Internet of vehicles data abnormity early warning system and method based on edge computing chip

Abstract

The invention discloses a car networking data abnormity early warning system and method based on an edge computing chip. Comprising a data acquisition module, a data preprocessing module, an edge computing chip core processing module, a data caching module, a network communication module, a cloud server management module, a user interaction module, an early warning strategy configuration module, a data security encryption module and a power management module. According to the invention, data is processed and analyzed in real time at a place close to a data source by using the localized computing capability of the edge computing chip, so that the delay of data transmission is greatly reduced, and data abnormity can be found in time and early warning can be given out. The flow of uploading the data to the cloud and the consumption of computing resources are reduced, and the operation cost of the system is reduced. And the data security encryption module encrypts the data to ensure the security and privacy of the data.

Description

Technical Field

[0001] The present invention relates to the field of vehicle networking technology, and specifically to a vehicle networking data anomaly warning system and method based on edge computing chips. Background Art

[0002] With the rapid development of connected vehicle (IoV) technology, data exchange between vehicles and the outside world is becoming increasingly frequent, and the amount of data generated is exploding. However, in IoV environments, data anomalies often occur due to factors such as sensor failures, communication interference, and malicious attacks. These anomalies can lead to vehicle control errors, traffic congestion, and safety accidents. Traditional IoV data anomaly warning methods typically upload data to the cloud for processing and analysis. This not only increases data transmission latency and costs, but can also prevent timely detection of data anomalies when the network is unstable. Edge computing chips, with their localized computing and real-time processing capabilities, can rapidly process and analyze data close to the data source. Therefore, using edge computing chips to build an IoV data anomaly warning system has important practical significance. Summary of the Invention

[0003] The purpose of the present invention is to provide a vehicle network data anomaly warning system and method based on edge computing chips to solve the problems raised in the above background technology.

[0004] To achieve the above objectives, the present invention provides the following technical solutions: an IoV data anomaly warning system based on an edge computing chip, comprising a data acquisition module, a data preprocessing module, an edge computing chip core processing module, a data cache module, a network communication module, a cloud server management module, a user interaction module, an early warning strategy configuration module, a data security encryption module, and a power management module;

[0005] The data acquisition module is used to collect various data in the Internet of Vehicles;

[0006] The data preprocessing module preprocesses the raw data collected by the data acquisition module, including data cleaning, data conversion, and data normalization operations;

[0007] The edge computing chip core processing module performs real-time analysis and processing on the pre-processed data based on the edge computing chip;

[0008] The data cache module is used to cache the intermediate data and historical data generated during the processing of the edge computing chip core processing module for subsequent query and analysis;

[0009] The network communication module is responsible for realizing communication between the edge computing chip and the cloud server, other vehicles and user terminals;

[0010] The cloud server management module is used to manage cloud server resources and store a large amount of historical data and algorithm models;

[0011] The user interaction module provides an interface for users to interact with the system, through which users can view the real-time data, abnormal warning information, and historical data statistics of the vehicle;

[0012] The warning strategy configuration module allows users to configure different warning strategies according to different vehicle types, usage scenarios and user needs;

[0013] The data security encryption module performs secure encryption processing on the data in the Internet of Vehicles to ensure the security and privacy of the data during collection, transmission, storage and processing;

[0014] The power management module is responsible for providing a stable power supply for the entire system, and managing and optimizing the power supply of the system.

[0015] Preferably, the various data of the data acquisition module include the vehicle's own sensor data (such as vehicle speed, acceleration, engine speed, tire pressure, fuel consumption, etc.), vehicle-mounted camera data, vehicle-mounted radar data, vehicle-to-vehicle communication data (V2V), and vehicle-to-infrastructure communication data (V2I); through various sensors and communication interfaces, it connects with various subsystems of the vehicle and the external Internet of Vehicles environment to obtain data in real time, and transmits the collected data in the form of raw data to the data preprocessing module.

[0016] Preferably, data cleaning in the data preprocessing module is to remove noise, duplicate data and invalid data from the data, and filter out data beyond a reasonable range by setting a threshold; data conversion is to convert data in different formats into a unified format for subsequent processing; data normalization is to scale the data to a specific range to improve the accuracy and efficiency of the algorithm; in the data cleaning process, the mean filtering algorithm is used to denoise the sensor data, and its formula is:

[0017]

[0018] Among them, x i Represents the i-th data in the original data sequence, y i Represents the i-th data after filtering, and n represents the half-width of the filtering window.

