Edge node-based installation information identification method, device, equipment and medium

Abstract

The application relates to an edge node-based installation information identification method, device, equipment and medium. The method comprises the following steps: in the case of detecting power-on, triggering an installation information identification instruction of an edge node, acquiring first multi-source feature data corresponding to the edge node, identifying the installation information of the edge node according to the first multi-source feature data corresponding to the edge node in the vehicle and a preset reference threshold library of node installation information, determining the preliminary installation information of the edge node, and based on different types of information in the preliminary installation information, performing cross verification processing to determine the current installation information of the edge node. The above method can identify the installation information of the edge node, and then improve the adaptability between the edge node and the vehicle according to the self-identification result.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, device and medium for identifying installation information based on edge nodes. Background Technology

[0002] As the automotive industry accelerates its development towards intelligence and connectivity, the vehicle's electronic and electrical architecture (EEA) is evolving from a traditional distributed architecture towards a more centralized and standardized form. The EEA includes edge network systems, and the adaptability of edge nodes, as the core execution units of these systems, to the vehicle is crucial for ensuring the stable and reliable operation of the entire vehicle's EEA.

[0003] Typically, the operating parameters of the edge node can be adjusted based on the installation information of the edge node on the vehicle (including the material of the mounting base, the installation location, and the installation method) to ensure the compatibility between the edge node and the vehicle.

[0004] However, there is no solution in the relevant technologies that can automatically identify the installation information of edge nodes, which leads to poor compatibility between edge nodes and vehicles. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, device, and medium for identifying installation information based on edge nodes to address the aforementioned technical problems.

[0006] Firstly, this application provides a method for identifying installation information based on edge nodes, applicable to any edge node within an edge network system in a vehicle; the method includes:

[0007] Upon detecting power-on, an installation information recognition command for the edge node is triggered to obtain the first multi-source feature data corresponding to the edge node;

[0008] Based on the first multi-source feature data corresponding to the edge nodes inside the vehicle and the preset benchmark threshold library of node installation information, the installation information of the edge nodes is identified to determine the preliminary installation information of the edge nodes.

[0009] Cross-validation is performed on different types of information in the initial installation information to determine the current installation information of the edge nodes.

[0010] In one embodiment, based on the first multi-source feature data corresponding to the edge nodes within the vehicle and a preset benchmark threshold library of node installation information, the installation information of the edge nodes is identified to determine the preliminary installation information of the edge nodes, including:

[0011] Obtain the corresponding first benchmark threshold from the preset benchmark threshold library;

[0012] Based on the first benchmark threshold, threshold matching is performed on the first multi-source feature data to obtain the threshold matching result;

[0013] Based on the threshold matching results, the preliminary installation information of the edge nodes is determined.

[0014] In one embodiment, preliminary installation information of the edge nodes is determined based on the threshold matching results, including:

[0015] If the threshold matching result is that the first multi-source feature data matches the first benchmark threshold, then the preliminary installation information of the edge node is obtained;

[0016] If the threshold matching result is that the first multi-source feature data does not match the first benchmark threshold, then the second multi-source feature data corresponding to the edge node within the target sampling period is obtained, and the installation information of the edge node is identified based on the second multi-source feature data to obtain the preliminary installation information of the edge node; the duration of the target sampling period is greater than the duration of the sampling period corresponding to the first multi-source feature data.

[0017] In one embodiment, cross-validation is performed based on different types of information in the initial installation information to determine the current installation information of the edge node, including:

[0018] Based on the rationality rules of node installation, cross-validation is performed on different types of information in the initial installation information to obtain cross-validation results;

[0019] Based on the cross-validation results and preliminary installation information, determine the current installation information of the edge nodes.

[0020] In one embodiment, the method further includes:

[0021] Given the current installation information of the edge nodes, obtain the third multi-source feature data corresponding to the edge nodes;

[0022] The preset benchmark threshold library is updated based on the third multi-source feature data to obtain the updated benchmark threshold library.

[0023] Based on the second benchmark threshold and the third multi-source feature data in the updated benchmark threshold library, the installation information of the edge nodes is re-identified to obtain the re-identification accuracy.

[0024] Based on the re-identification accuracy, the process of re-identifying the installation information of edge nodes is verified, and the process verification results are obtained.

[0025] In one embodiment, the method further includes:

[0026] Based on the first multi-source feature data and the third multi-source feature data, deviation processing is performed to obtain the deviation value between the first multi-source feature data and the third multi-source feature data.

[0027] If the deviation value does not meet the preset deviation range, the step of updating the preset benchmark threshold library based on the third multi-source feature data is executed.

[0028] In one embodiment, a preset benchmark threshold library is updated based on third multi-source feature data to obtain an updated benchmark threshold library, including:

[0029] In response to the correction instruction of the preset benchmark threshold library sent by the central processing unit in the edge network system, the preset benchmark threshold library is corrected to obtain the updated benchmark threshold library.

[0030] Secondly, this application also provides an installation information identification device based on edge nodes, comprising:

[0031] The data acquisition module is used to trigger the installation information identification command of the edge node when power-on is detected, and to acquire the first multi-source feature data corresponding to the edge node.

[0032] The identification module is used to identify the installation information of the edge nodes based on the first multi-source feature data corresponding to the edge nodes in the vehicle and the preset benchmark threshold library of node installation information, and to determine the preliminary installation information of the edge nodes.

[0033] The cross-validation module is used to perform cross-validation processing based on different types of information in the initial installation information to determine the current installation information of the edge nodes.

[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any of the embodiments of the first aspect described above.

[0035] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0036] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0037] The installation information identification method, apparatus, device, and medium based on edge nodes provided in this application embodiment include: triggering an installation information identification instruction for edge nodes when power is detected, acquiring first multi-source feature data corresponding to the edge nodes, identifying the installation information of the edge nodes based on the first multi-source feature data corresponding to the edge nodes in the vehicle and a preset benchmark threshold library of node installation information, determining the preliminary installation information of the edge nodes, and performing cross-validation processing based on different types of information in the preliminary installation information to determine the current installation information of the edge nodes. The aforementioned method can self-identify the installation information of edge nodes upon power-up, providing reliable information to improve the compatibility between edge nodes and vehicles. Furthermore, after identifying the installation information, the method cross-validates the preliminary installation information to determine the accuracy and reliability of the final acquired information. Additionally, the self-identification of edge node installation information improves the compatibility and reliability between edge nodes and vehicles, enabling plug-and-play functionality. This also improves vehicle mass production efficiency, reduces assembly error rates and costs, and meets the requirements of standardized and large-scale automotive production, demonstrating significant industrial application value. Moreover, the self-identification results provide installation-related data support for subsequent functions such as adaptive thermal management, vibration compensation, accuracy calibration, and fault warning, enhancing the reliability and stability of the electronic and electrical architecture. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is an application environment diagram of an edge node-based installation information identification method in one embodiment;

[0040] Figure 2 This is a flowchart illustrating an edge node-based installation information identification method in one embodiment.

