Internet of Things equipment intelligent management method and system, and electronic Internet of Things equipment

Abstract

The invention relates to the technical field of intelligent management scheme design of Internet of Things equipment, in particular to an intelligent management method and system of the Internet of Things equipment and electronic Internet of Things equipment. According to a preset time interval, the PING value and the packet loss rate of sample Internet of Things equipment in the operation process within a preset duration are obtained; recording the acquired data as a performance coupling state data set of the sample Internet of Things equipment; acquiring a performance coupling state data set of a first preset number of sample Internet of Things devices, further training an intelligent over-aging identification model of the Internet of Things devices, obtaining a performance coupling state data set of a target Internet of Things device after model training is completed, and obtaining a performance coupling state data set of the target Internet of Things device; therefore, whether the target Internet of Things equipment has an over-aging phenomenon is determined by using the trained model, real-time monitoring and reliable evaluation of the operation state of the Internet of Things equipment are realized, the aging phenomenon of the Internet of Things equipment can be found in time, and the Internet of Things equipment can be operated and maintained in time.

Description

Technical Field

[0001] The present invention relates to the technical field of design of intelligent management solutions for Internet of Things devices, and in particular to an intelligent management method and system for Internet of Things devices, and an electronic Internet of Things device. Background Art

[0002] IoT device hardware aging is primarily manifested in the following aspects: decreased processor performance, reduced memory capacity, slower hard drive read and write speeds, and aging network interface cards. These hardware changes can lead to a decline in the overall performance of IoT devices. When an IoT device's processor ages, its data processing ability weakens. When processing network packets, the processor needs to perform various calculations and operations. Insufficient processor performance increases packet processing time. An aging processor may require more time to decode and process network packets, increasing the time packets spend inside the IoT device and, in turn, round-trip time. Furthermore, when the network interface card of an IoT device ages, it can cause significant loss of critical data, impacting the reliability and accuracy of data transmission. Existing technologies for monitoring IoT device aging often rely on determining whether various hardware components in the device have failed or the cumulative usage time of the hardware components. For example, if a component in an IoT device has aged too long, it is presumed to need replacement. However, failure of a hardware component in an IoT device can affect the normal operation of the device and, in turn, the profitability of the business.

[0003] To sum up, how to monitor the operating status of IoT devices in real time and reliably evaluate them, promptly detect the aging of IoT devices, and then promptly perform operation and maintenance of IoT devices are solutions that existing technologies urgently need.

[0004] Therefore, the existing technology needs to be further developed. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide an intelligent management method and system for Internet of Things devices, and an electronic Internet of Things device, so as to solve the problems existing in the prior art.

[0006] To achieve the above technical objectives, according to a first aspect of the present invention, the present invention provides a method for intelligent management of IoT devices, the method comprising: S100. Obtain, at preset time intervals, a ping value and a packet loss rate of a sample IoT device during operation within a preset duration, and record the obtained data as a performance coupling status data set of the sample IoT device; collect a first preset number of performance coupling status data sets of the sample IoT devices, and divide the collected performance coupling status data sets of the sample IoT devices into a training data set and a validation data set according to a first preset ratio; S200: Using the collected training data set of sample IoT devices to train an IoT device over-aging intelligent recognition model, using the validation data set to optimize the IoT device over-aging intelligent recognition model, optimize model parameters, and complete the training of the IoT device over-aging intelligent recognition model; S300. When the model training is completed, the performance coupling status data set of the target IoT device is obtained, and the obtained performance coupling status data set of the target IoT device is input into the IoT device over-aging intelligent recognition model, so as to determine whether the target IoT device has excessive aging phenomenon, and determine whether to output an alarm signal regarding the excessive aging phenomenon of the target IoT device based on the determination result.

[0007] Specifically, determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal regarding the excessive aging of the target IoT device based on the determination result, includes: If it is determined that the target IoT device has an excessive aging phenomenon, an alarm signal indicating that the target IoT device has an excessive aging phenomenon is output, and target IoT device coding information of the target IoT device having an excessive aging phenomenon is output.

[0008] Specifically, the determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal indicating that the target IoT device has excessive aging according to the determination result, further includes: Determine whether the maximum packet loss rate in the obtained performance coupling status data set of the target Internet of Things device is greater than or equal to a first preset threshold value. If so, output a control signal for terminating all current data transmission tasks of the target Internet of Things device, terminate all current data transmission tasks of the target Internet of Things device, and output an alarm signal for terminating all current data transmission tasks of the target Internet of Things device; if not, control the target Internet of Things device to continue to perform the data transmission task, and output a prompt signal for repairing the target Internet of Things device as soon as possible.

