S220. Parse the information carried by each field in the hardware register values ​​and / or data packet frames to obtain Ethernet network-related status data as the corresponding initial status data.

[0048] In one example, the process of obtaining initial state data by reading hardware register values ​​in the vehicle Ethernet includes: the interface circuit of the vehicle Ethernet includes a MAC (Media Access Control) controller and a physical layer interface PHY. The MAC and the physical layer interface PHY can be connected through a specific interface. The MAC can access the registers of the physical layer interface PHY to obtain the hardware register values ​​in the PHY, and parse the information in the hardware register values ​​to obtain Ethernet network-related state data as initial state data.

[0049] In one example, the process of obtaining initial state data by reading data packets in the vehicle Ethernet includes: using tools that support Ethernet analysis to parse and display the specific information of Ethernet data packets, analyzing the key information of the data packets by the different information carried by each field contained in the vehicle Ethernet data frame, analyzing the communication mode and traffic of the data packets to determine the network status, and using the analyzed data as the initial state data.

[0050] S230. Input the initial state data of each network indicator in the vehicle Ethernet network into the anomaly detection model, and output the corresponding actual state detection value.

[0051] The creation process of both the anomaly detection model and the anomaly self-recovery model can be derived by analyzing and summarizing a large amount of posterior data and using pre-defined empirical rules. The model creation methods can include, but are not limited to, manually defining the value range of key Ethernet network status data, establishing a mathematical model based on empirical values ​​and adjusting parameters, etc. Alternatively, a keyword intelligent recognition model can be built using neural networks. Specific steps include: collecting a dataset containing relevant data; preprocessing the data and converting it into a suitable vector representation; selecting a suitable neural network architecture, such as a recurrent neural network (e.g., LSTM or GRU) or a combination of convolutional neural networks and recurrent neural networks; inputting the preprocessed data into the neural network for training, using appropriate loss functions (e.g., cross-entropy loss) and optimization algorithms (e.g., stochastic gradient descent) to adjust the model parameters; evaluating the model's performance using a validation dataset, and adjusting the model's hyperparameters, such as the number of network layers, neurons, and learning rate, based on the evaluation results to optimize the model until the recognition rate reaches the expected set value. At this point, a mature keyword recognition model based on a neural network is established, and the corresponding anomaly detection model and anomaly self-recovery model are obtained.

[0052] The mathematical model can include, but is not limited to: quadratic functions, logarithmic or exponential models, and pattern matching recognition models. Quadratic functions, logarithmic or exponential models only need to achieve a fitting and correction effect; pattern matching recognition models are models that can identify patterns based on data features.

[0053] In one example, if the anomaly detection model is a mathematical model, the initial state data of each network indicator in the vehicular Ethernet network is taken as a variable and input into the anomaly detection model, and the corresponding actual state detection value is output. If the anomaly detection model is a neural network model, the initial state data of each network indicator in the vehicular Ethernet network is taken as an input parameter and input into the anomaly detection model, and the corresponding actual state detection value is output.

[0054] In this embodiment, the initial state data of one or more network metrics in the vehicular Ethernet network can be directly input into the anomaly detection model to obtain the actual state detection value corresponding to the network metric. Of course, when multiple network metrics are detected simultaneously, the actual state detection value can be directly used as a reference value to assess whether the multiple network metrics are abnormal.

[0055] S240. Based on the comparison between the actual state detection value and the state detection threshold, the abnormal state data of the corresponding network indicators are obtained by filtering.

[0056] In one embodiment, abnormal state data of corresponding network indicators are filtered based on the comparison result between the actual state detection value and the state detection threshold. This includes: determining whether the actual state detection value is within the state range defined by the state detection threshold; if the actual state detection value is not within the state range, then the initial state data of all network indicators corresponding to the actual state detection value are taken as abnormal state data. Here, the state range refers to the range of values ​​in which the actual state detection value of a network indicator conforms to the expected operating state. In actual operation, the state range consists of two boundary values, corresponding to two pre-configured state detection thresholds. For example, the state detection thresholds are value 1 and value 2, and value 1 is less than value 2. The corresponding state range is composed of value 1 and value 2. If the actual state detection value of a network indicator is within the state range, then the initial state data of that network indicator conforms to the expected operating state; if the actual state detection value of a network indicator is not within the state range, then the initial state data of that network indicator does not conform to the expected operating state, and is therefore taken as abnormal state data.