[0041] Figure 3 This is a flowchart illustrating an edge node-based installation information identification method in another embodiment;

[0042] Figure 4 This is a flowchart illustrating an edge node-based installation information identification method in another embodiment;

[0043] Figure 5This is a flowchart illustrating an edge node-based installation information identification method in another embodiment;

[0044] Figure 6 This is a flowchart illustrating an edge node-based installation information identification method in another embodiment;

[0045] Figure 7 This is a structural block diagram of an edge node-based installation information identification device in one embodiment;

[0046] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] In the automotive field, the electronic and electrical architecture includes edge network systems, and edge nodes, as the core execution units of these systems, exhibit inconsistent operational stability and reliability under different installation conditions (including installation location, mounting base material, and installation method), leading to incompatibility between edge nodes and vehicles. For example, edge nodes installed in the engine compartment (high-temperature environment) are prone to overheating and frequency throttling due to fixed thermal protection thresholds; edge nodes installed on plastic bases (poor grounding) suffer from signal acquisition errors due to fixed filtering parameters; and edge nodes installed on adhesive-mounted (low-rigidity) devices experience accelerated aging due to fixed vibration tolerance parameters. Typically, the operating parameters of edge nodes can be adjusted based on their installation information on the vehicle (including mounting base material, installation location, and installation method) to ensure compatibility between the edge nodes and the vehicle. Related technologies primarily differentiate edge node installation information through manual calibration, hard coding, or flashing different firmware. This not only increases the workload and labor costs in vehicle production and assembly but also easily leads to calibration errors and firmware flashing mistakes, failing to meet the "plug-and-play" mass production requirements of edge nodes. However, there is no solution in the relevant technologies that can automatically identify the installation information of edge nodes, which leads to poor compatibility between edge nodes and vehicles.

[0049] The installation information identification method based on edge nodes provided in this application can be applied to, for example... Figure 1 In the application environment shown, this edge network system is a system within the vehicle's electronic and electrical architecture. For example... Figure 1As shown, the edge network system includes a central processing unit (CPU) and Mn edge nodes (M and n are both greater than 1 in the figure). The CPU communicates with each edge node. Each edge node has the same function and internal architecture. Each edge node includes a Remote Control Protocol (RCP) control module, a data acquisition module, and a memory. The data acquisition module may be, but is not limited to, a temperature acquisition unit, a vibration acquisition unit, an impedance detection unit, and an electromagnetic detection unit. The memory may be, but is not limited to, flash memory and memory chips. The temperature acquisition unit, vibration acquisition unit, impedance detection unit, and electromagnetic detection unit all communicate with the RCP control chip.

[0050] It should be noted that the RCP control chip in each edge node is connected to the central processing unit (CPU) via communication. This communication can be via Bluetooth, mobile data, Wi-Fi, etc. In this embodiment, the RCP control chip uses the Remote Control Protocol (RCP) to connect to the CPU via a communication bus. This communication bus can be automotive Ethernet. For example, 10Base-T1S Ethernet, with a data link bandwidth of 10Mbps, is suitable for low-power, long-distance, multi-node edge sensing and control scenarios. The communication bus can also be a CAN bus, such as CANXL, or even 100Mbps Ethernet. It is understood that the communication bus can be determined according to actual application requirements and is not specifically limited here. The aforementioned central computing node may include, but is not limited to, a Physical-Layer Transceiver (PHTV) module, a protocol processing module, a storage module, a wake-up decision module, and a power management module. Furthermore, in this embodiment, the CPU can be referred to as the central brain of the edge network system. In practical applications, when the computing power of one edge node is insufficient, the CPU can control multiple edge nodes to process synchronously.

[0051] Meanwhile, the RCP control chips in different edge nodes can be connected to each other via an edge network; specifically, multiple edge nodes under the same edge network are connected to the central computing unit via a 10Base-T1S vehicle Ethernet bus composed of a single pair of twisted-pair cables.

[0052] In one exemplary embodiment, such as Figure 2 As shown, an edge node-based installation information identification method is provided, which can be applied to... Figure 1 Taking any edge node in the edge network system of a vehicle as an example, this method can be implemented through the following steps:

[0053] Step S100: When power-on is detected, trigger the installation information recognition command of the edge node to obtain the first multi-source feature data corresponding to the edge node.

[0054] Specifically, when the RCP control chip in the edge node detects its own power-on, it can automatically trigger the edge node's installation information identification command, begin executing the edge node's installation information identification process, and coordinate the data acquisition modules within the edge node, such as the temperature acquisition unit, vibration acquisition unit, impedance detection unit, and electromagnetic detection unit, to work together. It sends data acquisition requests to these modules, instructing them to initialize themselves to clear stored historical data and begin acquiring corresponding data to obtain the first multi-source characteristic data corresponding to the edge node. This first multi-source characteristic data can include installation environment characteristic data, mounting base characteristic data, and installation stiffness characteristic data. The installation environment characteristic data can include the edge node's shell surface temperature, temperature change rate, and electromagnetic interference intensity, etc. The mounting base characteristic data can include the shell's impedance to ground, vibration response signal amplitude, vibration response signal frequency, and vibration response signal phase, etc. The installation stiffness characteristic data can include the vibration attenuation coefficient and installation stiffness, etc.

[0055] In this embodiment, the temperature acquisition unit is used to collect data such as the surface temperature and temperature change rate of the edge node shell; the vibration acquisition unit is used to collect data such as the amplitude, frequency, phase, vibration attenuation coefficient, and installation stiffness parameters of the vibration response signal; the impedance detection unit is used to collect data such as the impedance of the edge node shell to ground; and the electromagnetic detection unit is used to collect the electromagnetic interference intensity around the edge node. In addition, the vibration acquisition unit can also collect vibration transmission data during vehicle operation and calculate the vibration attenuation coefficient based on the vibration transmission coefficient. Simultaneously, it can send the vibration transmission data to the RCP control chip, which analyzes the vibration modes based on the vibration transmission data to obtain the installation stiffness parameters.

