Intelligent recorder management method and system based on AI

Abstract

The invention discloses an AI-based intelligent recorder management method and system, and relates to the technical field of intelligent equipment management. According to the AI-based intelligent recorder management method and system, environmental interference data and recorder resource state data are acquired through a sensor, environmental interference features are extracted in combination with a convolutional neural network, interference types are analyzed, and environmental interference factors are calculated. And according to the environment interference factor, evaluating the matching degree between the working load of the recorder and the environment to obtain an environment matching index which is used for measuring the working efficiency of the recorder in the current environment. The task execution feasibility is further judged through the environment matching degree index, and the task priority is dynamically adjusted according to the resource condition. Finally, through a fuzzy control algorithm, the working mode of the recorder is dynamically adjusted, task scheduling and resource allocation are optimized, intelligent management is achieved, and the adaptability and working stability of the recorder are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent device management, and specifically to an AI-based intelligent recorder management method and system. Background Art

[0002] With the rapid development of information technology, the application of intelligent devices in all walks of life is becoming more and more extensive. Especially in the field of data collection and recording, intelligent recorders are widely used in environmental monitoring, industrial control, medical diagnosis and other fields due to their efficient and accurate monitoring capabilities. In order to ensure that intelligent recorders can perform tasks continuously and stably in complex and changing environments, environmental adaptability and resource management become crucial. Especially in high-interference working environments, external environmental factors such as temperature fluctuations, electromagnetic interference, and low-frequency vibrations often significantly affect the work efficiency and task execution of recorders. Therefore, how to improve the environmental adaptability of intelligent recorders and optimize their workload scheduling has become a key research direction for improving the performance and reliability of intelligent recorders.

[0003] Most of the existing intelligent recorder management methods rely on traditional hardware optimization or static environmental adaptation strategies, which are usually difficult to effectively cope with the challenges brought by real-time environmental changes. Existing resource scheduling methods often do not take into account the dynamic impact of environmental interference on recorder performance, resulting in inflexible task priority management under strong interference or resource constraints, which may lead to task execution failure or inefficiency. In addition, traditional environmental adaptation mechanisms are usually unable to evaluate the match between the recorder and the external environment in real time, and lack intelligent dynamic adjustment of task priorities, and cannot fully utilize the resources of the recorder for optimization. Therefore, existing methods are difficult to meet the needs of efficient task execution in complex environments, and there are problems such as low efficiency and slow response. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an AI-based intelligent recorder management method and system, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an AI-based intelligent recorder management method, comprising the following steps: S1. Obtaining the recorder's external environmental interference data and recorder resource status data through sensors, extracting environmental interference features through convolutional neural networks, identifying environmental interference types, analyzing the impact of environmental interference on the recorder's workload, and obtaining environmental interference factors; S2. According to the environmental interference factors, analyzing the matching degree between the recorder's workload and the external environment, obtaining the environmental matching index, which is used to measure the recorder's work efficiency in the current environment; S3. According to the environmental matching index, judging the feasibility of the recorder's task execution, and dynamically adjusting the task priority according to the environmental interference and the recorder's resource status; S4. According to the environmental matching index and the priority of task execution, dynamically adjusting the recorder's working mode through a fuzzy control algorithm.

[0006] Furthermore, the external environment interference data includes temperature gradient data, electromagnetic interference data, and low-frequency vibration data; the recorder resource status data includes processor load, memory usage, storage space, network bandwidth, and battery power.

[0007] Furthermore, the specific process of extracting environmental interference features through convolutional neural networks and identifying environmental interference types is as follows: preprocessing the temperature gradient data, electromagnetic interference data, and low-frequency vibration data, including standardization and normalization processing. For vibration data, the time domain signal is converted into a frequency domain signal through fast Fourier transform; the preprocessed data is input into multiple convolutional layers of the convolutional neural network, and a sliding window operation is performed on the input data through multiple filters to extract environmental interference features, including temperature change features, electromagnetic interference features, and low-frequency vibration features; the environmental interference features extracted by the convolutional layer are processed by the pooling layer, and the data dimension is reduced by downsampling to generate a feature map. The feature map obtained from the convolutional layer and the pooling layer is flattened into a vector through the fully connected layer and sent to the classifier to perform weighted combination of different features to identify the environmental interference types of temperature change, electromagnetic interference, and vibration; the output is converted into a probability distribution through an activation function, and finally the label of the environmental interference type is output, including temperature interference, electromagnetic interference, and vibration interference.

[0008] Furthermore, the impact of environmental interference on the recorder workload is analyzed, and the specific process of obtaining the environmental interference factor is as follows: the environmental interference features are extracted by convolutional neural network, and the weights of the environmental interference features are analyzed hierarchically to calculate the impact factors of each environmental interference on the recorder workload, including temperature impact factor, electromagnetic interference impact factor and low-frequency vibration impact factor; the temperature impact factor, electromagnetic interference impact factor and low-frequency vibration impact factor are comprehensively processed to obtain the environmental interference factor.