[0019] Preferably, the core processing module of the edge computing chip integrates a variety of data anomaly detection algorithms, including statistical-based methods and machine learning-based methods (such as support vector machines and neural networks); the above algorithms are used to monitor the data in real time to determine whether there are anomalies in the data; at the same time, according to the warning rules set by the warning strategy configuration module, a corresponding warning signal is generated; the statistical-based method is the Z-score method. In the anomaly detection based on the Z-score method, the calculation formula is:

[0020]

[0021] Among them, x represents the data to be detected, μ represents the mean of the data, and σ represents the standard deviation of the data; when |Z| exceeds the set threshold, the data is judged to be abnormal data.

[0022] Preferably, the data cache module uses a high-speed cache chip or a memory chip to achieve fast storage and reading of data; at the same time, the data cache module manages the cached data, for example, eliminating and updating data according to the timestamp and importance of the data;

[0023] The network communication module supports multiple communication protocols, including but not limited to 4G, 5G, Wi-Fi, Bluetooth, and DSRC dedicated short-range communication, and can select appropriate communication protocols according to different communication scenarios to ensure reliable data transmission; when communicating with the cloud server, the network communication module uploads abnormal data and related information detected by the edge computing chip core processing module to the cloud server, and at the same time receives updated algorithm models and early warning strategy instructions issued by the cloud server.

[0024] Preferably, the cloud server management module conducts in-depth analysis and mining of the massive data in the Internet of Vehicles, and continuously optimizes the anomaly detection algorithm in the core processing module of the edge computing chip through big data analysis and machine learning technology, thereby improving the detection accuracy and adaptability of the system; at the same time, the cloud server management module provides users with data query, statistical analysis, and system management services;

[0025] In the user interaction module, users can also set and adjust the early warning strategy, such as setting the threshold for anomaly detection, selecting anomaly detection algorithm, and setting the early warning notification method (such as sound alarm, SMS notification, APP push, etc.).

[0026] Preferably, the warning strategy configuration module can set the parameters of anomaly detection (such as thresholds, window sizes, detection cycles, etc.), warning levels (such as level one warning, level two warning, level three warning), warning notification methods and recipients; the warning strategy configuration module stores the warning strategy set by the user in the system configuration file and passes it to the edge computing chip core processing module so that it can perform anomaly detection and warning according to the configured warning strategy.

[0027] Preferably, the data security encryption module uses an encryption algorithm (such as AES, RSA) to encrypt and decrypt data, and at the same time performs identity authentication and authorization on the communication process to prevent data from being maliciously tampered with, stolen and forged;

[0028] The power management module can detect the power supply status (such as voltage, current, and power consumption) and adjust the power output according to the system's operating status to achieve energy conservation and consumption reduction. For example, when the vehicle is turned off, the power management module can automatically switch to low-power mode to extend the system's standby time.

[0029] The early warning method of the Internet of Vehicles data anomaly early warning system based on the edge computing chip includes the following steps:

[0030] Step 1: Data acquisition: The data acquisition module collects data from the Internet of Vehicles in real time through various sensors and communication interfaces, and transmits the raw data to the data preprocessing module;

[0031] Step 2: Data preprocessing: The data preprocessing module cleans, converts, and normalizes the raw data to remove noise and invalid information, and converts the data into a format suitable for edge computing chip processing.

[0032] Step 3: Data anomaly detection: The edge computing chip core processing module analyzes and detects the pre-processed data in real time based on the warning strategy and anomaly detection algorithm configured in the warning strategy configuration module to determine whether the data is anomaly.