[0057] In one example, to determine if a single metric is abnormal, one can directly check if the actual state detection value of that metric falls within a pre-configured state range. To determine if multiple metrics are abnormal, these metrics can be combined into a function, and the function's value can be checked against a pre-configured state range. For example, z = ax + by, where z represents the actual state detection value, and x and y represent the initial state data of the two metrics. If z does not reach the pre-configured state detection threshold, then both x and y are considered abnormal state data.

[0058] S250. In response to abnormal state data meeting the abnormal self-recovery conditions, select the corresponding set of candidate self-recovery operations based on the abnormal root cause corresponding to the abnormal state data.

[0059] The candidate self-recovery operation set contains all self-recovery operations that can be executed based on the abnormal state data. The candidate self-recovery operation set must include at least one candidate self-recovery operation. In this embodiment, a pre-configured abnormal self-recovery model can be used to find all candidate self-recovery operations that match the root cause of the abnormality, thus forming the corresponding candidate self-recovery operation set.

[0060] S260. Determine the target self-recovery operation based on the self-recovery time and self-recovery cost of each candidate self-recovery operation in the candidate self-recovery operation set.

[0061] Here, self-recovery time refers to the execution time required for the candidate self-recovery operation to restore the network; self-recovery cost refers to the degree of impact of executing a candidate self-recovery operation on the vehicular Ethernet network; the smaller the self-recovery cost, the smaller the impact of executing the candidate self-recovery operation on the vehicular Ethernet network; the longer the self-recovery time, the longer the execution time required to execute the candidate self-recovery operation.

[0062] In one embodiment, determining the corresponding target self-recovery operation based on the self-recovery time and self-recovery cost of each candidate self-recovery operation in the candidate self-recovery operation set includes: comparing the self-recovery times and self-recovery costs among the candidate self-recovery operations in the candidate self-recovery operation set; selecting candidate self-recovery operations from the candidate self-recovery operation set whose self-recovery times meet a preset time length and whose self-recovery costs meet a preset cost threshold as the corresponding target self-recovery operation. Here, the preset time length refers to a pre-configured allowable self-recovery time threshold; the preset standby threshold refers to a pre-configured allowable self-recovery cost threshold.

[0063] In this embodiment, a pre-created anomaly self-recovery model can be used to determine the self-recovery time and self-recovery cost corresponding to each candidate self-recovery operation. Then, combining the strategy of minimizing self-recovery time and / or the strategy of minimizing self-recovery cost, a candidate self-recovery operation is selected from the set of candidate self-recovery operations as the target self-recovery operation. However, in actual operation, the self-recovery cost corresponding to the candidate self-recovery operation with the shortest self-recovery time in the set may not be the minimum, or the self-recovery time corresponding to the candidate self-recovery operation with the minimum self-recovery cost may not be the shortest. In this case, the self-recovery time and self-recovery cost of each candidate self-recovery operation in the set can be comprehensively considered to select an optimal candidate self-recovery operation as the target self-recovery operation. Specifically, the self-recovery time and self-recovery cost of each candidate self-recovery operation in the candidate self-recovery operation set can be compared. If there is a candidate self-recovery operation in the candidate self-recovery operation set whose self-recovery time meets a preset time length and whose self-recovery cost meets a preset cost threshold, then the candidate self-recovery operation whose self-recovery time is less than the preset time length and whose self-recovery cost is less than the preset cost threshold is directly selected from the candidate self-recovery operation set as the corresponding target self-recovery operation. Of course, in actual operation, if there are at least two candidate self-recovery operations in the candidate self-recovery operation set whose self-recovery time is less than the preset time length and whose self-recovery cost is less than the preset cost threshold, then one candidate self-recovery operation is selected from these at least two candidate self-recovery operations based on the shortest self-recovery time strategy; if the self-recovery times of these at least two candidate self-recovery operations are equal, then one candidate self-recovery operation is selected from these at least two candidate self-recovery operations with equal self-recovery times based on the minimum self-recovery cost strategy as the target self-recovery operation.

