CN118250108A - Port lock real-time monitoring system based on Internet of things technology - Google Patents

Abstract

The invention discloses a port lock real-time monitoring system based on the internet of things technology, and belongs to the technical field of intelligent monitoring. The system comprises: the system comprises an unlocking signal module, an unlocking request detection and information transmission module, a physical port unlocking module and an unlocking record storage module, wherein the unlocking signal module, the unlocking request detection and information transmission module, the physical port unlocking module and the unlocking record storage module firstly transmit an unlocking request to a port lock through an authorization module of an internet of things platform when an operation and maintenance person needs to unlock, then, the unlocking information is transmitted to the internet of things platform in response to the unlocking request received by an application program of the port lock, then, the unlocking information is transmitted to hardware of the port lock through the internet of things platform so as to unlock a physical port, and finally, the unlocking record is automatically stored to a log record application program through an application program of the port lock. In this way, the reliability and security of the port lock may be improved.

Description

Port lock real-time monitoring system based on Internet of things technology

Technical Field

The application relates to the field of intelligent monitoring, in particular to a port lock real-time monitoring system based on the technology of the Internet of things.

Background

The internet of things technology is a technology for connecting a physical world with a network world, and realizes the perception, control and management of the physical world through various sensors, controllers, intelligent terminals and other devices. The internet of things technology is widely applied in various fields, such as intelligent home, intelligent transportation, intelligent medical treatment and the like.

The internet of things technology also plays an important role in the real-time monitoring of the port lock. The port lock is a device for controlling the access authority of a physical port, which can prevent unauthorized personnel from accessing network equipment, protect the safety of the port of the network equipment, and is common in places such as a machine room, a data center and the like. The port lock is generally composed of two parts, namely hardware and software, wherein the hardware part is responsible for locking and unlocking a physical port, and the software part is responsible for realizing the management and control of the port lock. In order to improve the safety and reliability of the port lock, the port lock needs to be monitored in real time so as to discover and process abnormal situations in time.

However, the conventional port lock monitoring system generally needs to be manually operated, such as manual unlocking and recording of unlocking information, and in this way, problems of human negligence, inaccurate operation and the like exist, which easily causes errors or omission of unlocking records. In addition, the traditional port lock monitoring system can only record unlocking events, but cannot monitor the state of the port lock in real time, and cannot actively detect and alarm abnormal conditions. That is, the manual operation of the operation and maintenance personnel cannot obtain the unlocking record and abnormal condition of the port lock in time, which results in insufficient timely and effective monitoring and management of the port lock.

Therefore, a port lock real-time monitoring system based on the internet of things technology is desired.

Disclosure of Invention

The present application has been made to solve the above-mentioned technical problems. The application provides a port lock real-time monitoring system based on the internet of things technology, which can improve the reliability and safety of the port lock.

According to one aspect of the present application, there is provided a port lock real-time monitoring system based on the internet of things technology, comprising:

The unlocking signal module is used for sending an unlocking request to the port lock through the authorization module of the Internet of things platform when an operator needs to unlock;

the unlocking request detection and information transmission module is used for responding to the unlocking request received by the application program of the port lock and transmitting unlocking information to the Internet of things platform;

the physical port unlocking module is used for forwarding the unlocking information to the hardware of the port lock through the Internet of things platform so as to unlock the physical port;

And the unlocking record storage module is used for automatically storing the unlocking record to the log record application program through the application program of the port lock.

Compared with the prior art, the port lock real-time monitoring system based on the internet of things technology provided by the application comprises: the system comprises an unlocking signal module, an unlocking request detection and information transmission module, a physical port unlocking module and an unlocking record storage module, wherein the unlocking signal module, the unlocking request detection and information transmission module, the physical port unlocking module and the unlocking record storage module firstly transmit an unlocking request to a port lock through an authorization module of an internet of things platform when an operation and maintenance person needs to unlock, then, the unlocking information is transmitted to the internet of things platform in response to the unlocking request received by an application program of the port lock, then, the unlocking information is transmitted to hardware of the port lock through the internet of things platform so as to unlock a physical port, and finally, the unlocking record is automatically stored to a log record application program through an application program of the port lock. In this way, the reliability and security of the port lock may be improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below, the following drawings not being drawn to scale with respect to actual dimensions, emphasis instead being placed upon illustrating the gist of the present application.