[0033] Step 4: Early warning processing: If data anomalies are detected, the edge computing chip core processing module generates a corresponding early warning signal according to the early warning strategy, and sends an early warning notification to the user through the user interaction module. At the same time, the abnormal data and related information are uploaded to the cloud server management module through the network communication module;

[0034] Step 5: Data caching and storage: The data caching module caches intermediate data and historical data during the processing process, and the cloud server management module stores massive amounts of historical data and algorithm models for subsequent query, analysis, and model optimization;

[0035] Step 6: Configure and Update Warning Strategies: Users set and adjust warning strategies through the user interaction module. The warning strategy configuration module transmits the configured warning strategies to the edge computing chip's core processing module. Simultaneously, the cloud server management module automatically updates the anomaly detection algorithms and warning strategies in the edge computing chip's core processing module based on big data analysis and machine learning results.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] This invention leverages the localized computing power of edge computing chips to process and analyze data in real time, close to the data source. This significantly reduces data transmission latency, enabling timely detection of data anomalies and the issuance of early warnings. This reduces the amount of data traffic and computing resource consumption required to upload data to the cloud, lowering the system's operating costs. The data security encryption module encrypts data to ensure its security and privacy. Users can configure early warning strategies based on their needs, and the cloud server management module continuously optimizes anomaly detection algorithms to improve the system's detection accuracy and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a system principle diagram of the present invention;

[0039] Figure 2 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0041] See also Figure 1-2 , the present invention provides an Internet of Vehicles data anomaly warning system based on an edge computing chip, including a data acquisition module, a data preprocessing module, an edge computing chip core processing module, a data cache module, a network communication module, a cloud server management module, a user interaction module, a warning strategy configuration module, a data security encryption module and a power management module;

[0042] The data acquisition module is used to collect various data in the Internet of Vehicles;

[0043] The data preprocessing module preprocesses the raw data collected by the data acquisition module, including data cleaning, data conversion, and data normalization operations;

[0044] The edge computing chip core processing module performs real-time analysis and processing of pre-processed data based on the edge computing chip;

[0045] The data cache module is used to cache the intermediate data and historical data generated during the processing of the core processing module of the edge computing chip for subsequent query and analysis;

[0046] The network communication module is responsible for realizing communication between the edge computing chip and the cloud server, other vehicles and user terminals;

[0047] The cloud server management module is used to manage cloud server resources and store large amounts of historical data and algorithm models;

[0048] The user interaction module provides an interface for users to interact with the system, through which users can view the vehicle's real-time data, abnormal warning information, and historical data statistics;

[0049] The warning strategy configuration module allows users to configure different warning strategies based on different vehicle types, usage scenarios and user needs;

[0050] The data security encryption module securely encrypts the data in the Internet of Vehicles to ensure the security and privacy of the data during collection, transmission, storage and processing;

[0051] The power management module is responsible for providing a stable power supply for the entire system, while managing and optimizing the system's power supply.

[0052] The data acquisition module collects various data, including the vehicle's own sensor data (such as vehicle speed, acceleration, engine speed, tire pressure, fuel consumption, etc.), on-board camera data, on-board radar data, vehicle-to-vehicle communication data (V2V), and vehicle-to-infrastructure communication data (V2I); it connects with the vehicle's various subsystems and the external Internet of Vehicles environment through various sensors and communication interfaces to obtain data in real time, and transmits the collected data in the form of raw data to the data preprocessing module.

[0053] In the data preprocessing module, data cleaning is to remove noise, duplicate data, and invalid data from the data, and filter out data that exceeds a reasonable range by setting a threshold; data conversion is to convert data in different formats into a unified format for subsequent processing; data normalization is to scale the data to a specific range to improve the accuracy and efficiency of the algorithm; in the data cleaning process, the mean filter algorithm is used to denoise the sensor data, and its formula is:

[0054]

[0055] Among them, x iRepresents the i-th data in the original data sequence, y i Represents the i-th data after filtering, and n represents the half-width of the filtering window.

[0056] The core processing module of the edge computing chip integrates a variety of data anomaly detection algorithms, including statistical-based methods and machine learning-based methods (such as support vector machines and neural networks). These algorithms monitor data in real time to determine whether there are anomalies in the data. At the same time, according to the warning rules set by the warning strategy configuration module, corresponding warning signals are generated. The statistical-based method is the Z-score method. In the anomaly detection based on the Z-score method, the calculation formula is:

[0057]

[0058] Among them, x represents the data to be detected, μ represents the mean of the data, and σ represents the standard deviation of the data; when |Z| exceeds the set threshold, the data is judged to be abnormal data.

