Abnormality monitoring method of Internet of Things equipment, storage medium and computer program product

Abstract

The invention discloses an abnormity monitoring method of Internet of Things equipment, a storage medium and a computer program product, and relates to the technical field of Internet of Things, and the method comprises the steps: obtaining the current equipment state data of the Internet of Things equipment at the current moment; determining a data value range based on the current equipment state data, and detecting whether the current equipment state data is within the data value range; if the current equipment state data is not in the data value range, determining that the Internet of Things equipment is in an abnormal operation state at the current moment; and determining the current abnormal degree of the Internet of Things equipment at the current moment, determining a target strategy corresponding to the current abnormal degree from preset response strategies corresponding to different abnormal degrees, and controlling the Internet of Things equipment to operate according to the target strategy. According to the invention, the anomaly detection accuracy of the Internet of Things equipment and the overall reliability and efficiency of the system are improved.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to an abnormality monitoring method, storage medium and computer program product for Internet of Things devices. Background Art

[0002] With the development of IoT technology, more and more smart devices are integrated into various application scenarios such as smart homes, smart cities, and industrial automation. For example, in IoT and smart systems, in order to better integrate and utilize resources, super devices have emerged, that is, multiple physical devices are abstracted into a virtual whole through software definition, so as to facilitate unified management and scheduling. The status and performance of IoT devices directly affect the reliability and efficiency of the entire system. At present, most methods for detecting device anomalies in IoT devices are based on fixed threshold settings. However, due to environmental changes and workload uncertainty, fixed thresholds may cause a large number of missed reports and false reports, which may affect the normal operation of IoT devices.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide an abnormality monitoring method, storage medium and computer program product for an Internet of Things device, aiming to solve the technical problem of low accuracy in abnormality detection of Internet of Things devices.

[0005] To achieve the above purpose, the present application proposes a method for abnormal monitoring of IoT devices, the method comprising:

[0006] Acquire current device status data of the IoT device at the current moment, wherein the device status data is used to characterize the operating state of the IoT device at the current moment and the operating environment of the IoT device at the current moment;

[0007] Determine a data value range based on the current device status data, and detect whether the current device status data is within the data value range;

[0008] If the current device status data is not within the data value range, it is determined that the IoT device is in an abnormal operating state at the current moment;

[0009] Determine the current abnormality level of the IoT device at the current moment, determine a target strategy corresponding to the current abnormality level from preset response strategies corresponding to different abnormality levels, and control the operation of the IoT device according to the target strategy.

[0010] In one embodiment, before the step of determining the data value range based on the current device status data, the step further includes:

[0011] Acquire historical device status data before the current device status data;

[0012] The step of determining a data value range based on the current device status data comprises:

[0013] Moving a preset moving window according to a preset step length, and determining reference data at multiple moments from the current device state data and the historical device state data before the current moment through the moving window;

[0014] Calculate the benchmark mean and benchmark standard deviation of the benchmark data at each moment;

[0015] The floating value is obtained by weighting the benchmark standard deviation with a preset adjustment coefficient, the difference between the benchmark mean and the floating value is used as the lower limit, the sum of the benchmark mean and the floating value is used as the upper limit, and the data value range is determined based on the lower limit and the upper limit.

[0016] In one embodiment, the step of determining a data value range based on the current device status data includes:

[0017] The current device state data is input into a preset threshold output model to obtain the data value range, wherein the threshold output model is trained based on the initial device state data.

[0018] In one embodiment, before the step of inputting the current device status data into a preset threshold output model to obtain the data value range, the step further includes:

[0019] Acquire historical device status data before the current device status data;

[0020] When a trigger model update instruction is detected, the threshold output model is updated using the historical device status data before the current moment, and the updated threshold output model is used as the preset threshold output model.

[0021] In one embodiment, after the step of controlling the operation of the IoT device according to the target strategy, the method further includes:

[0022] Detecting whether the IoT device has returned to normal;

[0023] If the IoT device does not return to normal, determine to trigger a model update instruction;

[0024] The step of updating the threshold output model by using the historical device status data before the current moment comprises:

[0025] The threshold output model is updated based on the current abnormality level, the current device status data, and the historical device status data before the current moment.

[0026] In one embodiment, before the step of determining the data value range based on the current device status data, the step further includes:

[0027] Performing denoising processing on the current device status data to obtain denoised status data;

[0028] Determine an abnormal value in the denoised state data, and remove the abnormal value from the denoised state data to obtain abnormality-processed state data;

[0029] Performing data smoothing on the abnormality processed state data by using a sliding window technique to obtain smoothed state data;

[0030] The step of determining a data value range based on the current device status data comprises:

[0031] A data value range is determined based on the smoothing state data.

[0032] In one embodiment, the step of determining the current abnormality level of the IoT device at the current moment includes:

[0033] Obtaining the next moment operation status of the IoT device at the next moment;

[0034] If the operating state at the next moment is an abnormal operating state, the next moment is updated to the current moment, and the step of obtaining the operating state of the IoT device at the next moment is performed;

[0035] If the operating status at the next moment is a normal operating status, then determine the duration of the abnormality of the Internet of Things device at the current moment, and determine the degree of data deviation between the current device status data and the data value range, and use the abnormality duration and the data deviation degree as the current abnormality degree, wherein the abnormality duration is the duration of the continuous moments of the current moment and the Internet of Things device in the abnormal operating state before the current moment.

[0036] In one embodiment, the step of controlling the operation of the IoT device according to the target strategy includes:

[0037] If the current abnormality level is a mild abnormality, outputting warning information through the Internet of Things device;

[0038] If the current abnormality level is a moderate abnormality, reducing the device load of the IoT device;

[0039] If the current abnormality level is a severe abnormality, the device service of the IoT device is sent to a backup device, and the IoT device is shut down.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the abnormal monitoring method of the Internet of Things device as described above are implemented.

[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the abnormal monitoring method of the Internet of Things device as described above.

[0042] In the present application, by obtaining the current device status data of the Internet of Things device at the current moment, wherein the device status data is used to characterize the operating status of the Internet of Things device at the current moment and the operating environment of the Internet of Things device at the current moment; determining a data value range based on the current device status data, and detecting whether the current device status data is within the data value range; if the current device status data is not within the data value range, determining that the Internet of Things device is in an abnormal operating state at the current moment; determining the current abnormality degree of the Internet of Things device at the current moment, and determining a target strategy corresponding to the current abnormality degree from preset response strategies corresponding to different abnormality degrees, and controlling the operation of the Internet of Things device according to the target strategy.