[0009] Furthermore, the specific process of analyzing the workload and external environment of the recorder and obtaining the environmental matching index is as follows: according to the workload data of the recorder and the environmental interference factors, each interference factor is analyzed with the workload of the recorder to evaluate the impact of each interference factor on the various resources of the recorder; the influence relationship between each environmental interference and workload is modeled, and the influence of each environmental interference on the workload of the recorder is calculated through regression analysis; the influence of each interference factor is compared with the load status of the recorder to obtain the environmental matching index as a standard for measuring the working efficiency of the recorder in the current environment.

[0010] Furthermore, based on the environment matching index, the specific process of judging whether the recorder can perform the task in the current environment is as follows: based on the environment matching index, set the minimum environment matching threshold for task execution, and compare the environment matching index with the minimum environment matching threshold for task execution: if the environment matching index is greater than or equal to the minimum environment matching threshold, it means that the recorder can perform the task in the current environment and continue with task scheduling; if the environment matching index is less than the minimum environment matching threshold, it means that the recorder cannot effectively perform the task in the current environment.

[0011] Furthermore, the specific process of dynamically adjusting the task priority according to the environmental interference and the resource status of the recorder is as follows: if the recorder cannot effectively perform the task in the current environment, dynamically evaluate the current working status of the recorder according to the environmental interference factors and the resource status of the recorder, and obtain the task priority adjustment factor; determine the priority of the task according to the task priority adjustment factor.

[0012] Furthermore, the adjustment logic of dynamically adjusting the working mode of the recorder through the fuzzy control algorithm is as follows: taking the environment matching index and task priority as input variables; mapping the environment matching index and task priority into fuzzy sets respectively, and establishing a fuzzy rule base; according to the fuzzy rule base, combined with the current environment matching index and task priority, performing fuzzy reasoning, generating an adaptive working mode output, and dynamically adjusting the working mode of the recorder.

[0013] An AI-based intelligent recorder management system includes the following modules: an environmental interference factor extraction module, an environmental matching evaluation module, a task priority adjustment module, and a working mode adjustment module; the environmental interference factor extraction module is used to obtain the external environmental interference data and the recorder resource status data of the recorder through sensors, extract environmental interference features through convolutional neural networks, identify environmental interference types, analyze the impact of environmental interference on the recorder workload, and obtain environmental interference factors; the environmental matching evaluation module is used to analyze the matching degree between the recorder workload and the external environment according to the environmental interference factors, and obtain the environmental matching index, which is used to measure the work efficiency of the recorder in the current environment; the task priority adjustment module is used to judge the feasibility of recorder task execution according to the environmental matching index, and dynamically adjust the task priority according to the environmental interference and the recorder resource status; the working mode adjustment module is used to dynamically adjust the working mode of the recorder through a fuzzy control algorithm according to the environmental matching index and the priority of task execution.

[0014] The present invention has the following beneficial effects: (1) This AI-based intelligent recorder management method obtains external environmental interference data and recorder resource status data through sensors, and uses convolutional neural networks to extract environmental interference features. It can accurately identify the type of environmental interference, thereby deeply analyzing the impact of the environment on the recorder workload and obtaining environmental interference factors. It improves the accuracy of environmental adaptability analysis, helps to optimize the operating performance of the recorder under various environmental conditions, and effectively reduces the negative impact of external interference on the recorder performance.

[0015] (2) This AI-based intelligent recorder management system analyzes the environmental matching index, combines the recorder task priority, and uses a fuzzy control algorithm to dynamically adjust the recorder's working mode, which can optimize task scheduling according to real-time environmental changes and task requirements. This method improves the task execution efficiency of the recorder under different working conditions, enhances the intelligence and adaptability of the system, ensures the reasonable allocation of task priorities and flexible adjustment of working modes, and greatly improves the performance and stability of the recorder.

[0016] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an AI-based intelligent recorder management method of the present invention.

[0018] Figure 2 This is a flow chart of an AI-based intelligent recorder management system of the present invention. DETAILED DESCRIPTION

[0019] The embodiment of the present application solves the problems of low task execution efficiency, resource waste and poor stability of the recorder due to the impact of external interference on the workload in a complex environment through an AI-based intelligent recorder management method and system. By intelligently analyzing environmental interference factors and recorder resource conditions, dynamically adjusting task priorities and optimizing working modes, the adaptability and task execution efficiency of the recorder under different environmental conditions are improved, and the intelligent management and autonomous adjustment capabilities of the recorder are significantly enhanced.

[0020] The overall idea of ​​the solution in the embodiments of this application is as follows: The external environmental interference data and resource status data of the recorder are obtained through sensors, and the environmental interference features are extracted through convolutional neural networks to identify the type of environmental interference, analyze the impact of environmental interference on the recorder workload, and obtain environmental interference factors.

[0021] According to the environmental interference factors, the matching degree between the workload of the recorder and the external environment is analyzed to obtain the environmental matching index, which is used to measure the working efficiency of the recorder in the current environment.

[0022] The feasibility of recorder task execution is judged based on the environmental matching index, and the task priority is dynamically adjusted according to environmental interference and recorder resource status.

[0023] According to the environment matching index and the priority of task execution, the working mode of the recorder is dynamically adjusted through the fuzzy control algorithm.

