Electric welding machine usage authority verification method based on big data

Abstract

The present invention discloses a method for verifying the use authority of an electric welding machine based on big data, which specifically relates to the technical field of big data analysis. The method comprises the following steps: first, collecting the use authority verification data and request response data of the electric welding machine through log records to form a large data set; then performing permission request response analysis and security verification analysis based on the data set, and evaluating the performance of local resources; then deciding whether to enable temporary cloud resources based on the evaluation results, and performing a resource scheduling duration estimation; finally, closing the cloud resources after a predetermined duration is reached, resuming the use of local resources, and cyclically executing the above steps; the present invention can perform dynamic resource management through a permission verification response index and a security verification completion index, and can realize seamless switching between cloud and local resources. If local resources cannot meet the demand, cloud resources are automatically called to ensure the normal operation of a preset user identity authentication system for the electric welding machine, thereby reducing manual intervention and improving the efficiency of equipment management.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and more specifically, to a method for verifying welding machine usage authority based on big data. Background Art

[0002] With the advancement of industrial automation and intelligentization, the management of heavy equipment such as welding machines has become increasingly complex. Traditional methods for verifying welding machine access permissions typically rely on manual approval or simple identity verification systems. This approach is susceptible to human error and is inefficient for large-scale use. This can lead to improper operation, equipment misuse, or unauthorized use, especially in complex production environments, increasing safety risks.

[0003] In high-risk industrial sectors, particularly those requiring high-precision, high-security operations, verifying welding machine access permissions requires more than simple identity verification. It also considers a variety of factors, including operator qualifications, operating environment, and operational history. Traditional permission management systems cannot efficiently process large amounts of data and are slow to respond to dynamically changing operating conditions, making real-time, accurate permission verification difficult. Furthermore, with the advancement of intelligent manufacturing, improvements in data collection and processing capabilities, and the widespread adoption of big data technologies, permission verification using pre-configured welding machine user authentication systems and big data analysis has become a more scientific and efficient approach.

[0004] However, in actual applications, the preset welding machine user authentication system may encounter performance bottlenecks due to insufficient local resources, and cannot guarantee the quality of access permission verification. Therefore, the present invention proposes a welding machine access permission verification method based on big data to solve the above problem. Summary of the Invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The method for verifying the use authority of welding machines based on big data includes the following steps:

[0007] Step 1: When local resources are used, within a fixed time window, the welder usage permission verification data and permission request response data are collected through the log records in the preset welder user authentication system to form a large log data set;

[0008] Step 2: Perform permission request response analysis and security verification analysis based on the large log data set, and perform local resource performance evaluation based on the results of the permission request response analysis and security verification analysis;

[0009] Step 3: Based on the local resource performance evaluation results, decide whether to enable temporary cloud resources. When enabling temporary cloud resources, estimate the resource scheduling duration based on the results of permission request response analysis and security verification analysis to obtain the total duration of enabling temporary cloud resources.

[0010] Step 4: After the total duration of enabling temporary cloud resources is reached, close the temporary cloud resources, restore to local resource usage, and perform steps 1 to 3 again.

[0011] In a preferred embodiment, the preset welding machine user identity authentication system is used to perform permission verification based on the identity information input by the user and the preset permission rules, determine whether the user has the permission to use the welding machine, and control the enabling or disabling of the welding machine according to the determination result.

[0012] In a preferred embodiment, when performing permission request response analysis based on a large log data set, the result obtained is a permission verification response index, and when performing security verification analysis based on a large log data set, the result obtained is a security verification completion index.

[0013] In a preferred embodiment, the logic for obtaining the authority verification response index is:

[0014] In a fixed time window, obtain the time series data corresponding to the response time of each request. To emphasize the response efficiency within the time window, calculate the response time impact value corresponding to the time series data: ; represents the standard deviation of time series data, Indicates the time series data The response time of a request, Indicates the total number of requests corresponding to the time series data. Indicates the response time impact value corresponding to the time series data, Represents a preset non-zero constant;

[0015] Get the number of successfully processed permission verification requests, taking into account the penalty for failed requests, and calculate the penalty factor: ; Indicates the number of successfully processed permission verification requests. represents the penalty factor;

[0016] Get the number of requests received in each preset request subwindow. At the same time, to emphasize the impact of load on response, calculate the load impact value: ; Indicates the average number of requests received by all request sub-windows, Represents the standard deviation of the number of requests received by all request sub-windows, Indicates the load impact value;

[0017] The calculation formula for the authority verification response index is:

[0018] ; is the preset non-zero adjustment coefficient, 、 are all preset non-zero influence coefficients, Indicates the permission verification response index.