Fig. 1 is a schematic block diagram of a port lock real-time monitoring system based on the internet of things technology according to an embodiment of the present application.

Fig. 2 is a schematic block diagram of an abnormal condition monitoring module further included in the port lock real-time monitoring system based on the internet of things according to an embodiment of the present application.

Fig. 3 is a flowchart of a port lock real-time monitoring method based on the internet of things technology according to an embodiment of the present application.

Fig. 4 is an application scenario diagram of a port lock real-time monitoring system based on the internet of things technology according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.

As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.

A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.

Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

According to the technical scheme, the port lock real-time monitoring system based on the Internet of things technology is provided, the port lock can be connected with an Internet of things platform, remote control and real-time monitoring are achieved, and monitoring safety and convenience of the port lock are improved. Fig. 1 is a schematic block diagram of a port lock real-time monitoring system based on the internet of things technology according to an embodiment of the present application. As shown in fig. 1, a port lock real-time monitoring system 100 based on the internet of things technology according to an embodiment of the present application includes: the unlocking signal module 110 is configured to send an unlocking request to the port lock through an authorization module of the internet of things platform when an operator needs to unlock; the unlocking request detection and information sending module 120 is configured to send unlocking information to the platform of the internet of things in response to the application program of the port lock receiving the unlocking request; the physical port unlocking module 130 is configured to forward the unlocking information to hardware of the port lock through the internet of things platform to unlock a physical port; and an unlocking record saving module 140, configured to automatically save the unlocking record to the log record application program through the application program of the port lock.

Particularly, in the port lock real-time monitoring system based on the internet of things technology, the port lock real-time monitoring system further comprises an abnormal condition monitoring module 150, which is used for detecting the state of the port lock to determine whether the port lock has a fault. Correspondingly, if the abnormal condition of the port lock, such as a port lock fault and the like, is detected, the abnormal condition monitoring module can send an alarm prompt to operation and maintenance personnel so that the operation and maintenance personnel can take corresponding measures in time for processing.

Specifically, the technical concept of the application is to collect the monitoring image of the port lock through the camera, and introduce an image processing and analyzing algorithm at the rear end to analyze the monitoring image of the port lock, so as to judge whether the port lock has faults. Therefore, the real-time detection and remote control of the fault and abnormal state of the port lock can be realized based on the internet of things technology, so that the abnormal condition of the port lock can be found and processed in time, the intelligent level of the port lock is improved, and meanwhile, the reliability and safety of the port lock are also improved.

Accordingly, as shown in fig. 2, the abnormal situation monitoring module 150 includes: a port lock monitoring image acquisition unit 151 for receiving a port lock monitoring image acquired by the camera; the port lock region feature extraction unit 152 is configured to perform feature extraction on the port lock monitoring image by using a port lock region feature extractor based on a deep neural network model to obtain a port lock monitoring feature map; the port lock monitoring feature noise reduction unit 153 is configured to obtain a noise-reduced port lock monitoring feature map from the port lock monitoring feature map through a noise reduction sparser based on a per-position mask module; the port lock monitoring feature local visualization unit 154 is configured to pass the noise-reduced port lock monitoring feature map through a local information efficient modeling module to obtain a locally-salient port lock monitoring feature map as the locally-salient port lock monitoring feature; and a port lock fault detection unit 155 for determining whether a port lock has a fault based on the locally significant port lock monitoring feature.

More specifically, in the technical scheme of the application, firstly, a port lock monitoring image acquired by a camera is received. And then, performing feature mining on the port lock monitoring image by using a port lock region feature extractor with excellent performance in terms of implicit feature extraction of the image and based on a convolutional neural network model so as to extract state feature information about the port lock in the port lock monitoring image, thereby obtaining a port lock monitoring feature map.

Accordingly, in the port lock region feature extraction unit 152, the deep neural network model is a convolutional neural network model, that is, the port lock region feature extractor based on the deep neural network model is a port lock region feature extractor based on the convolutional neural network model. It is worth mentioning that convolutional neural network (Convolutional Neural Network, CNN) is a deep learning model, especially suitable for processing data with a grid structure, such as images and speech, which extracts features of the input data by a multi-layer convolution and pooling operation and classifies or regresses through fully connected layers. The convolutional neural network model is widely applied in the field of computer vision, can be used for tasks such as image classification, target detection, image generation and the like, and can automatically extract advanced semantic features in images by learning local features and spatial structures of the images. In the abnormal situation monitoring module, a convolutional neural network model is used as a port lock region feature extractor for extracting feature information in a port lock monitoring image. Through training the model, the port lock detection device has better feature extraction capability, so that accurate detection and fault judgment of the port lock state are realized.

