Optical cable eavesdropping intelligent monitoring method and related equipment

Abstract

The invention relates to the field of optical cable communication, and discloses an optical cable eavesdropping intelligent monitoring method and related equipment, and the method comprises the steps: obtaining a performance parameter in an optical fiber channel line; constructing a neural network model, training the neural network model, and analyzing and processing the performance parameters by using the trained neural network model to obtain an analysis result; and judging whether an eavesdropping behavior exists or not according to an analysis result, if so, triggering an alarm mechanism, interrupting communication, checking the eavesdropping situation, and then recovering the normal operation of the communication optical cable. By monitoring the performance parameters in the optical fiber channel line in real time, the potential eavesdropping behavior can be quickly found and responded, the real-time monitoring capability of communication safety is improved, and the duration of the eavesdropping behavior and the potential information leakage risk are reduced. And the neural network model is utilized to analyze and process the performance parameters, so that intelligent monitoring is realized.

Description

Technical Field

[0001] The invention relates to the field of optical cable communications, and in particular to an optical cable eavesdropping intelligent monitoring method and related equipment. Background Art

[0002] In information transmission technology, security and stability have always been the focus of the industry. With the rapid development of information technology, optical cable communication, as the cornerstone of modern communication networks, carries the task of transmitting a large amount of critical data. However, optical cable eavesdropping, as a highly concealed and difficult-to-detect illegal means of obtaining information, is increasingly becoming a major security risk facing optical cable communication systems.

[0003] Optical cable eavesdropping technology, with its "easy to hide" feature, can intercept and analyze the communication content in the optical cable without being easily detected by traditional detection methods. This highly concealed eavesdropping behavior seriously threatens the confidentiality and integrity of the communication content, and poses a huge risk to the information security of individuals, enterprises and even the country.

[0004] In order to meet this challenge, traditional optical cable communication security protection measures mainly include encryption technology and strengthening of physical protection layer. Encryption technology improves the confidentiality of data during transmission by encrypting the communication content; while the physical protection layer prevents external attackers from physically damaging or eavesdropping on the optical cable by strengthening the physical protection measures of the optical cable. These measures have improved the security of the optical cable communication system to a certain extent.

[0005] However, when faced with highly concealed fiber optic cable eavesdropping, traditional security measures often seem powerless. Eavesdroppers may use advanced eavesdropping techniques and equipment to bypass encryption technology protection, or eavesdrop through physical means without damaging the fiber optic cable. Especially in critical information infrastructure such as stability control systems, fiber optic cable eavesdropping may lead to more serious consequences. Once sensitive information is leaked, it will not only cause irreparable damage to the privacy of individuals and enterprises, but may also pose a direct threat to the stable operation of the system, thereby affecting the information security and stability of the entire society.

[0006] Given the limitations of traditional security protection measures, the industry urgently needs a more efficient and intelligent optical cable eavesdropping monitoring technology. Summary of the invention

[0007] In order to overcome the defects of the above-mentioned prior art, the purpose of the present invention is to provide an optical cable eavesdropping intelligent monitoring method and related equipment to solve the technical problem of how to improve the efficiency and intelligence of optical cable eavesdropping monitoring in the prior art.

[0008] The present invention is achieved through the following technical solutions: In a first aspect, the present invention provides an optical cable eavesdropping intelligent monitoring method, comprising: Obtaining performance parameters in a fiber channel line; Constructing a neural network model, training the neural network model, and using the trained neural network model to analyze and process performance parameters to obtain analysis results; Determine whether there is eavesdropping based on the analysis results. If so, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and then restore the normal operation of the communication optical cable.

[0009] Preferably, in the step of obtaining the performance parameters of the optical fiber channel line, the specific process is as follows: Collecting data samples of normal transmission and different eavesdropping situations in the optical fiber channel line, wherein the different eavesdropping situations include resonance eavesdropping, optical eavesdropping and diverter eavesdropping; Preprocess the data samples to obtain data information; The performance parameters in the optical fiber channel line are obtained based on the data information.