[0043] Compared with the traditional fixed threshold method, which is prone to missed reports and false reports when facing environmental changes and workload uncertainties, this application dynamically determines the data value range based on the current device status data that can reflect the actual situation of the device, rather than relying on a fixed threshold, thereby improving the accuracy of anomaly detection and reducing missed reports and false reports. In addition, after determining that the IoT device is in an abnormal operating state, the current degree of abnormality is further determined, and a suitable target strategy is selected from the preset response strategy to control the operation of the device. This refined control process can more effectively respond to different types of anomalies and ensure that the device resumes normal operation in the shortest possible time, thereby improving the overall reliability and efficiency of the system. As a result, this application improves the accuracy of anomaly detection of IoT devices and the reliability and efficiency of the system as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A flowchart of the first embodiment of the abnormal monitoring method for an Internet of Things device of the present application is provided;

[0047] Figure 2 A flowchart of the second embodiment of the abnormal monitoring method for an Internet of Things device of the present application is provided;

[0048] Figure 3 A flowchart of the third embodiment of the abnormal monitoring method for an Internet of Things device of the present application;

[0049] Figure 4 A schematic diagram of a simplified process of an abnormality monitoring method for an Internet of Things device provided in one embodiment of the present application;

[0050] Figure 5 This is a schematic diagram of the module structure of the abnormality monitoring device of the Internet of Things device according to the embodiment of the present application;

[0051] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the abnormal monitoring method of the Internet of Things device in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: by obtaining the current device status data of the Internet of Things device at the current moment, wherein the device status data is used to characterize the operating status of the Internet of Things device at the current moment and the operating environment of the Internet of Things device at the current moment; determining the data value range based on the current device status data, and detecting whether the current device status data is within the data value range; if the current device status data is not within the data value range, determining that the Internet of Things device is in an abnormal operating state at the current moment; determining the current abnormality degree of the Internet of Things device at the current moment, and determining the target strategy corresponding to the current abnormality degree from the preset response strategies corresponding to different abnormality degrees, and controlling the operation of the Internet of Things device according to the target strategy.

[0056] In this embodiment, for ease of description, the following description is made taking the abnormality monitoring device of the Internet of Things device as the execution subject.

[0057] With the development of IoT technology, more and more smart devices are integrated into various application scenarios such as smart homes, smart cities, and industrial automation. For example, in IoT and smart systems, in order to better integrate and utilize resources, super devices have emerged, that is, multiple physical devices are abstracted into a virtual whole through software definition, so as to facilitate unified management and scheduling. The status and performance of IoT devices directly affect the reliability and efficiency of the entire system. At present, most methods for detecting device anomalies in IoT devices are based on fixed threshold settings. However, due to environmental changes and workload uncertainty, fixed thresholds may cause a large number of missed reports and false reports, which may affect the normal operation of IoT devices.

[0058] The present application provides a solution that enables the present application to dynamically determine the data value range based on the current device status data that can reflect the actual situation of the device, rather than relying on a fixed threshold, thereby improving the accuracy of anomaly detection and reducing missed reports and false alarms. In addition, after determining that the IoT device is in an abnormal operating state, the current degree of abnormality is further determined, and a suitable target strategy is selected from the preset response strategy to control the operation of the device. This refined control process can more effectively respond to different types of anomalies and ensure that the device resumes normal operation in the shortest possible time, thereby improving the overall reliability and efficiency of the system. As a result, the present application improves the accuracy of anomaly detection of IoT devices and the reliability and efficiency of the system as a whole.

[0059] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device that can realize the above functions, an abnormality monitoring device of an Internet of Things device, etc. The following takes the abnormality monitoring device as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the present application embodiment provides an abnormal monitoring method for an Internet of Things device, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the abnormality monitoring method for IoT devices of the present application.

[0061] In this embodiment, the abnormality monitoring method of the Internet of Things device includes steps S10 to S40:

[0062] Step S10, obtaining current device status data of the IoT device at the current moment, wherein the device status data is used to characterize the operating state of the IoT device at the current moment and the operating environment of the IoT device at the current moment;

[0063] It should be noted that the current device status data refers to the data on the device operating status obtained by the IoT device through sensors or other data collection means at a specific time point or time period. The device status data is used to characterize the operating status of the IoT device at the current moment and the operating environment of the IoT device at the current moment. These data may include physical parameters such as temperature, humidity, pressure, speed, voltage, current, and logical parameters such as the device's operating status, working mode, and fault information. These data are the basis for abnormal monitoring and status evaluation of equipment.

[0064] It is understandable that by real-time monitoring and analysis of current equipment status data, abnormal conditions of equipment can be discovered in a timely manner, providing decision support for equipment maintenance and management.

[0065] Step S20, determining a data value range based on the current device status data, and detecting whether the current device status data is within the data value range;

[0066] It should be noted that the data value range refers to the interval between the maximum and minimum values ​​allowed for the IoT device status data under normal operating conditions. This range can be determined based on factors such as the device's design specifications, operating experience, and historical data, and is used to determine whether the device status data is within the normal range.

[0067] The system determines a reasonable value range for each status data based on historical data, equipment specifications, environmental requirements and other factors, compares the current equipment status data with this range, and determines whether the data is within the normal range. When the equipment status data exceeds the data value range, it is generally considered that the equipment is in an abnormal state and appropriate measures need to be taken to handle it.

[0068] It can be understood that in a specific implementation, the data value range can be determined based on the current device status data using a statistical method, or the data value range can be determined using a machine learning model. There is no specific limitation here and it can be set according to actual needs.

[0069] Exemplarily, before the step S20: determining the data value range based on the current device status data, the step further includes:

[0070] Step S01, performing denoising processing on the current device status data to obtain denoised status data;

[0071] In the process of abnormal monitoring of IoT devices, the device status data may contain various noises, such as sensor errors, data transmission errors, etc. These noises can be reduced or eliminated through denoising processing techniques, such as filtering algorithms and data smoothing, to obtain more accurate and reliable device status data, namely denoised status data.