In the actual fault detection process of the port lock, the port lock monitoring image may be interfered by various factors, such as light change, image blurring, camera shake, etc., which may cause noise and redundant information in the feature map. If the port lock monitoring feature map is not processed, the noise and redundant information may affect the subsequent feature analysis and classification results about the port lock, reducing the accuracy and reliability of the system for port lock monitoring. In addition, when the state detection of the port lock is actually carried out, the method is also considered to focus on the relevant region characteristic information about the port lock in the image, and other useless noise and background interference characteristics are filtered, so that key characteristics of the port lock are highlighted, and the judgment accuracy of the state of the port lock is improved. Based on the above, in the technical scheme of the application, the port lock monitoring feature map is further subjected to noise reduction through a noise reduction sparser based on a per-position mask module to obtain a noise-reduced port lock monitoring feature map. In particular, the noise reduction sparser based on the per-position mask module can identify and remove noise and background interference in the feature map according to pixel position information in the image. Through sparse representation and reconstruction of the feature map, the noise reduction sparser can remove noise parts so as to retain feature information related to the port lock state, and therefore the feature map after noise reduction is obtained. That is, the noise-reduced port lock monitoring feature map has clearer edges and more accurate feature representation, which is beneficial to subsequent feature analysis and classification. For example, in the abnormal condition monitoring module, the noise-reduced feature map can provide more reliable feature input, so that the classifier based on the deep learning model can more accurately judge whether the port lock has a fault or not.

Accordingly, the port lock monitoring feature noise reduction unit 153 is configured to: processing the port lock monitoring feature map through a noise reduction sparser based on a per-position mask module according to the following noise reduction formula to obtain the noise-reduced port lock monitoring feature map; the noise reduction formula is as follows:

；

；

Wherein, Monitoring feature graphs for the port lock,/>Is a threshold feature map,/>Monitoring a characteristic diagram for the noise-reduced port lock,/>Monitoring feature values of each position in the feature map for the port lock,/>For the feature value of each position in the threshold feature map,/>Representing multiplication by location,/>And/>Is super-parameter,/>A set of conditions representing a threshold function.

Further, it is considered that there are local port lock detail features in the port lock monitor image, which are important for port lock status and fault detection. However, as the structure of the convolutional neural network model in the traditional sense is a convolutional and pooling layer, the neurons with local receptive fields (such as 3×3 convolutional kernels) can be used for extracting features and pooling to reduce dimensions, and meanwhile, remarkable information on each channel is obtained, but the method has large receptive fields, so that the state feature distribution features about port locks in the extracted port lock monitoring image are fuzzy, and the quality detail feature information with resolution in the feature image is easily ignored. Therefore, in the technical scheme of the application, the noise-reduced port lock monitoring feature map is further subjected to a local information efficient modeling module to obtain a local salient port lock monitoring feature map. It should be understood that the local information efficient modeling module can increase a 1×1 convolution kernel and a ReLU activation function after traditional convolution, so that from the perspective of cross-channel pooling, the method is equivalent to implementing cascading cross-channel weighted pooling on a normal convolution layer, so that the model can learn the relation between channels, and the local detail characteristic information about the port lock in the port lock monitoring image is modeled and characterized more efficiently, so that the local detail characteristic of the port lock in the image is more prominent and highlighted, important local information of the port lock is highlighted, the influence of uncorrelated detail and noise is reduced, and the accuracy of port lock state and fault detection is improved.

Accordingly, the port lock monitoring feature local visualization unit 154 is configured to: processing the noise-reduced port lock monitoring feature map through a local information efficient modeling module according to the following saliency formula to obtain the local saliency port lock monitoring feature map; wherein, the saliency formula is:

；

Wherein, Representing the noise-reduced port lock monitoring characteristic diagram,/>Representing the local saliency port lock monitoring feature map,/>Representation/>Function,/>Indicating convolution processing using a 3 x 3 convolution kernel,/>A convolution process using a1×1 convolution kernel is shown.

And then, the local saliency port lock monitoring feature map passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the port lock has a fault or not. That is, the important local area saliency characteristic information of the port lock is used for classification processing, so that whether the port lock has faults or not is judged. Therefore, the real-time detection and remote control of the fault and abnormal state of the port lock can be realized based on the internet of things technology, so that the abnormal condition of the port lock can be found and processed in time.