[0010] Furthermore, performance parameters in the optical fiber channel line are obtained according to the data information, wherein the performance parameters include bit error rate, error vector magnitude and eye diagram, and characteristic parameters extracted from the eye diagram include eye width, eye height, Q factor and average power.

[0011] Preferably, the neural network model includes an input layer, a hidden layer and an output layer; wherein the hidden layer uses a ReLU activation function, and the output layer uses a Sigmoid activation function to output a probability value of 0 or 1.

[0012] Preferably, in the step of training the neural network model, the specific training process is as follows: The performance parameters are used as features for the input vector X=(x1, x2, ..., xn) of the neural network, and performance parameter labels are set, where the data with eavesdropping is marked as 1, and the data without eavesdropping is marked as 0; the input vector X=(x1, x2, ..., xn) is matched with the corresponding labels to form a data set; The data set is divided into a training set and a test set. During the training process, the training set updates the weights of the neural network through continuous iterations until the loss function converges or reaches the preset number of iterations, completing the neural network model training.

[0013] Furthermore, the test set is imported into the input end of the neural network model. After receiving the input data, the neural network model performs forward propagation. The input data passes through each layer of the neural network model. The neurons in each layer calculate the output value according to the weight and activation function until it reaches the output layer. In the output layer, the neurons are summed to obtain the analysis result, and whether there is eavesdropping behavior is determined based on the analysis result.

[0014] Furthermore, in the step of determining whether there is eavesdropping behavior based on the analysis results, the specific process is as follows: Set the output threshold to convert the analysis results into binary classification results; If the analysis result is greater than or equal to the output threshold, the output result is judged to be 1, indicating that eavesdropping behavior does exist; if the analysis result is less than the output threshold, the output result is judged to be 0, indicating that there is no eavesdropping behavior.

[0015] In a second aspect, the present invention provides an optical cable eavesdropping intelligent monitoring system, comprising: A performance parameter acquisition module, used to acquire performance parameters in a fiber channel line; The model processing module is used to construct a neural network model, train the neural network model, and use the trained neural network model to analyze and process the performance parameters to obtain analysis results; The execution module is used to determine whether there is eavesdropping based on the analysis results. If it is determined that there is eavesdropping, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and the normal operation of the communication optical cable is restored.

[0016] In a third aspect, the present invention further provides a mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the optical cable eavesdropping intelligent monitoring method as described above when executing the computer program.

[0017] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the optical cable eavesdropping intelligent monitoring method as described above are implemented.

[0018] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention provides an intelligent monitoring method for optical cable eavesdropping. By real-time monitoring of performance parameters in the optical fiber channel line, it is possible to quickly discover and respond to potential eavesdropping behaviors, thereby improving the real-time monitoring capability of communication security and reducing the duration of eavesdropping behaviors and the potential risk of information leakage. The performance parameters are analyzed and processed using a neural network model to achieve intelligent monitoring. This automated processing method not only improves monitoring efficiency, but also reduces the need for manual intervention and reduces the possibility of human error. By training the neural network model, it is possible to accurately identify data features that indicate the presence of eavesdropping behaviors. This high-precision recognition capability helps to accurately determine the presence of eavesdropping behaviors, avoid false positives and false negatives, and improve the accuracy and reliability of monitoring.

[0019] Furthermore, the forward propagation process of the neural network model can process a large amount of input data in a short time. When the test set is imported into the model, the model can quickly calculate the output value, thereby achieving a rapid response to eavesdropping behavior. This helps to timely discover and deal with potential eavesdropping threats in practical applications. By continuously iteratively updating the weights of the neural network during the training process, the model has learned how to accurately judge whether there is eavesdropping behavior based on the characteristics of the input data. In the testing phase, the model can use these learned features to accurately calculate the output value, thereby improving the accuracy of the judgment.