[0019] In a preferred embodiment, the logic for obtaining the security verification completion index is:

[0020] Get the total number of verifications for all requests within a fixed time window , the number of successful verifications completed, the number of failed verifications , Number of timed verifications , and the average response time for verification Then calculate the ratio of the number of successful verifications completed to the total number of verifications requested to obtain the verification completion rate within the time window. ;

[0021] The penalty term reflects the impact of failed and timed verification on the overall security verification efficiency. The corresponding formula for the penalty term is:

[0022] ; is the penalty item, is the failure penalty value, is the timeout penalty value; ; ; 、 are all preset non-zero penalty factors, and ;

[0023] Considering the impact of response time, an adjustment function is introduced :

[0024] ; The preset maximum verification acceptance response time, It is the preset adjustment coefficient, and its value is between 0 and 1;

[0025] The calculation formula for the safety verification completion index is:

[0026] ; Complete index for safety verification.

[0027] In a preferred embodiment, performing local resource performance evaluation refers to:

[0028] The security verification completion index and the authority verification response index are substituted into the pre-trained convolutional neural network model. The convolutional neural network model outputs a result of 0 or 1. When the result is 0, it is determined that the local resource performance meets the preset operating conditions of the user identity authentication system for the welding machine. When the result is 1, it is determined that the local resource performance does not meet the preset operating conditions of the user identity authentication system for the welding machine. When the result is 1, temporary cloud resources are enabled.

[0029] In a preferred embodiment, the total duration of enabling temporary cloud resources is determined by the following logic:

[0030] Obtaining the safety verification completion index , Authority Verification Response Index , and then substitute it into the resource scheduling duration estimation formula:

[0031] ; 、 are all preset non-zero conversion coefficients, Schedule buffer time for preset resources, The total duration for enabling temporary cloud resources.

[0032] Technical effects and advantages of the present invention:

[0033] The present invention performs dynamic resource management through the permission verification response index and the security verification completion index. The permission verification response index reflects the response efficiency of the system when processing permission requests. If the index is low, it means that the system's ability to process permission requests is limited, which may give unauthorized personnel the opportunity to operate the device. By dynamically adjusting resource configuration (for example, increasing computing resources), the system's response speed can be improved, thereby effectively preventing abuse and ensuring the safety of device use. The security verification completion index reflects the system's completion of security verification. If the security verification is not completed in a timely manner, it may cause loopholes in the system's operation permission verification, thereby increasing security risks.

[0034] The present invention enables intelligent switching between cloud and local operations based on the permission verification response index and the security verification completion index. When the permission verification response index is low, permission verification efficiency can be improved by increasing local computing resources (such as processors and memory). This intelligent resource scheduling ensures smooth welding machine operation under high load conditions. When the security verification completion index is low, it indicates poor completion of the security verification and potential system security risks. In this case, security can be improved by activating security resources, such as introducing high-performance firewalls and identity authentication systems. This dynamic adjustment not only improves system security but also ensures efficient resource utilization.

[0035] The present invention can achieve seamless switching between cloud and local resources. Local resources are mainly responsible for daily tasks such as permission verification and data processing. When local resources meet system requirements, efficient operation can be guaranteed. When the load is high or complex tasks need to be processed, it can be decided whether to enable cloud resources through evaluation. If local resources cannot meet the needs, cloud resources are automatically called to ensure the normal operation of the preset welding machine user identity authentication system. The activation of cloud resources is based on the permission verification response index and the security verification completion index. This makes the activation of cloud resources not only to cope with load pressure, but also to perform precise scheduling based on security and verification completion, reduce costs, and improve overall flexibility.