[0009] Specifically, determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal regarding the excessive aging of the target IoT device based on the determination result, includes: If it is determined that the target IoT device does not have an excessive aging phenomenon, a prompt signal indicating that the target IoT device does not have an excessive aging phenomenon is output.

[0010] Specifically, the sample IoT device and the target IoT device are the same type of IoT device.

[0011] Specifically, the method of using the collected training data set of sample IoT devices to train the IoT device over-aging intelligent recognition model, using the verification data set to optimize the IoT device over-aging intelligent recognition model, optimizing the model parameters, and completing the IoT device over-aging intelligent recognition model training includes: The training data set is input into the preset network layer in batches for training, and the preset network layer includes a Transformer network layer. The Transformer network layer is used to predict the next performance coupling state data set based on the current performance coupling state data set through forward propagation, and then obtain the predicted loss value; the loss value of the preset network layer is calculated and input into the optimizer for optimization to determine the direction in which the parameter gradient of the IoT device over-aging intelligent recognition model decreases fastest; the IoT device over-aging intelligent recognition model performs back propagation based on the loss value and the model's parameter gradient to optimize the parameters of the IoT device over-aging intelligent recognition model.

[0012] Specifically, the preset network layer also includes a ResNet network layer, which is used to classify and predict the output results based on the collected performance coupling status data set of the target Internet of Things device, and the classification results include whether the target Internet of Things device has excessive aging phenomenon and whether the target Internet of Things device does not have excessive aging phenomenon.

[0013] Specifically, the ResNet network layer is used to classify and predict the output results based on the collected performance coupling status data set of the target IoT device, including: When building Backbone, the Resnet network layer and the target IoT device encoding were added. After the training data set is input, the Resnet network layer begins layer-by-layer training. The training extracts features from the performance coupling status data set of the target IoT device, assisting the Transformer in predicting whether the target IoT device is over-aging. The extracted features are then used with the help of the target IoT device encoding to obtain the target IoT device's encoding information, which is used by relevant managers to locate the target IoT device when the target IoT device is over-aging.

[0014] According to a second aspect of the present invention, there is provided an intelligent management system for Internet of Things devices, comprising: An acquisition module is used to obtain the PING value and packet loss rate of the sample IoT device during operation within a preset time period at a preset time interval; A control module is used to obtain, at preset time intervals, the PING value and packet loss rate of the sample Internet of Things devices during their operation within a preset time period, and record the obtained data as a performance coupling status data set of the sample Internet of Things devices; collect a first preset number of performance coupling status data sets of the sample Internet of Things devices, and divide the collected performance coupling status data sets of the sample Internet of Things devices into a training data set and a verification data set according to a first preset ratio; train an Internet of Things device over-aging intelligent recognition model using the collected training data sets of the sample Internet of Things devices, and optimize the Internet of Things device over-aging intelligent recognition model using the verification data set, optimize the model parameters, and complete the training of the Internet of Things device over-aging intelligent recognition model; obtain the performance coupling status data set of the target Internet of Things device after the model training is completed, and input the obtained performance coupling status data set of the target Internet of Things device into the Internet of Things device over-aging intelligent recognition model, thereby determining whether the target Internet of Things device has an over-aging phenomenon, and determining whether to output an alarm signal regarding the existence of an over-aging phenomenon in the target Internet of Things device based on the determination result.

[0015] According to a third aspect of the present invention, there is provided an electronic Internet of Things device, comprising: a memory; and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the above-mentioned method for intelligent management of Internet of Things devices is implemented.