[0020] Furthermore, setting the output threshold actually defines a clear decision boundary in the model output space, which helps to clearly classify the continuous model output values ​​into two categories, namely, the presence of eavesdropping and the absence of eavesdropping, making the monitoring results more intuitive and easy to understand. The setting of the threshold is usually based on the performance of the model on the training set or validation set to ensure that false positives and false negatives are minimized while maintaining high sensitivity. This accuracy improvement is crucial to ensuring communication security. The binary classification results facilitate subsequent processing and decision-making. When the model output is 1, the alarm mechanism can be triggered immediately and necessary security measures can be taken; when the output is 0, it can be considered that the current communication is safe and no further intervention is required. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Flow chart of the optical cable eavesdropping intelligent monitoring method in an embodiment of the present invention; Figure 2 A flow chart of obtaining performance parameters in a fiber channel line in an embodiment of the present invention; Figure 3 A schematic diagram of eye diagram parameter definition in an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a neural network model in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an intelligent monitoring system for optical cable eavesdropping in an embodiment of the present invention; In the figure: 1. Performance parameter acquisition module; 2. Model processing module; 3. Execution module. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] The purpose of the present invention is to provide an optical cable eavesdropping intelligent monitoring method and related equipment to solve the technical problem of how to improve the efficiency and intelligence of optical cable eavesdropping monitoring in the prior art.

[0024] The present invention is further described in detail below in conjunction with the accompanying drawings: Example 1 See also Figure 1 In one embodiment of the present invention, a method for intelligent monitoring of optical cable eavesdropping is provided, comprising: Step 1, obtaining performance parameters in a fiber channel line; Specifically, according to Figure 2 As shown in FIG. 1 , in the step of obtaining the performance parameters of the optical fiber channel line, the specific process is as follows: Step 11, collecting data samples of normal transmission and different eavesdropping situations in the optical fiber channel line, wherein the different eavesdropping situations include resonance eavesdropping, optical eavesdropping and diverter eavesdropping; Among them, resonance eavesdropping is a method of intercepting communication signals through the micro-vibration of optical fiber. Using a resonance eavesdropper, you can obtain information transmitted in the optical fiber without directly touching the optical fiber. The optical fiber will produce micro-vibrations when transmitting data, and the resonance eavesdropper can capture these tiny vibrations and convert them into readable signals.

[0025] Optical eavesdropping is the use of optical technology to steal information transmitted in optical fiber communications. Between the photoelectric converters at the transmitting and receiving ends, light waves may leak to a certain extent. Attackers can use this leakage to steal communication signals and obtain information about communication data by analyzing the leaked light. In addition, attackers can also use the principle of mirror reflection to steal information.

[0026] The diverter eavesdropping method is a method of intercepting communication signals through the diverter of the optical fiber. In the process of optical fiber communication, it is often necessary to use an optical fiber diverter to adjust the optical path. Attackers can intercept data through this process and steal communication data without being detected by manipulating the optical fiber diverter.

[0027] Step 12, preprocessing the data samples to obtain data information; Specifically, the specific process is as follows: Obtain data information through data cleaning and data formatting of data samples; Among them, data cleaning involves removing noise from data samples and filling missing values ​​through interpolation and averaging methods; In data formatting, the data samples are normalized so that the scales of the data samples are the same.

[0028] Step 13, obtaining performance parameters in the optical fiber channel line according to the data information.

[0029] The performance parameters of the optical fiber channel line are obtained according to the data information, wherein the performance parameters include bit error rate, error vector amplitude and eye diagram, and the characteristic parameters extracted from the eye diagram include eye width, eye height, Q factor and average power.