[0072] It is understandable that denoising can significantly improve the quality of device status data and provide a more accurate basis for subsequent data analysis and anomaly detection. By reducing noise interference, the system can more accurately identify the true status of the device, thereby improving the robustness of the entire anomaly monitoring system.

[0073] Step S02, determining an abnormal value in the denoised state data, and removing the abnormal value from the denoised state data to obtain abnormality-processed state data;

[0074] After denoising, some extreme or abnormal data points may still exist in the denoised state data. By identifying and removing these outliers, we can ensure that the data for subsequent analysis is more stable and reliable. Specifically, statistical methods such as threshold judgment and box plot analysis can be used, which are not limited here. Removing outliers can reduce false positives caused by data anomalies and improve the accuracy of anomaly detection. In addition, the state data after anomaly processing is more stable, which is conducive to subsequent data analysis and anomaly detection.

[0075] Step S03, performing data smoothing processing on the state data after the abnormal processing by using a sliding window technology to obtain smoothed state data;

[0076] Sliding window technology is a commonly used data smoothing method. It reduces data fluctuations and noise by performing weighted averaging or other statistical processing on the data in the window. By applying sliding window technology to smooth the state data after abnormal processing, smoother and more stable state data can be obtained. The smoothed data is easier to identify minor abnormal changes, thereby improving the sensitivity of anomaly detection.

[0077] In this implementation, the step S20: determining the data value range based on the current device status data, includes:

[0078] Step S201, determining a data value range based on the smoothing state data.

[0079] After obtaining the smoothed state data, these data are used to determine the value range of the device state data for subsequent anomaly detection. It can be understood that the value range determined based on the smoothed state data is more accurate and reliable, which can reduce the occurrence of false positives and false negatives, help to formulate a more reasonable anomaly monitoring strategy, and improve the performance and stability of the entire system.

[0080] It should be noted that through steps such as denoising, outlier removal, data smoothing and value range determination, the quality of device status data and the accuracy of anomaly detection have been significantly improved, providing a strong guarantee for the healthy operation of IoT devices.

[0081] Step S30: if the current device status data is not within the data value range, it is determined that the IoT device is in an abnormal operation state at the current moment;

[0082] It should be noted that the abnormal operation state refers to the state in which the IoT device cannot work normally or its performance degrades due to various reasons during operation. The abnormal operation state may be manifested as the physical parameters of the device exceeding the normal range, logical parameter errors, fault alarms, etc. These abnormal states may cause device damage, downtime or degradation of service quality.

[0083] It is understandable that if the current device status data exceeds the normal range, the system determines that the device is in an abnormal state, providing a basis for rapid response and ensuring the accuracy of abnormality detection.

[0084] Step S40, determining the current abnormality level of the IoT device at the current moment, and determining a target strategy corresponding to the current abnormality level from preset response strategies corresponding to different abnormality levels, and controlling the operation of the IoT device according to the target strategy.

[0085] It should be noted that the current abnormality level refers to the degree to which the state data of an IoT device deviates from the normal threshold range or the severity of the abnormal condition at a certain moment or time period. The current abnormality level is usually measured by quantitative indicators, such as the duration of the abnormality, the degree of data deviation, etc. These indicators reflect the severity and urgency of the abnormal condition of the device.

[0086] After confirming the equipment abnormality, the severity of the abnormality is further determined. The specific method of determining the current abnormality level is not limited here, and can be set according to the corresponding quantitative indicators. For example, when the quantitative indicator of the current abnormality level is the duration of the abnormality, the current abnormality level can be determined by the range of the duration of the abnormality.

[0087] According to the severity of the abnormality, select the appropriate strategy from the preset response strategies to control the operation of the equipment to ensure the stable operation and service quality of the equipment. These strategies may include alarms, automatic adjustment of equipment parameters, starting backup equipment, etc. Specific strategies can be set according to actual needs and are not restricted here.

[0088] It is understandable that different response strategies are adopted according to different degrees of abnormalities to ensure the accuracy and effectiveness of processing, and automatic processing is achieved through preset response strategies to reduce manual intervention and improve processing efficiency.

[0089] This embodiment dynamically determines the data value range based on the current device status data that can reflect the actual situation of the device, rather than relying on a fixed threshold, thereby improving the accuracy of anomaly detection and reducing missed reports and false alarms. In addition, after determining that the IoT device is in an abnormal operating state, the current degree of abnormality is further determined, and a suitable target strategy is selected from the preset response strategy to control the operation of the device. This refined control process can more effectively respond to different types of anomalies and ensure that the device resumes normal operation in the shortest possible time, thereby improving the overall reliability and efficiency of the system. As a result, this embodiment improves the accuracy of anomaly detection of IoT devices and the reliability and efficiency of the system as a whole.

[0090] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , before the step S20: determining the data value range based on the current device status data, the method further includes:

[0091] Step A01, obtaining historical device status data before the current device status data;

[0092] Historical device status data refers to the data records about the operating status of the IoT device obtained through sensors or other data collection methods over the past period of time. These data record the status changes of the device at different time points, including data on normal operating status and abnormal status. Historical device status data can be used to analyze the operating rules, failure modes, performance change trends, etc. of the equipment, and provide data support for equipment maintenance and management.

[0093] In this embodiment, the step S20: determining the data value range based on the current device status data, includes:

[0094] Step S202, moving a preset moving window according to a preset step length, and determining reference data at multiple moments from the current device state data and the historical device state data before the current moment through the moving window;

[0095] Using the moving window technology, the system slides on the time axis according to the preset step size. In each window, the data at the corresponding moment is extracted from the current device status data and the historical device status data as the benchmark data, which is used to calculate the subsequent mean and standard deviation.

[0096] Step S203, calculating the benchmark mean and benchmark standard deviation of the benchmark data at each moment;

[0097] For the benchmark data within each moving window, the mean and standard deviation of the benchmark data at each moment are calculated. The mean reflects the average level of the data, while the standard deviation reflects the degree of dispersion of the data.

[0098] Step S204, weighting the benchmark standard deviation with a preset adjustment coefficient to obtain a floating value, taking the difference between the benchmark mean and the floating value as the lower limit, taking the sum of the benchmark mean and the floating value as the upper limit, and determining the data value range based on the lower limit and the upper limit.

[0099] The benchmark standard deviation is weighted using a preset adjustment coefficient to obtain a floating value, which reflects the volatility of the data. The benchmark mean minus the floating value is used as the lower limit of the data value range, and the benchmark mean plus the floating value is used as the upper limit. By calculating the adjustment coefficient and the floating value, the system can more flexibly adapt to the volatility of data of different device statuses.