[0036] Traditional methods of verifying the permissions of welding machines usually rely on manual review, which is complex and prone to errors, especially in environments with a large number of devices and frequent use. The present invention greatly reduces manual intervention and improves the efficiency of equipment management through an automated permission verification system, intelligent resource scheduling, and efficient switching between cloud and local resources. This automated management not only improves work efficiency, but also allows for better compliance with safety operating procedures, reduces the impact of human factors on equipment management, and avoids operational risks due to human errors. By analyzing the permission verification response index and the security verification completion index, the system can intelligently enable cloud resources or adjust local resources according to actual needs. This resource scheduling method avoids the waste of resources in the traditional static resource configuration mode, can maximize resource utilization efficiency, and reduce unnecessary costs. During the resource scheduling process, by switching between cloud and local resources, not only is the balance between system performance and security ensured, but costs can also be flexibly managed according to load conditions, reducing unnecessary consumption of cloud computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0038] Figure 1 This is a schematic diagram of the welding machine usage authority verification method based on big data in the present invention. DETAILED DESCRIPTION

[0039] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0040] Reference Figure 1 The following examples were obtained: Example

[0041] The method for verifying the use authority of welding machines based on big data includes the following steps:

[0042] Step 1: When local resources are used, within a fixed time window, log records in the preset welding machine user authentication system are used to collect welding machine usage permission verification data and permission request response data, forming a large log data set. By recording permission verification data and permission request response data during welding machine use, it can be ensured that every user's operation is strictly authenticated, and the entire permission verification process can be monitored in real time. This provides basic data for subsequent analysis and decision-making. As a dangerous industrial equipment, welding machines must have strict usage permission management. Previous manual review and traditional permission management methods are prone to human error and cannot achieve efficient and real-time monitoring. By collecting relevant log data and centrally managing it, accurate and traceable data support can be provided to the system.

[0043] Step 2: Based on the large log data set, permission request response analysis and security verification analysis are performed. Local resource performance is evaluated based on the results of these analyses. Through in-depth analysis of log data, key performance indicators such as permission request response time, success rate, and load impact are analyzed in real time, allowing for an assessment of the device's operational status and safety. Security verification analysis can identify potential risks and improve the safety of device operation. Electric welding machines can be exposed to security risks during operation, especially when permission verification is delayed or anomalies occur.

[0044] Step 3: Based on the results of the local resource performance evaluation, a decision is made on whether to enable temporary cloud resources. When enabling temporary cloud resources, a resource scheduling duration estimate is performed based on the results of permission request response analysis and security verification analysis, resulting in a total duration for enabling temporary cloud resources. By evaluating local resource performance, the welder's operating mode can be dynamically adjusted to determine whether to enable temporary cloud resources to enhance processing power. This not only improves resource utilization but also enables scalability under heavy loads, preventing performance issues that could affect welder use. In practical applications, the user authentication system used by the welder may experience performance bottlenecks due to various reasons, such as high load and network latency. By evaluating local resource performance, a real-time decision can be made on whether to enable cloud resources, ensuring high-quality applications.

[0045] Step 4: After the total duration of enabling temporary cloud resources is reached, the temporary cloud resources are closed, the use of local resources is restored, and steps 1 to 3 are performed again. Once the usage duration of the temporary cloud resources reaches the preset value, the system will close the cloud resources and restore the use of local resources to maintain resource balance. This flexible resource management method can reduce unnecessary costs and improve the sustainability of the overall system. Since cloud resources usually require payment, their use should be kept as simple as possible to avoid long-term unnecessary resource consumption. This step ensures the rational use of cloud resources, reduces costs, and guarantees operational stability through periodic local resource recovery.

[0046] With the advancement of industrial automation and digital technologies, intelligent management of equipment such as welding machines is becoming increasingly important. Traditional permission management and resource scheduling methods often suffer from slow response, low efficiency, and poor security. A big data-based welding machine access verification method is an innovative solution designed to address this need. By collecting and analyzing data and combining it with dynamic scheduling of cloud and local resources, it can effectively improve welding machine operational safety, management efficiency, and resource utilization.

[0047] The preset welding machine user identity authentication system is used to verify the authority based on the identity information entered by the user and the preset authority rules, determine whether the user has the authority to use the welding machine, and control the enabling or disabling of the welding machine based on the judgment result.