[0024] See also Figure 1 The embodiment of the present invention provides a technical solution: an AI-based intelligent recorder management method, comprising the following steps: S1. Obtaining the recorder's external environmental interference data and recorder resource status data through sensors, extracting environmental interference features through convolutional neural networks, identifying environmental interference types, analyzing the impact of environmental interference on the recorder's workload, and obtaining environmental interference factors; S2. According to the environmental interference factors, analyzing the matching degree between the recorder's workload and the external environment, obtaining an environmental matching index, which is used to measure the recorder's work efficiency in the current environment; S3. Judging the feasibility of the recorder's task execution based on the environmental matching index, and dynamically adjusting the task priority based on the environmental interference and the recorder's resource status; S4. Dynamically adjusting the recorder's working mode through a fuzzy control algorithm based on the environmental matching index and the priority of task execution.

[0025] In this implementation scheme, S1: In this step, the recorder collects interference data of the external environment (such as temperature, electromagnetic interference, vibration, etc.) and the resource status data of the recorder itself (such as processor load, memory usage, storage space, network bandwidth, battery power, etc.) in real time through the installed sensors. These data will provide a basis for subsequent analysis. The interference data is processed by a convolutional neural network (CNN), the features related to environmental interference are extracted, and the specific types of environmental interference (such as temperature fluctuations, electromagnetic interference, etc.) are identified, and then the impact of interference on the workload of the recorder is analyzed to obtain environmental interference factors. Sensors are devices used to collect external environmental information and internal resource status data of recorders. Common sensor types include temperature sensors, electromagnetic field sensors, acceleration sensors (for detecting vibrations), humidity sensors, etc. In the present invention, sensors are used to obtain interference data (such as temperature, electromagnetic interference and vibration, etc.) in the environment where the recorder is located and resource status data (such as processor load, memory, storage space, battery power, etc.) inside the recorder. Convolutional neural network (CNN) is a deep learning model widely used in image and signal processing. CNN extracts features from data through multiple convolutional layers and pooling layers. In the present invention, it is used to extract important features from environmental interference data collected by sensors. CNN can efficiently identify and classify different types of interference (such as temperature fluctuations, electromagnetic interference and low-frequency vibrations), thereby helping to determine their impact on the work of the recorder. Environmental interference factors refer to various factors in the external environment that may affect the normal operation of the recorder. In the present invention, environmental interference factors include temperature changes, electromagnetic interference and low-frequency vibrations. These factors are used to analyze the impact of the environment on the workload of the recorder, so as to subsequently optimize the work mode and task scheduling of the recorder. S2: According to the environmental interference factors extracted in step S1, this step will further analyze the matching degree between the workload of the recorder and the external environment. By calculating the environmental matching index, it is used to measure the working efficiency of the recorder in the current environment. This matching index can help identify the compatibility of the environment and the device status, so as to determine whether the recorder can efficiently perform tasks in the existing environment. The environmental matching index is a quantitative indicator for measuring the working efficiency of the recorder in a specific environment. By analyzing the environmental interference factors and the resource status of the recorder (such as processor load, memory usage, etc.), the index reflects the adaptability of the recorder to the current environment. When the environment matching index is high, it means that the recorder can efficiently perform tasks in the current environment; when the matching index is low, it may be necessary to adjust the task execution strategy or optimize the working mode. S3: Based on the environment matching index, the system will determine whether the recorder can complete the task in the current environment. If the environment matching index indicates that the current environment has a significant negative impact on task execution (such as high temperature, electromagnetic interference, etc.), the system will dynamically adjust the priority of the task based on the environmental interference and the status of the recorder resources.Adjusting the task priority helps ensure that high-priority tasks are processed first, while preventing low-priority tasks from being unable to execute smoothly due to excessive environmental interference. Task priority refers to the criteria for determining the order in which tasks are executed when multiple tasks are executed in parallel. The dynamic adjustment of task priority is based on the current resource status of the recorder, environmental interference, and the importance of the task. If the environment is unfavorable or resources are tight, the system will adjust the execution order according to the task priority to ensure that the most important tasks can be executed first with limited resources, avoiding task failure or delay due to insufficient resources.

[0026] S4: Dynamically adjust the working mode of the recorder through the fuzzy control algorithm. After the priority of task execution is determined, the system will adjust the working mode of the recorder through the fuzzy control algorithm. The fuzzy control algorithm can dynamically adjust the working state of the recorder (such as reducing power consumption, adjusting processing speed, changing working mode, etc.) according to the environmental matching index and task priority to adapt to environmental changes and improve the stability and efficiency of task execution. Fuzzy control allows flexible processing of input conditions (such as environmental interference, task priority, etc.), thereby achieving more precise regulation and optimization.

[0027] Specifically, the external environment interference data includes temperature gradient data, electromagnetic interference data, and low-frequency vibration data; the recorder resource status data includes processor load, memory usage, storage space, network bandwidth, and battery power.

