A data responsibility tracing method and system based on edge computing

Abstract

The present invention relates to the field of electronic digital data processing technology, and specifically to a data responsibility tracing method and system based on edge computing. The method includes: collecting environmental data around the production line, and obtaining regional environmental impact characteristic values through processing; obtaining operating data of each edge device, and obtaining a performance evaluation index of each edge device through processing, and matching the data load capacity of each edge device; collecting basic data of each edge device, and obtaining abnormal characteristic values of each edge device through processing; comprehensively analyzing to obtain a fault risk assessment index of each edge device, and performing risk assessment and feedback on each edge device; obtaining demand processing data of each edge device, and allocating data to each edge device and cloud processing equipment. The present invention can ensure that data is processed in a timely and effective manner, thereby improving the overall efficiency of data processing and the overall utilization of resources by providing a data responsibility tracing method and system based on edge computing.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and specifically to a data responsibility tracing method and system based on edge computing. Background Art

[0002] In the digital age, data has become a vital asset for businesses and society, and its authenticity and credibility are crucial for decision-making and judgment. Therefore, data accountability and provenance have become crucial for ensuring data security, maintaining data quality, and preventing data fraud. Furthermore, with the rapid development of the Internet of Things, 5G / 6G communication technologies, and smart devices, increasing computing and data storage demands are being pushed to the edge of the network. This trend has made edge computing a crucial means of achieving large-scale real-time computing, optimizing network bandwidth, and reducing latency.

[0003] For example, the invention patent with announcement number CN116579008A is a data tracking and tracing method based on identification, which includes the following steps: S1: Log extraction and parsing step, collecting and pulling log information, extracting and parsing the log data; S2: Log analysis step, aggregating the parsed log data with the data identification ID as the dimension; searching for identification information based on the data identification ID, extracting the fuzzy hash of the data content recorded in the identification, and calculating the similarity between the data; extracting the user ID data in the log, obtaining the identity information corresponding to the user ID; obtaining the system information or device information corresponding to the system ID, and completing the association between data and people and devices; S3: Tracing result presentation step, presenting the results of the log analysis in S2 with the data ID as the dimension. This method achieves source tracing, responsibility location, and credible evidence collection for data leakage incidents, and plays a certain deterrent and regulatory role, helping users to deal with data security risks in a timely manner.

[0004] For example, the invention patent with announcement number CN113010906B is a trusted data traceability method and system based on blockchain. This method includes: data upload verification: before data is uploaded, the verifier verifies the integrity and legality of the data itself, and uploads the verified data to the blockchain subsidiary chain; data trusted traceability: tracing the data uploaded to the blockchain subsidiary chain to establish a secure, complete and trusted data lifecycle; data permission control: setting user identities, and after identity verification, granting different rights and responsibilities to different identities; user behavior control: all user behaviors are retained in the blockchain. Once malicious behavior is discovered, it can be traced and held accountable, and users cannot deny their actions.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: the computing power of current edge devices is usually limited, and it is difficult to process large-scale data sets or complex data tracing tasks. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides a data responsibility tracing method and system based on edge computing, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a data responsibility tracing method based on edge computing, including: obtaining the edge devices of the target production line, marking them as each edge device, collecting the surrounding environmental data of the production line, and obtaining the regional environmental impact characteristic value after processing.

[0008] The operating data of each edge device is obtained, and the performance evaluation index of each edge device is obtained after processing. The data capacity that can be carried by each edge device is matched according to the performance evaluation index of each edge device.

[0009] The basic data of each edge device is collected and processed to obtain the abnormal characteristic value of each edge device.

[0010] Based on the regional environmental impact characteristic value, the performance evaluation index of each edge device and the abnormal characteristic value of each edge device, a comprehensive analysis is conducted to obtain the fault risk assessment index of each edge device. Based on the fault risk assessment index of each edge device, risk assessment of each edge device is performed and feedback is provided.

[0011] Obtain the required processing data of each edge device, and allocate data to each edge device and cloud processing device based on the data capacity of each edge device and risk assessment results.

[0012] As a further method, the regional environmental impact characteristic value is obtained through processing. The specific process is: the environmental data around the production line, including: dust concentration, electromagnetic interference intensity, electrostatic discharge charge and vibration intensity of each environmental monitoring point during equipment operation, is extracted from the system database to obtain the critical dust concentration, critical electromagnetic interference intensity, critical electrostatic discharge charge and critical vibration intensity, and the regional environmental impact characteristic value is obtained through comprehensive analysis. The regional environmental impact characteristic value is used to quantitatively evaluate the negative impact of the abnormal environment in the region on each edge device, and provide a basis for the failure risk assessment of each edge device.

[0013] As a further method, the performance evaluation index of each edge device is obtained through processing. The specific process is: the operation data of each edge device includes: the data throughput, processor utilization, memory utilization, response time and read and write speed of each edge device at each time monitoring point during operation, and the critical processor utilization, critical memory utilization, critical data throughput, critical response time and critical read and write speed are extracted from the system database. The performance evaluation index of each edge device is obtained through comprehensive analysis. The performance evaluation index of each edge device is used to quantitatively evaluate the operating performance of each edge device and provide a basis for performance evaluation of each edge device.

[0014] As a further method, the data volume that can be carried by each edge device is matched. The specific matching process is: extracting a mapping set of the data volume that can be carried corresponding to the performance evaluation index interval of each edge device from the system database, and obtaining the data volume that can be carried by each edge device according to the performance evaluation index matching of each edge device.

[0015] As a further method, the abnormal characteristic value of each edge device is obtained through processing. The specific process is: the basic data of each edge device, including: the voltage, current and power of each edge device at each time monitoring point during operation, is extracted from the system database to obtain the rated voltage, rated current, rated power, allowable deviation current, allowable deviation voltage and allowable deviation power, and based on the regional environmental impact characteristic value, a comprehensive analysis is performed to obtain the abnormal characteristic value of each edge device. The abnormal characteristic value of each edge device is used to quantitatively evaluate the degree of abnormality of each edge device and provide a basis for fault risk assessment of each edge device.