[0056] In practical applications, the temperature acquisition unit, vibration acquisition unit, impedance detection unit, and electromagnetic detection unit can collect corresponding data and send them to the RCP control chip. Among them, the installation stiffness in the first multi-source characteristic data can be calculated by the RCP control chip based on the vibration amplitude, vibration frequency, vibration phase, and / or vibration attenuation coefficient.

[0057] It should be noted that the aforementioned edge nodes can be installed at any location on the vehicle, and this embodiment of the application does not limit this.

[0058] Step S200: Based on the first multi-source feature data corresponding to the edge nodes inside the vehicle and the preset benchmark threshold library of node installation information, the installation information of the edge nodes is identified to determine the preliminary installation information of the edge nodes.

[0059] Specifically, the RCP control chip in the edge node can acquire a pre-trained recognition model, and then input the first multi-source feature data corresponding to the edge node in the vehicle and the preset benchmark threshold library of node installation information into the recognition model. After recognizing the installation information of the edge node, it outputs the preliminary installation information of the edge node.

[0060] Optionally, the above recognition model may be composed of at least one of the following: convolutional neural network model, fully connected neural network model, residual neural network model, long short-term memory neural network model, etc.

[0061] In practical applications, the RCP control chip in the edge node can perform comparison and matching processes based on the first multi-source feature data corresponding to the edge node in the vehicle and the preset benchmark threshold library of node installation information to complete the identification and processing of the edge node's installation information and obtain the preliminary installation information of the edge node.

[0062] In this embodiment, the preliminary installation information of the edge node may include at least two of the following: the installation location of the edge node on the vehicle, the material of the mounting base, and the installation method. The installation location may be in the engine compartment (environmental characteristics: high temperature, strong vibration, strong electromagnetic environment), the passenger compartment (environmental characteristics: normal temperature, weak vibration, weak electromagnetic environment), etc. The mounting base material may be a metal bracket (characterized by high conductivity, good grounding, and fast heat dissipation), a plastic component (characterized by medium conductivity, poor grounding, and moderate heat dissipation), or glass (characterized by low conductivity, no grounding, and poor heat dissipation), etc. The installation method may be screw fixing (characterized by high rigidity, good fastness, and fast vibration attenuation), clip fixing (characterized by medium rigidity, moderate fastness, and moderate vibration conduction), or adhesive fixing (characterized by low rigidity, easy attenuation of fastness, and strong vibration conduction), etc.

[0063] Step S300: Perform cross-validation based on different types of information in the preliminary installation information to determine the current installation information of the edge node.

[0064] The RCP control chip in the edge node can employ cross-validation to cross-validate different types of information in the initial installation information to obtain the current installation information of the edge node. Optionally, the aforementioned cross-validation method can be timeline cross-validation, logical consistency verification, reverse tracing verification, etc.

[0065] In addition, the RCP control chip can acquire a pre-trained algorithm model, then input the initial installation information into the algorithm model, perform cross-validation on different types of information in the initial installation information, and output the current installation information of the edge node.

[0066] It should be noted that, in order to ensure the accuracy of the installation information of the edge nodes, the above steps S100-S300 can be executed periodically. The execution cycle can be set according to actual needs, such as 3s, 5s, etc.

[0067] The technical solution in this application embodiment, upon detecting power-on, triggers an edge node installation information recognition command, acquires the first multi-source feature data corresponding to the edge node, and identifies the edge node installation information based on the first multi-source feature data corresponding to the edge node in the vehicle and a preset benchmark threshold library for node installation information. This identifies the preliminary installation information of the edge node, and performs cross-validation processing based on different types of information in the preliminary installation information to determine the current installation information of the edge node. This method can self-identify the edge node's installation information when the edge node is powered on, providing reliable information to improve the compatibility between the edge node and the vehicle. Furthermore, after identifying the edge node's installation information... Furthermore, the preliminary installation information needs to be cross-validated to determine the accuracy and reliability of the final installation information. In addition, the above method can self-identify the installation information of edge nodes, thereby improving the adaptability and reliability between edge nodes and vehicles based on the self-identification results. This enables edge nodes to meet the plug-and-play requirement, thereby improving the mass production efficiency of vehicles, reducing the production assembly error rate and cost, and adapting to the needs of standardized and large-scale vehicle production. It has extremely high industrial application value. Moreover, based on the self-identification results, it can provide installation information-related data support for the subsequent adaptive thermal management, vibration compensation, accuracy calibration, fault early warning and other functions of edge nodes, thereby improving the reliability and stability of the electronic and electrical architecture.

[0068] The following describes the process of identifying the installation information of edge nodes and determining their preliminary installation information based on the first multi-source feature data corresponding to the edge nodes within the vehicle and a preset benchmark threshold library of node installation information. In one embodiment, as... Figure 3 As shown, the process in step S200 above may include:

[0069] Step S201: Obtain the corresponding first benchmark threshold from the preset benchmark threshold library.

[0070] In practical applications, the edge node also includes a memory, and a preset benchmark threshold library is stored in the memory to ensure that the preset benchmark threshold library is not lost after the edge node loses power and is recharged. Simultaneously, the memory can also store the edge node's current installation information, current recognition status (e.g., successful or abnormal recognition), and historical recognition results.

[0071] Specifically, the RCP control chip in the edge node can call or load a preset benchmark threshold library from memory and obtain a first benchmark threshold from the preset benchmark threshold library. The first benchmark threshold can include multiple different types of benchmark thresholds, and the number of benchmark threshold types can be equal to the number of feature data types in the first multi-source feature data.

[0072] It should be noted that the first benchmark threshold in the preset benchmark threshold library can be calibrated based on a large amount of experimental data; the aforementioned preset benchmark threshold library may include an installation location benchmark threshold library, an installation base material benchmark threshold library, and an installation method benchmark threshold library. Specifically, the installation location benchmark threshold library may include benchmark thresholds for temperature range, vibration intensity range, and electromagnetic interference intensity range for different installation locations (engine compartment, passenger compartment, etc.); the installation base material benchmark threshold library may include benchmark thresholds for the range of shell-to-ground impedance and vibration response characteristic parameters for different base materials (metal, plastic, glass, etc.); and the installation method benchmark threshold library may include benchmark thresholds for vibration stiffness parameters and vibration attenuation coefficient ranges for different fixing methods (screw fixing, clip fixing, adhesive fixing, etc.).