[0059] The data cache module uses a high-speed cache chip or memory chip to achieve fast data storage and reading. At the same time, the data cache module manages the cached data, such as eliminating and updating data according to the data's timestamp and importance.

[0060] Network communication module: supports multiple communication protocols, including but not limited to 4G, 5G, Wi-Fi, Bluetooth, and DSRC dedicated short-range communication. It can select appropriate communication protocols according to different communication scenarios to ensure reliable data transmission. When communicating with the cloud server, the network communication module uploads abnormal data and related information detected by the core processing module of the edge computing chip to the cloud server, and at the same time receives updated algorithm models and early warning strategy instructions issued by the cloud server.

[0061] The cloud server management module conducts in-depth analysis and mining of massive amounts of data in the Internet of Vehicles. Through big data analysis and machine learning technologies, it continuously optimizes the anomaly detection algorithm in the core processing module of the edge computing chip, improving the detection accuracy and adaptability of the system. At the same time, the cloud server management module provides users with data query, statistical analysis, and system management services.

[0062] In the user interaction module, users can also set and adjust early warning strategies, such as setting anomaly detection thresholds, selecting anomaly detection algorithms, and setting early warning notification methods (such as sound alarms, SMS notifications, APP push, etc.).

[0063] The early warning strategy configuration module can set the parameters of anomaly detection (such as thresholds, window sizes, detection cycles, etc.), warning levels (such as level one warning, level two warning, level three warning), warning notification methods, and recipients; the early warning strategy configuration module stores the warning strategy set by the user in the system configuration file and passes it to the core processing module of the edge computing chip so that it can perform anomaly detection and warning according to the configured warning strategy.

[0064] The data security encryption module uses encryption algorithms (such as AES, RSA) to encrypt and decrypt data, and performs identity authentication and authorization on the communication process to prevent data from being maliciously tampered with, stolen, and forged;

[0065] The power management module monitors the power supply status (such as voltage, current, and power level) and adjusts the power output based on the system's operating state, thereby saving energy and reducing consumption. For example, when the vehicle is turned off, the power management module can automatically switch to low-power mode to extend the system's standby time.

[0066] The early warning method of the Internet of Vehicles data anomaly early warning system based on the edge computing chip includes the following steps:

[0067] Step 1: Data acquisition: The data acquisition module collects data from the Internet of Vehicles in real time through various sensors and communication interfaces, and transmits the raw data to the data preprocessing module;

[0068] Step 2: Data preprocessing: The data preprocessing module cleans, converts, and normalizes the raw data to remove noise and invalid information, and converts the data into a format suitable for edge computing chip processing.

[0069] Step 3: Data anomaly detection: The edge computing chip core processing module analyzes and detects the pre-processed data in real time based on the warning strategy and anomaly detection algorithm configured in the warning strategy configuration module to determine whether the data is anomaly.

[0070] Step 4: Early warning processing: If data anomalies are detected, the edge computing chip core processing module generates a corresponding early warning signal according to the early warning strategy, and sends an early warning notification to the user through the user interaction module. At the same time, the abnormal data and related information are uploaded to the cloud server management module through the network communication module;

[0071] Step 5: Data caching and storage: The data caching module caches intermediate data and historical data during the processing process, and the cloud server management module stores massive amounts of historical data and algorithm models for subsequent query, analysis, and model optimization;

[0072] Step 6: Configure and Update Warning Strategies: Users set and adjust warning strategies through the user interaction module. The warning strategy configuration module transmits the configured warning strategies to the edge computing chip's core processing module. Simultaneously, the cloud server management module automatically updates the anomaly detection algorithms and warning strategies in the edge computing chip's core processing module based on big data analysis and machine learning results.

[0073] Example:

[0074] The data acquisition module collects real-time vehicle operating data and external data from the connected vehicle network through various onboard sensors (such as speed sensors, accelerometers, and tire pressure sensors) and communication interfaces (such as the CAN bus and Ethernet). The data preprocessing module cleans the collected raw data, removing obviously unreasonable data (such as data indicating a speed exceeding the vehicle's maximum design speed) and converting the data into a unified format, such as converting the output units of different sensors to standard units.