[0028] In this implementation scheme, the external environment interference data includes the following important dimensions: Temperature gradient data: The temperature gradient refers to the rate of change and distribution of temperature in the environment where the recorder is located. Temperature changes directly affect the working state of the recorder, especially when the device is overheated, which may cause performance degradation, hardware failure or system crash. By collecting temperature gradient data, the system can monitor the temperature changes around the recorder in real time and identify temperature fluctuations that may cause device failure in advance. Electromagnetic interference data: Electromagnetic interference (EMI) refers to the impact of electromagnetic waves caused by external electronic devices or natural phenomena in the environment (such as lightning, radio waves, etc.) on the signal transmission of the recorder. Electromagnetic interference can cause the signal quality of the recorder to deteriorate and even affect the data storage and processing functions. Collecting electromagnetic interference data helps to identify and avoid interference sources to ensure the stable operation of the recorder. Low-frequency vibration data: Low-frequency vibration usually comes from mechanical movement, traffic flow or natural earthquakes in the external environment. Excessive vibration may affect the sensor accuracy of the recorder, resulting in measurement errors or equipment damage. The collection of low-frequency vibration data helps to monitor the vibration intensity in the environment in real time, thereby avoiding negative impacts on the accuracy of the recorder. Recorder resource status data: Processor load: The processor load of the recorder indicates the current computing power usage of the processor, usually measured by CPU utilization or processor cycle occupancy. High load may mean that the device is performing complex tasks or there is a performance bottleneck, which may cause the recorder to respond slowly or delay task execution. Memory usage: Memory usage indicates the current memory resource usage of the recorder. Excessive memory usage may cause the system to be unable to load new tasks or perform data processing operations. The adequacy of memory directly affects the processing speed of tasks and the responsiveness of the system. Storage space: Storage space refers to the hard disk or flash memory space available to the recorder. Sufficient storage space is critical to the normal operation of the recorder, especially when performing large-scale data collection and storage tasks. Insufficient space may cause data loss, task interruption, or device crash. Network bandwidth: Network bandwidth refers to the communication capability between the recorder and external systems (such as cloud platforms, other devices, etc.). Limited bandwidth may cause slow or interrupted data transmission, affecting real-time data synchronization and task execution efficiency. Battery power: Battery power refers to the remaining battery energy in the recorder device. Low battery will limit the operating time of the device and may cause the device to shut down at a critical moment. Therefore, the battery level is an important indicator to evaluate whether the logger can continue to perform its mission.

[0029] Specifically, the specific process of extracting environmental interference features through convolutional neural networks and identifying environmental interference types is as follows: preprocessing the temperature gradient data, electromagnetic interference data, and low-frequency vibration data, including standardization and normalization processing. For vibration data, the time domain signal is converted into a frequency domain signal through fast Fourier transform; the preprocessed data is input into multiple convolutional layers of the convolutional neural network, and a sliding window operation is performed on the input data through multiple filters to extract environmental interference features, including temperature change features, electromagnetic interference features, and low-frequency vibration features; the environmental interference features extracted by the convolutional layer are processed by the pooling layer, and the data dimension is reduced by downsampling to generate a feature map. The feature map obtained from the convolutional layer and the pooling layer is flattened into a vector through the fully connected layer and sent to the classifier to perform weighted combination of different features to identify the environmental interference types of temperature change, electromagnetic interference, and vibration; the output is converted into a probability distribution through an activation function, and finally the label of the environmental interference type is output, including temperature interference, electromagnetic interference, and vibration interference.

[0030] In this implementation scheme, data preprocessing: standardization and normalization processing: data preprocessing is to eliminate the influence of different dimensions on the analysis results. Temperature gradient, electromagnetic interference and low-frequency vibration data usually have different numerical ranges. Standardization usually adjusts the data to zero mean and unit variance, while normalization scales the data to a specific range (such as 0 to 1). This preprocessing helps the convolutional neural network (CNN) to effectively learn the pattern of the data and avoid some features from having excessive influence on the learning process due to large values. Fourier transform of low-frequency vibration data: vibration data is usually a time domain signal. In order to convert it into a form that can reveal frequency characteristics, a fast Fourier transform (FFT) is used to convert the time domain signal into a frequency domain signal. FFT can extract periodic components, namely frequency characteristics, from the vibration signal to help identify interference caused by vibration. Input data to the convolution layer: The preprocessed data (including temperature gradient, electromagnetic interference, and low-frequency vibration data) will be fed into the convolution layer of the convolutional neural network as input. The function of the convolution layer is to extract features from the input data by performing a sliding window operation through multiple filters (convolution kernels). The filter slides over the input data to extract local features, and the convolution layer learns specific patterns in the image or signal (such as temperature changes, electromagnetic wave frequency components, vibration patterns, etc.). Convolution operation: The convolution operation is to perform a weighted summation of the filter (matrix) and the input data (such as temperature, vibration, etc.), and then pass it to the next layer through an activation function (such as ReLU). Different filters can identify different local patterns, such as temperature rise, periodic fluctuations in vibration, etc. The role of the pooling layer: The feature map extracted by the convolution layer usually has a high dimension. The main role of the pooling layer is to reduce the dimension of the data through downsampling (such as maximum pooling or average pooling), thereby reducing the amount of calculation and the risk of overfitting, while retaining important features. The pooling operation will reduce the spatial size of the data, greatly reducing the number of parameters of the network and improving training efficiency. Maximum pooling: In the pooling operation, the maximum pooling technique is usually used, that is, the maximum value in each window is selected as the representative of the window. This helps to retain the most significant features in the input data. Flatten the feature map and feed it into the fully connected layer: The pooled feature map is flattened into a one-dimensional vector and fed into the fully connected layer. The role of the fully connected layer is to perform a weighted combination of different features through linear transformations to generate high-level abstract features. At this point, the network has a deeper understanding of the impact of each feature in the input data. Weighted combination: In the fully connected layer, each neuron is connected to all neurons in the previous layer, and the output is calculated by weighted summation. This process is equivalent to weighted summation of the features extracted from the convolutional layer and the pooling layer to comprehensively consider various interference factors. Classification operation: After the fully connected layer, the output is fed into the classifier.The classifier is usually a softmax layer, which converts the features extracted from the network into a probability distribution, thereby assigning a probability value to each type of environmental interference (such as temperature interference, electromagnetic interference, and vibration interference). Each output category corresponds to an environmental interference type. Activation function: In the classification stage, the activation function (softmax) is used to convert the network output into a probability distribution to ensure that the classification result meets expectations. The Softmax function converts the raw output value (unnormalized score) into a probability value, indicating the probability of occurrence of each type of environmental interference. Final output: Based on the result of the activation function, the network outputs the probability distribution of each type of environmental interference, and determines the final environmental interference label based on the maximum probability value. For example, if the network predicts that the temperature interference category has the highest probability, "temperature interference" is output as the final result.