[0073] Step S202: Based on the first benchmark threshold, threshold matching is performed on the first multi-source feature data to obtain the threshold matching result.

[0074] In practical applications, the RCP control chip can perform threshold matching on a first reference threshold and first multi-source feature data according to preset rules to obtain a threshold matching result. Optionally, the preset rules may include specific implementation strategies for threshold matching.

[0075] In addition, the RCP control chip can also acquire a pre-trained threshold matching model, and then input the first benchmark threshold and the first multi-source feature data into the threshold matching model for threshold matching, and output the threshold matching result.

[0076] In practical applications, the aforementioned first reference threshold may include the reference threshold in the installation location reference threshold library, the reference threshold in the installation base material reference threshold library, and the reference threshold in the installation method reference threshold library.

[0077] Specifically, the RCP control chip can perform threshold matching on the installation environment feature data in the first multi-source feature data based on the reference threshold in the installation position reference threshold library, perform threshold matching on the installation base feature data in the first multi-source feature data based on the reference threshold in the installation base material reference threshold library, and perform threshold matching on the installation stiffness feature data in the first multi-source feature data based on the reference threshold in the installation method reference threshold library, to obtain the threshold matching result.

[0078] Step S203: Determine the preliminary installation information of the edge nodes based on the threshold matching results.

[0079] Specifically, the RCP control chip can analyze and / or filter the threshold matching results to obtain preliminary installation information for the edge nodes. Alternatively, the RCP control chip can acquire a pre-trained algorithm model, input the threshold matching results into the algorithm model, and the algorithm model will output preliminary installation information for the edge nodes.

[0080] When identifying the installation location of edge nodes, the RCP control chip can perform threshold matching on the installation environment feature data in the first multi-source feature data based on the benchmark thresholds in the installation location benchmark threshold library. For example, the benchmark thresholds in the installation location benchmark threshold library include temperature thresholds, electromagnetic interference intensity thresholds, and temperature change rate thresholds. Taking a temperature threshold of 80~150℃ or -10~40℃, a temperature change rate threshold of 5℃ / min, and an electromagnetic interference intensity threshold of 100dBμV / m as examples, the RCP control chip can determine whether the temperature in the first multi-source feature data is within the temperature threshold of 80~150℃, whether the temperature change rate in the first multi-source feature data is greater than or equal to the temperature change rate threshold of 5℃ / min, and whether the electromagnetic interference intensity in the first multi-source feature data is greater than or equal to the electromagnetic interference intensity threshold of 100dBμV / m. If the temperature remains between 80 and 150°C, the temperature change rate is greater than or equal to 5°C / min, and the electromagnetic interference intensity is greater than or equal to 100 dBμV / m during the time required to acquire the first multi-source feature data, then the initial installation location of the edge node is determined to be the engine compartment; if the temperature remains between -10 and 40°C, the temperature change rate is less than or equal to 2°C / min, and the electromagnetic interference intensity is less than 50 dBμV / m during the time required to acquire the first multi-source feature data, then the initial installation location of the edge node is determined to be the passenger compartment; otherwise, the RCP control chip acquires the second multi-source feature data and performs a re-identification process.

[0081] Simultaneously, when identifying the mounting base material of the edge nodes, the RCP control chip can perform threshold matching on the mounting base feature data in the first multi-source feature data based on the benchmark thresholds in the mounting base material benchmark threshold library. For example, the benchmark thresholds in the mounting base material benchmark threshold library include the shell-to-ground impedance threshold and the vibration attenuation coefficient threshold. Taking a shell-to-ground impedance threshold of 10Ω, 100~1000Ω, or 1000Ω, and a vibration attenuation coefficient threshold of 0.4, 0.8, or 0.4~0.8 as examples, the RCP control chip can determine whether the shell-to-ground impedance in the first multi-source feature data is less than or equal to the shell-to-ground impedance threshold of 10Ω and whether the vibration attenuation coefficient in the first multi-source feature data is greater than or equal to the vibration attenuation coefficient threshold of 0.8. If the shell-to-ground impedance remains less than or equal to 10Ω and the vibration attenuation coefficient is greater than or equal to 0.8 within the time required to collect the first multi-source feature data, the RCP control chip can determine the appropriate threshold. If the initial mounting base material of the edge node is determined to be a metal base, and the inner shell impedance to ground remains between 100 and 1000 Ω and the vibration attenuation coefficient remains between 0.4 and 0.8 for the duration required to collect the first multi-source feature data, then the initial mounting base material of the edge node is determined to be a plastic base. If the inner shell impedance to ground remains greater than 1000 Ω and the vibration attenuation coefficient is less than 0.4 for the duration required to collect the first multi-source feature data, then the mounting base material of the edge node is determined to be a glass base. Furthermore, it can be determined whether the waveform of the vibration response signal is stable within the duration required to collect the first multi-source feature data. If it is stable, the initial mounting base material of the edge node is determined to be a glass base. Otherwise, the RCP control chip acquires the second multi-source feature data and performs a re-identification process.

[0082] In this embodiment, different reference thresholds are used for different mounting base materials; among them, the vibration response signal amplitude of metal base material is small and decays quickly, and the vibration attenuation coefficient threshold is set to 0.8; the vibration response signal amplitude of plastic base material is medium and decays moderately, and the vibration attenuation coefficient threshold is set to 0.4~0.8; the vibration response signal amplitude of glass base material is large and decays slowly, and the vibration attenuation coefficient threshold is set to 0.4.