[0100] Specifically, the data value range = [μ_w-kσ_w,μ_w+kσ_w], where (μ_w) is the real-time mean and (σ_w) is the standard deviation, and k is the adjustment coefficient.

[0101] It can be understood that by introducing historical data reference, moving window technology, mean and standard deviation calculation, and floating value determination, a comprehensive, dynamic and accurate analysis of device status data is achieved. These steps together improve the accuracy, flexibility and adaptability of anomaly detection, help to timely discover and handle device anomalies, and ensure the stable operation of the IoT system.

[0102] In one feasible implementation, the step 20: determining the data value range based on the current device status data, includes:

[0103] Step S205, inputting the current device state data into a preset threshold output model to obtain the data value range, wherein the threshold output model is trained based on the initial device state data.

[0104] The threshold output model is trained based on the initial device state data of the IoT device, and the model output is the corresponding data value range, that is, the learning goal of the model is to identify the normal fluctuation range of the device state data. In this implementation, there is no restriction on the model structure and training process of the threshold output model, and it can be set according to actual needs.

[0105] The data value range of the current device status data is determined by a pre-trained threshold output model. When new current device status data is input into the model, the model will output a data value range based on its learned knowledge. This range represents the expected fluctuation of the device status data under normal circumstances. It can be understood that by introducing a machine learning model, the system can automatically determine the data value range based on the device status data without manually setting fixed thresholds, thereby improving the automation and intelligence level of abnormal monitoring. Since the model is trained based on the historical status data of the device, it can adapt to the state changes of the device under different workloads and environmental conditions, that is, the model can dynamically adjust the data value range to reflect the current actual state of the device, thereby improving the accuracy and flexibility of anomaly detection.

[0106] In a feasible implementation manner, before the step S205: inputting the current device status data into a preset threshold output model to obtain the data value range, the method further includes:

[0107] Step B01, obtaining historical device status data before the current device status data;

[0108] Retrieve and obtain the historical status data of IoT devices before the current moment from storage devices or data warehouses. This data records key information such as the device's operating status, performance parameters, environmental indicators, etc. over a period of time, and is the basis for subsequent model training and updating.

[0109] By continuously accumulating historical data, the system can better adapt to the state changes of the equipment under different environments and conditions, and provide rich historical data support for subsequent model training, updating and anomaly detection, ensuring that the model can learn the normal operating mode and characteristics of the equipment, and improve the accuracy and adaptability of anomaly detection.

[0110] Step B02: when a trigger model update instruction is detected, the threshold output model is updated by using the historical device status data before the current moment, and the updated threshold output model is used as the preset threshold output model.

[0111] It should be noted that the model update instruction can be triggered by monitoring specific trigger conditions (such as significant changes in device status data, model performance degradation, etc.) in advance. When the trigger model update instruction is detected, the threshold output model is updated using the historical device status data before the current moment. The update process may include retraining the model, adjusting model parameters, or updating the model structure to ensure that the model can continue to reflect the latest status and data distribution of the device. The updated model will replace the original preset model and become the new anomaly detection benchmark.

[0112] By updating the model regularly or on demand, we can ensure that the model can continuously adapt to changes in device status, improve the accuracy and efficiency of anomaly detection, help improve the generalization and robustness of the model, reduce the occurrence of false positives and false negatives, improve the performance of the entire anomaly monitoring system, ensure that the anomaly monitoring system of IoT devices can operate stably in the long term, and provide strong support for the health management and maintenance of equipment.

[0113] In a feasible implementation manner, after the step S40: controlling the operation of the IoT device according to the target strategy, the step further includes:

[0114] Step C01, detecting whether the IoT device has returned to normal;

[0115] By continuously monitoring the device status data, it is determined whether the device has recovered from an abnormal state to a normal state. Specifically, the IoT device can be detected by real-time monitoring and analysis of the device performance parameters, operating status, and environmental indicators. The specific process is not limited here. By detecting the device status in real time, the system can promptly detect whether the device has recovered, and take corresponding measures to prevent the device from being in an abnormal state for a long time.

[0116] Step C02: if the IoT device does not return to normal, determine to trigger a model update instruction;

[0117] If the IoT device does not return to normal, it means that the current threshold output model may not accurately reflect the latest status of the device or data distribution, so the model needs to be updated to improve the accuracy of anomaly detection and determine the trigger model update instruction. By updating the model, the system can more accurately reflect the latest status of the device, improve the accuracy and adaptability of anomaly detection, help reduce false positives and false negatives caused by outdated or inaccurate models, and improve the performance of the entire anomaly monitoring system.

[0118] The step B02: updating the threshold output model by using the historical device status data before the current moment, comprises:

[0119] Step B021: updating the threshold output model based on the current abnormality level, the current device status data, and the historical device status data before the current moment.

[0120] After triggering the model update instruction, the system will update the threshold output model according to the current abnormality level, current device status data and historical device status data, retrain the model, adjust model parameters or update the model structure to ensure that the model can more accurately reflect the latest status and data distribution of the device.

[0121] It is understandable that by comprehensively considering the current degree of abnormality, current equipment status data and historical data, the system can update the model more accurately, improve the accuracy and generalization ability of the model by continuously learning and adapting to changes in equipment status, and continuously optimize the performance of the abnormality monitoring system.

