Quantum key distribution network situation assessment method, device, equipment and medium

Abstract

The embodiment of the invention provides a quantum key distribution network situation assessment method and device, equipment and a medium. The method comprises the following steps: acquiring performance data of a quantum key distribution network; the performance data comprises network structure data, key performance data, communication quality data, data transmission data and an evaluation model; determining a comprehensive influence factor according to the performance data; the comprehensive influence factor is used for reflecting the importance degree of the performance data to the quantum key distribution network situation; and according to the performance data, the comprehensive influence factor and the evaluation model, determining the situation of the target quantum key distribution network, thereby significantly improving the security and reliability of the QKD network. Potential security vulnerabilities and attack risks can be found and coped with in time through evaluation of the network situation, and the security and high efficiency of the key distribution process are ensured.

Description

Technical Field

[0001] The present invention relates to the field of quantum key distribution network situation technology, and in particular to a quantum key distribution network situation assessment method, device, equipment and medium. Background Art

[0002] Quantum Key Distribution (QKD) networks, as cutting-edge technologies in the field of quantum communications, provide a revolutionary solution for information security by leveraging the principles of quantum mechanics to achieve secure key distribution. With the continuous maturity of QKD technology and its increasing application, building a stable, efficient, and secure QKD network has become an important goal. In the process of network operation and management, accurate assessment of network status is crucial to ensuring the security and reliability of QKD networks. Network status covers multiple aspects such as the network's operating status, performance, and security threats, and is an important basis for understanding network health, optimizing network configuration, and formulating emergency response strategies. For QKD networks, network status assessment can not only reveal potential security vulnerabilities and attack risks, but also help administrators adjust network policies in a timely manner to ensure the security and efficiency of the key distribution process.

[0003] However, numerous challenges remain in assessing QKD network status. On the one hand, the unique characteristics of QKD networks require assessment methods that accurately reflect network security and key distribution efficiency. On the other hand, as networks expand in size and become more complex, assessment methods must also be real-time, adaptive, and scalable to cope with the ever-changing network state. Existing technologies often struggle to simultaneously meet these requirements, limiting the accuracy and real-time nature of network status assessments and hindering effective support for network management. Therefore, developing a new method that can comprehensively, accurately, and in real time assess QKD network status has become an urgent challenge. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a quantum key distribution network situation assessment method, apparatus, device and medium that overcome the above problems or at least partially solve the above problems.

[0005] In order to solve the above problems, an embodiment of the present invention discloses a method for assessing the situation of a quantum key distribution network, the method comprising:

[0006] Obtaining performance data of a quantum key distribution network; the performance data includes network structure data, key performance data, communication quality data, data transmission data, and an evaluation model;

[0007] Determining a comprehensive impact factor based on the performance data; the comprehensive impact factor is used to reflect the importance of the performance data to the quantum key distribution network situation;

[0008] Determine the target quantum key distribution network situation based on the performance data, the comprehensive influencing factors and the evaluation model.

[0009] Optionally, the evaluation model is a neural network model optimized by a cuckoo search algorithm, and determining the target quantum key distribution network status according to the performance data, the comprehensive influencing factor, and the evaluation model includes:

[0010] The target quantum key distribution network situation is determined based on the performance data, the comprehensive influencing factors and the neural network model optimized by the cuckoo search algorithm.

[0011] Optionally, determining a target quantum key distribution network situation based on the performance data, the comprehensive impact factor, and a neural network model optimized by a cuckoo search algorithm includes:

[0012] Determining a step size adjustment parameter of a cuckoo algorithm in a neural network model optimized by the cuckoo search algorithm according to the comprehensive influencing factor;

[0013] A target quantum key distribution network state is determined based on the performance data, the step size adjustment parameter, and a neural network model optimized by a cuckoo search algorithm.

[0014] Optionally, the network structure data includes network structure degree centrality data, and determining the comprehensive impact factor based on the performance data includes:

[0015] Obtaining a first weight according to the network structure centrality data;

[0016] A comprehensive impact factor is determined based on the network structure centrality data, the first weight, the key performance data, the communication quality data and the data transmission data.