[0083] In addition, when identifying the installation method of edge nodes, the RCP control chip can perform threshold matching on the installation stiffness feature data in the first multi-source feature data based on the benchmark threshold in the installation method benchmark threshold library. For example, the baseline thresholds in the installation method reference threshold library include installation stiffness parameter thresholds and vibration attenuation coefficient thresholds. Taking installation stiffness parameter thresholds equal to 1000 N / m, 500 N / m, or 500~1000 N / m, and vibration attenuation coefficient thresholds equal to 0.3, 0.7, or 0.3~0.7 as examples, the RCP control chip can determine whether the installation stiffness parameter in the first multi-source feature data is greater than or equal to the installation stiffness parameter threshold of 1000 N / m and whether the vibration attenuation coefficient in the first multi-source feature data is greater than or equal to the vibration attenuation coefficient threshold of 0.7. If the installation stiffness parameter is continuously greater than or equal to 1000 N / m and the vibration attenuation coefficient is greater than or equal to 0.7 within the time required to collect the first multi-source feature data, then the initial installation method of the edge node is determined to be screw fixing. If the installation stiffness parameter is continuously within 500~1000 N / m and the vibration attenuation coefficient is within 0.3~0.7 within the time required to collect the first multi-source feature data, then the edge node is determined to be screw fixing. The initial installation method for the edge node is snap-fit ​​fixing. If the installation stiffness parameter remains below 500Ω and the vibration attenuation coefficient is below 0.3 within the time required to collect the first multi-source feature data, the initial installation method for the edge node is determined to be adhesive fixing. Since the tightness of adhesive fixing is easily affected by high temperature and vibration (e.g., high temperature in the engine compartment accelerates adhesive aging), additional specialized monitoring logic is required to ensure the timeliness and accuracy of the identification results. Therefore, the stability of the vibration response signal amplitude and vibration attenuation coefficient can be monitored simultaneously within the time required to collect the first multi-source feature data. If a sudden change in the vibration response signal amplitude (change greater than or equal to 30%) is detected in the first multi-source feature data, and the vibration attenuation coefficient drops sharply (drop greater than or equal to 0.1), it can be determined that the adhesive is loose, and an installation status abnormality signal is output. This abnormality signal can also be reported to the central processing unit to provide a reference for subsequent maintenance. Otherwise, the RCP control chip acquires the second multi-source feature data and performs a re-identification process.

[0084] In the embodiments of this application, different reference thresholds are used for different installation methods. Among them, screw fixing has high rigidity and good fastening, and the vibration attenuation is fast during the transmission process. Correspondingly, the installation stiffness parameter threshold is set to 1000 N / m and the vibration attenuation coefficient threshold is set to 0.7. Clip fixing has medium rigidity and moderate fastening, and the vibration transmission attenuation degree is between screw fixing and adhesive fixing. Correspondingly, the installation stiffness parameter threshold is set to 500~1000 N / m and the vibration attenuation coefficient threshold is set to 0.3~0.7. Adhesive fixing has low rigidity and easy attenuation of fastening, and the vibration attenuation is slow during the transmission process. Correspondingly, the installation stiffness parameter threshold is set to 500 N / m and the vibration attenuation coefficient threshold is set to 0.3.

[0085] It should be noted that the order in which the installation location, mounting base material, and installation method of the edge node are identified can be set arbitrarily. However, in this embodiment, the order in which the installation location, mounting base material, and installation method of the edge node are identified can be set according to the identification weights of the installation location, mounting base material, and installation method.

[0086] In one embodiment, the process of determining the preliminary installation information of the edge nodes based on the threshold matching result in step S203 above may include:

[0087] If the threshold matching result shows that the first multi-source feature data matches the first benchmark threshold, then the preliminary installation information of the edge node is obtained. If the threshold matching result shows that the first multi-source feature data does not match the first benchmark threshold, then the second multi-source feature data corresponding to the edge node within the target sampling period is obtained, and the installation information of the edge node is identified based on the second multi-source feature data to obtain the preliminary installation information of the edge node. The duration of the target sampling period is longer than the duration of the sampling period corresponding to the first multi-source feature data.

[0088] It should be noted that the aforementioned first benchmark threshold can be a fixed value or a threshold range; this embodiment does not limit this. The duration of the target sampling period can be greater than the duration of the sampling period corresponding to the first multi-source feature data. To ensure the integrity and accuracy of the acquired multi-source feature data, the sampling period of the multi-source feature data can be set to a value greater than 5s, 8s, or 9s. For example, if the duration of the sampling period corresponding to the first multi-source feature data is 10s, the corresponding duration of the target sampling period is 20s; if the duration of the sampling period corresponding to the first multi-source feature data is 8s, the corresponding duration of the target sampling period is 15s.

[0089] In this embodiment of the application, if the threshold matching result is that the first multi-source feature data matches the first benchmark threshold, then the specific preliminary installation information of the edge node can be obtained.

[0090] Simultaneously, if the threshold matching result indicates a mismatch between the first multi-source feature data and the first benchmark threshold, the RCP control chip can acquire the second multi-source feature data corresponding to the edge nodes within the target sampling period, and re-execute the installation information identification process based on the second multi-source feature data, that is, re-execute the above steps S100-S300 based on the second multi-source feature data. Here, the second multi-source feature data corresponding to the edge nodes within the target sampling period can be understood as the multi-source feature data corresponding to the edge nodes acquired after extending the sampling period.

[0091] When re-executing the identification process, the newly collected second multi-source feature data is used. This newly collected second multi-source feature data can truly reflect the current installation status (such as changes in feature parameters caused by aging of adhesive or loosening of clips), thus improving the accuracy of the identification results.

[0092] It should be noted that if the installation information identification process is re-executed based on the second multi-source feature data, and the second multi-source feature data still fails to meet the threshold matching condition corresponding to the first benchmark threshold, then an abnormal installation position signal for the edge node will be output, and further cross-validation processing will be required.

[0093] The technical solution in this application embodiment obtains the corresponding first benchmark threshold from a preset benchmark threshold library, performs threshold matching on the first multi-source feature data based on the first benchmark threshold to obtain the threshold matching result, and determines the preliminary installation information of the edge node according to the threshold matching result. The above method does not require the participation of complex algorithms, thereby reducing the complexity of obtaining the preliminary installation information of the edge node, speeding up the acquisition of the preliminary installation information of the edge node, and improving the efficiency of obtaining the preliminary installation information of the edge node.

[0094] The following describes the process of cross-validating different types of information based on the preliminary installation information. In one embodiment, as... Figure 4 As shown, the process in step S300 above can be implemented in the following way:

[0095] Step S301: Based on the rationality rules of node installation, cross-validate different types of information in the preliminary installation information to obtain cross-validation results.

[0096] Specifically, the RCP control chip can acquire a pre-trained cross-validation model, and then input the rationality rules of node installation and the preliminary installation information of edge nodes into the cross-validation model. The cross-validation model performs cross-validation processing on different types of information in the preliminary installation information based on the rationality rules of node installation and outputs the cross-validation results.

[0097] Optionally, the cross-validation model described above may consist of at least one of the following: a fully connected neural network model, a long short-term memory neural network model, a residual neural network model, and a recurrent recurrent neural network model.