[0016] Beneficial effects: The present invention obtains the PING value and packet loss rate of the sample Internet of Things devices during their operation within a preset time period at preset time intervals, and records the obtained data as a performance coupling status data set of the sample Internet of Things devices; collects a first preset number of performance coupling status data sets of sample Internet of Things devices, and then trains an intelligent recognition model for excessive aging of Internet of Things devices, thereby realizing real-time monitoring and reliable evaluation of the operating status of Internet of Things devices, and timely discovering the aging phenomenon of Internet of Things devices, and then timely operating and maintaining the Internet of Things devices, thereby greatly improving the timeliness, intelligence and reliability of intelligent operation and maintenance of Internet of Things devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a method for intelligent management of IoT devices provided in a specific embodiment of the present invention; Figure 2 This is a system composition diagram of the IoT device intelligent management system provided in a specific embodiment of the present invention; Figure 3This is a structural diagram of an intelligent identification model for excessive aging of IoT devices provided in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the drawings of the present invention. Based on the embodiments in this application, other similar embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application. In addition, the directional words mentioned in the following embodiments, such as "up", "down", "left", "right", etc., are only reference to the directions of the drawings. Therefore, the directional words used are used to illustrate rather than limit the invention.

[0019] The present invention will be further described below with reference to the accompanying drawings and preferred embodiments.

[0020] See also Figure 1 The present invention provides an intelligent management method for Internet of Things devices, comprising: S100. Obtain the PING value and packet loss rate of the sample IoT device during its operation within a preset time period at preset time intervals, and record the obtained data as a performance coupling status data set of the sample IoT device; collect a first preset number of performance coupling status data sets of the sample IoT devices, and divide the collected performance coupling status data sets of the sample IoT devices into a training data set and a validation data set according to a first preset ratio.

[0021] Specifically, the sample IoT device and the target IoT device are the same type of IoT device.

[0022] It is understandable that the types of the sample IoT devices and target IoT devices include but are not limited to server IoT devices and computer IoT devices.

[0023] It should be noted that the steps before step S100 include: A preset time interval, a preset duration, a first preset threshold, a first preset number, a first preset ratio, a first preset round, and a second preset round are preset in the control module.

[0024] It can be understood that the preset time interval, preset duration, first preset threshold, first preset quantity, first preset ratio, first preset round, and second preset round can be specifically set according to the actual needs of the user of the present invention. The present invention does not limit the specific values ​​of the above parameters. There is no rule for setting the specific values ​​of the above parameters, as long as it is applicable to the intelligent management method of Internet of Things devices proposed in the present invention.

[0025] Preferably, the present invention sets the preset time interval to 15 seconds, the present invention sets the preset time to 30 minutes, the present invention sets the first preset number to 2000, the present invention sets the first preset ratio to 8:2, the present invention sets the first preset round to 20,000 times, the present invention sets the second preset round to 300, and the present invention sets the first preset threshold to 0.5%. The above settings can further improve the performance of the model and the efficiency of model training, and greatly improve the accuracy and reliability of the IoT device over-aging intelligent recognition model of the target IoT device of the present invention.

[0026] It is understandable that before the intelligent identification model for excessive aging of IoT devices is officially put into use, the present invention obtains 2,000 performance coupling status data sets of target IoT devices during normal operation of the sample IoT devices, and relevant management personnel confirm that the 2,000 performance coupling status data sets of the target IoT devices are normal according to industry specifications.

[0027] It is understandable that if the IoT device does not experience aging, there will be a certain coupling relationship between the data in the performance coupling status data set of the sample IoT device, and theoretically no mutation will occur. However, if the IoT device experiences excessive aging, such as when the network interface card of the IoT device ages, this coupling relationship will be broken, such as abnormal fluctuations in packet loss rate or PING value, and such fluctuations are difficult to monitor using a conventional single threshold. Therefore, the present invention designs and trains an intelligent recognition model for excessive aging of IoT devices based on this.

[0028] S200: Use the training data set of the collected sample IoT devices to train an IoT device over-aging intelligent recognition model, use the verification data set to optimize the IoT device over-aging intelligent recognition model, optimize the model parameters, and complete the IoT device over-aging intelligent recognition model training.

[0029] Specifically, the method of using the collected training data set of sample IoT devices to train the IoT device over-aging intelligent recognition model, using the verification data set to optimize the IoT device over-aging intelligent recognition model, optimizing the model parameters, and completing the IoT device over-aging intelligent recognition model training includes: The training data set is input into the preset network layer in batches for training, and the preset network layer includes a Transformer network layer. The Transformer network layer is used to predict the next performance coupling state data set based on the current performance coupling state data set through forward propagation, and then obtain the predicted loss value; the loss value of the preset network layer is calculated and input into the optimizer for optimization to determine the direction in which the parameter gradient of the IoT device over-aging intelligent recognition model decreases fastest; the IoT device over-aging intelligent recognition model performs back propagation based on the loss value and the model's parameter gradient to optimize the parameters of the IoT device over-aging intelligent recognition model.