[0048] The preset welding machine user authentication system is considered as prior art in the present invention. It verifies the user's identity information input by the user and the preset permission rules to ensure that only qualified users can use the welding machine, and prohibits the use of the welding machine if the user does not meet the permission requirements. The following details its implementation and significance:

[0049] How the system works: User identity verification: Before using the welding machine, the user needs to enter identity information, such as username, work number, or other authentication information. The system compares the entered identity information with the user data stored in the database to confirm whether the user's identity meets the requirements for using the welding machine.

[0050] Permission rule verification: Each user's identity information is pre-set with a certain permission level. For example, some users may only have permission to operate a simple welding machine, while others may have permission to use a high-precision welding machine. The system verifies the user's identity based on pre-set permission rules (such as the user's department, job type, and training certificates). If the user meets the permission requirements, the system allows them to use the welding machine; otherwise, the operation is prohibited.

[0051] Controlling the activation or disabling of welding machines: After identity verification and permission rule verification, the system can control the activation and disabling of welding machines in real time. If user authentication fails, the system will refuse to start the device. This system can be linked with hardware interfaces such as the welding machine's control panel and control software to achieve physical-level control of the welding machine's start and stop.

[0052] System Significance: Ensuring Safety: Electric welders are high-risk industrial equipment. Improper operation can lead to equipment damage or serious safety incidents. Identity verification and permission checks ensure that only authorized personnel can operate the equipment, significantly reducing the risk of unqualified personnel operating the equipment. The system can restrict high-risk operations based on user operation history or qualification requirements. For example, untrained personnel are prohibited from operating high-voltage welders, avoiding safety hazards.

[0053] Improved operational management efficiency: Through permission verification, managers can monitor the usage of each welding machine in real time, ensuring that operators are qualified and preventing unauthorized use or misuse of equipment. The system's automated identity verification and permission checking reduces the workload of manual approval and monitoring, improving overall equipment management efficiency.

[0054] Enhanced operation traceability: Each time a welding machine is enabled or disabled, it is associated with user identity information, operation time, and other data. The system records the operation log, providing complete operation traceability. This provides data support for equipment management, problem diagnosis, and accountability. This traceability not only helps trace the source of problems but also facilitates subsequent equipment maintenance and audits.

[0055] Compliance: Many industrial safety sectors have strict compliance requirements for equipment use, particularly for equipment involved in hazardous operations. Identity verification systems ensure that operators meet compliance standards, such as receiving necessary training and possessing valid operating certificates. This permission management mechanism helps meet corporate and industry compliance requirements and avoid legal disputes or safety incidents caused by improper operation.

[0056] Flexible permission management: Preset permission rules can be flexibly configured based on the company's organizational structure, personnel training, equipment type, and other factors to meet management needs at different levels. The system not only authenticates users but also dynamically adjusts permission configuration based on permission rules, ensuring the system remains flexible and scalable under changing operational requirements.

[0057] When analyzing permission request responses based on large log datasets, the result is the Permission Verification Response Index. When analyzing security verification based on large log datasets, the result is the Security Verification Completion Index. The Permission Verification Response Index is calculated by analyzing time series data of permission request response times. It reflects the system's response efficiency and load when processing permission requests. This index combines factors such as the standard deviation of response time, the number of successfully processed requests, the penalty factor for failed requests, and the impact of request load.

[0058] Optimizing System Performance: The Permission Verification Response Index accurately reflects the system's efficiency in processing permission requests within different time windows. If response times are excessive or the standard deviation is large, the system may be experiencing performance bottlenecks or overload. Using this index, administrators can promptly identify system performance issues and make optimization adjustments. The response time calculation takes into account all requests, ensuring the system maintains high responsiveness even under high load.

[0059] For welding machine users, a faster permission verification response time means they can obtain authorization to use the equipment more quickly, thereby improving work efficiency. However, a prolonged response time can negatively impact the user experience and delay work progress. The permission verification response index can be used as a performance optimization indicator, helping system maintenance personnel adjust system resource allocation to improve the overall user experience.

[0060] Delays in request responses may be caused by malicious attacks (such as denial of service attacks) or system anomalies. Monitoring the permission verification response index can help identify these potential security risks and take measures to enhance system security.

[0061] The security verification completion index is calculated by analyzing factors such as successful verifications, failed verifications, timed verifications, and verification response time during the security verification process. It reflects the system's efficiency and success rate in performing security verifications.