[0030] Among them, the eye diagram parameters are defined as follows Figure 3 As shown in the figure, the influence of inter-symbol crosstalk and noise can be observed from the eye diagram, which reflects the overall characteristics of the digital signal, thereby estimating the quality of the system. Therefore, eye diagram analysis is the core of signal integrity analysis of high-speed interconnection systems. Eye width reflects the total jitter of the signal, which is the size of the eye diagram on the horizontal axis. It is defined as the time difference between the left and right crossing points in a UI. The time points within the crossing range are calculated based on the histogram average at the two zero crossing points in the signal. Eye height reflects the noise tolerance of the signal on the transmission line, which is the distance of the blank area on the vertical axis. If the instantaneous value of the noise exceeds half of the eye height, an erroneous decision may occur. Q factor is a parameter for measuring the signal-to-noise ratio of the eye diagram. It is defined as the ratio of the signal power to the noise power of the receiver under the optimal decision threshold. Q factor comprehensively reflects the quality of the eye diagram. The higher the Q factor, the better the quality of the eye diagram and the higher the signal-to-noise ratio. Q factor is generally affected by noise, optical power, electrical signal impedance matching and other factors. Average power The average power reflected by the eye diagram is the average value of the entire data stream. The average power is the average value of the histogram and should be 50% of the total eye amplitude.

[0031] Step 2: construct a neural network model, train the neural network model, and use the trained neural network model to analyze and process the performance parameters to obtain analysis results; Specifically, the neural network model includes an input layer, a hidden layer and an output layer; the hidden layer uses a ReLU activation function, and the output layer uses a Sigmoid activation function to output a probability value of 0 or 1.

[0032] Among them, this embodiment uses computer learning and reasoning to accurately detect illegal wiretapping through the nonlinear relationship between monitoring data and actual status. Deep learning is a machine learning method developed from artificial neural networks. Its deep structure and powerful feature learning ability can automatically extract, select and optimize features from a large amount of data. Therefore, artificial neural networks are an adaptive statistical modeling tool that has more advantages than traditional logical reasoning calculations. The system will autonomously learn the tiny feature value differences caused by different wiretapping methods in different locations, and then perform regression calculations to finally calculate whether there is wiretapping or not. The neural network model structure is as follows: Figure 4 As shown, the neural network model used in this embodiment is a multi-layer feedforward network, which consists of three parts: Input layer: Many neurons receive a large number of nonlinear input messages, and the input messages are called input vectors; Hidden layer: It is the layers composed of many neurons and links between the input layer and the output layer. The number of nodes is more than that of the input layer and the output layer.

[0033] Output layer: Messages are transmitted, analyzed, and weighed in neuron links to form output results. The output message is called an output vector.

[0034] Each layer of neurons in a neural network has input and output, where the input is the output of the previous layer of network neurons; each layer is composed of Ni network neurons, where Ni represents N on the i-th layer; each network neuron on Ni takes the output of the corresponding network neuron on the previous layer as its input, and the connection between the network neuron and the corresponding network neuron is called a synapse. In the mathematical model, each synapse has a weighted value called a weight. To calculate the value of a certain network neuron on the i-th layer, it is equal to each weight multiplied by the output of the corresponding network neuron on the i-1-th layer, and then the sum of all is obtained to obtain a certain network neuron value on the i-th layer, and then the value is passed through the differentiable Sigmoid function on the network neuron to control the output size, because it is differentiable and continuous, which is convenient for processing. The output of the network neuron is calculated layer by layer, and then the weight size is adjusted inversely according to the output until the error function converges, and then the final output layer network neuron value is used to determine whether it is eavesdropped or not.

[0035] Specifically, in the training steps of the neural network model, the specific training process is as follows: The performance parameters are used as features for the input vector X=(x1, x2, ..., xn) of the neural network, and performance parameter labels are set, where the data with eavesdropping is marked as 1, and the data without eavesdropping is marked as 0; the input vector X=(x1, x2, ..., xn) is matched with the corresponding labels to form a data set; The data set is divided into a training set and a test set. During the training process, the training set updates the weights of the neural network through continuous iterations until the loss function converges or reaches the preset number of iterations, completing the neural network model training.