[0098] In this embodiment, the RCP control chip can directly perform cross-validation on different types of information in the preliminary installation information based on the rationality rules of node installation, so as to filter out information that does not conform to the rationality rules from the preliminary installation information and obtain the cross-validation results.

[0099] In practical applications, the above-mentioned rules for the rationality of node installation are also the rules for the rationality of edge node installation. These rules can be constructed based on industry common sense regarding vehicle installation scenarios. Optionally, the above-mentioned rules may include: screw fixing methods mostly use metal or plastic bases; adhesive fixing methods mostly use plastic or glass bases; passenger compartments can be adapted to three base materials (metal, plastic, and glass); plastic base materials in engine compartments are preferentially fixed with screws; glass base materials are mostly fixed with adhesives or clips; glass base materials cannot be used when the installation location is in the engine compartment (because the engine compartment is a high-temperature, strong vibration, and strong electromagnetic environment, and glass has poor heat dissipation, low rigidity, and no grounding, making it unsuitable for the usage requirements of this scenario); glass base materials cannot be used when the installation method is screw fixing (because screw fixing requires the base to achieve fastening, and glass is brittle and cannot withstand the pressure of screw tightening, making it easily damaged and not in line with actual installation specifications); metal base materials cannot be used when the installation method is adhesive fixing and the installation location is in the engine compartment.

[0100] For example, taking the reasonableness rule that glass base material cannot be used when the installation location is in the engine compartment as an example, if the preliminary installation information includes the installation location as the engine compartment and the installation base material as glass base, then the cross-validation result is determined to be cross-validation failure; taking the reasonableness rule that glass base material cannot be used when the installation location is in the engine compartment and the installation method is screw fixing as an example, if the preliminary installation information includes the installation base material as glass base and the installation method as screw fixing, then the cross-validation result is determined to be cross-validation failure; taking the reasonableness rule that metal base material cannot be used when the installation method is adhesive fixing and the installation location is in the engine compartment as an example, if the preliminary installation information includes the installation location as the engine compartment, the installation base material as metal base, and the installation method as adhesive fixing, then the cross-validation result is determined to be cross-validation failure.

[0101] Step S302: Determine the current installation information of the edge nodes based on the cross-validation results and preliminary installation information.

[0102] Specifically, the RCP control chip can analyze and process the cross-validation results and preliminary installation information to obtain the current installation information of the edge nodes.

[0103] The cross-validation results can include cross-validation pass and cross-validation fail. In this embodiment, the preliminary installation information that passes cross-validation can be determined as the current installation information of the edge node. Otherwise, if the preliminary installation information fails cross-validation, multi-source feature data can be re-collected, and steps S100-S300 can be executed based on the re-collected multi-source feature data. After re-executing N times consecutively, if cross-validation continues to fail, an identification anomaly signal can be sent to the central processing unit so that the central processing unit controls the edge node to enter a safe mode. Optionally, N can be greater than 2, and this value can be set according to actual needs.

[0104] The technical solution in this application embodiment can perform cross-validation processing on different types of information in the preliminary installation information based on the rationality rules of node installation to obtain cross-validation results. Based on the cross-validation results and the preliminary installation information, the current installation information of the edge node is determined, so that the final obtained current installation information conforms to the rationality rules of the edge node, avoiding misidentification and improving the accuracy of the identification results.

[0105] In some scenarios, the baseline threshold required for threshold matching can be optimized and updated to make the threshold matching results more realistic, maintain the real-time validity of the baseline threshold, and adapt to changes in the installation status during long-term vehicle use (such as adhesive aging or loosening of clips), ensuring long-term stability and accuracy of recognition precision. In one embodiment, after performing the above step S300, as... Figure 5 As shown, the above method may further include the following steps:

[0106] Step S400: After determining the current installation information of the edge node, obtain the third multi-source feature data corresponding to the edge node.

[0107] In practical applications, the preset benchmark threshold library can be periodically optimized and updated to improve recognition accuracy and adapt to changes in installation status during long-term vehicle use, ensuring stable recognition accuracy over the long term and meeting the installation requirements of different vehicle models and layouts. Correspondingly, the RCP control chip, upon determining the current installation information of the edge node, can acquire the third multi-source feature data corresponding to the edge node. Optionally, the sampling period of the aforementioned third multi-source feature data may be equal to or different from that of the first multi-source feature data; this embodiment does not limit this aspect.

[0108] The cycle for optimizing and updating the preset benchmark threshold library can be 12 hours, 18 hours, etc. In this embodiment, 24 hours is used as an example for explanation.

[0109] Step S500: Update the preset benchmark threshold library based on the third multi-source feature data to obtain the updated benchmark threshold library.

[0110] In practical applications, the RCP control chip can acquire a threshold library update model, then input both the third multi-source feature data and the preset benchmark threshold library into the threshold library update model. Based on the third multi-source feature data, the preset benchmark threshold library is updated, and the updated benchmark threshold library is output. Optionally, the above-mentioned update of the preset benchmark threshold library can be understood as the process of updating the first benchmark threshold in the preset benchmark threshold library.

[0111] In one embodiment, the process of updating the preset benchmark threshold library based on the third multi-source feature data to obtain the updated benchmark threshold library in step S500 above may include: in response to the correction instruction of the preset benchmark threshold library sent by the central processing unit in the edge network system, correcting the preset benchmark threshold library to obtain the updated benchmark threshold library.

[0112] It should be noted that, in addition to periodically and proactively optimizing and updating the preset benchmark threshold library, it can also be passively updated to improve the timeliness and comprehensiveness of the optimization and update. Specifically, the central processing unit in the edge network system can also send a correction instruction for the preset benchmark threshold library to the RCP control chip. Correspondingly, the RCP control chip responds to the correction instruction for the preset benchmark threshold library sent by the central processing unit in the edge network system, corrects the preset benchmark threshold library, and obtains the updated benchmark threshold library.

[0113] It should be noted that the central processing unit can generate correction instructions for a preset baseline threshold library based on the vehicle's operating conditions (movement, driving process, and usage scenario) and the vehicle's layout requirements, triggering real-time optimization updates.

[0114] The method of modifying the preset benchmark threshold library is the same as the method of updating the preset benchmark threshold library in step S500 above, and this embodiment of the application does not limit this.

[0115] Step S600: Based on the second benchmark threshold and the third multi-source feature data in the updated benchmark threshold library, the installation information of the edge nodes is re-identified to obtain the re-identification accuracy.