[0122] Exemplarily, the process of determining the data value range through the model and performing device anomaly detection can be: obtaining the current device status data of the Internet of Things device at the current moment; inputting the current device status data into the preset threshold output model to obtain the data value range; detecting whether the current device status data is within the data value range; if the current device status data is not within the data value range, determining that the Internet of Things device is in an abnormal operation state at the current moment; determining the current abnormality degree of the Internet of Things device, and determining the target strategy corresponding to the current abnormality degree according to the preset response strategy corresponding to different abnormality degrees, and controlling the operation of the Internet of Things device according to the strategy; after executing the target strategy, detecting whether the Internet of Things device has returned to normal operation; if the Internet of Things device has not returned to normal, determining to trigger a model update instruction, specifically, obtaining historical device status data before the current moment, updating the threshold output model based on the current abnormality degree, the current device status data and the historical device status data, and using the new data to retrain or adjust the model parameters to improve the accuracy and adaptability of the model; the updated threshold output model will be used as the preset model for the next abnormal monitoring, and will continue to participate in the device status data value range determination and anomaly detection process. For example, taking the smart air conditioner in a smart home as an example, the process of determining the data value range and performing device abnormality detection through the model can be: the built-in sensor of the smart air conditioner monitors indoor temperature, humidity, air conditioner operating power and other parameters in real time, and transmits these data to the central control system through the Internet of Things technology; the central control system uses a preset threshold output model to determine the normal value range of parameters such as indoor temperature and humidity based on the initial state data and historical operation data of the smart air conditioner; if the indoor temperature suddenly rises or falls and exceeds the preset normal range, the system will detect the abnormality; the system comprehensively evaluates the current abnormality of the smart air conditioner based on factors such as the degree to which the indoor temperature deviates from the normal range and the duration of the abnormality; according to the degree of abnormality, the system may choose to send a warning message to the user, automatically adjust the air conditioner power to try to restore normal status, or shut down the air conditioner to prevent further damage; after executing the target strategy, the system continues to monitor the status of the smart air conditioner to determine whether it has resumed normal operation; if the smart air conditioner has not resumed normal operation, the model update instruction is triggered, and the threshold output model is retrained using the latest device status data and historical data to improve the detection capability of the abnormal state of the smart air conditioner.

[0123] It can be understood that by forming a closed-loop process of device status monitoring, model updating and optimization in the abnormal monitoring process of IoT devices, the healthy operation of IoT devices and the long-term stability of the system are ensured through continuous monitoring and model updating.

[0124] Based on the first and / or second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those of the first and / or second embodiments can be referred to the above description, and will not be described in detail later. Figure 3 The step S40: determining the current abnormality level of the IoT device at the current moment, comprises:

[0125] Step S401, obtaining the next moment operation status of the IoT device at the next moment;

[0126] The operating status at the next moment refers to the expected operating status of the IoT device at a certain point in the future or within a period of time. The operating status at the next moment is usually predicted and estimated based on factors such as the current device status data, historical data, and operating rules.

[0127] Real-time or regular acquisition of the operating status of IoT devices at the next moment can monitor the operation of the equipment in real time, detect anomalies in a timely manner, and dynamically track changes in the status of the equipment, providing a basis for subsequent abnormality assessment and strategy formulation.

[0128] Step S402: if the operating state at the next moment is an abnormal operating state, the next moment is updated to the current moment, and the step of obtaining the operating state of the IoT device at the next moment is performed;

[0129] When it is detected that the device is still in an abnormal operating state at the next moment, the next moment is updated to the current moment, and the status of the device at the next time point is continuously monitored. Through recursive monitoring, the system can continuously track the abnormal state of the device and accumulate the duration of the abnormal operating state for subsequent judgment of the degree of abnormality.

[0130] Step S403, if the operating state at the next moment is a normal operating state, determine the duration of the abnormality of the IoT device at the current moment, and determine the degree of data deviation between the current device state data and the data value range, and use the duration of the abnormality and the degree of data deviation as the current degree of abnormality, wherein the duration of the abnormality is the duration of the continuous moments of the current moment and the IoT device being in the abnormal operating state before the current moment.

[0131] It should be noted that the duration of abnormality refers to the continuous length of time from the device entering the abnormal state to returning to the normal state. This indicator reflects the persistence and impact range of the abnormal event. The degree of data deviation refers to the degree of deviation between the current device status data and its normal value range. This indicator provides a direct measure of the severity of the abnormality by quantifying the data difference.

[0132] When the system detects that the device will resume normal operation at the next moment, it will calculate the duration of the abnormality of the device in the current abnormal event (i.e., the length of time from the device's abnormality to its recovery), and calculate the degree of data deviation of the current device status data relative to the normal value range. The degree of data deviation and the duration of the abnormality are used as quantitative representations of the current degree of abnormality. Through the two indicators of abnormal duration and data deviation, the severity and scope of impact of abnormal events can be quantitatively evaluated, and abnormal handling strategies can be formulated more accurately, such as issuing alarms, triggering repair processes, etc., to improve the efficiency and accuracy of abnormal handling and provide data support for subsequent decision-making and strategy formulation.

[0133] Exemplarily, the process of determining the current abnormality level and determining the operation strategy may be: obtaining the current device status data of the IoT device at the current moment; determining the data value range, and detecting whether the current device status data is within the data value range; if the current device status data is within the data value range, the device is considered to be in a normal operating state and no further processing is required; if the current device status data is not within the data value range, it is determined that the device is in an abnormal operating state, and the current abnormality level of the IoT device at the current moment is determined. The specific process of determining the current abnormality level may be: obtaining the next moment operating state of the IoT device at the next moment, if the operating state at the next moment is still abnormal, updating the current moment to the next moment, and repeating the step of obtaining the operating state at the next moment to form a recursion, when it is detected that the operating state at the next moment is normal, calculating the abnormality duration from the current moment to the end of the abnormality (i.e., the next moment is a normal state), and calculating the data deviation degree between the current device status data and the data value range, and using the abnormality duration and the data deviation degree as indicators of the current abnormality level; according to the current abnormality level of the device, select a suitable strategy from the preset response strategies, for example, if the abnormality level of the device is high, it may be necessary to stop the device operation immediately and send an alarm to the maintenance personnel.

[0134] It is understandable that by acquiring device status in real time, recursively monitoring abnormal events, and quantitatively evaluating the degree of abnormality, accurate monitoring and evaluation of abnormal events in IoT devices are achieved, providing strong support for the healthy operation and abnormality handling of equipment.

[0135] In one feasible implementation, the step S40: the step of controlling the operation of the IoT device according to the target strategy includes:

[0136] Step S404: if the current abnormality is a mild abnormality, outputting warning information through the Internet of Things device;

[0137] During the abnormal monitoring process of IoT devices, when it is detected that the current abnormality level of the device is a mild abnormality, warning information is output through the IoT device (such as a display screen, indicator light or sound alarm, etc.). These warning information usually include key information such as abnormality type, abnormality level, and occurrence time, so that operators can quickly understand the abnormal condition of the equipment and take corresponding measures.