Accordingly, the port lock failure detection unit 155 includes: and the fault detection subunit is used for enabling the local saliency port lock monitoring feature diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the port lock has a fault or not.

Further, the fault detection subunit includes: the expansion secondary unit is used for expanding the local saliency port lock monitoring feature images into optimized classification feature vectors according to row vectors or column vectors; the full-connection coding secondary unit is used for carrying out full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier so as to obtain a coding classification feature vector; and a classification secondary unit, configured to input the encoded classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

That is, in the technical solution of the present application, the labels of the classifier include that the port lock has a fault (first label) and that the port lock has no fault (second label), wherein the classifier determines to which classification label the locally-salient port lock monitoring feature map belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether the port lock has a fault", which is just two kinds of classification tags, and the probability that the output feature is the sum of the two classification tags sign, that is, p1 and p2 is one. Therefore, the classification result of whether the port lock has a fault is actually converted into a class probability distribution conforming to the two classes of the natural law through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether the port lock has a fault.

It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.

Particularly, in the technical scheme of the application, after the port lock monitoring image passes through the port lock area feature extractor based on the convolutional neural network model, each feature matrix of the obtained port lock monitoring feature image is used for expressing the image semantic feature of the port lock monitoring image, and channel correlation of the convolutional neural network model is arranged among the feature matrices. And after the port lock monitoring feature map is subjected to noise reduction through a noise reduction sparser based on a position mask module to obtain a noise reduction port lock monitoring feature map, and the noise reduction port lock monitoring feature map is subjected to local information efficient modeling module to obtain a local salified port lock monitoring feature map, the image semantic feature spatial distribution of each feature matrix of the local salified port lock monitoring feature map is further strengthened, but the channel distribution correlation among the feature matrices of the local salified port lock monitoring feature map is also degraded, so that when the local salified port lock monitoring feature map is subjected to classification regression training through a classifier, the local salified port lock monitoring feature map has poor regression constraint relative to the overall distribution of the classifier, and the accuracy of the classification result is affected.

In a preferred example, the fault detection subunit includes: performing feature flattening on the local saliency port lock monitoring feature map to obtain a local saliency port lock monitoring feature vector; calculating the sum of the square root of the length of the local salified port lock monitoring feature vector and the point of the inverse of the square root of the second norm of the local salified port lock monitoring feature vector to obtain a local salified port lock monitoring semantic offset feature vector; calculating an exponential function based on a natural constant of the local saliency port lock monitoring semantic offset feature vector to obtain a local saliency port lock monitoring semantic offset prediction feature vector; calculating the product of a local saliency port lock monitoring feature vector and a dot product of a norm and a weight super parameter of the local saliency port lock monitoring feature vector to obtain a local saliency port lock monitoring semantic constraint feature vector; calculating the point sum of the local saliency port lock monitoring semantic offset prediction feature vector and the local saliency port lock monitoring semantic constraint feature vector to obtain an optimized local saliency port lock monitoring feature vector; and passing the optimized local saliency port lock monitoring feature vector through the classifier to obtain the classification result.

In the above preferred example, the local normalized coordinates as the respective feature values for the local normalized port lock monitoring feature vector are represented by the structured norm of the local normalized port lock monitoring feature vector, the vector overall distribution of the local normalized port lock monitoring feature vector is determined to represent the class offset prediction direction of the respective feature values of the local normalized port lock monitoring feature vector as a center with respect to the class rotation offset of the feature values, and feature value constraint is performed by the bounding box of the vector feature value distribution of the local normalized port lock monitoring feature vector, so as to promote the constraint of the local normalized port lock monitoring feature vector under the overall regression distribution, thereby promoting the training speed of the model and the accuracy of the classification result obtained by the local normalized port lock monitoring feature vector through the classifier. Therefore, the real-time detection and remote control of the fault and abnormal state of the port lock can be realized based on the internet of things technology, so that the abnormal condition of the port lock can be found and processed in time, the intelligent level of the port lock is improved, and meanwhile, the reliability and safety of the port lock are also improved.

In summary, the port lock real-time monitoring system 100 based on the internet of things technology according to the embodiment of the application is illustrated, which can improve the reliability and safety of the port lock.