[0116] Specifically, the RCP control chip can perform the above steps S100-S300 based on the second reference threshold and the third multi-source feature data in the updated reference threshold library to optimize the installation information identification process, re-identify the installation information of the edge nodes to complete the closed-loop processing, and obtain the re-identification accuracy after re-identification.

[0117] In practical applications, the second benchmark threshold can cover the first benchmark threshold among the preset benchmark thresholds.

[0118] Step S700: Based on the re-identification accuracy, verify the re-identification process of the installation information of the edge nodes to obtain the process verification result.

[0119] Furthermore, the RCP control chip can compare the re-identification accuracy with the preset accuracy to verify the re-identification process of the installation information of the edge nodes and obtain the process verification result.

[0120] If the re-identification accuracy rate is greater than the preset accuracy rate, the process verification result can be determined as the re-identification process of the installation information of the edge node has passed, indicating that the updated benchmark threshold library can be used normally in the identification process; otherwise, the process verification result can be determined as the re-identification process of the installation information of the edge node has failed.

[0121] Optionally, the aforementioned preset accuracy rate can be user-defined or determined based on historical experience values.

[0122] In practical applications, to reduce the amount of data processed when updating the preset benchmark threshold library, the preset benchmark threshold library can be verified before updating. Only when an update is determined to be necessary should the update process begin. This process is described below. In one embodiment, after executing the process in step S400 above, as... Figure 6 As shown, the above method also includes:

[0123] Step S800: Perform deviation processing on the first multi-source feature data and the third multi-source feature data to obtain the deviation value between the first multi-source feature data and the third multi-source feature data.

[0124] Specifically, the RCP control chip can directly update the preset benchmark threshold library based on third-party multi-source feature data.

[0125] In this embodiment, the RCP control chip can first subtract the first multi-source feature data and the third multi-source feature data to achieve deviation processing and obtain the deviation value between the first multi-source feature data and the third multi-source feature data.

[0126] Step S900: If the deviation value does not meet the preset deviation range, perform the step of updating the preset benchmark threshold library based on the third multi-source feature data.

[0127] In practical applications, the RCP control chip can indicate that the installation information of the edge node has changed (such as changes in installation status: loosening of the adhesive leading to a decrease in the vibration attenuation coefficient; changes in environment: long-term high temperature in the engine compartment leading to a decrease in temperature threshold adaptability) when the deviation value does not meet the preset deviation range. In such cases, it is necessary to perform the step of updating the preset benchmark threshold library based on third-party multi-source feature data.

[0128] Optionally, the aforementioned preset deviation range can be user-defined or determined based on historical experience values.

[0129] In this embodiment, the preset deviation range can be a deviation value less than or equal to a preset percentage. Optionally, the preset percentage can be equal to 3%, 5%, 6%, etc., and this value can be flexibly set according to the actual situation.

[0130] In addition, the RCP control chip can indicate that there is no need to update the preset benchmark threshold library if the deviation value meets the preset deviation range.

[0131] The technical solution in this application embodiment, after determining the current installation information of the edge node, obtains the third multi-source feature data corresponding to the edge node, updates the preset benchmark threshold library based on the third multi-source feature data to obtain the updated benchmark threshold library, and re-identifies the installation information of the edge node based on the second benchmark threshold and the third multi-source feature data in the updated benchmark threshold library, obtains the re-identification accuracy, and verifies the re-identification process of the edge node's installation information based on the re-identification accuracy to obtain the process verification result. The above method can optimize and update the benchmark threshold required for threshold matching, making the threshold matching result more realistic, improving the adaptability of the recognition algorithm to different vehicle models and different layouts, and improving the accuracy of the recognition result, so as to provide reliable data support for subsequent applications. At the same time, the above method can identify the installation information of the edge node through cross-validation mechanism and benchmark threshold dynamic optimization mechanism, which can improve the accuracy and longevity of installation information recognition.

[0132] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0133] Based on the same inventive concept, this application also provides an edge node-based installation information identification device for implementing the above-described edge node-based installation information identification method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more edge node-based installation information identification device embodiments provided below can be found in the limitations of the edge node-based installation information identification method described above, and will not be repeated here.

[0134] In one exemplary embodiment, such as Figure 7 As shown, an edge node-based installation information identification device is provided, applicable to any edge node within a vehicle's edge network system. The device includes: a data acquisition module 11, an identification module 12, and a cross-validation module 13, wherein:

[0135] The data acquisition module 11 is used to trigger the installation information identification instruction of the edge node when power-on is detected, and to acquire the first multi-source feature data corresponding to the edge node.

[0136] The identification module 12 is used to identify the installation information of the edge nodes based on the first multi-source feature data corresponding to the edge nodes in the vehicle and the preset benchmark threshold library of node installation information, and to determine the preliminary installation information of the edge nodes.

[0137] The cross-validation module 13 is used to perform cross-validation processing based on different types of information in the preliminary installation information to determine the current installation information of the edge node.

[0138] The installation information identification device based on edge nodes provided in this application can be used to execute the technical solutions in the above-described installation information identification method based on edge nodes in this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0139] In one embodiment, the identification module 12 includes: an acquisition unit, a threshold matching unit, and a first determination unit, wherein:

[0140] The acquisition unit is used to acquire the corresponding first benchmark threshold from a preset benchmark threshold library;

[0141] The threshold matching unit is used to perform threshold matching on the first multi-source feature data based on a first benchmark threshold to obtain the threshold matching result;

[0142] The first determining unit is used to determine the preliminary installation information of the edge nodes based on the threshold matching results.

[0143] The installation information identification device based on edge nodes provided in this application can be used to execute the technical solutions in the above-described installation information identification method based on edge nodes in this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0144] In one embodiment, the first determining unit is specifically used for:

[0145] If the threshold matching result is that the first multi-source feature data matches the first benchmark threshold, then the preliminary installation information of the edge node is obtained;

[0146] If the threshold matching result is that the first multi-source feature data does not match the first benchmark threshold, then the second multi-source feature data corresponding to the edge node within the target sampling period is obtained, and the installation information of the edge node is identified based on the second multi-source feature data to obtain the preliminary installation information of the edge node; the duration of the target sampling period is greater than the duration of the sampling period corresponding to the first multi-source feature data.