[0016] As a further method, the comprehensive analysis obtains the fault risk assessment index of each edge device. The specific analysis process is: based on the regional environmental impact characteristic value, the performance evaluation index of each edge device and the abnormal characteristic value of each edge device, the comprehensive analysis obtains the fault risk assessment index of each edge device. The failure risk assessment index of each edge device is used to quantitatively assess the risk level of possible failure of each edge device, providing a basis for fault risk assessment of each edge device.

[0017] As a further method, the risk assessment of each edge device is performed and feedback is given. The specific assessment process is: extracting a fault risk assessment index threshold from the system database, comparing the fault risk assessment index of each edge device with the fault risk assessment index threshold; if the fault risk assessment index of an edge device is higher than or equal to the fault risk assessment index threshold, then the edge device is marked as a faulty device and a risk warning is issued for the faulty device; if the fault risk assessment index of an edge device is lower than the fault risk assessment index threshold, then the edge device is marked as a normal device, and the result is displayed and output.

[0018] As a further method, data is allocated to each edge device and cloud processing device based on the data capacity of each edge device and the risk assessment results. The specific allocation strategy is: when an edge device is a normal device, the required processing data of the edge device is compared with the data capacity of the edge device. If the required processing data of the edge device is greater than the data capacity of the edge device, the excess data needs to be allocated to each target edge device and cloud processing device for processing. If the required processing data of the edge device is less than or equal to the data capacity of the edge device, data processing is performed directly without additional allocation operations.

[0019] When an edge device is a faulty device, the required processing data of the edge device is distributed to each target edge device and cloud processing device for processing, and the edge device does not process data.

[0020] As a further method, the specific numerical expression of the abnormal characteristic value of each edge device is:

[0021]

[0022] Where, Indicates the abnormal characteristic value of the nth edge device, represents the regional environmental impact characteristic value, α nj represents the voltage of the nth edge device at the jth time monitoring point, β nj represents the current of the nth edge device at the jth time monitoring point, γ nj represents the power of the nth edge device at the jth time monitoring point, α 0 Indicates rated voltage, β 0 Indicates rated current, γ 0 represents the rated power, Δα represents the allowable deviation current, Δβ represents the allowable deviation voltage, Δγ represents the allowable deviation power, ω1 represents the equipment abnormality impact factor corresponding to the preset regional environmental impact characteristic value, ω2 represents the equipment abnormality impact factor corresponding to the preset voltage, ω3 represents the equipment abnormality impact factor corresponding to the preset current, and ω4 represents the equipment abnormality impact factor corresponding to the preset power.

[0023] The second aspect of the present invention provides a data responsibility tracing system based on edge computing, including: a regional environmental impact assessment module, an edge device performance assessment module, an edge device abnormal feature assessment module, an edge device failure risk assessment module, a data distribution module and a system database.

[0024] The regional environmental impact assessment module is used to obtain the edge devices of the target production line, mark each edge device, collect the environmental data around the production line, and obtain the regional environmental impact characteristic value after processing.

[0025] The edge device performance evaluation module is used to obtain the operating data of each edge device, obtain the performance evaluation index of each edge device after processing, and match the data capacity that each edge device can carry according to the performance evaluation index of each edge device.

[0026] The edge device abnormal feature evaluation module is used to collect basic data of each edge device and obtain the abnormal feature value of each edge device after processing.

[0027] The edge device failure risk assessment module is used to comprehensively analyze the regional environmental impact characteristic value, the performance evaluation index of each edge device and the abnormal characteristic value of each edge device to obtain the failure risk assessment index of each edge device, and perform risk assessment and feedback on each edge device based on the failure risk assessment index of each edge device.

[0028] The data allocation module is used to obtain the required processing data of each edge device and allocate data to each edge device and cloud processing device based on the data capacity of each edge device and risk assessment results.

[0029] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0030] (1) The present invention provides a data responsibility tracing method and system based on edge computing. According to the data capacity of the edge devices and the risk assessment results, the data is intelligently distributed to each edge device and cloud processing device, ensuring that the data is processed in a timely and effective manner. This distribution method avoids excessive concentration or idleness of data, helps to avoid waste and idleness of resources, improves the overall utilization of resources and the overall efficiency of data processing, and also helps to prevent data loss and damage, thereby improving the fault tolerance and stability of the system.

[0031] (2) By analyzing comprehensive, multi-dimensional equipment operating environment data, the present invention helps to more accurately predict the type and timing of possible equipment failures, thereby improving the accuracy and reliability of failure prediction. By issuing early warning signals in the event of abnormal environmental factors, measures can be taken in advance to prevent equipment failures, reduce the risk of production interruptions, and help improve the reliability and stability of equipment and extend its service life.

[0032] (3) The present invention can comprehensively evaluate the performance status of edge devices by comprehensively analyzing various performance indicators of the devices, timely discover performance bottlenecks and potential problems, and understand the resource utilization of the devices, which helps to optimize resource allocation and improve resource utilization efficiency. At the same time, by matching the performance and data volume of edge devices, it can ensure that resources are fully utilized and avoid resource waste and performance bottlenecks.

[0033] (4) The present invention can help analyze edge device anomalies more accurately by comprehensively analyzing regional environmental impacts and voltage, current, and power anomalies of edge devices, which helps optimize device maintenance, improve system stability, and enhance environmental adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0035] Figure 1 Schematic diagram of the method of the present invention.

[0036] Figure 2 This is a schematic diagram of system module connections of the present invention.

[0037] Figure 3 Schematic diagram of the functional relationship between the fault risk assessment index of the edge device involved in an embodiment of the present invention and the performance evaluation index of the edge device. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0039] Reference Figure 1 As shown, the first aspect of the present invention provides a data responsibility tracing method based on edge computing, including: obtaining the edge devices of the target production line, marking them as each edge device, collecting the surrounding environmental data of the production line, and obtaining the regional environmental impact characteristic value after processing.

[0040] It should be explained that the edge devices specifically refer to intelligent edge computing gateways, which can collect data from various devices (such as sensors, cameras, etc.) and perform preliminary processing locally.