[0030] It can be understood that Transformer is a deep learning model based on the self-attention mechanism, which consists of a multi-head attention mechanism and a feedforward neural network. It can process sequence data and capture long-distance dependencies. The Transformer model does not contain traditional convolutional layers, but processes each element in the input sequence through an attention layer. The typical structure of Transformer includes an encoder and a decoder, where the encoder is composed of multiple identical layers stacked together, and the decoder adds a self-attention layer on the basis of the encoder to process sequence generation tasks. The present invention uses Transformer to supplement global context information, enhances the model's capabilities in feature extraction and global understanding, greatly improves the performance of the model, and greatly reduces the computational cost.

[0031] Specifically, the preset network layer also includes a ResNet network layer, which is used to classify and predict the output results based on the collected performance coupling status data set of the target Internet of Things device, and the classification results include whether the target Internet of Things device has excessive aging phenomenon and whether the target Internet of Things device does not have excessive aging phenomenon.

[0032] It should be noted here that ResNet is a deep convolutional neural network that solves the gradient vanishing problem in deep network training by introducing residual connections. The core component of ResNet is the residual block, which usually contains two or three convolutional layers and a skip connection. The latter allows the gradient to bypass these convolutional layers directly. The network structure of ResNet can be very deep. These networks extract the characteristics of the PING value and packet loss rate of the sample IoT devices during the operation within a preset time by stacking multiple residual blocks, and classify and predict the output results through global average pooling and fully connected layers. The classification results include whether the target IoT device has excessive aging or not.

[0033] See also Figure 3The present invention combines the ResNet network layer and the Transformer network layer. ResNet is good at extracting local features of the PING value and packet loss rate of sample IoT devices in the training data set during operation within a preset time, while Transformer can supplement global context information. This combination can enhance the model's capabilities in feature extraction and global understanding, greatly improve the model's performance, and greatly reduce the computational cost.

[0034] It can be understood that the ResNet network layer is used to classify and predict the output results through the performance coupling status data set of the target IoT device collected in the training data set and the validation data set. The specific steps are: (1) First, the training dataset is placed in the Backbones network layer of the model. Backbone refers to a series of convolutional layers that constitute the skeleton of the neural network. The main function of these layers is to extract the features of the input data. The Backbone network is usually composed of multiple convolutional layers, pooling layers, and activation functions. It can extract meaningful feature representations from the original data. Backbones is composed of multiple Backbones, and the core network layer in Backbone is the Resnet network layer. After the dataset is input into the model, the performance coupling status data set of the target IoT device will be input into Backbones for training; (2) When constructing Backbone, the Resnet network layer and the target IoT device encoding are added. The Resnet network layer starts layer-by-layer training after the training data set is input. The training extracts features from the performance coupling status data set of the target IoT device, and assists the Transformer in predicting whether the target IoT device has excessive aging. The extracted features are used with the help of the target IoT device encoding to obtain the encoding information of the target IoT device, which is used by relevant management personnel to locate the target IoT device when the target IoT device has excessive aging, further improving the timeliness of IoT device maintenance and thereby improving the usability of the present invention.

[0035] Specifically, the method of using the collected training data set to train the IoT device over-aging intelligent recognition model for the target IoT device, using the validation data set to optimize the IoT device over-aging intelligent recognition model for the target IoT device, optimizing the model parameters, and completing the training of the IoT device over-aging intelligent recognition model for the target IoT device, further includes: After each training, the verification data set is input into the preset network layer of the previous training in batches for model parameter verification, and cyclic training is performed. The total number of training rounds is set to the first preset round; the loss value of the preset network layer is recorded, and it is determined whether the loss value meets the first preset condition. Based on the judgment result, it is determined whether to end the training and output the model parameters.

[0036] Specifically, after each training, the verification data set is input into the preset network layer of the previous training in batches to verify the model parameters, and the cyclic training is performed, including the following methods: When the number of training times is insufficient and a model needs to be optimized, the only option is to start training from the beginning. Therefore, the present invention develops a method for continuing the following training based on the previously trained model parameter file. (1) Provide custom parameters, which can be set according to user needs to continue training based on any training parameters; (2) Load the parameters of the custom model file; (3) Put the validation data set into the custom parameter network layer for validation, obtain the loss value and record the model parameters of the model corresponding to the minimum loss value during training; (4) Based on this set of model parameters, forward propagation training and back propagation are performed, and the optimizer optimizes the parameters to obtain a new set of data; (5) Put the verification data into the new data network layer for inference to obtain the loss value; (6) Perform cyclic training to obtain the best model and complete model optimization.