[0031] Specifically, the specific process of analyzing the impact of environmental interference on the recorder workload and obtaining the environmental interference factor is as follows: the environmental interference features extracted by the convolutional neural network are analyzed by hierarchical analysis of the weights of the environmental interference features to calculate the impact factors of each environmental interference on the recorder workload, including temperature impact factor, electromagnetic interference impact factor and low-frequency vibration impact factor; the temperature impact factor, electromagnetic interference impact factor and low-frequency vibration impact factor are comprehensively processed to obtain the environmental interference factor.

[0032] In this implementation scheme, the impact of environmental interference on the workload of the recorder is analyzed and the environmental interference factor is calculated. The calculation can be performed according to the following steps. The design of the formula needs to combine the environmental interference features extracted by the convolutional neural network and the analysis of the weights of the environmental interference features by the analytic hierarchy process (AHP). The calculation formula of the environmental interference factor is: ; Formula explanation: : Environmental interference factor, which represents the total impact of temperature, electromagnetic interference and low-frequency vibration on the recorder's workload. The operating environment temperature of the recorder. : Reference temperature, usually the standard operating temperature of the recorder. : Temperature variation range, used to standardize temperature variation. : Frequency of temperature disturbance. : Maximum value of temperature interference frequency. : Weight coefficient of temperature interference. Gain index of temperature influence, used to adjust the influence of temperature on interference factors. :Electromagnetic field strength. Reference electromagnetic field strength. :The range of variation of electromagnetic field strength. : The frequency of the electromagnetic interference signal, : Maximum frequency of electromagnetic interference. Weighting factor for electromagnetic interference. The influence index of electromagnetic interference intensity on interference factor. :Vibration amplitude. : Maximum value of vibration amplitude. Vibration frequency (unit: Hz). Weighting factor for low frequency vibrations. The gain index of low-frequency vibration to interference factor. Weight coefficient: , , : Represents the weighted coefficients of temperature, electromagnetic interference and low-frequency vibration on environmental interference factors. These coefficients are adjusted according to specific application scenarios to ensure that the impact of different interference factors is reflected in proportion. The recorder works.

[0033] Specifically, the specific process of analyzing the workload and external environment of the recorder and obtaining the environmental matching index is as follows: according to the workload data of the recorder and the environmental interference factors, each interference factor is analyzed with the workload of the recorder, and the impact of each interference factor on the various resources of the recorder is evaluated; the influence relationship between each environmental interference and workload is modeled, and the influence of each environmental interference on the workload of the recorder is calculated through regression analysis; the influence degree of each interference factor is compared with the load status of the recorder to obtain the environmental matching index as a standard for measuring the working efficiency of the recorder in the current environment.

[0034] In this implementation, the calculation process is as follows: Impact assessment of interference factors: Determine the impact of each environmental interference (such as temperature, electromagnetic interference, vibration) on the recorder workload through regression analysis. The results of the regression analysis can be obtained through the coefficient and environmental disturbance data The relationship between load and interference is modeled: The impact of each interference factor on the recorder workload is expressed by This difference measure is used to build a model to ensure that the impact of interference on workload increases as the difference increases. Comprehensive evaluation and matching index calculation: The impact of each interference factor is multiplied by the workload of the recorder, and the final environmental matching index is calculated by adjusting the nonlinear regression function. The result reflects the working efficiency of the recorder in the current environment. Obtain the environment matching index. The following is a specific formula based on regression analysis. The calculation formula of the environment matching index is ; Formula explanation: Environmental matching index is a measure of the working efficiency of the recorder in the current environment. The higher the value, the better the matching between the environment and the workload of the recorder, and the higher the working efficiency. Environmental interference factor Including the influence of environmental factors such as temperature, electromagnetic interference and low-frequency vibration. For different interference factors, you can use the corresponding number To distinguish, the recorder workload : The resource load of the recorder, including processor load, memory usage, storage space, network bandwidth, and battery power. Different workload data are numbered . Regression function: Through regression analysis, we model the relationship between the impact of each interference factor and the workload of the recorder. In the regression function: : The value corresponding to the load status data of the recorder The numerical value corresponding to the environmental interference factor. The coefficient obtained in the regression analysis represents the weight of the impact of environmental interference on the workload of the recorder. Nonlinear adjustment: By adjusting the difference between workload and environmental interference The index is adjusted so that the matching index value is lower when the difference is large and higher when the difference is small. This adjustment uses a logistic regression model (Sigmoid function), where: : Through this index term, the environmental matching degree decreases rapidly as the difference between load and interference factors increases.