[0075] The core processing module of the edge computing chip uses a high-performance edge computing chip, such as the Nvidia Jetson series chip, to perform real-time anomaly detection on pre-processed data. Taking vehicle speed data as an example, the Z-score method is used for anomaly detection. First, the mean μ and standard deviation μ of the vehicle speed data over a period of time are calculated. Then, for each real-time collected vehicle speed data x, its Z-score value is calculated. When |Z| exceeds a set threshold (such as 3), the vehicle speed data is judged to be abnormal data and a warning signal is generated.

[0076] The warning signal is displayed on the vehicle's display screen via the user interaction module, and the driver is alerted by an audible alarm. Simultaneously, abnormal data and related information (such as vehicle location and timestamp) are uploaded to the cloud server management module via the network communication module for further analysis and processing.

[0077] Users can configure different warning strategies through the user interaction module, such as setting different speed anomaly detection thresholds for different driving scenarios (urban roads, highways). The warning strategy configuration module stores the user-defined strategies in the system and transmits them to the core processing module of the edge computing chip, enabling it to perform anomaly detection based on different strategies.

[0078] The data security encryption module encrypts data during transmission and storage, for example, using the AES encryption algorithm to ensure data security. The power management module automatically adjusts the system's operating mode based on the vehicle's power status, operating normally when the vehicle is started and entering low-power mode when the vehicle is turned off to conserve power.

[0079] This invention leverages the localized computing power of edge computing chips to process and analyze data in real time, close to the data source. This significantly reduces data transmission latency, enabling timely detection of data anomalies and the issuance of early warnings. This reduces the amount of data traffic and computing resource consumption required to upload data to the cloud, lowering the system's operating costs. The data security encryption module encrypts data to ensure its security and privacy. Users can configure early warning strategies based on their needs, and the cloud server management module continuously optimizes anomaly detection algorithms to improve the system's detection accuracy and adaptability.

[0080] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The IoV data anomaly warning system based on edge computing chips is characterized by: It includes data acquisition module, data preprocessing module, edge computing chip core processing module, data cache module, network communication module, cloud server management module, user interaction module, early warning strategy configuration module, data security encryption module and power management module; The data acquisition module is used to collect various data in the Internet of Vehicles; The data preprocessing module preprocesses the raw data collected by the data acquisition module, including data cleaning, data conversion, and data normalization operations; The edge computing chip core processing module performs real-time analysis and processing on the pre-processed data based on the edge computing chip; The data cache module is used to cache the intermediate data and historical data generated during the processing of the edge computing chip core processing module for subsequent query and analysis; The network communication module is responsible for realizing communication between the edge computing chip and the cloud server, other vehicles and user terminals; The cloud server management module is used to manage cloud server resources and store a large amount of historical data and algorithm models; The user interaction module provides an interface for users to interact with the system, through which users can view the real-time data, abnormal warning information, and historical data statistics of the vehicle; The warning strategy configuration module allows users to configure different warning strategies according to different vehicle types, usage scenarios and user needs; The data security encryption module performs secure encryption processing on the data in the Internet of Vehicles to ensure the security and privacy of the data during collection, transmission, storage and processing; The power management module is responsible for providing a stable power supply for the entire system, and managing and optimizing the power supply of the system.

2. The IoV data anomaly warning system based on an edge computing chip according to claim 1 is characterized by: The data acquisition module collects various data, including the vehicle's own sensor data, on-board camera data, on-board radar data, communication data between vehicles, and communication data between vehicles and infrastructure; it connects with various subsystems of the vehicle and the external Internet of Vehicles environment through various sensors and communication interfaces to obtain data in real time, and transmits the collected data in the form of raw data to the data preprocessing module.

3. The IoV data anomaly warning system based on an edge computing chip according to claim 1 is characterized by: Data cleaning in the data preprocessing module is to remove noise, duplicate data and invalid data in the data, and filter out data that exceeds a reasonable range by setting a threshold; Data conversion is to convert data in different formats into a unified format for subsequent processing; data normalization is to scale the data to a specific range to improve the accuracy and efficiency of the algorithm; in the data cleaning process, the mean filter algorithm is used to denoise the sensor data. The formula is: Among them, x i Represents the i-th data in the original data sequence, y i Represents the i-th data after filtering, and n represents the half-width of the filtering window.