[0036] Among them, the test set is imported into the input end of the neural network model. After receiving the input data, the neural network model performs forward propagation. The input data passes through each layer of the neural network model. The neurons in each layer calculate the output value according to the weight and activation function until it reaches the output layer. In the output layer, the neurons are summed to obtain the analysis result, and whether there is eavesdropping behavior is determined based on the analysis result.

[0037] When the neural network model is trained, its purpose is to conduct statistical data modeling analysis and statistical learning based on the slight differences in the data. The data processed by DSP is used as the input of the artificial neural network model, and the output is used to determine whether eavesdropping occurs. When there is eavesdropping on the link, the change of the channel characteristic parameters will directly reflect on the trained neural network model, causing the corresponding output to change, thus realizing intelligent monitoring of optical cable eavesdropping.

[0038] Step 3: Determine whether there is eavesdropping based on the analysis results. If it is determined that there is eavesdropping, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and then the normal operation of the communication optical cable is restored.

[0039] Specifically, in the step of determining whether there is eavesdropping behavior based on the analysis results, the specific process is as follows: Set the output threshold to convert the analysis results into binary classification results; If the analysis result is greater than or equal to the output threshold, the output result is judged to be 1, indicating that eavesdropping behavior does exist; if the analysis result is less than the output threshold, the output result is judged to be 0, indicating that there is no eavesdropping behavior.

[0040] In this embodiment, the output threshold is a key parameter that determines how the analysis results are classified. The setting of the threshold is usually based on the performance of the model on the training set or the validation set, as well as the tolerance for false positives and false negatives in practical applications. When the analysis result is greater than or equal to the output threshold, the system believes that there is a high possibility of eavesdropping, so the output result is judged to be 1. When the analysis result is less than the output threshold, the system believes that there is a high possibility that there is no eavesdropping, so the output result is judged to be 0. Once it is determined that there is eavesdropping (the output result is 1), the system will trigger an alarm mechanism to remind relevant personnel to pay attention and take necessary safety measures. At the same time, the system will interrupt communication in order to investigate and process the eavesdropping situation. The investigation and processing may include physical inspection, data analysis and other steps to ensure the safety of the communication cable. After the investigation and processing is completed, the system will restore the normal operation of the communication cable.

[0041] In this embodiment, according to the analysis results of the optical cable monitoring system or the anti-eavesdropping system, when it is determined that there is eavesdropping, the system will automatically trigger an alarm. The system will send an alarm message to relevant personnel through a preset alarm method (such as text messages, emails, system prompts, etc.). Among them, the alarm message should contain key information such as the time, location, and possible eavesdropping device type of the eavesdropping behavior. After the relevant personnel arrive at the scene, they first confirm the existence of the eavesdropping behavior, which can be verified by physical inspection, data analysis, etc. After confirming the eavesdropping behavior, in order to prevent further leakage of sensitive information, it is necessary to immediately interrupt the transmission of the communication optical cable. A comprehensive investigation of the optical cable and its surrounding environment is carried out to find possible eavesdropping devices. Professional anti-eavesdropping equipment can be used for detection, such as radio frequency scanners, RFID detectors, etc. After handling the eavesdropping device, the interrupted communication optical cable needs to be repaired to restore normal communication transmission. After the repair is completed, the performance of the optical cable needs to be tested to ensure that the transmission quality meets the requirements. After confirming that the performance of the optical cable is normal, the transmission of the communication optical cable can be restored.

[0042] In summary, the present invention provides an intelligent monitoring method for optical cable eavesdropping, which can quickly detect and respond to potential eavesdropping behaviors by real-time monitoring of performance parameters in optical fiber channel lines, thereby improving the real-time monitoring capability of communication security and reducing the duration of eavesdropping behaviors and the potential risk of information leakage. The performance parameters are analyzed and processed using a neural network model to achieve intelligent monitoring. This automated processing method not only improves monitoring efficiency, but also reduces the need for manual intervention and reduces the possibility of human error. By training the neural network model, it is able to accurately identify data features that indicate the presence of eavesdropping behaviors. This high-precision recognition capability helps to accurately determine the presence of eavesdropping behaviors, avoid false alarms and missed alarms, and improve the accuracy and reliability of monitoring.