[0035] Specifically, according to the environment matching index, the specific process of judging whether the recorder can perform the task in the current environment is as follows: according to the environment matching index, set the minimum environment matching threshold for task execution, and compare the environment matching index with the minimum environment matching threshold for task execution: if the environment matching index is greater than or equal to the minimum environment matching threshold, it means that the recorder can perform the task in the current environment and continue with task scheduling; if the environment matching index is less than the minimum environment matching threshold, it means that the recorder cannot effectively perform the task in the current environment.

[0036] In this implementation scheme, environmental matching index calculation: the environmental matching index is calculated through the aforementioned steps, and this index reflects the work efficiency and adaptability of the recorder in the current environment. Setting a minimum environmental matching threshold: setting a minimum environmental matching threshold, which represents the minimum environmental conditions required for the recorder to effectively perform tasks. Generally speaking, this value is pre-set according to the complexity of the task and the requirements of the environment. Matching comparison: compare the calculated environmental matching index with the set minimum environmental matching threshold: if the environmental matching index is greater than or equal to the minimum threshold: it means that the environmental conditions are suitable for performing the task, and the recorder can continue with task scheduling. If the environmental matching index is less than the minimum threshold: it means that the current environment is not suitable for performing the task, the recorder cannot effectively perform the task, and the task or environmental settings may need to be adjusted.

[0037] Specifically, the specific process of dynamically adjusting the task priority according to the environmental interference and the resource status of the recorder is as follows: if the recorder cannot effectively perform the task in the current environment, dynamically evaluate the current working status of the recorder according to the environmental interference factors and the resource status of the recorder, and obtain the task priority adjustment factor; determine the priority of the task according to the task priority adjustment factor.

[0038] In this implementation scheme, the current working status of the recorder is evaluated: if the recorder cannot effectively perform tasks in the current environment (such as excessive environmental interference or insufficient resources), the working status of the recorder needs to be evaluated first. This involves a comprehensive analysis of environmental interference factors (such as temperature, electromagnetic interference, vibration, etc.) and recorder resource status (such as processor load, memory, storage, bandwidth, battery power, etc.) to understand the current working environment and the adequacy of recorder resources. In order to dynamically adjust the task priority according to environmental interference factors and the resource status of the recorder, a task priority adjustment factor is defined to reflect the change in the priority of task execution. This factor needs to take into account the impact of environmental interference on the performance of the recorder and the use of recorder resources. The following is the calculation formula of this factor and its explanation: The formula for the task priority adjustment factor is: ; Parameter explanation Task priority adjustment factor, which indicates the adjustment value of the current task relative to the original priority. , the task priority is increased; if , the task priority is reduced. Environmental interference weight factor is used to indicate the degree of influence of environmental interference on task priority. This factor reflects the influence of different environmental interferences (such as temperature, electromagnetic interference, vibration, etc.) on recorder resources and task execution. Changes in environmental interference factors measure the impact of current environmental interference on the work of the recorder. For example, higher temperatures or strong electromagnetic interference may cause the performance of the recorder to deteriorate, requiring the priority of the task to be adjusted. Specifically, It can be obtained by quantifying the type and intensity of environmental interference, usually expressed as a negative or positive value (a negative value indicates that the interference is severe and the task priority needs to be lowered; a positive value indicates that the environment is suitable and the task priority can be increased). : The recorder resource status weight factor indicates the influence of the recorder's available resources (such as processor load, memory, bandwidth, battery power, etc.) on the task priority. This factor is used to measure whether the task priority needs to be adjusted when resources are tight. The resource status of the recorder changes, measuring the impact of the current resource usage on the task. For example, if the processor or memory load of the recorder is high, the priority of the task needs to be adjusted to prevent the system from being overloaded. Specifically, Indicates the change in the current resource status relative to the maximum available resources, usually expressed as a negative or positive value (negative values ​​indicate insufficient resources and the task priority needs to be lowered, positive values ​​indicate sufficient resources and the task priority can be increased). Once the task priority adjustment factor is obtained , the priority of the task can be adjusted according to its value; if , indicating that the task priority needs to be improved, and the task can be executed first. , indicating that the task priority needs to be lowered and the task can be postponed. ,It shows that the environment and resource conditions have no impact on task execution, and the task priority remains unchanged.

[0039] Specifically, the adjustment logic of dynamically adjusting the working mode of the recorder through the fuzzy control algorithm is as follows: taking the environment matching index and task priority as input variables; mapping the environment matching index and task priority into fuzzy sets respectively, and establishing a fuzzy rule base; according to the fuzzy rule base, combined with the current environment matching index and task priority, performing fuzzy reasoning, generating an adaptive working mode output, and dynamically adjusting the working mode of the recorder.