[0037] It is understood that the training method used in this invention is batch training, which means that each time the model parameters are updated, only a portion of the samples in the validation dataset, called a batch, is used. The advantages of batch training are that it can reduce memory consumption, speed up training, increase randomness, and promote model generalization.

[0038] It should be noted here that, in the present invention, batch_size=4, where batch_size is the batch size. For example, when batch_size=4, it means that two performance coupling state data sets are selected from the verification data set each time and put into the model for verification.

[0039] Specifically, determining whether the loss value satisfies the first preset condition, and determining whether to terminate the training and output the model parameters based on the determination result, includes: If the loss value satisfies the first preset condition, the training is terminated and the parameters of the IoT device over-aging intelligent recognition model of the current target IoT device are output; if the loss value does not satisfy the first preset condition, the training is continued; The first preset condition is that after the second preset round of training, the loss value obtained in the next round of training is greater than or equal to the loss value that occurred during the second preset round of training.

[0040] It can be understood that the present invention preferably sets the maximum round of cyclic training to 20,000 times, which can effectively ensure the accuracy of the model prediction of the present invention and record the loss value of the model training. The present invention sets the second preset round to 300, that is, when the loss value of the training no longer decreases within 300 rounds of training, the round with the smallest loss value in the 300 rounds of training is saved as the parameter of the best verification round, and the best model file is generated. The above setting makes the training rounds no longer rely on manual judgment, but uses the deep learning model for automatic training, which improves the accuracy of the model prediction, and automatically ends the training when the accuracy meets the requirements, greatly saving training time, and effectively preventing overfitting, thereby greatly improving the intelligence level of the present invention and the efficiency of model training.

[0041] Furthermore, the specific process of the present invention for training the IoT device over-aging intelligent recognition model for the target IoT device is as follows: (1) Obtain the latent vector mean mu and logarithmic variance logvar of the target IoT device during the forward propagation process of the IoT device over-aging intelligent recognition model; (2) Calculate a reasonable loss value representing the training effect: Calculate the divergence: k1=-0.5*(1+logvar-mu^2-(e^logvar)); Calculate the loss between the performance coupling state data set and the predicted value in the validation data set: loss=L1+k1*k1_weight; Among them, loss is the loss value, k1 is the divergence, k1_weight is the proportion of k1, and its value is 10. L1 is the absolute difference between the predicted value and the true value. The calculation formula of L1 is as follows: ; Among them, A is the L1 loss in pytorch, which calculates the average or sum of the absolute differences between two tensors; the shape of A is N*C*H*W, which indicates that it is a four-dimensional tensor, N represents the number of samples (Batch Size), indicating that there are N data points, C represents the number of channels (Channels), H and W represent height and width respectively, which are usually the two-dimensional spatial dimensions of the input features; P represents the padding value, which is a Boolean type, and the shape of P is c*h*w*1. The dimensions of P are the same as the dimensions of A in terms of channel, height, and width, but there is no number of samples N, which means that P is a mask or padding information for a feature map of each sample. The Boolean value of P may be used to mark whether the elements in A are filled (True) or valid (False).

[0042] (3) The loss value when using the validation dataset to validate the current model network; (4) If the validation loss of this round is less than that of the previous round, the best model parameters are replaced with the training model of this round; (5) Put the rounds and loss values ​​into the dictionary one by one; (6) Compare the loss value of the current round with the loss value of the 300 rounds before this round (parameters are provided and can be set according to actual needs, the default is 300), that is, traverse the loss values ​​from epoch-300 to epoch-1 (epoch is the training round, and comparison is performed when the epoch is greater than 300). If the loss values ​​of the current round of epoch are all greater than the loss values ​​from (epoch-300) to (epoch-1), then stop training.

[0043] (7) Save the best model parameters in the cyclic validation as a ckpt model file.

[0044] Specifically, determining whether the loss value satisfies the first preset condition, and determining whether to terminate the training and output the model parameters based on the determination result, includes: If the loss value meets the first preset condition, the training is terminated and the parameters of the IoT device over-aging intelligent recognition model of the current target IoT device are output; if the loss value does not meet the first preset condition, the training is continued.