[0041] Specifically, the regional environmental impact characteristic value is obtained after processing, and the specific process is as follows: the surrounding environmental data of the production line, including: dust concentration, electromagnetic interference intensity, electrostatic discharge charge and vibration intensity of each environmental monitoring point during equipment operation, are extracted from the system database to obtain the critical dust concentration, critical electromagnetic interference intensity, critical electrostatic discharge charge and critical vibration intensity, and the regional environmental impact characteristic value is obtained through comprehensive analysis. The regional environmental impact characteristic value is used to quantitatively evaluate the negative impact of the abnormal environment in the region on each edge device, and provide a basis for the failure risk assessment of each edge device.

[0042] It should be explained that the dust concentration in the air can be measured by collecting air samples and using professional particulate matter concentration measuring instruments (such as PM2.5 detectors). Professional electromagnetic interference measurement equipment, such as electromagnetic field strength meters, can be used to monitor the electromagnetic interference intensity of the target area in real time. Charge measurement equipment, such as a Faraday cup, can be used to measure the amount of electrostatic discharge charge. Vibration measurement equipment, such as a piezoelectric accelerometer, can be used to monitor the vibration intensity of the target area in real time.

[0043] In a specific embodiment, the numerical expression of the regional environmental impact characteristic value is:

[0044]

[0045] Where, represents the regional environmental impact characteristic value, t represents the time variable, t∈[t0, t1], t1 represents the current time point, t0 represents the monitoring start time point, i represents the number of each environmental monitoring point, i=1, 2, 3, ..., h, h represents the total number of environmental monitoring points, H i (t) represents the dust concentration at the i-th environmental monitoring point at time t, G i (t) represents the electromagnetic interference intensity of the i-th environmental monitoring point at time t, D i (t) represents the electrostatic discharge charge at the i-th environmental monitoring point at time t, Z i (t) represents the vibration intensity of the i-th environmental monitoring point at time t, ΔH represents the critical dust concentration, ΔG represents the critical electromagnetic interference intensity, ΔD represents the critical electrostatic discharge charge, ΔZ represents the critical vibration intensity, μ1 represents the regional environmental impact factor corresponding to the preset dust concentration, μ2 represents the regional environmental impact factor corresponding to the preset electromagnetic interference intensity, μ3 represents the regional environmental impact factor corresponding to the preset electrostatic discharge charge, and μ4 represents the regional environmental impact factor corresponding to the preset vibration intensity.

[0046] It should be explained that when the dust concentration, electromagnetic interference intensity, electrostatic discharge charge and vibration intensity are greater, the corresponding regional environmental impact characteristic value will be greater, indicating that the negative impact of the regional abnormal environment on each edge device will also be greater.

[0047] It should be explained that, in this embodiment, μ1 represents the regional environmental impact factor corresponding to the preset dust concentration, μ2 represents the regional environmental impact factor corresponding to the preset electromagnetic interference intensity, μ3 represents the regional environmental impact factor corresponding to the preset electrostatic discharge charge, and μ4 represents the regional environmental impact factor corresponding to the preset vibration intensity, which respectively represent the numerical values of the degree of influence of the unit values of dust concentration, electromagnetic interference intensity, electrostatic discharge charge and vibration intensity on the regional environment. When used, the regional environmental impact factor corresponding to the dust concentration, the regional environmental impact factor corresponding to the electromagnetic interference intensity, the regional environmental impact factor corresponding to the electrostatic discharge charge and the regional environmental impact factor corresponding to the vibration intensity can be directly obtained from the system database. The corresponding relationship of the impact factor can be a pre-set mapping relationship. For example, the dust concentration, electromagnetic interference intensity, electrostatic discharge charge and vibration intensity of each environmental monitoring point are respectively mapped with the regional environmental impact factors corresponding to the dust concentration, electromagnetic interference intensity, electrostatic discharge charge and vibration intensity preset in the system database to form a mapping set. The real-time dust concentration, electromagnetic interference intensity, electrostatic discharge charge and vibration intensity are input into the mapping set to obtain the regional environmental impact factor corresponding to the dust concentration, the regional environmental impact factor corresponding to the electromagnetic interference intensity, the regional environmental impact factor corresponding to the electrostatic discharge charge and the regional environmental impact factor corresponding to the vibration intensity. The mapping relationship can be one-to-one or many-to-one. The above impact factors are all extracted from the system database, and the value range is between 0 and 1.

[0048] It should be noted that dust accumulation can clog equipment cooling vents and fans, causing overheating and increasing the likelihood of electromagnetic radiation and interference. Tiny particles in dust can carry static electricity, increasing the risk of electrostatic discharge (ESD), which can disrupt the stability of electromagnetic fields. Furthermore, friction between dust particles can easily generate static electricity, increasing the charge generated by ESD. ESD can cause short circuits or component damage within the equipment, impacting normal operation. Electromagnetic interference can interfere with the equipment's ESD protection system, reducing its effectiveness. Electromagnetic waves generated by ESD can also disrupt the normal operation of other equipment. Vibration can loosen or damage internal connections, increasing the risk of dust and EMI entering the equipment. By simultaneously monitoring multiple environmental factors, such as dust concentration, EMI, ESD, and vibration, more comprehensive and multi-dimensional data on the equipment's operating environment can be obtained. This helps more accurately predict the type and timing of potential equipment failures, improving the accuracy and reliability of failure predictions. Combining historical data with real-time monitoring data can establish a risk warning mechanism that issues timely warning signals when environmental factors are abnormal. This allows for proactive action to prevent equipment failures, reduce the risk of production interruptions, and improve equipment reliability and stability, extending its service life.

[0049] The operating data of each edge device is obtained, and the performance evaluation index of each edge device is obtained after processing. The data capacity that can be carried by each edge device is matched according to the performance evaluation index of each edge device.