[0017] Optionally, the key performance data includes a key generation rate and a key consumption rate, and determining a comprehensive impact factor based on the performance data includes:

[0018] Obtaining a second weight according to the key generation rate;

[0019] Obtaining a third weight according to the key consumption rate;

[0020] A comprehensive impact factor is determined based on the network structure data, the key generation rate, the second weight, the key consumption rate, the third weight, the communication quality data, and the data transmission data.

[0021] Optionally, the communication quality data includes a quantum bit error rate, and determining a comprehensive impact factor based on the performance data includes:

[0022] Obtaining a fourth weight according to the quantum bit error rate;

[0023] A comprehensive influencing factor is determined based on the network structure data, the key performance data, the quantum bit error rate, the fourth weight and the data transmission data.

[0024] Optionally, the data transmission data includes a data receiving rate and a data forwarding rate, and determining a comprehensive impact factor based on the performance data includes:

[0025] determining a fifth weight according to the data receiving rate;

[0026] determining a sixth weight according to the data forwarding rate;

[0027] A comprehensive impact factor is determined based on the network structure data, the key performance data, the communication quality data and the data receiving rate, the fifth weight, the data forwarding rate and the sixth weight.

[0028] Optionally, determining the target quantum key distribution network state according to the performance data, the step size adjustment parameter, and the neural network model optimized by the cuckoo search algorithm includes:

[0029] Obtaining initial model parameters of the neural network model in the neural network model optimized by the cuckoo search algorithm;

[0030] Determining optimized model parameters according to the step size adjustment parameter, the cuckoo algorithm and the initial model parameters;

[0031] A target quantum key distribution network state is determined based on the performance data, the optimization model parameters, and the neural network model.

[0032] On the other hand, an embodiment of the present invention further discloses a quantum key distribution network situation assessment device, the device comprising:

[0033] A network data acquisition module is used to obtain performance data of the quantum key distribution network; the performance data includes network structure data, key performance data, communication quality data, data transmission data and evaluation model;

[0034] An impact factor determination module, configured to determine a comprehensive impact factor based on the performance data; the comprehensive impact factor is configured to reflect the importance of the performance data to the quantum key distribution network situation;

[0035] The network situation acquisition module allows the user to determine the target quantum key distribution network situation based on the performance data, the comprehensive influencing factors, and the evaluation model.

[0036] Optionally, the evaluation model is a neural network model optimized by a cuckoo search algorithm, and the network situation acquisition module includes:

[0037] The first network situation acquisition submodule is used to determine the target quantum key distribution network situation based on the performance data, the comprehensive influencing factor and the neural network model optimized by the cuckoo search algorithm.

[0038] Optionally, the first network situation acquisition submodule includes:

[0039] a step size adjustment parameter acquisition unit, configured to determine a step size adjustment parameter of the cuckoo algorithm in the neural network model optimized by the cuckoo search algorithm according to the comprehensive influencing factor;

[0040] The second network situation acquisition unit is used to determine the target quantum key distribution network situation based on the performance data, the step size adjustment parameter and the neural network model optimized by the cuckoo search algorithm.

[0041] Optionally, the network structure data includes network structure degree centrality data, and the impact factor determination module includes:

[0042] A first weight acquisition submodule, configured to acquire a first weight according to the network structure centrality data;

[0043] The first impact factor determination submodule is used to determine a comprehensive impact factor based on the network structure centrality data, the first weight, the key performance data, the communication quality data and the data transmission data.

[0044] Optionally, the key performance data includes a key generation rate and a key consumption rate, and the impact factor determination module includes:

[0045] A second weight acquisition submodule, configured to acquire a second weight according to the key generation rate;

[0046] A third weight acquisition submodule, configured to acquire a third weight according to the key consumption rate;

[0047] The second influencing factor determination submodule is used to determine a comprehensive influencing factor based on the network structure data, the key generation rate, the second weight, the key consumption rate, the third weight, the communication quality data and the data transmission data.

[0048] Optionally, the communication quality data includes a quantum bit error rate, and the impact factor determination module includes:

[0049] a fourth weight acquisition submodule, configured to acquire a fourth weight according to the quantum bit error rate;

[0050] The third influencing factor determination submodule is used to determine the comprehensive influencing factor based on the network structure data, the key performance data, the quantum bit error rate, the fourth weight and the data transmission data.