[0064] S270, Use target self-recovery operation to perform network self-recovery of vehicle Ethernet.

[0065] The technical solution of this embodiment, based on the above embodiment, finds the root cause of the abnormal state data, and forms a set of candidate self-recovery operations that match the root cause of the abnormality. Then, it selects the optimal self-recovery operation from the set of candidate self-recovery operations, which takes into account the shortest self-recovery time and the lowest self-recovery cost, as the corresponding target self-recovery operation. The target self-recovery operation is then used to restore the vehicle Ethernet network, thereby achieving the effect of automatic monitoring and self-recovery of abnormalities and improving the robustness of the system.

[0066] In one embodiment, the network self-recovery method further includes: determining a reporting mode for abnormal status data based on the abnormality priority of the abnormal status data; when the abnormality priority reaches a priority threshold, reporting the abnormal status data to the cloud server using a first reporting mode; and when the abnormality priority does not reach the priority threshold, reporting the abnormal status data to the cloud server using a second reporting mode. The abnormality priority characterizes the severity of the abnormality; a higher severity corresponds to a higher abnormality priority, and vice versa. The reporting mode characterizes the frequency at which the vehicle reports abnormal status data to the cloud server. For example, the reporting modes include a first reporting mode and a second reporting mode; the first reporting mode refers to a periodic data reporting method; the second reporting mode can also be called an event-driven reporting mode, i.e., a real-time data reporting method. If the anomaly priority of abnormal status data reaches the priority threshold, it indicates that the severity of the anomaly is too high and needs to be handled promptly. In this case, the abnormal status data can be reported to the cloud server in real time so that the cloud server can take corresponding countermeasures. If the anomaly priority of abnormal status data does not reach the priority threshold, it indicates that the severity of the anomaly is low. In order to save data transmission overhead, the anomaly can be reported periodically, such as once a day or once a week.

[0067] In an embodiment, Figure 4 This is a flowchart of another network self-recovery method provided in this embodiment of the invention. This embodiment, as a preferred embodiment, specifically describes the implementation process of network self-recovery. Figure 4 As shown, the network self-recovery process in this embodiment includes the following steps:

[0068] S410. Create an anomaly detection model and an anomaly self-recovery model.

[0069] S420: Obtain the initial status data of the global Ethernet network.

[0070] S430. Input the initial state data into the anomaly detection model and determine whether there is any abnormal state data. If yes, execute S440; otherwise, execute S470.

[0071] S440: Periodically report abnormal status data to the cloud server.

[0072] S450. Input the abnormal state data into the abnormal self-recovery model and determine whether it meets the self-recovery conditions. If yes, execute S460; otherwise, execute S470.

[0073] S460 performs network self-recovery processing on the vehicle Ethernet.

[0074] S470, No action taken.

[0075] In one embodiment, Figure 5 This is a schematic diagram of the structure of a network self-recovery device provided in an embodiment of the present invention. Figure 5 As shown, the device includes: an acquisition module 510, an anomaly detection module 520, and an anomaly self-recovery module 530.

[0076] The acquisition module 510 is used to acquire the initial status data of the full-domain vehicular Ethernet network in the target vehicle;

[0077] Anomaly detection module 520 is used to perform anomaly detection on the initial state data and filter out abnormal state data.

[0078] The anomaly self-recovery module 530 is used to perform network self-recovery of the vehicle Ethernet in response to abnormal state data meeting the anomaly self-recovery conditions.