[0050] Specifically, the performance evaluation index of each edge device is obtained after processing. The specific process is: the operation data of each edge device includes: the data throughput, processor utilization, memory utilization, response time and read and write speed of each edge device at each time monitoring point during operation, and the critical processor utilization, critical memory utilization, critical data throughput, critical response time and critical read and write speed are extracted from the system database. The performance evaluation index of each edge device is obtained through comprehensive analysis. The performance evaluation index of each edge device is used to quantitatively evaluate the operating performance of each edge device and provide a basis for performance evaluation of each edge device.

[0051] It should be explained that the read and write speed refers to the amount of data read and written per second by the gateway storage device.

[0052] It's important to note that you can monitor processor utilization, memory usage, storage I / O performance, and response time using built-in operating system tools. For example, Windows' Task Manager and Linux's top, htop, and iostat can be used. Network throughput can also be monitored using the Performance Monitor tool, which can create charts to visually display data transfer rates.

[0053] In a specific embodiment, the numerical expression of the performance evaluation index of each edge device is:

[0054]

[0055] Where, represents the performance evaluation index of the nth edge device, e represents a natural constant, n represents the number of each edge device, n = 1, 2, 3, ..., m, m represents the total number of edge devices, j represents the number of each time monitoring point, j = 1, 2, 3, ..., d, d represents the total number of time monitoring points, τM nj represents the data throughput of the nth edge device at the jth time monitoring point, τW nj represents the processor utilization of the nth edge device at the jth time monitoring point, τL nj represents the memory usage of the nth edge device at the jth time monitoring point, τN nj represents the response time of the nth edge device at the jth time monitoring point, τP nj represents the read and write speed of the nth edge device at the jth time monitoring point, ΔτW represents the critical processor utilization, ΔτL represents the critical memory usage, ΔτM represents the critical data throughput, ΔτN represents the critical response time, and ΔτP represents the critical read and write speed. Indicates the edge device performance impact factor corresponding to the preset processor usage, Indicates the edge device performance impact factor corresponding to the preset memory usage, Indicates the edge device performance impact factor corresponding to the preset data throughput, Indicates the edge device performance impact factor corresponding to the preset response time, Indicates the edge device performance impact factor corresponding to the preset read and write speed.

[0056] It needs to be explained that when the data throughput is greater, the processor utilization is lower, the memory usage is lower, the response time is shorter, and the read and write speed is greater, the performance evaluation index of the corresponding edge device will be greater, indicating that the operating performance of the edge device will be better.

[0057] It should be explained that in this embodiment Indicates the edge device performance impact factor corresponding to the preset processor usage, Indicates the edge device performance impact factor corresponding to the preset memory usage, Indicates the edge device performance impact factor corresponding to the preset data throughput, Indicates the edge device performance impact factor corresponding to the preset response time, It indicates the edge device performance impact factor corresponding to the preset read and write speed, which respectively indicates the degree of influence of the unit values of processor utilization, memory utilization, data throughput, response time and read and write speed on the edge device operation performance. When used, the edge device performance impact factor corresponding to the processor utilization, the edge device performance impact factor corresponding to the memory utilization, the edge device performance impact factor corresponding to the data throughput, the edge device performance impact factor corresponding to the response time and the edge device performance impact factor corresponding to the read and write speed can be directly obtained from the system database. The corresponding relationship can be a preset mapping relationship, for example, the processor utilization, memory utilization, data throughput, response time and read and write speed of each time monitoring point are According to the throughput, response time and read-write speed, a mapping set is formed with the edge device performance influencing factors corresponding to the processor utilization, memory usage, data throughput, response time and read-write speed preset in the system database. The real-time processor utilization, memory usage, data throughput, response time and read-write speed are input into the mapping set to obtain the edge device performance influencing factor corresponding to the processor utilization, the edge device performance influencing factor corresponding to the memory usage, the edge device performance influencing factor corresponding to the data throughput, the edge device performance influencing factor corresponding to the response time and the edge device performance influencing factor corresponding to the read-write speed. The mapping relationship can be one-to-one or many-to-one. The above-mentioned influencing factors are all extracted from the system database, and the value range is between 0 and 1.

[0058] It's important to note that when processor utilization increases, memory usage may also increase, as processing tasks often require memory to store data and instructions. Processors may need to frequently read or write to storage while processing data, so high processor utilization can lead to increased storage I / O performance requirements. If storage I / O performance is insufficient to meet processor processing needs, it can become a system bottleneck, causing the processor to wait. When memory is insufficient, the system may use disk space as virtual memory (swap space), which increases storage I / O operations. Low network throughput can cause data transfer to become a bottleneck, impacting the efficient utilization of processor and memory resources. System response time is affected by processor, memory, and storage performance. If any of these resources becomes a bottleneck, response time will increase. At the same time, efficient resource utilization can reduce response time. Comprehensively analyzing processor utilization, memory usage, data throughput, response time, and read / write speeds provides a comprehensive performance evaluation framework, helping to understand the overall health of the device and quickly identify performance bottlenecks.

[0059] It's important to explain that by comprehensively analyzing the above metrics, we can comprehensively assess the performance of edge devices and identify performance bottlenecks and potential issues. Based on the assessment results, targeted optimization measures can be developed, such as hardware upgrades, software algorithm optimization, and resource allocation adjustments, to improve device performance. By monitoring the changing trends of key performance indicators, we can promptly detect precursors to device failures, such as a sudden increase in processor utilization or a sustained increase in memory usage. This helps us take proactive measures to prevent device failures, reducing repair costs and the risk of production interruptions. By comprehensively analyzing data from various monitoring points in time, we can understand the device's resource utilization, such as whether processor, memory, and storage resources are allocated appropriately. Based on this, we can optimize resource allocation and improve resource efficiency.

[0060] Furthermore, the data volume that can be carried by each edge device is matched, and the specific matching process is: extracting a mapping set of the data volume that can be carried corresponding to the performance evaluation index interval of each edge device from the system database, and obtaining the data volume that can be carried by each edge device according to the performance evaluation index matching of each edge device.

[0061] It's important to note that by matching edge device performance with data volume, resources can be fully utilized, avoiding resource waste and performance bottlenecks. Allocating data to edge devices with appropriate performance can speed up data processing and improve real-time performance and accuracy.