[0138] Step S405: if the current abnormality level is a moderate abnormality, reducing the device load of the IoT device;

[0139] When the current abnormality of the IoT device reaches a moderate level, the device load of the IoT device is reduced to prevent the abnormal condition from further deteriorating. The specific method can be to reduce the computing power of the device, reduce the data transmission rate, shut down some non-core functions, etc. There is no restriction here and it can be set according to actual needs. It is understandable that by reducing the device load, the energy consumption and wear of the device can be reduced. Timely reduction of the device burden helps prevent the abnormal condition from further deteriorating, reduce the risk of equipment failure, and extend the service life of the device.

[0140] Step S406: If the current abnormality level is a severe abnormality, the device service of the IoT device is sent to a backup device, and the IoT device is shut down.

[0141] When the current abnormality of an IoT device reaches a critical level, the IoT device's business will be sent to the backup device and the current device will be shut down to ensure the overall security and stable operation of the IoT and the continuity and stability of the service. This may include complex operations such as real-time migration of data and smooth switching of business. There is no restriction here and it can be set according to actual needs. It is understandable that by sending the business to the backup device, the continuity and stability of the service can be ensured, and users can avoid any interruption or impact. Shutting down the abnormal device in time can prevent further damage to the device and reduce maintenance costs and downtime.

[0142] By taking different control measures according to the degree of abnormality of the equipment, we can ensure timely warning and response of the equipment, and prevent further deterioration of the abnormal situation by reducing the load and migrating business, thereby improving the reliability and stability of the entire IoT system.

[0143] For example, in order to help understand the implementation process of the abnormal monitoring method of the Internet of Things device obtained by combining the above-mentioned embodiment 1, embodiment 2 and embodiment 3, please refer to Figure 4 , Figure 4 A brief flowchart of an abnormal monitoring method for an IoT device is provided, specifically:

[0144] 1. Data collection and data preprocessing:

[0145] 1.1 Equipment status data collection, deploy sensors and monitoring systems, and collect multi-dimensional status data of equipment in real time. These data include but are not limited to hardware indicators (such as CPU (Central Processing Unit) utilization, memory usage, temperature, power consumption), network indicators (such as bandwidth utilization, latency, packet loss rate) and environmental indicators (such as temperature, humidity, vibration). Set the data collection frequency to ensure the real-time and accuracy of the data, for example, collect data once per second (that is, obtain the current device status data of the IoT device at the current moment).

[0146] 1.2 Data cleaning and denoising: Use Kalman filter or moving average method to denoise the data, eliminate the impact of random fluctuations, identify and process abnormal values ​​in the data, such as data points beyond a reasonable range or abnormal spikes caused by acquisition errors (that is, denoise the current device status data to obtain denoised status data; determine the abnormal values ​​in the denoised status data, and remove the abnormal values ​​from the denoised status data to obtain the status data after abnormal processing).

[0147] 1.3 Data smoothing: Sliding window technology is used to smooth the data. An appropriate window size is selected (for example, the most recent 10 data points), and the mean within the window is calculated to eliminate the impact of short-term fluctuations on subsequent threshold calculations (i.e., the data after abnormal processing is smoothed by the sliding window technology to obtain smoothed state data).

[0148] 2. Calculation and adjustment of dynamic thresholds [Lower_t, Upper_t] (i.e., determining the data value range based on the current device status data):

[0149] 2.1 Determine the dynamic threshold range (i.e., data value range) based on statistics. Set a moving window, the window size (W) can be set to the most recent 100 data points, calculate the real-time mean (μ_w) and standard deviation (σ_w) of the data in the window, and then determine the dynamic adjustment threshold range based on the real-time mean and standard deviation. The dynamic threshold range = [μ_w-kσ_w, μ_w+kσ_w], where k is the adjustment coefficient (i.e., Where W is the moving window size, μ_w and σ_w are the mean and standard deviation of the data in the window, i represents the number of data points, and t represents the current time.

[0150] 2.2 Determine the dynamic threshold range based on the machine learning model. Train a machine learning model (such as linear regression, support vector machine SVM or neural network), input the real-time status characteristics of the device (such as CPU utilization, temperature, bandwidth utilization, etc.), and output the dynamic threshold range: [Lower_t, Upper_t] = f(x_t), where x_t is the current state feature vector. Update the model parameters regularly or based on real-time data to adapt to changes in device status.

[0151] 3. Anomaly detection and response:

[0152] 3.1 Anomaly detection (that is, if the current device status data is not within the data value range, it is determined that the IoT device is in an abnormal operating state at the current moment). For each time point (t), the device status data (x_t) is compared with the dynamic threshold range. If x_t is not within the range of [Lower_t, Upper_t], it is determined to be abnormal. The time, duration, degree of deviation and other information of the abnormal event are recorded for subsequent analysis and response. According to the severity, duration and scope of impact of the abnormality, the abnormal event is classified as mild, moderate or severe. A priority is set for each abnormal event to determine the urgency of the response and the resource scheduling strategy.

[0153] 3.2 Response strategy execution (that is, determining the current abnormality level of the IoT device at the current moment, and determining the target strategy corresponding to the current abnormality level from the preset response strategies corresponding to different abnormality levels, and controlling the operation of the IoT device according to the target strategy). For mild abnormalities, the system records the abnormality log and reminds the operation and maintenance personnel to check through the early warning mechanism. Continue to monitor the device status. If the abnormality persists or worsens, upgrade the response level. For moderate abnormalities, the system automatically executes predefined response measures, such as reducing the task load of the device, reducing the operating frequency of the device, or adjusting the cooling system of the device, and sends notifications to the operation and maintenance personnel, suggesting equipment inspection or maintenance. For severe abnormalities, immediately implement emergency measures, such as automatic shutdown, switching to backup equipment, or starting redundant systems to prevent equipment damage or system crashes, trigger emergency plans, and start fault recovery processes to ensure system stability and business continuity.

[0154] 4. The system continuously monitors the effectiveness of response measures. If the device status returns to normal after the response, confirm the effectiveness of the current threshold setting. If abnormal events occur frequently, adjust the threshold range or optimize the detection model to reduce false positives or false negatives.

[0155] For example, using reinforcement learning algorithms (such as Q-learning) to optimize threshold adjustment strategies and response mechanisms, learning the best threshold settings and response measures through reward and penalty mechanisms, and automatically updating model parameters as the equipment ages or the environment changes to ensure detection accuracy and response efficiency. For example, long-term data analysis, regularly retrospectively analyzing historical abnormal data, identifying long-term trends and changes in equipment performance, updating the equipment's threshold output model, and adjusting the threshold setting strategy based on the analysis results to ensure that the system always maintains the best detection capabilities during the equipment life cycle.