[0045] Specifically, the first preset condition is: after the second preset round of training, the loss value obtained in the next round of training is greater than or equal to the loss value that occurred during the second preset round of training.

[0046] S300. When the model training is completed, the performance coupling status data set of the target IoT device is obtained, and the obtained performance coupling status data set of the target IoT device is input into the IoT device over-aging intelligent recognition model, so as to determine whether the target IoT device has excessive aging phenomenon, and determine whether to output an alarm signal regarding the excessive aging phenomenon of the target IoT device based on the determination result.

[0047] Specifically, determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal regarding the excessive aging of the target IoT device based on the determination result, includes: If it is determined that the target IoT device has an excessive aging phenomenon, an alarm signal indicating that the target IoT device has an excessive aging phenomenon is output, and target IoT device coding information of the target IoT device having an excessive aging phenomenon is output.

[0048] Specifically, the determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal indicating that the target IoT device has excessive aging according to the determination result, further includes: Determine whether the maximum packet loss rate in the obtained performance coupling status data set of the target Internet of Things device is greater than or equal to a first preset threshold value. If so, output a control signal for terminating all current data transmission tasks of the target Internet of Things device, terminate all current data transmission tasks of the target Internet of Things device, and output an alarm signal for terminating all current data transmission tasks of the target Internet of Things device; if not, control the target Internet of Things device to continue to perform the data transmission task, and output a prompt signal for repairing the target Internet of Things device as soon as possible.

[0049] It can be understood that the present invention terminates all current data transmission tasks of the target IoT device in a timely manner when the maximum packet loss rate is greater than or equal to the first preset threshold, and outputs an alarm signal regarding all current data transmission tasks of the terminated target IoT device, thereby preventing the loss or error of key data transmitted by the target IoT device, thereby preventing the impact on the precise operation of other production and operation systems of the enterprise, preventing losses to the enterprise, further improving the intelligence, security and reliability of the intelligent operation and maintenance of IoT devices, improving the management quality of IoT devices, and improving the benefits of the enterprise.

[0050] Specifically, determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal regarding the excessive aging of the target IoT device based on the determination result, includes: If it is determined that the target IoT device does not have an excessive aging phenomenon, a prompt signal indicating that the target IoT device does not have an excessive aging phenomenon is output.

[0051] It can be understood that the present invention obtains the PING value and packet loss rate of the sample Internet of Things devices during their operation within a preset time period at preset time intervals, and records the obtained data as a performance coupling status data set of the sample Internet of Things devices; collects a first preset number of performance coupling status data sets of sample Internet of Things devices, and then trains an intelligent recognition model for excessive aging of Internet of Things devices, thereby realizing real-time monitoring and reliable evaluation of the operating status of Internet of Things devices, and timely discovering the aging phenomenon of Internet of Things devices, and then timely operating and maintaining Internet of Things devices, which greatly improves the timeliness, intelligence and reliability of intelligent operation and maintenance of Internet of Things devices.

[0052] See also Figure 2 The present invention provides another embodiment, which provides an intelligent management system for Internet of Things devices, comprising: The acquisition module 100 is used to obtain the PING value and packet loss rate of the sample IoT device during operation within a preset time period at a preset time interval; The control module 200 is used to obtain the PING value and packet loss rate of the sample Internet of Things devices during their operation within a preset time period at preset time intervals, and record the obtained data as a performance coupling status data set of the sample Internet of Things devices; collect the performance coupling status data sets of a first preset number of sample Internet of Things devices, and divide the collected performance coupling status data sets of the sample Internet of Things devices into a training data set and a verification data set according to a first preset ratio; use the collected training data sets of the sample Internet of Things devices to train an Internet of Things device over-aging intelligent recognition model, use the verification data set to optimize the model of the Internet of Things device over-aging intelligent recognition model, optimize the model parameters, and complete the training of the Internet of Things device over-aging intelligent recognition model; and use the performance coupling status data set of the target Internet of Things device after the model training is completed, and input the obtained performance coupling status data set of the target Internet of Things device into the Internet of Things device over-aging intelligent recognition model, thereby determining whether the target Internet of Things device has an over-aging phenomenon, and determining whether to output an alarm signal regarding the existence of an over-aging phenomenon in the target Internet of Things device based on the determination result.