[0062] The basic data of each edge device is collected and processed to obtain the abnormal characteristic value of each edge device.

[0063] Specifically, the abnormal characteristic value of each edge device is obtained after processing, and the specific process is: the basic data of each edge device, including: the voltage, current and power of each edge device at each time monitoring point during operation, are extracted from the system database to obtain the rated voltage, rated current, rated power, allowable deviation current, allowable deviation voltage and allowable deviation power, and based on the regional environmental impact characteristic value, a comprehensive analysis is performed to obtain the abnormal characteristic value of each edge device. The abnormal characteristic value of each edge device is used to quantitatively evaluate the degree of abnormality of each edge device and provide a basis for fault risk assessment of each edge device.

[0064] It's important to note that you can use high-precision voltmeters and ammeters to directly measure the voltage and current of edge devices. You can also use specialized power measurement instruments, such as power analyzers or power meters, to directly measure the power of edge devices. These instruments typically offer high precision and stability, ensuring accurate measurement results.

[0065] In a specific embodiment, the numerical expression of the abnormal characteristic value of each edge device is:

[0066]

[0067] Where, Indicates the abnormal characteristic value of the nth edge device, represents the regional environmental impact characteristic value, α nj represents the voltage of the nth edge device at the jth time monitoring point, β nj represents the current of the nth edge device at the jth time monitoring point, γ n j represents the power of the nth edge device at the jth time monitoring point, α 0 Indicates rated voltage, β 0 Indicates rated current, γ 0 represents the rated power, Δα represents the allowable deviation current, Δβ represents the allowable deviation voltage, Δγ represents the allowable deviation power, ω1 represents the equipment abnormality impact factor corresponding to the preset regional environmental impact characteristic value, ω2 represents the equipment abnormality impact factor corresponding to the preset voltage, ω3 represents the equipment abnormality impact factor corresponding to the preset current, and ω4 represents the equipment abnormality impact factor corresponding to the preset power.

[0068] It should be explained that when the voltage, current and power of the edge device deviate more from the rated voltage, current and power, and the regional environmental impact characteristic value is also greater, the corresponding edge device abnormal characteristic value is also greater, indicating that the degree of abnormality of the edge device is also greater.

[0069] It should be explained that in this embodiment, ω1 represents the device abnormality impact factor corresponding to the preset regional environmental impact characteristic value, ω2 represents the device abnormality impact factor corresponding to the preset voltage, ω3 represents the device abnormality impact factor corresponding to the preset current, and ω4 represents the device abnormality impact factor corresponding to the preset power, which respectively represent the numerical values of the degree of influence of the regional environmental impact characteristic value, voltage, current, and power unit values on the device abnormality. When used, the device abnormality impact factor corresponding to the regional environmental impact characteristic value, the device abnormality impact factor corresponding to the voltage, the device abnormality impact factor corresponding to the current, and the device abnormality impact factor corresponding to the power can be directly obtained from the system database. The corresponding relationship can be a pre-set mapping relationship. For example, the voltage, current, power and regional environmental impact characteristic values of each time monitoring point are respectively mapped to the device abnormality impact factors corresponding to the voltage, current, power and regional environmental impact characteristic values of each time monitoring point preset in the system database to form a mapping set. The voltage, current, power and regional environmental impact characteristic values of each time monitoring point in real time are input into the mapping set to obtain the device abnormality impact factor corresponding to the regional environmental impact characteristic value, the device abnormality impact factor corresponding to the voltage, the device abnormality impact factor corresponding to the current and the device abnormality impact factor corresponding to the power. The mapping relationship can be one-to-one or many-to-one. The above impact factors are all extracted from the system database and have a value range of 0 to 1.

[0070] It's important to note that abnormal voltage, current, and power on edge devices often reflect issues within the device or its external environment. Overvoltage can be caused by grid voltage fluctuations, lightning strikes, and other factors, damaging the device. Undervoltage can be caused by insufficient grid power or excessively long lines, leading to decreased device performance. Long-term overloaded operation of the device can result in excessive current, potentially damaging the device. A short circuit within or outside the device can cause a sharp increase in current. A low power factor can be caused by an imbalance in the device's internal capacitors and inductors, impacting grid efficiency. Power fluctuations can be caused by external interference or internal device faults, impacting device stability. Comprehensive analysis of regional environmental impacts and voltage, current, and power anomalies on edge devices can help more accurately analyze edge device anomalies and improve diagnostic accuracy, thereby optimizing device maintenance, enhancing system stability, and enhancing environmental adaptability.

[0071] Based on the regional environmental impact characteristic value, the performance evaluation index of each edge device and the abnormal characteristic value of each edge device, a comprehensive analysis is conducted to obtain the fault risk assessment index of each edge device. Based on the fault risk assessment index of each edge device, risk assessment of each edge device is performed and feedback is provided.

[0072] Specifically, a comprehensive analysis is performed to obtain the fault risk assessment index of each edge device. The specific analysis process is as follows: based on the regional environmental impact characteristic value, the performance evaluation index of each edge device and the abnormal characteristic value of each edge device, a comprehensive analysis is performed to obtain the fault risk assessment index of each edge device. The fault risk assessment index of each edge device is used to quantitatively assess the risk level of possible failure of each edge device, providing a basis for performing fault risk assessment on each edge device.

[0073] In a specific embodiment, the numerical expression of the failure risk assessment index of each edge device is:

[0074]

[0075] Where, represents the fault risk assessment index of the nth edge device, represents the performance evaluation index of the nth edge device, Indicates the abnormal characteristic value of the nth edge device, represents the regional environmental impact characteristic value, θ1 represents the fault risk impact factor corresponding to the preset performance evaluation index of the edge device, θ2 represents the fault risk impact factor corresponding to the preset edge device abnormal characteristic value, and θ3 represents the fault risk impact factor corresponding to the preset regional environmental impact characteristic value.