[0156] For another example, the adjustment coefficient in the dynamic threshold range is adjusted according to the current abnormality level.

[0157] In this embodiment, for the device that performs abnormality detection for the first time, an initial threshold (Lower, Upper) is set, where Lower = μ-kσ, Upper = μ+kσ, μ is the mean of historical data of the same type of device, σ is the standard deviation of historical data of the same type of device, and k is the adjustment coefficient.

[0158] This embodiment can dynamically adjust the threshold range in device status monitoring, accurately detect abnormal events, and ensure the stable operation of the system through an adaptive response mechanism. It not only improves the accuracy and response speed of abnormality detection, but also continuously optimizes the detection strategy through adaptive learning to adapt to long-term changes in device status. It is suitable for a wide range of Internet of Things and intelligent system scenarios, and significantly improves the efficiency of device management.

[0159] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the abnormal monitoring method of the IoT device of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0160] This application also provides an abnormal monitoring device for IoT devices, please refer to Figure 5 , the abnormality monitoring device of the Internet of Things device includes:

[0161] An acquisition module 10 is used to acquire current device status data of the IoT device at the current moment, wherein the device status data is used to characterize the operating state of the IoT device at the current moment and the operating environment of the IoT device at the current moment;

[0162] A detection module 20, configured to determine a data value range based on the current device status data, and detect whether the current device status data is within the data value range;

[0163] A determination module 30, configured to determine that the IoT device is in an abnormal operation state at the current moment if the current device state data is not within the data value range;

[0164] The execution module 40 is used to determine the current abnormality level of the IoT device at the current moment, and determine the target strategy corresponding to the current abnormality level from the preset response strategies corresponding to different abnormality levels, and control the operation of the IoT device according to the target strategy.

[0165] Optionally, the abnormality monitoring device of the Internet of Things device is also used for:

[0166] Acquire historical device status data before the current device status data;

[0167] The detection module 20 is used to:

[0168] Moving a preset moving window according to a preset step length, and determining reference data at multiple moments from the current device state data and the historical device state data before the current moment through the moving window;

[0169] Calculate the benchmark mean and benchmark standard deviation of the benchmark data at each moment;

[0170] The floating value is obtained by weighting the benchmark standard deviation with a preset adjustment coefficient, the difference between the benchmark mean and the floating value is used as the lower limit, the sum of the benchmark mean and the floating value is used as the upper limit, and the data value range is determined based on the lower limit and the upper limit.

[0171] Optionally, the detection module 20 is used to:

[0172] The current device state data is input into a preset threshold output model to obtain the data value range, wherein the threshold output model is trained based on the initial device state data.

[0173] Optionally, the device is also used for:

[0174] Acquire historical device status data before the current device status data;

[0175] When a trigger model update instruction is detected, the threshold output model is updated using the historical device status data before the current moment, and the updated threshold output model is used as the preset threshold output model.

[0176] Optionally, the device is also used for:

[0177] Detecting whether the IoT device has returned to normal;

[0178] If the IoT device does not return to normal, determine to trigger a model update instruction;

[0179] The step of updating the threshold output model by using the historical device status data before the current moment comprises:

[0180] The threshold output model is updated based on the current abnormality level, the current device status data, and the historical device status data before the current moment.

[0181] Optionally, the device is also used for:

[0182] Performing denoising processing on the current device status data to obtain denoised status data;

[0183] Determine an abnormal value in the denoised state data, and remove the abnormal value from the denoised state data to obtain abnormality-processed state data;

[0184] Performing data smoothing on the abnormality processed state data by using a sliding window technique to obtain smoothed state data;

[0185] The step of determining a data value range based on the current device status data comprises:

[0186] A data value range is determined based on the smoothing state data.

[0187] Optionally, the execution module 40 is used to:

[0188] Obtaining the next moment operation status of the IoT device at the next moment;

[0189] If the operating state at the next moment is an abnormal operating state, the next moment is updated to the current moment, and the step of obtaining the operating state of the IoT device at the next moment is performed;

[0190] If the operating status at the next moment is a normal operating status, then determine the duration of the abnormality of the Internet of Things device at the current moment, and determine the degree of data deviation between the current device status data and the data value range, and use the abnormality duration and the data deviation degree as the current abnormality degree, wherein the abnormality duration is the duration of the continuous moments of the current moment and the Internet of Things device in the abnormal operating state before the current moment.

[0191] Optionally, the execution module 40 is used to:

[0192] If the current abnormality level is a mild abnormality, outputting warning information through the Internet of Things device;

[0193] If the current abnormality level is a moderate abnormality, reducing the device load of the IoT device;

[0194] If the current abnormality level is a severe abnormality, the device service of the IoT device is sent to a backup device, and the IoT device is shut down.

[0195] The abnormality monitoring device for the Internet of Things device provided by the present application adopts the abnormality monitoring method for the Internet of Things device in the above-mentioned embodiment, which can solve the technical problem of low accuracy in abnormality detection of the Internet of Things device. Compared with the prior art, the beneficial effects of the abnormality monitoring device for the Internet of Things device provided by the present application are the same as the beneficial effects of the abnormality monitoring method for the Internet of Things device provided by the above-mentioned embodiment, and other technical features in the abnormality monitoring device for the Internet of Things device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0196] The present application provides an abnormality monitoring device for an Internet of Things device, and the abnormality monitoring device for an Internet of Things device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the abnormality monitoring method for the Internet of Things device in the above-mentioned embodiment one.

[0197] Reference below Figure 6 , which shows a schematic diagram of the structure of an abnormal monitoring device for an Internet of Things device suitable for implementing the embodiment of the present application. The abnormal monitoring device for an Internet of Things device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The abnormality monitoring device of the Internet of Things device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0198] like Figure 6As shown, the abnormal monitoring device of the Internet of Things device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the abnormal monitoring device of the Internet of Things device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the abnormal monitoring device of the Internet of Things device to communicate wirelessly or wired with other devices to exchange data. Although the abnormal monitoring device of the Internet of Things device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0199] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0200] The abnormality monitoring device for the Internet of Things device provided by the present application adopts the abnormality monitoring method for the Internet of Things device in the above-mentioned embodiment, which can solve the technical problem of low accuracy in abnormality detection of the Internet of Things device. Compared with the prior art, the beneficial effects of the abnormality monitoring device for the Internet of Things device provided by the present application are the same as the beneficial effects of the abnormality monitoring method for the Internet of Things device provided by the above-mentioned embodiment, and other technical features in the abnormality monitoring device for the Internet of Things device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0201] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0202] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0203] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the abnormality monitoring method for the Internet of Things device in the above-mentioned embodiment.