[0051] Optionally, the data transmission data includes a data receiving rate and a data forwarding rate, and the impact factor determination module includes:

[0052] a fifth weight obtaining submodule, configured to determine a fifth weight according to the data receiving rate;

[0053] a sixth weight obtaining submodule, configured to determine a sixth weight according to the data forwarding rate;

[0054] The fourth impact factor determination submodule is used to determine a comprehensive impact factor based on the network structure data, the key performance data, the communication quality data and the data receiving rate, the fifth weight, the data forwarding rate and the sixth weight.

[0055] Optionally, the second network situation acquisition unit includes:

[0056] A model parameter acquisition subunit, used to obtain initial model parameters of the neural network model in the neural network model optimized by the cuckoo search algorithm;

[0057] an optimization parameter determination subunit, configured to determine optimization model parameters according to the step size adjustment parameter, the cuckoo algorithm, and the initial model parameters;

[0058] The third network situation acquisition subunit is used to determine the target quantum key distribution network situation based on the performance data, the optimization model parameters and the neural network model.

[0059] Accordingly, an embodiment of the present invention discloses an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various steps of the above-mentioned quantum key distribution network situation assessment method embodiment are implemented.

[0060] Accordingly, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various steps of the above-mentioned quantum key distribution network situation assessment method embodiment are implemented.

[0061] The embodiments of the present invention include the following advantages: The embodiments of the present invention provide a comprehensive and accurate information basis for subsequent situation assessment by obtaining performance data of the quantum key distribution network, including network structure data, key performance data, communication quality data, data transmission data, etc. On the basis of obtaining the performance data, comprehensive influencing factors are further determined. These factors reflect the importance of different performance data to the situation of the quantum key distribution network. By introducing comprehensive influencing factors, the network situation can be evaluated more accurately and the influence of key factors can be highlighted. Combining performance data, comprehensive influencing factors and evaluation models, the situation of the target quantum key distribution network can be accurately determined. By comprehensively, accurately and in real time evaluating the QKD network situation, the embodiments of the present invention significantly improve the security and reliability of the QKD network. Through the evaluation of the network situation, potential security vulnerabilities and attack risks can be discovered and responded to in a timely manner, ensuring the security and efficiency of the key distribution process. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flowchart of an embodiment of a method for assessing the situation of a quantum key distribution network according to the present invention;

[0063] Figure 2 This is a flow chart of an embodiment of a method for assessing the situation of a quantum key distribution network according to the present invention;

[0064] Figure 3 It is a structural block diagram of an embodiment of a quantum key distribution network situation assessment device of the present invention. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0066] A QKD network is based on quantum key distribution technology. This technology uses the principles of quantum mechanics to achieve secure communication. It allows two or more users to create a shared, unknown, random key over an insecure communication channel to encrypt and decrypt information. The generation of this key is based on the measurement principles of quantum mechanics; any attempt to eavesdrop will inevitably change the quantum state, making it detectable by the legitimate user. A QKD network typically consists of multiple nodes, which are connected via quantum and classical channels. The quantum channel is used to transmit quantum bits to generate keys, while the classical channel is used to transmit auxiliary information during the key generation process and the final generated key. The goal of a QKD network is to provide a theoretically unconditionally secure key distribution mechanism to support a variety of secure communication applications.

[0067] Network status refers to the comprehensive reflection of a network's state, trends, and capabilities at a specific moment or over a period of time. Network status encompasses multiple aspects of the network, including structure, performance, security, and stability. It serves as a crucial basis for assessing network health, predicting network development trends, and formulating network management strategies.

[0068] Network Situation Awareness (NSA) is a key concept in network management. It refers to the comprehensive, accurate, and real-time understanding and control of network status. By collecting and analyzing various network information, such as traffic data, log information, and security events, the NSA system can monitor network status and changes in real time, promptly identify potential security threats and performance bottlenecks, and provide decision-making support for network administrators.

[0069] One of the core concepts of the embodiments of the present invention is to use the performance data of the QKD network to determine the comprehensive influencing factor, and then adjust the QKD network situation assessment model through the comprehensive influencing factor to make the model prediction results more suitable for the QKD network.