[0076] It should be understood that if Figure 3As shown, curve a represents the functional relationship between the fault risk assessment index of the corresponding edge device and the performance evaluation index of the edge device when the abnormal characteristic value of the edge device is 0.3 and the regional environmental impact characteristic value is 0.5. Curve b represents the functional relationship between the fault risk assessment index of the corresponding edge device and the performance evaluation index of the edge device when the abnormal characteristic value of the edge device is 0.4 and the regional environmental impact characteristic value is 0.5. Curve c represents the functional relationship between the fault risk assessment index of the corresponding edge device and the performance evaluation index of the edge device when the abnormal characteristic value of the edge device is 0.3 and the regional environmental impact characteristic value is 0.6.

[0077] It should be explained that in this embodiment, the failure risk impact factor corresponding to the performance evaluation index of the edge device is set to 0.6, the failure risk impact factor corresponding to the abnormal characteristic value of the edge device is set to 0.4, and the failure risk impact factor corresponding to the regional environmental impact characteristic value is set to 0.5.

[0078] It should be explained that when the performance evaluation index of the edge device is smaller and the abnormal characteristic value of the edge device and the regional environmental impact characteristic value are larger, the corresponding failure risk assessment index of the edge device will be larger, indicating that the risk of failure of the edge device is also greater.

[0079] It should be explained that in this embodiment, θ1 represents the fault risk impact factor corresponding to the preset performance evaluation index of the edge device, θ2 represents the fault risk impact factor corresponding to the preset abnormal characteristic value of the edge device, and θ3 represents the fault risk impact factor corresponding to the preset regional environmental impact characteristic value, which respectively represent the numerical values of the degree of influence of the performance evaluation index of the edge device, the abnormal characteristic value of the edge device, and the regional environmental impact characteristic value on the device failure risk. When used, the fault risk impact factor corresponding to the performance evaluation index of the edge device, the fault risk impact factor corresponding to the abnormal characteristic value of the edge device, and the fault risk impact factor corresponding to the regional environmental impact characteristic value can be directly obtained from the system database. The system can be a pre-set mapping relationship. For example, the performance evaluation index of the edge device, the abnormal characteristic value of the edge device and the regional environmental impact characteristic value are respectively mapped to the fault risk impact factors corresponding to the performance evaluation index of the edge device, the abnormal characteristic value of the edge device and the regional environmental impact characteristic value preset in the system database to form a mapping set. The performance evaluation index of the real-time edge device, the abnormal characteristic value of the edge device and the regional environmental impact characteristic value are input into the mapping set to obtain the fault risk impact factor corresponding to the performance evaluation index of the edge device, the fault risk impact factor corresponding to the abnormal characteristic value of the edge device and the fault risk impact factor corresponding to the regional environmental impact characteristic value. The mapping relationship can be one-to-one or many-to-one. The above-mentioned impact factors are all extracted from the system database, and the value range is between 0 and 1.

[0080] Furthermore, risk assessment is performed on each edge device and feedback is given. The specific assessment process is: the fault risk assessment index threshold is extracted from the system database, and the fault risk assessment index of each edge device is compared with the fault risk assessment index threshold. If the fault risk assessment index of an edge device is higher than or equal to the fault risk assessment index threshold, the edge device is marked as a faulty device and a risk warning is issued for the faulty device. If the fault risk assessment index of an edge device is lower than the fault risk assessment index threshold, the edge device is marked as a normal device and the result is displayed and output.

[0081] Obtain the required processing data of each edge device, and allocate data to each edge device and cloud processing device based on the data capacity of each edge device and risk assessment results.

[0082] Specifically, data is allocated to each edge device and cloud processing device based on the data capacity of each edge device and the risk assessment results. The specific allocation strategy is: when an edge device is a normal device, the required processing data of the edge device is compared with the data capacity of the edge device. If the required processing data of the edge device is greater than the data capacity of the edge device, the excess data needs to be allocated to each target edge device and cloud processing device for processing. If the required processing data of the edge device is less than or equal to the data capacity of the edge device, data processing is performed directly without additional allocation operations.

[0083] When an edge device is a faulty device, the required processing data of the edge device is distributed to each target edge device and cloud processing device for processing, and the edge device does not process data.

[0084] It should be noted that the requested processing data of each edge device refers to the data obtained by performing a series of preliminary processing operations on the raw data before the data is transmitted from the edge device to the edge computing node. The target devices are edge devices that are operating normally and can carry a data volume greater than the requested processing data. The excess data volume refers to the difference between the requested processing data of the edge device and the data volume that can be carried.

[0085] It should be explained that intelligently distributing data to edge devices and cloud processing devices based on the edge device's data capacity and risk assessment results ensures timely and efficient data processing. This distribution method avoids excessive concentration or idle data, improving overall data processing efficiency. Taking the risk assessment results of edge devices into account during data distribution ensures that data is allocated to more reliable and secure devices for processing. This helps prevent data loss and corruption. Distributing data across multiple edge devices and cloud processing devices for distributed processing improves the system's fault tolerance and stability. Even if a device fails, other devices can continue processing data, ensuring normal system operation. Intelligent distribution based on the data capacity of each edge device also ensures that each device is fully utilized. This helps avoid resource waste and idleness, improving overall resource utilization.

[0086] Reference Figure 2 As shown, the second aspect of the present invention provides a data responsibility tracing system based on edge computing, including: a regional environmental impact assessment module, an edge device performance assessment module, an edge device abnormal feature assessment module, an edge device failure risk assessment module, a data distribution module and a system database.

[0087] The regional environmental impact assessment module is used to obtain the edge devices of the target production line, mark each edge device, collect the environmental data around the production line, and obtain the regional environmental impact characteristic value after processing.

[0088] The edge device performance evaluation module is used to obtain the operating data of each edge device, obtain the performance evaluation index of each edge device after processing, and match the data capacity that each edge device can carry according to the performance evaluation index of each edge device.

[0089] The edge device abnormal feature evaluation module is used to collect basic data of each edge device and obtain the abnormal feature value of each edge device after processing.

[0090] The edge device failure risk assessment module is used to comprehensively analyze the regional environmental impact characteristic value, the performance evaluation index of each edge device and the abnormal characteristic value of each edge device to obtain the failure risk assessment index of each edge device, and perform risk assessment and feedback on each edge device based on the failure risk assessment index of each edge device.