[0043] Among them, the forward propagation process of the neural network model can process a large amount of input data in a short time. When the test set is imported into the model, the model can quickly calculate the output value, thereby achieving a rapid response to eavesdropping behavior. This helps to timely discover and deal with potential eavesdropping threats in practical applications. By continuously iteratively updating the weights of the neural network during the training process, the model has learned how to accurately judge whether there is eavesdropping behavior based on the characteristics of the input data. In the testing phase, the model can use these learned features to accurately calculate the output value, thereby improving the accuracy of the judgment.

[0044] Among them, setting the output threshold actually defines a clear decision boundary in the model output space, which helps to clearly classify the continuous model output values ​​into two categories, namely, the presence of eavesdropping and the absence of eavesdropping, making the monitoring results more intuitive and easy to understand. The setting of the threshold is usually based on the performance of the model on the training set or validation set to ensure that false positives and false negatives are minimized while maintaining high sensitivity. This accuracy improvement is crucial to ensuring communication security. The binary classification results facilitate subsequent processing and decision-making. When the model output is 1, the alarm mechanism can be triggered immediately and necessary security measures can be taken; when the output is 0, it can be considered that the current communication is safe and no further intervention is required.

[0045] Example 2 according to Figure 5 As shown, the present invention also provides an optical cable eavesdropping intelligent monitoring system, including a performance parameter acquisition module 1, a model processing module 2 and an execution module 3; The performance parameter acquisition module 1 is used to acquire the performance parameters in the optical fiber channel line; Model processing module 2, used to construct a neural network model, train the neural network model, and use the trained neural network model to analyze and process performance parameters to obtain analysis results; Execution module 3 is used to determine whether there is eavesdropping based on the analysis results. If it is determined that there is eavesdropping, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and the normal operation of the communication optical cable is restored.

[0046] Example 3 The present invention also provides a mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, such as an optical cable eavesdropping intelligent monitoring program.

[0047] When the processor executes the computer program, the steps of the optical cable eavesdropping intelligent monitoring method are implemented, for example: Obtaining performance parameters in a fiber channel line; Constructing a neural network model, training the neural network model, and using the trained neural network model to analyze and process performance parameters to obtain analysis results; Determine whether there is eavesdropping based on the analysis results. If so, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and then restore the normal operation of the communication optical cable.

[0048] Alternatively, when the processor executes the computer program, the functions of each module in the above system are realized, for example: The performance parameter acquisition module 1 is used to acquire the performance parameters in the optical fiber channel line; Model processing module 2, used to construct a neural network model, train the neural network model, and use the trained neural network model to analyze and process performance parameters to obtain analysis results; Execution module 3 is used to determine whether there is eavesdropping based on the analysis results. If it is determined that there is eavesdropping, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and the normal operation of the communication optical cable is restored.

[0049] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the mobile terminal.

[0050] For example, the computer program may be divided into a performance parameter acquisition module 1, a model processing module 2, and an execution module 3; The specific functions of each module are as follows: The performance parameter acquisition module 1 is used to acquire the performance parameters in the optical fiber channel line; Model processing module 2, used to construct a neural network model, train the neural network model, and use the trained neural network model to analyze and process performance parameters to obtain analysis results; Execution module 3 is used to determine whether there is eavesdropping based on the analysis results. If it is determined that there is eavesdropping, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and the normal operation of the communication optical cable is restored.

[0051] The mobile terminal may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The mobile terminal may include, but is not limited to, a processor and a memory.

[0052] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the mobile terminal, and uses various interfaces and lines to connect various parts of the entire mobile terminal.

[0053] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the mobile terminal by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0054] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0055] Example 4 The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the optical cable eavesdropping intelligent monitoring method are implemented.