[0070] Reference Figure 1 , shows a flowchart of the steps of embodiment 1 of a quantum key distribution network situation assessment method of the present invention, which may specifically include the following steps:

[0071] Step 101: Acquire performance data of a quantum key distribution network; the performance data includes network structure data, key performance data, communication quality data, data transmission data, and an evaluation model;

[0072] The primary task in this step is to collect or acquire performance data on the quantum key distribution network. This data forms the basis for subsequent analysis, evaluation of network performance, and optimization. This data includes, but is not limited to, network structure data, which describes basic information such as the network's physical layout, node connectivity, and network topology. Key performance data reflects the efficiency and security of key generation, distribution, and usage. Communication quality data, including signal transmission stability, bit error rate, and latency, is used to assess the reliability and efficiency of network communications. Data transmission data, including network traffic volume and transmission rate, is used to understand the network's data processing capabilities.

[0073] In addition, an evaluation model is required. This model is one or more mathematical models or algorithms used to analyze and evaluate network performance. These models can quantitatively evaluate the overall performance of the network based on the collected performance data, or predict the network's performance under different conditions.

[0074] Step 101 is the starting point of the quantum key distribution network performance evaluation or optimization process. Its core task is to comprehensively collect network performance data to provide a basis for subsequent analysis and decision-making.

[0075] Step 102: determining a comprehensive impact factor based on the performance data; the comprehensive impact factor is used to reflect the importance of the performance data to the status of the quantum key distribution network;

[0076] Step 102 is a critical analysis phase in determining the state of the quantum key distribution network. The core objective of this step is to determine one or more comprehensive impact factors based on the collected performance data (network structure data, key performance data, communication quality data, and data transmission data). Comprehensive impact factors are one or more indicators used to quantify the degree to which various performance data items affect the overall state or performance of the quantum key distribution network. These factors not only reflect the numerical value of each performance data item, but more importantly, reveal their relative importance and influence on network operation and security performance.

[0077] In one example, weights need to be assigned to various performance metrics. The weights depend on the importance of each data item to the overall network performance or security. For example, key generation rate and bit error rate have a direct impact on network security and therefore may be assigned higher weights. However, since the dimensions and value ranges of various performance metrics vary, standardization is required to convert the data to the same dimension for comparison and comprehensive analysis.

[0078] The standardized data and corresponding weights are used to perform a comprehensive calculation using a specific mathematical algorithm to obtain a comprehensive impact factor. This factor can be a single value or a vector or matrix containing multiple dimensions, which is not limited in this embodiment of the present invention.

[0079] Finally, the calculated comprehensive impact factors can be interpreted and analyzed. This includes identifying which performance data has the greatest impact on the network situation, which may be potential weaknesses or areas for improvement, and how these impact factors fluctuate over time or as network conditions change.

[0080] Through step 102, the current situation of the quantum key distribution network can be more clearly understood, key performance indicators and potential risk points can be identified, and a scientific basis can be provided for subsequent network optimization, security reinforcement or resource allocation.

[0081] In one embodiment, the network structure data includes network structure degree centrality data, and step 102 includes the following sub-steps:

[0082] Network structure centrality data describes the degree of connectivity between nodes in a network, such as quantum key distribution devices. Degree centrality typically refers to the number of direct connections a node has with other nodes, reflecting its importance or "centrality" within the network. In a quantum key distribution network, certain nodes have higher degree centrality due to their greater number of connections to other nodes, indicating that these nodes play a more important role in the network.

[0083] In one example, degree centrality data can be calculated using the following formula:

[0084] Among them, C D (v) is the degree centrality value of node v in the QKD network, d(v) represents the degree of node v, that is, the number of nodes directly connected to node v, and N represents the total number of network topology points, that is, the total number of all nodes in the network. Because when calculating degree centrality, the node itself is usually not counted in the connected node book, because the value is generally taken as N-1.

[0085] The higher the degree centrality value, the more connections the node has in the network, and therefore the more important or central it is in the network. In a QKD network, by calculating the degree centrality of each node, we can assess the importance and centrality of each node in the network, which is crucial for network design and optimization.

[0086] Sub-step S11, obtaining a first weight according to the network structure centrality data;

[0087] Based on the network structure degree centrality data, weights are assigned to each node or performance data item. The first weight here specifically refers to the weight directly related to the network structure degree centrality. The size of the weight is generally proportional to the degree centrality of the network node. That is, the higher the degree centrality of the node or related data item, the greater the weight assigned in the calculation of the comprehensive impact factor.

[0088] Sub-step S12, determining a comprehensive impact factor based on the network structure centrality data, the first weight, the key performance data, the communication quality data and the data transmission data.