[0204] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0205] The above-mentioned computer-readable storage medium may be included in the abnormality monitoring device of the Internet of Things device; or it may exist independently without being assembled into the abnormality monitoring device of the Internet of Things device.

[0206] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an abnormality monitoring device of an Internet of Things device, the abnormality monitoring device of the Internet of Things device: obtains current device status data of the Internet of Things device at the current moment, wherein the device status data is used to characterize the operating status of the Internet of Things device at the current moment and the operating environment of the Internet of Things device at the current moment; determines a data value range based on the current device status data, and detects whether the current device status data is within the data value range; if the current device status data is not within the data value range, determines that the Internet of Things device is in an abnormal operating state at the current moment; determines the current abnormality degree of the Internet of Things device at the current moment, and determines a target strategy corresponding to the current abnormality degree from preset response strategies corresponding to different abnormality degrees, and controls the operation of the Internet of Things device according to the target strategy.

[0207] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0208] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0209] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0210] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned abnormality monitoring method for the Internet of Things device, and can solve the technical problem of low accuracy in abnormality detection of the Internet of Things device. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the abnormality monitoring method for the Internet of Things device provided by the above-mentioned embodiment, and will not be repeated here.

[0211] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for abnormal monitoring of Internet of Things devices.

[0212] The computer program product provided by the present application can solve the technical problem of low accuracy in detecting anomalies in IoT devices. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the method for monitoring anomalies in IoT devices provided by the above-mentioned embodiment, and will not be elaborated here.

[0213] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for monitoring abnormality of an Internet of Things device, characterized in that: The abnormality monitoring method of the Internet of Things device includes: Acquire current device status data of the IoT device at the current moment, wherein the device status data is used to characterize the operating state of the IoT device at the current moment and the operating environment of the IoT device at the current moment; Determine a data value range based on the current device status data, and detect whether the current device status data is within the data value range; If the current device status data is not within the data value range, it is determined that the IoT device is in an abnormal operating state at the current moment; Determine the current abnormality level of the IoT device at the current moment, determine a target strategy corresponding to the current abnormality level from preset response strategies corresponding to different abnormality levels, and control the operation of the IoT device according to the target strategy.

2. The abnormality monitoring method of the Internet of Things device according to claim 1, characterized in that: Before the step of determining the data value range based on the current device status data, the step further includes: Acquire historical device status data before the current device status data; The step of determining a data value range based on the current device status data comprises: Moving a preset moving window according to a preset step length, and determining reference data at multiple moments from the current device state data and the historical device state data before the current moment through the moving window; Calculate the benchmark mean and benchmark standard deviation of the benchmark data at each moment; The floating value is obtained by weighting the benchmark standard deviation with a preset adjustment coefficient, the difference between the benchmark mean and the floating value is used as the lower limit, the sum of the benchmark mean and the floating value is used as the upper limit, and the data value range is determined based on the lower limit and the upper limit.

3. The abnormality monitoring method of the Internet of Things device according to claim 1, characterized in that: The step of determining a data value range based on the current device status data comprises: The current device state data is input into a preset threshold output model to obtain the data value range, wherein the threshold output model is trained based on the initial device state data.

4. The abnormality monitoring method of the Internet of Things device according to claim 3, characterized in that: Before the step of inputting the current device status data into a preset threshold output model to obtain the data value range, the step further includes: Acquire historical device status data before the current device status data; When a trigger model update instruction is detected, the threshold output model is updated using the historical device status data before the current moment, and the updated threshold output model is used as the preset threshold output model.

5. The abnormality monitoring method of the Internet of Things device according to claim 4, characterized in that: After the step of controlling the operation of the IoT device according to the target strategy, the method further includes: Detecting whether the IoT device has returned to normal; If the IoT device does not return to normal, determine to trigger a model update instruction; The step of updating the threshold output model by using the historical device status data before the current moment comprises: The threshold output model is updated based on the current abnormality level, the current device status data, and the historical device status data before the current moment.

6. The abnormality monitoring method of the Internet of Things device according to claim 1, characterized in that: Before the step of determining the data value range based on the current device status data, the step further includes: Performing denoising processing on the current device status data to obtain denoised status data; Determine an abnormal value in the denoised state data, and remove the abnormal value from the denoised state data to obtain abnormality-processed state data; Performing data smoothing on the abnormality processed state data by using a sliding window technique to obtain smoothed state data; The step of determining a data value range based on the current device status data comprises: A data value range is determined based on the smoothing state data.

7. The abnormality monitoring method of the Internet of Things device according to claim 1, characterized in that: The step of determining the current abnormality level of the IoT device at the current moment includes: Obtaining the next moment operation status of the IoT device at the next moment; If the operating state at the next moment is an abnormal operating state, the next moment is updated to the current moment, and the step of obtaining the operating state of the IoT device at the next moment is performed; If the operating status at the next moment is a normal operating status, then determine the duration of the abnormality of the Internet of Things device at the current moment, and determine the degree of data deviation between the current device status data and the data value range, and use the abnormality duration and the data deviation degree as the current abnormality degree, wherein the abnormality duration is the duration of the continuous moments of the current moment and the Internet of Things device in the abnormal operating state before the current moment.

8. The abnormality monitoring method for an Internet of Things device according to any one of claims 1 to 7, characterized in that: The step of controlling the operation of the IoT device according to the target strategy includes: If the current abnormality level is a mild abnormality, outputting warning information through the Internet of Things device; If the current abnormality level is a moderate abnormality, reducing the device load of the IoT device; If the current abnormality level is a severe abnormality, the device service of the IoT device is sent to a backup device, and the IoT device is shut down.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the abnormality monitoring method for an Internet of Things device as described in any one of claims 1 to 8 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the abnormality monitoring method for an Internet of Things device according to any one of claims 1 to 8 are implemented.

Images