[0062] The Safety Verification Completion Index displays the percentage of safety verifications successfully completed by the system within a specific time period, reflecting the system's performance in ensuring operational safety. A higher index indicates an efficient safety verification process, effectively preventing unauthorized users from operating welding machines and ensuring safety. A lower index may indicate a high number of failed or timed verifications, meaning potential safety risks may not be identified and prevented in a timely manner.

[0063] The Security Verification Completion Index can help administrators promptly identify potential security risks in the system. If the system fails to complete effective security verification, unauthorized personnel may gain operational privileges, increasing the probability of security incidents. Using this index, managers can quickly identify vulnerabilities in the system and perform targeted repairs. For example, a decrease in the index may indicate a slowdown in the system's verification response, resulting in the security verification not being completed within the scheduled time, which may in turn create security risks. In certain industries or regions, the use of equipment must comply with strict safety regulations and legal requirements. The Security Verification Completion Index provides a quantitative standard that can help equipment managers track and record the completion of each verification process to ensure that the system meets relevant compliance requirements. Failure to complete the security verification may lead to compliance issues and increase legal risks.

[0064] The Permission Verification Response Index and the Security Verification Completion Index are two key indicators for assessing system efficiency and security. Continuous monitoring of these two indices allows for timely identification of potential performance bottlenecks and security risks, enabling the implementation of optimization measures to ensure efficient and secure system operation. These indices provide quantitative data support, helping administrators make more informed decisions. For example, when the Permission Verification Response Index is low, administrators can consider increasing system resources; when the Security Verification Completion Index decreases, security resources can be strengthened to enhance system security. The resource scheduling mentioned later, including system resources and security resources, these two indices provide a basis for resource scheduling. Based on this direction, resources can be scheduled according to a pre-defined scheduling method. The specific scheduling implementation method can be any existing method known to those skilled in the art that achieves efficient and secure system operation, without limitation. Ultimately, efficient and secure system operation is essential. Using these two indices, the system can intelligently assess when to activate additional cloud resources or adjust the allocation of local resources, ensuring efficient system operation under varying load conditions.

[0065] The logic for obtaining the permission verification response index is as follows:

[0066] In a fixed time window, obtain the time series data corresponding to the response time of each request. To emphasize the response efficiency within the time window, calculate the response time impact value corresponding to the time series data: ; represents the standard deviation of time series data, Indicates the time series data The response time of a request, Indicates the total number of requests corresponding to the time series data. Indicates the response time impact value corresponding to the time series data, Represents a preset non-zero constant to avoid calculation anomalies; the core idea of ​​this formula is to measure the overall response capability of time series data. In order to emphasize the importance of fast response, an exponential function (exp) is used for calculation, so that the larger response time impact value will be exponentially magnified to highlight the poor response performance. The formula uses normalization, that is, ,This can reduce the impact of uneven data distribution on ,computing and improve the adaptability to different load conditions.

[0067] Get the number of successfully processed permission verification requests, taking into account the penalty for failed requests, and calculate the penalty factor: ; Indicates the number of successfully processed permission verification requests. Represents the penalty factor; this formula is used to measure the system's ability to handle failed requests, ensuring that additional penalties are given when permission verification fails. The reason for using a logarithmic function: When there are many failed requests, the logarithmic function can slow down the growth rate, preventing the exponential from dropping too quickly and preventing excessive penalties. When the number of successfully processed requests is large, will also increase, thus encouraging the system to maximize its success rate.

[0068] Get the number of requests received in each preset request subwindow. At the same time, to emphasize the impact of load on response, calculate the load impact value: ; Indicates the average number of requests received by all request sub-windows, Represents the standard deviation of the number of requests received by all request sub-windows, Represents the load impact value; the load directly affects the efficiency of permission verification. Therefore, by calculating the number of requests in a request subwindow and its standard deviation, we can assess the stability of the system under different loads. Since an increase in the number of requests often indicates increased system load, we use the exponential function exp to amplify the impact value to highlight the impact of high load.

[0069] The calculation formula for the authority verification response index is:

[0070] ; is the preset non-zero adjustment coefficient, 、 These are all preset non-zero impact coefficients, which are used to adjust the weights of response time and load impact values ​​to ensure adaptability in different scenarios. The permission verification response index (PDI) is a flexible, stable, and controllable calculation model for the permission verification response index. This model can be used to evaluate a system's real-time permission verification capabilities and provide data support for subsequent resource scheduling and optimization.