[0091] The data allocation module is used to obtain the required processing data of each edge device and allocate data to each edge device and cloud processing device based on the data capacity of each edge device and risk assessment results.

[0092] In a specific embodiment, the system database is used to store relevant data in the process of data allocation between edge devices and cloud processing devices, including critical dust concentration, critical electromagnetic interference intensity, critical electrostatic discharge charge and critical vibration intensity, edge device performance impact factor corresponding to processor utilization, edge device performance impact factor corresponding to memory utilization, edge device performance impact factor corresponding to data throughput, edge device performance impact factor corresponding to response time and edge device performance impact factor corresponding to read and write speed, fault risk assessment index threshold and data extracted from the system database in the above embodiments. Data can be extracted from the data warehouse through direct query, data flow, ETL (extract, transform, load) tasks, etc. The data warehouse is a database system for storing large amounts of historical data, usually used to support applications such as decision support systems and online analytical processing. It can also obtain data related to data allocation between edge devices and cloud processing devices by accessing public data sets. Relevant data can also be obtained through network access and application access. The database provides a series of application interfaces. By calling these application interfaces, you can connect to the database, perform query and update operations, etc. in the application.

[0093] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

Claims

1. A data responsibility tracing method based on edge computing, characterized in that: include: Obtain the edge devices of the target production line, mark them as edge devices, collect environmental data around the production line, and obtain regional environmental impact characteristic values after processing; Obtain the operating data of each edge device, process it to obtain the performance evaluation index of each edge device, and match the data capacity of each edge device according to the performance evaluation index of each edge device; Collect basic data from each edge device and obtain abnormal feature values of each edge device through processing; Based on the regional environmental impact characteristic value, the performance evaluation index of each edge device, and the abnormal characteristic value of each edge device, a comprehensive analysis is conducted to obtain the fault risk assessment index of each edge device. Based on the fault risk assessment index of each edge device, a risk assessment is performed on each edge device and feedback is provided. Obtain the required processing data of each edge device and allocate data to each edge device and cloud processing device based on the data capacity of each edge device and risk assessment results; The regional environmental impact characteristic value is obtained through processing, and the specific process is as follows: The environmental data surrounding the production line includes: dust concentration, electromagnetic interference intensity, electrostatic discharge charge, and vibration intensity at each environmental monitoring point during equipment operation. Critical dust concentration, critical electromagnetic interference intensity, critical electrostatic discharge charge, and critical vibration intensity are extracted from the system database and comprehensively analyzed to obtain regional environmental impact characteristic values; The performance evaluation index of each edge device is obtained through processing, and the specific process is as follows: The operation data of each edge device includes: data throughput, processor utilization, memory usage, response time and read / write speed at each monitoring point during the operation of each edge device, extracting the critical processor utilization, critical memory usage, critical data throughput, critical response time and critical read / write speed from the system database, and comprehensively analyzing the performance evaluation index of each edge device; The abnormal characteristic value of each edge device is obtained through processing, and the specific process is as follows: The basic data of each edge device includes: the voltage, current and power of each edge device at each monitoring point during operation, the rated voltage, rated current, rated power, allowable deviation current, allowable deviation voltage and allowable deviation power are extracted from the system database, and the abnormal characteristic value of each edge device is obtained by comprehensive analysis based on the regional environmental impact characteristic value; The comprehensive analysis obtains the fault risk assessment index of each edge device. The specific analysis process is as follows: Based on the regional environmental impact characteristic value, the performance evaluation index of each edge device, and the abnormal characteristic value of each edge device, a comprehensive analysis is performed to obtain the failure risk assessment index of each edge device; The numerical expression of the regional environmental impact characteristic value is: Where, represents the regional environmental impact characteristic value, t represents the time variable, t∈[t0, t1], t1 represents the current time point, t0 represents the monitoring start time point, i represents the number of each environmental monitoring point, i=1,2,3,...,h, h represents the total number of environmental monitoring points, H i (t) represents the dust concentration at the i-th environmental monitoring point at time t, G i (t) represents the electromagnetic interference intensity of the i-th environmental monitoring point at time t, D i (t) represents the electrostatic discharge charge at the i-th environmental monitoring point at time t, Z i (t) represents the vibration intensity of the i-th environmental monitoring point at time t, ΔH represents the critical dust concentration, ΔG represents the critical electromagnetic interference intensity, ΔD represents the critical electrostatic discharge charge, ΔZ represents the critical vibration intensity, μ1 represents the regional environmental impact factor corresponding to the preset dust concentration, μ2 represents the regional environmental impact factor corresponding to the preset electromagnetic interference intensity, μ3 represents the regional environmental impact factor corresponding to the preset electrostatic discharge charge, and μ4 represents the regional environmental impact factor corresponding to the preset vibration intensity; The numerical expression of the performance evaluation index of each edge device is: Where, represents the performance evaluation index of the nth edge device, e represents a natural constant, n represents the number of each edge device, n = 1, 2, 3, ..., m, m represents the total number of edge devices, j represents the number of each time monitoring point, j = 1, 2, 3, ..., d, d represents the total number of time monitoring points, τM nj represents the data throughput of the nth edge device at the jth time monitoring point, τW nj represents the processor utilization of the nth edge device at the jth time monitoring point, τL nj represents the memory usage of the nth edge device at the jth time monitoring point, τN nj represents the response time of the nth edge device at the jth time monitoring point, τP nj represents the read and write speed of the nth edge device at the jth time monitoring point, ΔτW represents the critical processor utilization, ΔτL represents the critical memory usage, ΔτM represents the critical data throughput, ΔτN represents the critical response time, and ΔτP represents the critical read and write speed. Indicates the edge device performance impact factor corresponding to the preset processor usage, Indicates the edge device performance impact factor corresponding to the preset memory usage, Indicates the edge device performance impact factor corresponding to the preset data throughput, Indicates the edge device performance impact factor corresponding to the preset response time, Indicates the edge device performance impact factor corresponding to the preset read and write speed; The numerical expression of the abnormal characteristic value of each edge device is: Where, Indicates the abnormal characteristic value of the nth edge device, represents the regional environmental impact characteristic value, α nj represents the voltage of the nth edge device at the jth time monitoring point, β nj represents the current of the nth edge device at the jth time monitoring point, γ nj represents the power of the nth edge device at the jth time monitoring point, α 0 Indicates rated voltage, β 0 Indicates rated current, γ 0 represents the rated power, Δα represents the allowable deviation current, Δβ represents the allowable deviation voltage, Δγ represents the allowable deviation power, ω1 represents the equipment abnormality impact factor corresponding to the preset regional environmental impact characteristic value, ω2 represents the equipment abnormality impact factor corresponding to the preset voltage, ω3 represents the equipment abnormality impact factor corresponding to the preset current, and ω4 represents the equipment abnormality impact factor corresponding to the preset power. The numerical expression of the performance evaluation index of each edge device is: Where, represents the performance evaluation index of the nth edge device, e represents a natural constant, n represents the number of each edge device, n = 1, 2, 3, ..., m, m represents the total number of edge devices, j represents the number of each time monitoring point, j = 1, 2, 3, ..., d, d represents the total number of time monitoring points, τM nj represents the data throughput of the nth edge device at the jth time monitoring point, τW nj represents the processor utilization of the nth edge device at the jth time monitoring point, τL nj represents the memory usage of the nth edge device at the jth time monitoring point, τN nj represents the response time of the nth edge device at the jth time monitoring point, τP nj represents the read and write speed of the nth edge device at the jth time monitoring point, ΔτW represents the critical processor utilization, ΔτL represents the critical memory usage, ΔτM represents the critical data throughput, ΔτN represents the critical response time, and ΔτP represents the critical read and write speed. Indicates the edge device performance impact factor corresponding to the preset processor usage, Indicates the edge device performance impact factor corresponding to the preset memory usage, Indicates the edge device performance impact factor corresponding to the preset data throughput, Indicates the edge device performance impact factor corresponding to the preset response time, Indicates the edge device performance impact factor corresponding to the preset read and write speed.