[0053] It should be noted here that the present invention obtains the PING value and packet loss rate of the sample Internet of Things devices during their operation within a preset time period at preset time intervals, and records the obtained data as a performance coupling status data set of the sample Internet of Things devices; collects a first preset number of performance coupling status data sets of sample Internet of Things devices, and then trains an intelligent recognition model for excessive aging of Internet of Things devices, thereby realizing real-time monitoring and reliable evaluation of the operating status of Internet of Things devices, and timely discovering the aging phenomenon of Internet of Things devices, and then timely operating and maintaining Internet of Things devices, which greatly improves the timeliness, intelligence and reliability of intelligent operation and maintenance of Internet of Things devices.

[0054] In a preferred embodiment, the present application further provides an electronic Internet of Things device, comprising: A memory; and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method for intelligent management of IoT devices is implemented. The computer IoT device can be broadly defined as a server, a terminal, or any other electronic IoT device with the necessary computing and / or processing capabilities. In one embodiment, the computer IoT device may include a processor, memory, a network interface, a communication interface, etc. connected via a system bus. The processor of the computer IoT device can be used to provide the necessary computing, processing, and / or control capabilities. The memory of the computer IoT device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface and communication interface of the computer IoT device can be used to connect to and communicate with external IoT devices via a network. When the computer program is executed by the processor, the steps of the method of the present invention are performed.

[0055] The present invention can be implemented as a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the steps of the method of an embodiment of the present invention to be performed. In one embodiment, the computer program is distributed across a plurality of network-coupled computer IoT devices or processors so that the computer program is stored, accessed, and executed in a distributed manner by one or more computer IoT devices or processors. A single method step / operation, or two or more method steps / operations, can be performed by a single computer IoT device or processor or by two or more computer IoT devices or processors. One or more method steps / operations can be performed by one or more computer IoT devices or processors, and one or more other method steps / operations can be performed by one or more other computer IoT devices or processors. One or more computer IoT devices or processors can perform a single method step / operation, or perform two or more method steps / operations.

[0056] Those skilled in the art will appreciate that the method steps of the present invention can be performed by instructing related hardware, such as a computer IoT device or processor, through a computer program. The computer program can be stored in a non-transitory computer-readable storage medium, and when the computer program is executed, the steps of the present invention are performed. Depending on the circumstances, any reference herein to memory, storage, database, or other media may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0057] It can be understood that the present invention obtains the PING value and packet loss rate of the sample Internet of Things devices during their operation within a preset time period at preset time intervals, and records the obtained data as a performance coupling status data set of the sample Internet of Things devices; collects a first preset number of performance coupling status data sets of sample Internet of Things devices, and then trains an intelligent recognition model for excessive aging of Internet of Things devices, thereby realizing real-time monitoring and reliable evaluation of the operating status of Internet of Things devices, and timely discovering the aging phenomenon of Internet of Things devices, and then timely operating and maintaining Internet of Things devices, which greatly improves the timeliness, intelligence and reliability of intelligent operation and maintenance of Internet of Things devices.

[0058] The various technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification as long as such combination does not conflict.

[0059] The specific embodiments of the present invention described above do not limit the scope of protection of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent management of Internet of Things devices, characterized in that: The method comprises: S100. Obtain, at preset time intervals, a ping value and a packet loss rate of a sample IoT device during operation within a preset duration, and record the obtained data as a performance coupling status data set of the sample IoT device; collect a first preset number of performance coupling status data sets of the sample IoT devices, and divide the collected performance coupling status data sets of the sample IoT devices into a training data set and a validation data set according to a first preset ratio; S200: Using the collected training data set of sample IoT devices to train an IoT device over-aging intelligent recognition model, using the validation data set to optimize the IoT device over-aging intelligent recognition model, optimize model parameters, and complete the training of the IoT device over-aging intelligent recognition model; S300. When the model training is completed, the performance coupling status data set of the target IoT device is obtained, and the obtained performance coupling status data set of the target IoT device is input into the IoT device over-aging intelligent recognition model, so as to determine whether the target IoT device has excessive aging phenomenon, and determine whether to output an alarm signal regarding the excessive aging phenomenon of the target IoT device based on the determination result.

2. The method for intelligent management of IoT devices according to claim 1, characterized in that: The determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal indicating that the target IoT device has excessive aging according to the determination result, includes: If it is determined that the target IoT device has an excessive aging phenomenon, an alarm signal indicating that the target IoT device has an excessive aging phenomenon is output, and target IoT device coding information of the target IoT device having an excessive aging phenomenon is output.