[0040] In this implementation scheme, input variable definition: the input variables of the fuzzy control algorithm are the environment matching index and the task priority. These two variables reflect the working efficiency of the recorder in the current environment and the urgency of the task. Fuzzy set mapping: the environment matching index and the task priority are mapped to fuzzy sets respectively. For example: the environment matching index is mapped as: high, medium, and low (indicating environmental adaptability). The task priority is mapped as: high, medium, and low (indicating the urgency of the task). These mappings will be converted into fuzzy sets according to the membership function in the fuzzy control algorithm according to the predetermined rules, representing the fuzzy nature of the environment and the task. Establish a fuzzy rule base: define the working mode that should be adopted under different combinations of environment matching index and task priority. For example: if the environment matching is high and the task priority is high, a more efficient and full-power working mode can be selected. If the environment matching is low and the task priority is low, an energy-saving or low-power working mode can be selected. If the task priority is high but the environment matching is low, a protection mode may be adopted to reduce risks. Fuzzy reasoning and working mode output: according to the current environment matching index and task priority, through fuzzy reasoning, combined with the fuzzy rule base, the working mode output is generated. Fuzzy reasoning is to operate the input variables of the fuzzy set through the rule base to obtain a fuzzy conclusion (adaptive working mode). The output adaptive working mode will indicate the specific working mode that the recorder should adopt (for example: full power mode, energy saving mode, protection mode). Dynamically adjust the recorder working mode: Finally, according to the results of fuzzy reasoning, the working mode of the recorder is dynamically adjusted to optimize the working efficiency and stability of the recorder under the current environment and task conditions. Through dynamic adjustment, the recorder can operate in the best way under different environmental interference and resource conditions.

[0041] An AI-based intelligent recorder management system includes the following modules: an environmental interference factor extraction module, an environmental matching evaluation module, a task priority adjustment module, and a working mode adjustment module; the environmental interference factor extraction module is used to obtain the external environmental interference data of the recorder and the resource status data of the recorder through sensors, extract environmental interference features through convolutional neural networks, identify environmental interference types, analyze the impact of environmental interference on the workload of the recorder, and obtain environmental interference factors; the environmental matching evaluation module is used to analyze the matching degree between the workload of the recorder and the external environment according to the environmental interference factors, and obtain the environmental matching index, which is used to measure the work efficiency of the recorder in the current environment; the task priority adjustment module is used to judge the feasibility of the execution of the recorder task according to the environmental matching index, and dynamically adjust the task priority according to the environmental interference and the resource status of the recorder; the working mode adjustment module is used to dynamically adjust the working mode of the recorder through a fuzzy control algorithm according to the environmental matching index and the priority of task execution.

[0042] In this implementation scheme, the environmental interference factor extraction module: This module collects interference data (such as temperature, electromagnetic interference, vibration, etc.) of the external environment of the recorder and the resource status data of the recorder (such as processor load, memory usage, storage space, etc.) through sensors. Then, the environmental interference features in these data are extracted through a convolutional neural network (CNN), the interference type is identified, and the impact of the interference on the workload of the recorder is analyzed, and finally the environmental interference factor is obtained. Environmental matching evaluation module: This module uses the information obtained from the environmental interference factor to analyze the matching degree between the workload of the recorder and the current external environment, and calculates the environmental matching index. The environmental matching index is an indicator to measure the working efficiency of the recorder in the current environment, which can reflect the adaptation of the environmental conditions and the performance of the recorder. Task priority adjustment module: Based on the environmental matching index, this module determines whether the recorder can effectively perform tasks in the current environment. If the environmental matching index is low, it means that the environmental conditions are not suitable for performing tasks. The system will dynamically adjust the priority of the task according to the environmental interference and the resource status of the recorder. Tasks with higher priorities will be executed first, and low-priority tasks may be delayed or abandoned. Working mode adjustment module: This module adjusts the working mode of the recorder through fuzzy control algorithm according to the environment matching index and task priority. The fuzzy control algorithm can flexibly adjust the working state of the recorder (for example, reduce power consumption, improve performance or adjust other system parameters) according to different situations of environment matching and task priority to ensure the smooth execution of the task.

[0043] In summary, this application has at least the following effects: An AI-based intelligent recorder management method and system, through the extraction and analysis of environmental interference factors, the system can monitor and evaluate the impact of the external environment on the performance of the recorder in real time, so as to dynamically adjust the working mode of the recorder to ensure its stable operation under different environmental conditions. Through environmental matching evaluation and task priority adjustment, the system can reasonably arrange task priorities according to environmental changes and the resource status of the recorder, avoid the execution of inefficient tasks, and improve the utilization efficiency of system resources. By dynamically adjusting the working mode through the fuzzy control algorithm, the system can optimize the working state of the recorder according to the environmental matching degree and task priority, thereby reducing unnecessary energy consumption and improving work efficiency.

[0044] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0045] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0046] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0048] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An AI-based intelligent recorder management method, characterized in that: The following steps are involved: S1. Obtain the external environmental interference data and resource status data of the recorder through sensors, extract environmental interference features through convolutional neural networks, identify environmental interference types, analyze the impact of environmental interference on the workload of the recorder, and obtain environmental interference factors; S2. Analyze the matching degree between the workload of the recorder and the external environment according to the environmental interference factors, and obtain the environmental matching index, which is used to measure the working efficiency of the recorder in the current environment; S3. Determine the feasibility of the recorder task execution based on the environmental matching index, and dynamically adjust the task priority based on environmental interference and recorder resource status; S4. According to the environment matching index and the priority of task execution, the working mode of the recorder is dynamically adjusted through the fuzzy control algorithm.