[0079] In one embodiment, the vehicular Ethernet includes at least one domain controller, wherein the on-chip system in the domain controller establishes communication connections with other nodes within the domain, and the on-chip system in the domain controller establishes communication connections with on-chip systems in other domain controllers outside the domain; the acquisition module 510 includes:

[0080] The read unit is used to read hardware register values ​​and / or data packet frames from other nodes in the corresponding domain controller through the on-chip system in each domain controller;

[0081] The parsing unit is used to parse the information carried by each field in the hardware register values ​​and / or data packet frames to obtain Ethernet network-related status data as the corresponding initial status data.

[0082] In one embodiment, the anomaly detection module 520 includes:

[0083] The determination unit is used to input the initial state data of each network indicator in the vehicle Ethernet network into the anomaly detection model and output the corresponding actual state detection value.

[0084] The detection unit is used to filter out abnormal state data of the corresponding network indicators based on the comparison between the actual state detection value and the state detection threshold.

[0085] In one embodiment, the detection unit includes:

[0086] The judgment subunit is used to determine whether the actual state detection value is within the state range constituted by the state detection threshold.

[0087] The detection subunit is used to treat the initial state data of all network indicators corresponding to the actual state detection value as abnormal state data if the actual state detection value is not within the state range.

[0088] In one embodiment, the process of determining whether abnormal state data meets the abnormal self-recovery conditions includes:

[0089] Construct corresponding anomaly judgment vectors based on abnormal state data;

[0090] The anomaly detection vector is input into the anomaly self-recovery model to obtain the corresponding anomaly root cause;

[0091] Determine whether the anomaly self-recovery conditions are met based on the root cause of the anomaly.

[0092] In one embodiment, constructing a corresponding anomaly judgment vector based on the abnormal state data includes: forming a data set of abnormal state data corresponding to each network indicator; arranging the data set of each network indicator according to a predetermined arrangement rule to obtain the corresponding anomaly judgment vector.

[0093] In one embodiment, network self-recovery of the vehicular Ethernet is specifically used for:

[0094] Select the corresponding set of candidate self-recovery operations based on the root cause of the abnormal state data;

[0095] The target self-recovery operation is determined based on the self-recovery time and self-recovery cost of each candidate self-recovery operation in the candidate self-recovery operation set.

[0096] The target self-recovery operation is used to perform network self-recovery of the vehicle Ethernet.

[0097] In one embodiment, the target self-recovery operation is determined based on the self-recovery time and self-recovery cost corresponding to each candidate self-recovery operation in the candidate self-recovery operation set, specifically for:

[0098] The self-recovery time and self-recovery cost of each candidate self-recovery operation are compared in the candidate self-recovery operation set.

[0099] Select candidate self-recovery operations from the set of candidate self-recovery operations whose self-recovery time meets the preset time length and whose self-recovery cost meets the preset cost threshold, and use them as the corresponding target self-recovery operations.

[0100] In one embodiment, the network self-recovery device further includes:

[0101] The determination module is used to determine the reporting mode of abnormal status data based on the abnormality priority of the abnormal status data.

[0102] The first reporting module is used to report abnormal status data to the cloud server in the first reporting mode when the abnormal priority reaches the priority threshold.

[0103] The second reporting module is used to report abnormal status data to the cloud server in the second reporting mode when the abnormal priority does not reach the priority threshold.

[0104] The network self-recovery device provided in this embodiment of the invention can execute the network self-recovery method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0105] In one embodiment, Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of the present invention, such as... Figure 6 The diagram illustrates a schematic representation of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0106] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0108] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as network self-recovery methods.

[0109] In some embodiments, the network self-recovery method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the network self-recovery method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the network self-recovery method by any other suitable means (e.g., by means of firmware).

[0110] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0114] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0115] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0116] This application also provides a computer program product, including a computer program that, when executed by a processor, can implement the network self-recovery method provided in any embodiment of this application.

[0117] In the implementation of the computer program product, computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0118] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0119] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for network self-recovery, the method comprising: The method comprises: acquiring initial state data of a global vehicle Ethernet network in a target vehicle; performing anomaly detection on the initial state data to obtain abnormal state data; performing network self-recovery on the vehicle Ethernet network in response to the abnormal state data meeting an anomaly self-recovery condition.