4. The IoV data anomaly warning system based on an edge computing chip according to claim 1 is characterized by: The core processing module of the edge computing chip integrates multiple data anomaly detection algorithms, including statistical-based methods and machine learning-based methods. These algorithms monitor data in real time to determine whether there are anomalies in the data. At the same time, according to the warning rules set by the warning strategy configuration module, corresponding warning signals are generated. The statistical-based method is the Z-score method. In the anomaly detection based on the Z-score method, the calculation formula is: Among them, x represents the data to be detected, μ represents the mean of the data, and σ represents the standard deviation of the data; when |Z| exceeds the set threshold, the data is judged to be abnormal data.

5. The IoV data anomaly warning system based on an edge computing chip according to claim 1 is characterized by: The data cache module uses a high-speed cache chip or a memory chip to achieve fast storage and reading of data; at the same time, the data cache module manages the cached data; The network communication module supports multiple communication protocols, including but not limited to 4G, 5G, Wi-Fi, Bluetooth, and DSRC dedicated short-range communication, and can select appropriate communication protocols according to different communication scenarios to ensure reliable data transmission; when communicating with the cloud server, the network communication module uploads abnormal data and related information detected by the edge computing chip core processing module to the cloud server, and at the same time receives updated algorithm models and early warning strategy instructions issued by the cloud server.

6. The IoV data anomaly warning system based on an edge computing chip according to claim 1 is characterized by: The cloud server management module conducts in-depth analysis and mining of massive amounts of data in the Internet of Vehicles. Through big data analysis and machine learning technology, it continuously optimizes the anomaly detection algorithm in the core processing module of the edge computing chip, improving the detection accuracy and adaptability of the system. At the same time, the cloud server management module provides users with data query, statistical analysis, and system management services. In the user interaction module, users can also set and adjust early warning strategies.

7. The IoV data anomaly warning system based on an edge computing chip according to claim 1 is characterized by: The warning strategy configuration module can set the parameters, warning level, warning notification method and recipients of anomaly detection; the warning strategy configuration module stores the warning strategy set by the user in the system configuration file and passes it to the edge computing chip core processing module so that it can perform anomaly detection and warning according to the configured warning strategy.

8. The IoV data anomaly warning system based on edge computing chip according to claim 1 is characterized by: The data security encryption module uses encryption algorithms to encrypt and decrypt data, and at the same time performs identity authentication and authorization on the communication process to prevent data from being maliciously tampered with, stolen, and forged; The power management module can detect the state of the power supply and adjust the output of the power supply according to the working state of the system to achieve energy saving and consumption reduction.

9. The early warning method of the vehicle network data abnormality early warning system based on the edge computing chip according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Data acquisition: The data acquisition module collects data from the Internet of Vehicles in real time through various sensors and communication interfaces, and transmits the raw data to the data preprocessing module; Step 2: Data preprocessing: The data preprocessing module cleans, converts, and normalizes the raw data to remove noise and invalid information, and converts the data into a format suitable for edge computing chip processing. Step 3: Data anomaly detection: The edge computing chip core processing module analyzes and detects the pre-processed data in real time based on the warning strategy and anomaly detection algorithm configured in the warning strategy configuration module to determine whether the data is anomaly. Step 4: Early warning processing: If data anomalies are detected, the edge computing chip core processing module generates a corresponding early warning signal according to the early warning strategy, and sends an early warning notification to the user through the user interaction module. At the same time, the abnormal data and related information are uploaded to the cloud server management module through the network communication module; Step 5: Data caching and storage: The data caching module caches intermediate data and historical data during the processing process, and the cloud server management module stores massive amounts of historical data and algorithm models for subsequent query, analysis, and model optimization; Step 6. Warning strategy configuration and update: Users set and adjust warning strategies through the user interaction module. The warning strategy configuration module transmits the configured warning strategies to the edge computing chip core processing module. At the same time, the cloud server management module can automatically update the anomaly detection algorithm and warning strategy in the edge computing chip core processing module based on big data analysis and machine learning results.

Images