[0071] The logic for obtaining the safety verification completion index is as follows:

[0072] Get the total number of verifications for all requests within a fixed time window , the number of successful verifications completed, the number of failed verifications , Number of timed verifications , and the average response time for verification Then calculate the ratio of the number of successful verifications completed to the total number of verifications requested to obtain the verification completion rate within the time window. The percentage of verifications successfully completed by the system within a given time window serves as a direct measure of system efficiency. Calculated as the ratio of successful verifications to the total number of verifications, this effectively measures the overall verification success rate, with values ​​ranging from 0 to 1. When WC is close to 1, the system's processing capacity is strong and security verifications are nearly fully completed. When WC is too low, the verification success rate is poor, potentially indicating a high incidence of failures or timeouts.

[0073] The penalty term reflects the impact of failed and timed verification on the overall security verification efficiency. The corresponding formula for the penalty term is:

[0074] ; is the penalty item, is the failure penalty value, is the timeout penalty value; ; ; 、 are all preset non-zero penalty factors, and The penalty term reflects failures and timeouts encountered during the security verification process. By increasing the penalty term, the final value of the security verification completion index (AQ) is reduced. The higher the number of failed and timeout verifications, the higher the P value, which reduces the AQ and ensures that the system is not mistakenly judged as efficient despite a high failure rate. This means that failed verification has a greater impact than timed verification. This is because failed verification usually means there is a problem with the system authentication process, while timed verification may be caused by short-term system congestion or network delay, so they are given different weights.

[0075] This design approach can more reasonably reflect the impact of different verification anomalies on overall security.

[0076] Considering the impact of response time, an adjustment function is introduced :

[0077] ; The preset maximum verification acceptance response time, This is a preset adjustment factor, ranging from 0 to 1. This function is used to account for the impact of verification time on security assessment. A shorter verification time indicates a higher system efficiency. Conversely, a longer verification time indicates a slower system response, potentially impacting overall security. hour, A linear decrease indicates that the verification response time exceeds the maximum acceptable value, affecting verification efficiency, and therefore requires a certain deduction from the system's security evaluation. Using a linear decrease ensures that the adjustment range is controllable and does not excessively penalize short-term abnormal fluctuations.

[0078] The calculation formula for the safety verification completion index is: ; This is the security verification completion index. By quantifying the verification success rate, failure rate, timeout rate, and response time, a comprehensive security verification completion index (AQ) is provided to evaluate the system's verification efficiency. The successful verification ratio (WC) serves as the base score, directly reflecting the completion of the verification. The penalty item (P) for failed and timed verifications is used as a deduction item to ensure that the system is not considered efficient despite a large number of failures or timeouts. The adjustment function for the average response time further strengthens the impact of time factors in verification, ensuring that the system can operate under the premise of efficiency and security. This formula not only focuses on the verification success rate, but also combines the penalties for failures and timeouts, and further considers the impact of response time, thereby constructing a complete evaluation system that balances performance and security. This design approach enables the security verification system to be dynamically adjusted according to different business needs, improving overall reliability and practicality.

[0079] Performing a local resource performance assessment means:

[0080] The security verification completion index and the authority verification response index are substituted into the pre-trained convolutional neural network model. The convolutional neural network model outputs a result of 0 or 1. When the result is 0, it is determined that the local resource performance meets the preset operating conditions of the user identity authentication system for the welding machine. When the result is 1, it is determined that the local resource performance does not meet the preset operating conditions of the user identity authentication system for the welding machine. When the result is 1, temporary cloud resources are enabled.

[0081] The security verification completion index and permission verification response index are used as input, and the CNN model is allowed to learn and process these two parameters to determine whether the local resources meet the preset operating conditions. When the output of the CNN model is 0, it means that under the current operating conditions, the local resources can meet the operating requirements of the welding machine user authentication system. At this time, there is no need to enable temporary cloud resources, and the system can continue to use local resources for permission verification and security verification. If local resources can meet the system requirements, the activation of temporary cloud resources is avoided, unnecessary resource consumption is reduced, efficiency is improved, and operating costs are reduced. When the output of the CNN model is 1, it means that the current local resources cannot meet the operating requirements of the welding machine user authentication system. At this time, the system determines that temporary cloud resources need to be enabled to supplement the shortage of local resources.