As described above, the port lock real-time monitoring system 100 based on the internet of things according to the embodiment of the present application may be implemented in various terminal devices, for example, a server having the port lock real-time monitoring algorithm based on the internet of things according to the embodiment of the present application. In one example, the port lock real-time monitoring system 100 based on the internet of things technology according to the embodiment of the present application may be integrated into a terminal device as a software module and/or a hardware module. For example, the port lock real-time monitoring system 100 based on the internet of things technology according to the embodiment of the present application may be a software module in the operating system of the terminal device, or may be an application program developed for the terminal device; of course, the port lock real-time monitoring system 100 based on the internet of things technology according to the embodiment of the application may also be one of numerous hardware modules of the terminal device.

Alternatively, in another example, the port lock real-time monitoring system 100 based on the internet of things technology and the terminal device according to the embodiment of the present application may be separate devices, and the port lock real-time monitoring system 100 based on the internet of things technology may be connected to the terminal device through a wired and/or wireless network, and transmit the interaction information according to the agreed data format.

Fig. 3 is a flowchart of a port lock real-time monitoring method based on the internet of things technology according to an embodiment of the present application. As shown in fig. 3, a port lock real-time monitoring method based on the internet of things technology according to an embodiment of the present application includes: s110, when an operation and maintenance person needs to unlock, an unlocking request is sent to a port lock through an authorization module of the Internet of things platform; s120, responding to the unlocking request received by the application program of the port lock, and sending unlocking information to the Internet of things platform; s130, forwarding the unlocking information to hardware of the port lock through the Internet of things platform to unlock a physical port; and S140, automatically storing unlocking records to a log record application program through the application program of the port lock.

In a specific example, the port lock real-time monitoring method based on the internet of things technology further includes an abnormal condition monitoring step, where the abnormal condition monitoring step includes: receiving a port lock monitoring image acquired by a camera; performing feature extraction on the port lock monitoring image through a port lock region feature extractor based on a deep neural network model to obtain a port lock monitoring feature map; the port lock monitoring feature map is subjected to noise reduction through a noise reduction sparser based on a per-position mask module to obtain a post-noise reduction port lock monitoring feature map; the noise-reduced port lock monitoring feature map is subjected to a local information efficient modeling module to obtain a local saliency port lock monitoring feature map as the local saliency port lock monitoring feature; and determining whether a port lock is faulty based on the locally-salient port lock monitoring feature.

Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described port lock real-time monitoring method based on the internet of things have been described in detail in the above description of the port lock real-time monitoring system 100 based on the internet of things with reference to fig. 1 to 2, and thus, repetitive descriptions thereof will be omitted.

Fig. 4 is an application scenario diagram of a port lock real-time monitoring system based on the internet of things technology according to an embodiment of the present application. As shown in fig. 4, in this application scenario, first, a port lock monitoring image (for example, D illustrated in fig. 4) acquired by a camera is received, and then the port lock monitoring image is input to a server (for example, S illustrated in fig. 4) in which a port lock real-time monitoring algorithm based on the internet of things technology is deployed, where the server can process the port lock monitoring image using the port lock real-time monitoring algorithm based on the internet of things technology to obtain a classification result for indicating whether a port lock has a fault.

It should be appreciated that physical port security (Physical Port Security) is a very important part of network security policies, the main task of which is to protect the physical connections of network devices, including ports, cables and connection devices of network devices.

Common device ports include the following classes: USB port: the universal serial bus (Universal Serial Bus) is a communication interface between the computer and the external device, and the USB port comprises USB Type-A, USB Type-B, USB Type-C, USB Micro-B and other interface types, and is suitable for various types of devices. HDMI Port: HDMI (high definition multimedia interface) is a digital interface for video and audio signal transmission, and the HDMI port is mainly used for connecting devices such as a display, a television, a projector, and a sound. Vga port: VGA (video graphics array) is an analog signal interface, and is mainly used for connecting VGA display, projector and other devices. Dvi port: DVI (digital video interface) is a digital interface for transmitting video signals, and includes two types of DVI-D (digital signal) and DVI-a (analog signal). Rj-45 port: RJ-45 (twisted pair ethernet ports) is an interface for connecting ethernet devices, and RJ-45 ports are mainly used for connecting routers, switches, hubs, network cards, and the like. Thunderbolt port: thunder and lightning is a high-speed interface, supports data transmission, video transmission and charging functions, and the thunder and lightning port is mainly used for connecting Mac computers, docking stations, hard disks and other devices. Displayport port: displayPort (display port) is a digital video interface, and is mainly used for connecting devices such as a display, a television and the like. 8. Optical fiber port: fiber ports are mainly used for high-speed data transmission, such as fiber ethernet, fiber SDH, etc. 9. An ethernet port: the network card ports are used to connect network devices such as routers, switches, hubs, etc. 10. Audio interface: the audio interface includes earphone jack, microphone jack, audio line input/output, etc. types for connecting with the audio device. In summary, physical port security is a very important aspect of network security, and comprehensive security measures need to be taken to ensure the security of devices and network connections.