2. The method of claim 1, wherein, The vehicle Ethernet network comprises at least one domain controller, a system on chip in the domain controller is communicatively connected to other nodes in the domain, and the system on chip in the domain controller is communicatively connected to a system on chip in other domain controllers outside the domain; the acquiring of the initial state data of the global Ethernet network in the target vehicle comprises: reading, by the system on chip in each domain controller, hardware register values and / or data packet data frames of other nodes in the corresponding domain controller; parsing information borne by each field in the hardware register values and / or the data packet data frames to obtain state data related to the Ethernet network as the corresponding initial state data.

3. The method of claim 1, wherein, The performing of anomaly detection on the initial state data to obtain abnormal state data comprises: inputting the initial state data of each network indicator in the vehicle Ethernet network into an anomaly detection model to output corresponding actual state detection values; screening abnormal state data of the corresponding network indicator according to a comparison result between the actual state detection values and state detection threshold values.

4. The method of claim 3, wherein, The screening of abnormal state data of the corresponding network indicator according to a comparison result between the actual state detection values and state detection threshold values comprises: determining whether the actual state detection values are within a state range constituted by the state detection threshold values; if the actual state detection values are not within the state range, regarding the initial state data of all network indicators corresponding to the actual state detection values as abnormal state data.

5. The method of claim 1, wherein, The judgment process of whether the abnormal state data meets the anomaly self-recovery condition comprises: constructing a corresponding anomaly judgment vector according to the abnormal state data; inputting the anomaly judgment vector into an anomaly self-recovery model to obtain a corresponding anomaly root cause; determining whether the anomaly self-recovery condition is met based on the anomaly root cause.

6. The method of claim 5, wherein, The constructing of a corresponding anomaly judgment vector according to the abnormal state data comprises: constructing a data set of abnormal state data corresponding to each network indicator; arranging the data set of each network indicator according to a predetermined arrangement rule to obtain the corresponding anomaly judgment vector.

7. The method of claim 1, wherein, The performing of network self-recovery on the vehicle Ethernet network comprises: selecting a corresponding candidate self-recovery operation set according to the anomaly root cause corresponding to the abnormal state data; determining a corresponding target self-recovery operation according to a self-recovery time and a self-recovery cost corresponding to each candidate self-recovery operation in the candidate self-recovery operation set; performing network self-recovery on the vehicle Ethernet network by using the target self-recovery operation.

8. The method of claim 7, wherein, The determining of a corresponding target self-recovery operation according to a self-recovery time and a self-recovery cost corresponding to each candidate self-recovery operation in the candidate self-recovery operation set comprises: compare self-recovery times between each candidate self-recovery operation in the candidate self-recovery operation set, and compare self-recovery costs between each candidate self-recovery operation; select, from the candidate self-recovery operation set, a candidate self-recovery operation whose self-recovery time meets a preset time length and whose self-recovery cost meets a preset cost threshold, as a corresponding target self-recovery operation.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: determining a reporting mode of the abnormal state data according to an abnormal priority of the abnormal state data; when the abnormal priority reaches a priority threshold, reporting the abnormal state data to a cloud server in a first reporting mode; when the abnormal priority does not reach the priority threshold, reporting the abnormal state data to the cloud server in a second reporting mode.

10. A network self-recovery apparatus, characterized by, comprise: an acquisition module configured to acquire initial state data of a global vehicle Ethernet network in a target vehicle; an abnormality detection module configured to perform abnormality detection on the initial state data to obtain abnormal state data; an abnormality self-recovery module configured to perform network self-recovery on the vehicle Ethernet network in response to the abnormal state data meeting abnormality self-recovery conditions.

11. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the network self-recovery method of any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to execute the network self-recovery method of any one of claims 1-9 when executed.

13. A computer program product, characterised in that, The computer program product comprises a computer program which, when executed by the processor, implements the network self-recovery method according to any one of claims 1-9.

Images