[0082] Temporarily enabling cloud resources can dynamically expand system resources based on actual load demands, avoiding delayed system response times or system malfunctions due to insufficient local resources. By temporarily using cloud resources, the welder's user authentication system can be kept in good working order while avoiding the high cost of long-term cloud resource use. The introduction of a security verification completion index reflects the security and integrity of the system during verification, ensuring that the system is not vulnerable to attack or tampering when processing user authentication. The permission verification response index allows for real-time evaluation of the system's response efficiency, especially under high loads, ensuring that welder access permissions can be quickly verified and avoiding the impact of long response times on production efficiency. Inputting these two indices into a convolutional neural network comprehensively considers the system's security and performance, enabling dynamic resource management.

[0083] The application of convolutional neural networks enables the system to automatically determine when to use cloud resources and when to rely on local resources based on trained models, making resource management more intelligent and automated. Based on the model's output, the system can automatically adapt to varying load conditions without manual intervention, thereby improving system autonomy and responsiveness.

[0084] The permission verification response index reflects the system's response efficiency during the permission verification process. If the index is low, it indicates that the system responds slowly or does not process in a timely manner under high load. Administrators can consider improving processing efficiency by increasing system resources (such as computing power or storage capacity).

[0085] The Security Verification Completion Index measures the system's efficiency in completing all verification requests. A decrease in this index indicates reduced system verification efficiency, potentially indicating security vulnerabilities or inappropriate resource allocation. Administrators can strengthen security resources (such as firewalls and authentication processing capabilities) to improve security and mitigate potential failures or risks.

[0086] These two indices provide guidance on the system's resource requirements in different areas: When the permission verification response index is low, the system may require more computing resources to improve processing speed. When the security verification completion index is low, additional security resources may be needed to ensure efficient and secure verification. Based on these two indices, the system can dynamically schedule resources, increasing computing or security resources as needed to ensure efficient and secure system operation.

[0087] The convolutional neural network model uses two indices (the security verification completion index and the permission verification response index) as input to comprehensively consider current system performance and resource requirements. The convolutional neural network training process automatically identifies system bottlenecks under different conditions and, based on these inputs, determines whether resource scheduling is necessary. The security verification completion index helps the network identify potential performance degradation during the verification process and make timely adjustments.

[0088] Relying solely on the permission verification response index may not fully reflect the security and stability of the system, especially when security verification efficiency is low. By inputting the security verification completion index, the convolutional neural network can more accurately assess the impact of security verification on overall system performance, thereby improving the predictive accuracy of resource scheduling and ensuring that additional security resources can be activated when needed.

[0089] Even if the permission verification response index is good, if the security verification completion index is low, the system may face higher security risks. By combining these two indices and inputting them into the convolutional neural network, the system ensures that while the permission response is efficient, the effectiveness of security verification is also taken into account. This ensures that the network not only focuses on performance but also security, ensuring the system strikes a balance between performance and security. By inputting these key indicators, the convolutional neural network can automatically learn and adjust resource allocation strategies, not only considering the timeliness of permission responses but also effectively managing verification security. This allows for intelligent resource scheduling and avoids errors caused by human intervention.

[0090] The total duration of enabling temporary cloud resources is determined by the following logic: Get the security verification completion index , Authority Verification Response Index , and then substitute it into the resource scheduling duration estimation formula:

[0091] ; 、 These are preset, non-zero conversion coefficients that adjust the impact of the Security Verification Completion Index and the Permission Verification Response Index on the total duration. These parameters allow you to adjust the impact of security and permission verification based on the specific needs and priorities of your system. This may reflect the impact of security verification on resource scheduling time. It reflects the impact of the permission verification response. Adjusting these two coefficients can make the system respond dynamically to different situations. Schedule buffer time for preset resources, The total duration of temporary cloud resource activation. By predicting and dynamically scheduling system resource requirements, cloud resources are enabled when needed and their usage duration is rationally planned according to preset parameters to optimize resource utilization and cost management. By integrating the efficiency of security and permission verification with resource scheduling, resource utilization is ensured to be targeted, avoiding unnecessary resource waste. By accurately calculating the duration of cloud resource activation, the system can more effectively manage cloud resources, reducing costs while improving performance.