3. The method for intelligent management of IoT devices according to claim 1, characterized in that: The determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal indicating that the target IoT device has excessive aging according to the determination result, further includes: Determine whether the maximum packet loss rate in the obtained performance coupling status data set of the target Internet of Things device is greater than or equal to a first preset threshold value. If so, output a control signal for terminating all current data transmission tasks of the target Internet of Things device, terminate all current data transmission tasks of the target Internet of Things device, and output an alarm signal for terminating all current data transmission tasks of the target Internet of Things device; if not, control the target Internet of Things device to continue to perform the data transmission task, and output a prompt signal for repairing the target Internet of Things device as soon as possible.

4. The method for intelligent management of IoT devices according to claim 1, wherein: The determining whether the target IoT device has excessive aging, and determining whether to output an alarm signal indicating that the target IoT device has excessive aging according to the determination result, includes: If it is determined that the target IoT device does not have an excessive aging phenomenon, a prompt signal indicating that the target IoT device does not have an excessive aging phenomenon is output.

5. The method for intelligent management of IoT devices according to claim 1, wherein: The sample IoT device and the target IoT device are the same IoT device.

6. The method for intelligent management of IoT devices according to claim 1, wherein: The method includes: using the training data set of the collected sample IoT devices to train the IoT device over-aging intelligent recognition model; using the verification data set to optimize the IoT device over-aging intelligent recognition model; optimizing the model parameters; and completing the IoT device over-aging intelligent recognition model training, including: The training data set is input into the preset network layer in batches for training, and the preset network layer includes a Transformer network layer. The Transformer network layer is used to predict the next performance coupling state data set based on the current performance coupling state data set through forward propagation, and then obtain the predicted loss value; the loss value of the preset network layer is calculated and input into the optimizer for optimization to determine the direction in which the parameter gradient of the IoT device over-aging intelligent recognition model decreases fastest; the IoT device over-aging intelligent recognition model performs back propagation based on the loss value and the model's parameter gradient to optimize the parameters of the IoT device over-aging intelligent recognition model.

7. The method for intelligent management of IoT devices according to claim 1, wherein: The preset network layer also includes a ResNet network layer, which is used to classify and predict the output results based on the collected performance coupling status data set of the target Internet of Things device, and the classification results include whether the target Internet of Things device has excessive aging phenomenon and whether the target Internet of Things device does not have excessive aging phenomenon.

8. The method for intelligent management of IoT devices according to claim 7, characterized in that: The ResNet network layer is used to classify and predict the output results based on the collected performance coupling status data set of the target IoT device, including: When building Backbone, the Resnet network layer and the target IoT device encoding were added. After the training data set is input, the Resnet network layer begins layer-by-layer training. The training extracts features from the performance coupling status data set of the target IoT device, assisting the Transformer in predicting whether the target IoT device is over-aging. The extracted features are then used with the help of the target IoT device encoding to obtain the target IoT device's encoding information, which is used by relevant managers to locate the target IoT device when the target IoT device is over-aging.

9. An intelligent management system for Internet of Things devices, characterized in that: include: An acquisition module is used to obtain the PING value and packet loss rate of the sample IoT device during operation within a preset time period at a preset time interval; The control module is configured to obtain, at preset time intervals, a ping value and a packet loss rate of the sample IoT devices during operation within a preset time period, and record the obtained data as a performance coupling status data set of the sample IoT devices; collect the performance coupling status data sets of a first preset number of sample IoT devices, and divide the collected performance coupling status data sets of the sample IoT devices into a training data set and a validation data set according to a first preset ratio; It is used to train an IoT device over-aging intelligent recognition model using the training data set of the collected sample IoT devices, and to optimize the IoT device over-aging intelligent recognition model using the verification data set, optimize the model parameters, and complete the training of the IoT device over-aging intelligent recognition model; it is used to obtain the performance coupling status data set of the target IoT device after the model training is completed, and input the obtained performance coupling status data set of the target IoT device into the IoT device over-aging intelligent recognition model, and then determine whether the target IoT device has over-aging phenomenon, and determine whether to output an alarm signal regarding the existence of over-aging phenomenon of the target IoT device based on the determination result.

10. An electronic Internet of Things device, characterized in that: include: Memory; and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method for intelligent management of Internet of Things devices according to any one of claims 1 to 8 is implemented.

Images