[0147] The installation information identification device based on edge nodes provided in this application can be used to execute the technical solutions in the above-described installation information identification method based on edge nodes in this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0148] In one embodiment, the cross-validation module 13 includes: a cross-validation unit and a first determination unit, wherein:

[0149] Based on the rationality rules of node installation, cross-validation is performed on different types of information in the initial installation information to obtain cross-validation results;

[0150] Based on the cross-validation results and preliminary installation information, determine the current installation information of the edge nodes.

[0151] The installation information identification device based on edge nodes provided in this application can be used to execute the technical solutions in the above-described installation information identification method based on edge nodes in this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0152] In one embodiment, the edge node-based installation information identification device further includes: an acquisition module, an update module, a re-identification module, and a process verification module, wherein:

[0153] The acquisition module is used to acquire the third multi-source feature data corresponding to the edge node after determining the current installation information of the edge node;

[0154] The update module is used to update the preset benchmark threshold library based on the third multi-source feature data to obtain the updated benchmark threshold library.

[0155] The re-identification module is used to re-identify the installation information of edge nodes based on the second benchmark threshold and the third multi-source feature data in the updated benchmark threshold library, and obtain the re-identification accuracy.

[0156] The process verification module is used to verify the re-identification process of the installation information of the edge nodes based on the re-identification accuracy, and obtain the process verification result.

[0157] The installation information identification device based on edge nodes provided in this application can be used to execute the technical solutions in the above-described installation information identification method based on edge nodes in this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0158] In one embodiment, the edge node-based installation information identification device further includes: a deviation processing module and an execution module, wherein:

[0159] The deviation processing module is used to perform deviation processing based on the first multi-source feature data and the third multi-source feature data to obtain the deviation value between the first multi-source feature data and the third multi-source feature data.

[0160] The execution module is used to perform the step of updating the preset benchmark threshold library based on third-party multi-source feature data when the deviation value does not meet the preset deviation range.

[0161] The installation information identification device based on edge nodes provided in this application can be used to execute the technical solutions in the above-described installation information identification method based on edge nodes in this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0162] In one embodiment, the update module is specifically used for:

[0163] In response to the correction instruction of the preset benchmark threshold library sent by the central processing unit in the edge network system, the preset benchmark threshold library is corrected to obtain the updated benchmark threshold library.

[0164] The installation information identification device based on edge nodes provided in this application can be used to execute the technical solutions in the above-described installation information identification method based on edge nodes in this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0165] Each module in the aforementioned edge node-based installation information identification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0166] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores first, second, and third multi-source feature data corresponding to edge nodes. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements an edge node-based installation information identification method.

[0167] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0168] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the methods of any of the above embodiments.

[0169] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods of any of the above embodiments.

[0170] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods of any of the above embodiments.

[0171] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one of relational databases and non-relational databases. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0173] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for identifying installation information based on edge nodes, characterized in that, The method is applied to any edge node within a vehicle edge network system; the method includes: Upon detecting power-on, an installation information identification command for the edge node is triggered to obtain the first multi-source feature data corresponding to the edge node; Based on the first multi-source feature data corresponding to the edge nodes inside the vehicle and the preset benchmark threshold library of node installation information, the installation information of the edge nodes is identified to determine the preliminary installation information of the edge nodes. Cross-validation is performed on different types of information in the preliminary installation information to determine the current installation information of the edge node.

2. The method according to claim 1, characterized in that, The step of identifying the installation information of the edge nodes based on the first multi-source feature data corresponding to the edge nodes in the vehicle and the preset benchmark threshold library of node installation information, and determining the preliminary installation information of the edge nodes, includes: Obtain the corresponding first benchmark threshold from the preset benchmark threshold library; Based on the first benchmark threshold, threshold matching is performed on the first multi-source feature data to obtain the threshold matching result; Based on the threshold matching results, the preliminary installation information of the edge nodes is determined.

3. The method according to claim 2, characterized in that, The step of determining the preliminary installation information of the edge node based on the threshold matching result includes: If the threshold matching result is that the first multi-source feature data matches the first benchmark threshold, then the preliminary installation information of the edge node is obtained; If the threshold matching result is that the first multi-source feature data does not match the first benchmark threshold, then the second multi-source feature data corresponding to the edge node within the target sampling period is obtained, and the installation information of the edge node is identified according to the second multi-source feature data to obtain the preliminary installation information of the edge node; the duration of the target sampling period is greater than the duration of the sampling period corresponding to the first multi-source feature data.

4. The method according to any one of claims 1-3, characterized in that, The process of cross-validating different types of information in the preliminary installation information to determine the current installation information of the edge node includes: Based on the rationality rules of node installation, cross-validation is performed on different types of information in the preliminary installation information to obtain cross-validation results; Based on the cross-validation results and the preliminary installation information, the current installation information of the edge node is determined.

5. The method according to any one of claims 1-3, characterized in that, The method further includes: Once the current installation information of the edge node is determined, the third multi-source feature data corresponding to the edge node is obtained; The preset benchmark threshold library is updated based on the third multi-source feature data to obtain the updated benchmark threshold library; Based on the second benchmark threshold in the updated benchmark threshold library and the third multi-source feature data, the installation information of the edge node is re-identified to obtain the re-identification accuracy. Based on the re-identification accuracy, the re-identification process of the installation information of the edge nodes is verified to obtain the process verification result.

6. The method according to claim 5, characterized in that, The method further includes: Based on the first multi-source feature data and the third multi-source feature data, a deviation processing is performed to obtain the deviation value between the first multi-source feature data and the third multi-source feature data. If the deviation value does not meet the preset deviation range, the step of updating the preset benchmark threshold library based on the third multi-source feature data is performed.

7. The method according to claim 5, characterized in that, The step of updating the preset benchmark threshold library based on the third multi-source feature data to obtain the updated benchmark threshold library includes: In response to a correction instruction for the preset benchmark threshold library sent by the central processing unit in the edge network system, the preset benchmark threshold library is corrected to obtain the updated benchmark threshold library.

8. An installation information identification device based on edge nodes, characterized in that, The device includes: The data acquisition module is used to trigger an installation information identification command for the edge node when power-on is detected, and to acquire the first multi-source feature data corresponding to the edge node. The identification module is used to identify the installation information of the edge nodes based on the first multi-source feature data corresponding to the edge nodes in the vehicle and a preset benchmark threshold library of node installation information, and to determine the preliminary installation information of the edge nodes. The cross-validation module is used to perform cross-validation processing based on different types of information in the preliminary installation information to determine the current installation information of the edge node.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images