The importance of the port lock of the Internet of things equipment comprises: 1. effectively protecting the inside of the equipment: a physical port is a primary channel through which a device connects to other systems or devices. These ports, if not effectively plugged, may become entrances for malicious attackers to the inside of the device. The physical port is used for blocking, so that hardware and software in the equipment can be effectively protected. 2. System security is enhanced: blocking physical ports helps to prevent unauthorized access and malicious attacks. By preventing an attacker from entering the device, the risk of the device being attacked can be reduced, and the safety of the device data is protected. 3. Prevention of external attacks: plugging the physical port may prevent unauthorized external access. This helps to ensure that the enterprise network is protected from external attackers, protecting the enterprise data and systems from security. 4. The safety risk is reduced: physical port plugging helps to reduce equipment security risks. By placing the physical port in a secure range, an attacker can be effectively prevented from attacking with the port of the device. 5. Simplified maintenance and management: plugging the physical ports helps to simplify maintenance and management of the device. This allows the enterprise to focus more on other aspects of network security, such as application security, authentication, and access control. 6. Improving the usability of the equipment: blocking the physical port can prevent the equipment from failing to work normally due to attack. This helps to improve the usability of the device and reduce disruption of service due to device failure. 7. Adapt to changing threat environments: with the continual change of network threat environments, enterprises need to take corresponding security measures to cope with new threats. Blocking the physical port helps the enterprise to remain secure and stable in dealing with changing threat environments. In summary, plugging a physical port is of great importance in terms of equipment safety. Enterprises should pay attention to the equipment physical port blocking work and formulate corresponding security policies and measures to ensure the safety of equipment and networks.

The port lock of the Internet of things is used for monitoring the physical port of the equipment in real time by combining hardware and software, so that the operation and maintenance personnel can authorize unlocking, record automatic storage, work order automatic recording and alarm event reminding. The method can realize real-time monitoring of the physical port of the equipment, unlocking authorization, automatic record storage, automatic work order record and alarm event reminding in a mode of combining hardware and software.

Specifically, regarding the hardware portion, it includes: internet of things equipment: such as an intelligent gateway or router, for connecting all port locks and receiving and forwarding data; port lock hardware: such as a physical port lock, for controlling the switching of a physical port; internet of things key: the intelligent lock has the management function of the Internet of things, detects corresponding authorization during unlocking, and gives an alarm to remind a manager when the intelligent lock is not matched with the port lock.

Regarding the software portion, it includes: internet of things platform: the method is used for managing the Internet of things equipment, port locks and other related equipment; port lock application: the system is used for monitoring the state of the physical port in real time, including whether unlocking is authorized; logging application: all unlocking events used for storing automatic records are convenient to trace; work order system: the system is used for recording and managing unlocking requests, including requesters, request time, unlocking states and the like; and (3) an alarm system: the alarm device is used for giving alarm reminding to related personnel when abnormal conditions (such as illegal unlocking, port lock faults and the like) occur.

When operation and maintenance personnel need to unlock, an authorization function on the platform of the Internet of things can be used to send an unlocking request to the port lock. And after receiving the unlocking request, the port lock application program sends unlocking information to the Internet of things platform. And the internet of things platform forwards unlocking information to port locking hardware to unlock the physical port. Meanwhile, the port lock application program automatically saves the unlocking record to the log record application program.

In the operation and maintenance process, the work order system can be used for recording and managing the unlocking request. The work order system can classify and inquire the work orders according to the dimensions of time, personnel, equipment and the like. Meanwhile, operation and maintenance personnel can check unlocking records and logs in the work order system so as to be convenient for tracing and analysis. If abnormal conditions such as illegal unlocking, port lock faults and the like occur, the alarm system can send alarm reminding to related personnel. The operation and maintenance personnel can check the alarm event in the alarm system and take corresponding measures for processing. By means of the combination of hardware and software, the port lock of the Internet of things can be monitored in real time, unlocking is authorized, automatic record storage, automatic work order recording and alarm event reminding can be achieved, and therefore operation and maintenance efficiency and safety are improved.