[0092] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0093] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0094] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0095] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0096] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for verifying the use authority of welding machines based on big data, characterized in that: The following steps are involved: Step 1: When local resources are used, within a fixed time window, the welder usage permission verification data and permission request response data are collected through the log records in the preset welder user authentication system to form a large log data set; Step 2: Perform permission request response analysis and security verification analysis based on the large log data set, and perform local resource performance evaluation based on the results of the permission request response analysis and security verification analysis; Step 3: Based on the local resource performance evaluation results, decide whether to enable temporary cloud resources. When enabling temporary cloud resources, estimate the resource scheduling duration based on the results of permission request response analysis and security verification analysis to obtain the total duration of enabling temporary cloud resources. Step 4: After the total duration of the temporary cloud resource activation is reached, the temporary cloud resource is closed, the local resource usage is restored, and steps 1 to 3 are performed again; When analyzing permission request responses based on a large log data set, the result is the permission verification response index. When analyzing security verification based on a large log data set, the result is the security verification completion index. The logic for obtaining the permission verification response index is as follows: In a fixed time window, obtain the time series data corresponding to the response time of each request. To emphasize the response efficiency within the time window, calculate the response time impact value corresponding to the time series data: ; represents the standard deviation of time series data, Indicates the time series data The response time of a request, Indicates the total number of requests corresponding to the time series data. Indicates the response time impact value corresponding to the time series data, Represents a preset non-zero constant; Get the number of successfully processed permission verification requests, taking into account the penalty for failed requests, and calculate the penalty factor: ; Indicates the number of successfully processed permission verification requests. represents the penalty factor; Get the number of requests received in each preset request subwindow. At the same time, to emphasize the impact of load on response, calculate the load impact value: ; Indicates the average number of requests received by all request sub-windows, Represents the standard deviation of the number of requests received by all request sub-windows, Indicates the load impact value; The calculation formula for the authority verification response index is: ; is the preset non-zero adjustment coefficient, 、 are all preset non-zero influence coefficients, Indicates the permission verification response index.

2. The method for verifying the use authority of a welding machine based on big data according to claim 1, characterized in that: The preset welding machine user identity authentication system is used to verify the authority based on the identity information entered by the user and the preset authority rules, determine whether the user has the authority to use the welding machine, and control the enabling or disabling of the welding machine based on the judgment result.

3. The method for verifying the use authority of an electric welding machine based on big data according to claim 2, characterized in that: The logic for obtaining the safety verification completion index is as follows: Get the total number of verifications for all requests within a fixed time window , the number of successful verifications completed, the number of failed verifications , Number of timed verifications , and the average response time for verification Then calculate the ratio of the number of successful verifications completed to the total number of verifications requested to obtain the verification completion rate within the time window. ; The penalty term reflects the impact of failed and timed verification on the overall security verification efficiency. The corresponding formula for the penalty term is: ; is the penalty item, is the failure penalty value, is the timeout penalty value; ; ; 、 are all preset non-zero penalty factors, and ; Considering the impact of response time, an adjustment function is introduced : ; The preset maximum verification acceptance response time, It is the preset adjustment coefficient, and its value is between 0 and 1; The calculation formula for the safety verification completion index is: ; Complete index for safety verification.

4. The method for verifying the use authority of a welding machine based on big data according to claim 3, characterized in that: Performing a local resource performance assessment means: The security verification completion index and the authority verification response index are substituted into the pre-trained convolutional neural network model. The convolutional neural network model outputs a result of 0 or 1. When the result is 0, it is determined that the local resource performance meets the preset operating conditions of the user identity authentication system for the welding machine. When the result is 1, it is determined that the local resource performance does not meet the preset operating conditions of the user identity authentication system for the welding machine. When the result is 1, temporary cloud resources are enabled.

5. The method for verifying the use authority of a welding machine based on big data according to claim 4, characterized in that: The total duration for enabling temporary cloud resources is determined by the following logic: Obtaining the safety verification completion index , Authority Verification Response Index , and then substitute it into the resource scheduling duration estimation formula: ; 、 are all preset non-zero conversion coefficients, Schedule buffer time for preset resources, The total duration for enabling temporary cloud resources.

Images