2. The data responsibility tracing method based on edge computing according to claim 1 is characterized by: The regional environmental impact characteristic value obtained through processing also includes: The regional environmental impact characteristic value is used to quantitatively evaluate the negative impact of the regional abnormal environment on each edge device, providing a basis for the failure risk assessment of each edge device.

3. The data responsibility tracing method based on edge computing according to claim 1 is characterized by: The performance evaluation index of each edge device obtained through processing also includes: The performance evaluation index of each edge device is used to quantitatively evaluate the operating performance of each edge device and provide a basis for performance evaluation of each edge device.

4. The data responsibility tracing method based on edge computing according to claim 3 is characterized by: The data volume that can be carried by each edge device is matched. The specific matching process is as follows: A mapping set of the data carrying capacity corresponding to the performance evaluation index interval of each edge device is extracted from the system database, and the data carrying capacity of each edge device is obtained according to the performance evaluation index matching of each edge device.

5. The data responsibility tracing method based on edge computing according to claim 1 is characterized in that: The abnormal characteristic value of each edge device obtained through processing also includes: The abnormal characteristic value of each edge device is used to quantitatively evaluate the abnormality degree of each edge device and provide a basis for fault risk assessment of each edge device.

6. The data responsibility tracing method based on edge computing according to claim 5 is characterized by: The comprehensive analysis to obtain the failure risk assessment index of each edge device also includes: The failure risk assessment index of each edge device is used to quantitatively assess the risk level of possible failure of each edge device, providing a basis for performing failure risk assessment on each edge device.

7. The data responsibility tracing method based on edge computing according to claim 6 is characterized by: The risk assessment and feedback of each edge device are performed as follows: The fault risk assessment index threshold is extracted from the system database, and the fault risk assessment index of each edge device is compared with the fault risk assessment index threshold. If the fault risk assessment index of an edge device is higher than or equal to the fault risk assessment index threshold, the edge device is marked as a faulty device and a risk warning is issued for the faulty device. If the fault risk assessment index of an edge device is lower than the fault risk assessment index threshold, the edge device is marked as a normal device and the result is displayed and output.

8. The data responsibility tracing method based on edge computing according to claim 7 is characterized by: The data is distributed to each edge device and cloud processing device based on the data volume that each edge device can carry and the risk assessment results. The specific distribution strategy is: When an edge device is a normal device, the edge device's required processing data is compared with the edge device's carryable data volume. If the edge device's required processing data is greater than the edge device's carryable data volume, the excess data volume needs to be distributed to each target edge device and cloud processing device for processing. If the edge device's required processing data is less than or equal to the edge device's carryable data volume, data processing is performed directly without additional allocation operations. When an edge device is a faulty device, the required processing data of the edge device is distributed to each target edge device and cloud processing device for processing, and the edge device does not process data.

9. A system using the data responsibility tracing method based on edge computing as described in any one of claims 1 to 8, characterized in that: include: Regional environmental impact assessment module, edge device performance assessment module, edge device abnormal feature assessment module, edge device failure risk assessment module, data allocation module and system database; The regional environmental impact assessment module is used to obtain edge devices of the target production line, mark each edge device, collect environmental data around the production line, and obtain regional environmental impact characteristic values after processing; The edge device performance evaluation module is used to obtain the operating data of each edge device, obtain the performance evaluation index of each edge device after processing, and match the data load capacity of each edge device according to the performance evaluation index of each edge device; The edge device abnormal feature evaluation module is used to collect basic data of each edge device and obtain the abnormal feature value of each edge device after processing; The edge device failure risk assessment module is used to comprehensively analyze the regional environmental impact characteristic value, the performance evaluation index of each edge device, and the abnormal characteristic value of each edge device to obtain the failure risk assessment index of each edge device. Based on the failure risk assessment index of each edge device, the module conducts risk assessment on each edge device and provides feedback. The data allocation module is used to obtain the required processing data of each edge device and allocate data to each edge device and cloud processing device based on the data capacity of each edge device and risk assessment results.

Images