According to another aspect of the present application there is also provided a non-volatile computer readable storage medium having stored thereon computer readable instructions which when executed by a computer can perform a method as described above.

Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.

The application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

The foregoing is illustrative of the present application and is not to be construed as limiting thereof. Although a few exemplary embodiments of this application have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this application. Accordingly, all such modifications are intended to be included within the scope of this application as defined in the following claims. It is to be understood that the foregoing is illustrative of the present application and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The application is defined by the claims and their equivalents.

Claims (7)

1. Port lock real-time monitoring system based on internet of things technology, which is characterized by comprising:

The unlocking signal module is used for sending an unlocking request to the port lock through the authorization module of the Internet of things platform when an operator needs to unlock;

the unlocking request detection and information transmission module is used for responding to the unlocking request received by the application program of the port lock and transmitting unlocking information to the Internet of things platform;

the physical port unlocking module is used for forwarding the unlocking information to the hardware of the port lock through the Internet of things platform so as to unlock the physical port;

And the unlocking record storage module is used for automatically storing the unlocking record to the log record application program through the application program of the port lock.

2. The internet of things-based port lock real-time monitoring system of claim 1, further comprising an abnormal situation monitoring module, the abnormal situation monitoring module comprising:

the port lock monitoring image acquisition unit is used for receiving the port lock monitoring image acquired by the camera;

the port lock area feature extraction unit is used for carrying out feature extraction on the port lock monitoring image through a port lock area feature extractor based on the deep neural network model so as to obtain a port lock monitoring feature map;

The port lock monitoring feature noise reduction unit is used for obtaining a noise-reduced port lock monitoring feature map through a noise reduction sparser based on a per-position mask module;

The port lock monitoring feature local visualization unit is used for enabling the noise-reduced port lock monitoring feature map to pass through a local information efficient modeling module to obtain a local salient port lock monitoring feature map as the local salient port lock monitoring feature;

And the port lock fault detection unit is used for determining whether the port lock has a fault or not based on the local saliency port lock monitoring characteristic.

3. The internet of things-based port lock real-time monitoring system of claim 2, wherein the deep neural network model is a convolutional neural network model.

4. The internet of things-based port lock real-time monitoring system according to claim 3, wherein the port lock monitoring feature noise reduction unit is configured to:

Processing the port lock monitoring feature map through a noise reduction sparser based on a per-position mask module according to the following noise reduction formula to obtain the noise-reduced port lock monitoring feature map;

the noise reduction formula is as follows:

；

；

Wherein, Monitoring feature graphs for the port lock,/>Is a threshold feature map,/>Monitoring a characteristic diagram for the noise-reduced port lock,/>Monitoring feature values of each position in the feature map for the port lock,/>For the feature value of each position in the threshold feature map,/>Representing multiplication by location,/>And/>Is super-parameter,/>A set of conditions representing a threshold function.

5. The port lock real-time monitoring system based on the internet of things technology according to claim 4, wherein the port lock monitoring feature local display unit is configured to:

processing the noise-reduced port lock monitoring feature map through a local information efficient modeling module according to the following saliency formula to obtain the local saliency port lock monitoring feature map;

Wherein, the saliency formula is:

；

Wherein, Representing the noise-reduced port lock monitoring characteristic diagram,/>Representing the local saliency port lock monitoring feature map,/>Representation/>Function,/>Indicating the use of a3 x 3 convolution kernel for the convolution process,A convolution process using a1×1 convolution kernel is shown.

6. The internet of things-based port lock real-time monitoring system according to claim 5, wherein the port lock fault detection unit comprises:

and the fault detection subunit is used for enabling the local saliency port lock monitoring feature diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the port lock has a fault or not.

7. The internet of things-based port lock real-time monitoring system of claim 6, wherein the fault detection subunit comprises:

the expansion secondary unit is used for expanding the local saliency port lock monitoring feature images into optimized classification feature vectors according to row vectors or column vectors;

the full-connection coding secondary unit is used for carrying out full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier so as to obtain a coding classification feature vector;

And the classification secondary unit is used for inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.