2. According to the AI-based intelligent recorder management method of claim 1, it is characterized by: The external environment interference data includes temperature gradient data, electromagnetic interference data, and low-frequency vibration data; Logger resource status data includes processor load, memory usage, storage space, network bandwidth, and battery power.

3. According to the AI-based intelligent recorder management method of claim 2, it is characterized by: The specific process of extracting environmental interference features through convolutional neural networks and identifying environmental interference types is as follows: Preprocess the temperature gradient data, electromagnetic interference data, and low-frequency vibration data, including standardization and normalization. For vibration data, convert the time domain signal into the frequency domain signal through fast Fourier transform; The preprocessed data is input into multiple convolutional layers of the convolutional neural network, and a sliding window operation is performed on the input data through multiple filters to extract environmental interference features, including temperature change features, electromagnetic interference features, and low-frequency vibration features; The environmental interference features extracted by the convolution layer are processed by the pooling layer, which reduces the data dimension through downsampling and generates a feature map. The feature map obtained from the convolution layer and the pooling layer is flattened into a vector through the fully connected layer and sent to the classifier. The weighted combination of different features is used to identify the environmental interference types such as temperature change, electromagnetic interference, and vibration. The output is converted into a probability distribution through an activation function, and finally the label of the environmental interference type is output, including temperature interference, electromagnetic interference, and vibration interference.

4. The AI-based intelligent recorder management method according to claim 3 is characterized in that: Analyze the impact of environmental interference on the workload of the recorder and obtain the specific process of environmental interference factors as follows: The environmental interference features extracted by the convolutional neural network are analyzed by hierarchical analysis of the weights of the environmental interference features to calculate the impact factors of each environmental interference on the recorder workload, including temperature impact factor, electromagnetic interference impact factor and low-frequency vibration impact factor; The temperature influence factor, electromagnetic interference influence factor and low-frequency vibration influence factor are processed comprehensively to obtain the environmental interference factor.

5. The AI-based intelligent recorder management method according to claim 4 is characterized in that: The specific process of analyzing the workload and external environment of the recorder and obtaining the environment matching index is as follows: According to the workload data of the recorder and the environmental interference factors, each interference factor is analyzed with the workload of the recorder to evaluate the impact of each interference factor on the resources of the recorder; Model the impact relationship between each environmental interference and workload, and calculate the impact of each environmental interference on the recorder workload through regression analysis; The influence degree of each interference factor is compared with the load status of the recorder to obtain the environmental matching index, which is used as a standard to measure the working efficiency of the recorder in the current environment.

6. The AI-based intelligent recorder management method according to claim 5 is characterized in that: According to the environment matching index, the specific process of judging whether the recorder can perform tasks in the current environment is as follows: According to the environment matching index, set the minimum environment matching threshold for task execution, and compare the environment matching index with the minimum environment matching threshold for task execution: If the environment matching index is greater than or equal to the minimum environment matching threshold, it means that the recorder can perform the task in the current environment and continue to schedule the task; If the environment matching index is less than the minimum environment matching threshold, it means that the recorder cannot effectively perform the task in the current environment.

7. The AI-based intelligent recorder management method according to claim 6 is characterized in that: The specific process of dynamically adjusting task priorities based on environmental interference and recorder resource conditions is as follows: If the recorder cannot effectively perform the task in the current environment, dynamically evaluate the current working status of the recorder according to the environmental interference factors and the resource status of the recorder, and obtain the task priority adjustment factor; Determine the priority of the task based on the task priority adjustment factor.

8. The AI-based intelligent recorder management method according to claim 7 is characterized in that: The adjustment logic of dynamically adjusting the working mode of the recorder through the fuzzy control algorithm is as follows: The environment fit index and task priority were used as input variables; The environment matching index and task priority are mapped into fuzzy sets respectively, and a fuzzy rule base is established; According to the fuzzy rule base, combined with the current environment matching index and task priority, fuzzy reasoning is performed to generate adaptive working mode output and dynamically adjust the working mode of the recorder.

9. An AI-based intelligent recorder management system, applied to an AI-based intelligent recorder management method according to any one of claims 1 to 8, characterized in that: It includes the following modules: environmental interference factor extraction module, environmental matching evaluation module, task priority adjustment module, and work mode adjustment module; The environmental interference factor extraction module is used to obtain the external environmental interference data and resource status data of the recorder through sensors, extract environmental interference features through convolutional neural networks, identify environmental interference types, analyze the impact of environmental interference on the workload of the recorder, and obtain environmental interference factors; The environment matching evaluation module is used to analyze the matching degree between the workload of the recorder and the external environment according to the environmental interference factors, and obtain the environment matching index, which is used to measure the working efficiency of the recorder in the current environment; The task priority adjustment module is used to determine the feasibility of the recorder task execution according to the environmental matching index, and dynamically adjust the task priority according to the environmental interference and the recorder resource status; The working mode adjustment module is used to dynamically adjust the working mode of the recorder through a fuzzy control algorithm according to the environment matching index and the priority of task execution.

Images