[0056] If the module / unit integrated in the mobile terminal is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0057] Based on this understanding, the present invention implements all or part of the processes in the above method, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned aggregate reinforcement learning resource scheduling method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0058] The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0059] It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0060] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An intelligent monitoring method for optical cable eavesdropping, characterized in that: include: Obtaining performance parameters in a fiber channel line; Constructing a neural network model, training the neural network model, and using the trained neural network model to analyze and process performance parameters to obtain analysis results; Determine whether there is eavesdropping based on the analysis results. If so, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and then restore the normal operation of the communication optical cable.

2. The optical cable eavesdropping intelligent monitoring method according to claim 1 is characterized in that: In the step of obtaining the performance parameters of the optical fiber channel line, the specific process is as follows: Collecting data samples of normal transmission and different eavesdropping situations in the optical fiber channel line, wherein the different eavesdropping situations include resonance eavesdropping, optical eavesdropping and diverter eavesdropping; Preprocessing the data samples to obtain data information; The performance parameters in the optical fiber channel line are obtained based on the data information.

3. The optical cable eavesdropping intelligent monitoring method according to claim 2 is characterized in that: The performance parameters in the optical fiber channel line are obtained according to the data information, wherein the performance parameters include bit error rate, error vector amplitude and eye diagram, and the characteristic parameters extracted from the eye diagram include eye width, eye height, Q factor and average power.

4. The optical cable eavesdropping intelligent monitoring method according to claim 1 is characterized in that: The neural network model includes an input layer, a hidden layer and an output layer; the hidden layer uses a ReLU activation function, and the output layer uses a Sigmoid activation function to output a probability value of 0 or 1.

5. The optical cable eavesdropping intelligent monitoring method according to claim 1 is characterized in that: In the step of training the neural network model, the specific training process is as follows: The performance parameters are used as features for the input vector X=(x1, x2, ..., xn) of the neural network, and performance parameter labels are set, where the data with eavesdropping is marked as 1, and the data without eavesdropping is marked as 0; the input vector X=(x1, x2, ..., xn) is matched with the corresponding labels to form a data set; The data set is divided into a training set and a test set. During the training process, the training set updates the weights of the neural network through continuous iterations until the loss function converges or reaches the preset number of iterations, completing the neural network model training.

6. The optical cable eavesdropping intelligent monitoring method according to claim 5 is characterized in that: The test set is imported into the input end of the neural network model. After receiving the input data, the neural network model performs forward propagation. The input data passes through each layer of the neural network model. The neurons in each layer calculate the output value according to the weight and activation function until it reaches the output layer. In the output layer, the neurons are summed to obtain the analysis result, and whether there is eavesdropping behavior is determined based on the analysis result.

7. The optical cable eavesdropping intelligent monitoring method according to claim 6 is characterized in that: In the step of judging whether there is eavesdropping behavior according to the analysis result, the specific process is as follows: Set the output threshold to convert the analysis results into binary classification results; If the analysis result is greater than or equal to the output threshold, the output result is judged as 1, indicating that eavesdropping behavior does exist; If the analysis result is less than the output threshold, the output result is judged to be 0, indicating that there is no eavesdropping behavior.

8. An intelligent monitoring system for optical cable eavesdropping, characterized in that: include: A performance parameter acquisition module, used to acquire performance parameters in a fiber channel line; The model processing module is used to construct a neural network model, train the neural network model, and use the trained neural network model to analyze and process the performance parameters to obtain analysis results; The execution module is used to determine whether there is eavesdropping based on the analysis results. If it is determined that there is eavesdropping, the alarm mechanism is triggered, and the communication is interrupted to investigate and deal with the eavesdropping situation, and the normal operation of the communication optical cable is restored.

9. A mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the optical cable eavesdropping intelligent monitoring method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the optical cable eavesdropping intelligent monitoring method as described in any one of claims 1 to 7 are implemented.

Images