[0089] Network structure degree centrality data, the first weight derived based on degree centrality, key performance data, communication quality data, and data transmission data. These data together form the basis for evaluating the status of the quantum key distribution network. Using the above data, a comprehensive calculation is performed through a specific mathematical algorithm to derive one or more comprehensive influencing factors. These factors comprehensively consider performance data from multiple aspects such as network structure, key performance, communication quality, and data transmission, as well as their importance in the network. Through this embodiment, the performance of the quantum key distribution network can be scientifically and comprehensively evaluated, and key nodes and potential risk points in the network can be identified. This provides powerful decision-making support for subsequent network optimization, security reinforcement, or resource allocation.

[0090] In one embodiment, the key performance data includes a key generation rate and a key consumption rate, and step 102 includes the following sub-steps:

[0091] The key generation rate is an important metric for measuring the performance of a quantum key distribution network. It represents the number of new keys the network can generate per unit time. A higher key generation rate generally indicates a stronger key generation capability and greater security.

[0092] In one example, the key generation rate may be calculated as:

[0093] Where T is the unit time, QuKey_Generate is the amount of keys generated in T time, and r is the key generation rate.

[0094] Correspondingly, the key consumption rate is another key performance metric, representing the number of keys consumed per unit time. This rate is dependent on factors such as network traffic volume and key update frequency. A reasonable key consumption rate ensures that network security requirements are met while avoiding key waste.

[0095] In one example, the key consumption rate may be calculated as:

[0096] Where T is the unit time, QuKey_Consume is the amount of key consumed in T time, and c is the key consumption rate.

[0097] Sub-step S21, obtaining a second weight according to the key generation rate;

[0098] Based on the importance of the key generation rate, a weight is assigned to it, namely the second weight. This weight reflects the relative importance of the key generation rate in the calculation of the comprehensive impact factor.

[0099] Sub-step S22, obtaining a third weight according to the key consumption rate;

[0100] Based on the importance of the key consumption rate, a weight is assigned to it, namely the third weight. This weight reflects the relative influence of the key consumption rate in the calculation of the comprehensive impact factor.

[0101] Sub-step S23, determining a comprehensive impact factor based on the network structure data, the key generation rate, the second weight, the key consumption rate, the third weight, the communication quality data and the data transmission data.

[0102] Network structure data, key generation rate, secondary weight, key consumption rate, tertiary weight, communication quality data, and data transmission data. Together, these data form a comprehensive foundation for assessing the state of a quantum key distribution network. Using this data, a specific mathematical algorithm performs a comprehensive calculation. This calculation considers each data item and its corresponding weight to derive one or more comprehensive impact factors. These factors comprehensively reflect the overall performance of the network in terms of structure, key performance, communication quality, and data transmission. The comprehensive impact factor is an important indicator for evaluating the performance of a quantum key distribution network. By analyzing and comparing the comprehensive impact factors at different times or under different network conditions, potential problems, optimization points, or security risks in the network can be identified, providing a scientific basis for network management and optimization.

[0103] In one embodiment, the communication quality data includes a quantum bit error rate, and step 102 includes the following sub-steps:

[0104] The Quantum Bit Error Rate (QBER) is a crucial parameter in the field of quantum communication. It is used to measure the probability of errors occurring in quantum bits during transmission.

[0105] QBER is defined as the ratio of false counts to total counts per unit time, that is, the ratio of the number of error bits to the total number of received bits. It reflects the transmission quality and reliability of the quantum communication system.

[0106] In one example, the calculation formula of QBER can be expressed as:

[0107] Where QuBit_Error represents the number of received error bits, QuBit is the total number of received bits, and E represents QBER.

[0108] Sub-step S31, obtaining a fourth weight according to the quantum bit error rate;

[0109] Based on the importance of QBER, a weight is assigned to it, namely the fourth weight. This weight reflects the relative importance of QBER in the calculation of the comprehensive impact factor. Generally, the lower the QBER, the greater its corresponding weight in the comprehensive evaluation, because low bit error rate is crucial to ensuring the security and reliability of QKD networks.

[0110] Sub-step S32, determining a comprehensive impact factor based on the network structure data, the key performance data, the quantum bit error rate, the fourth weight and the data transmission data.

[0111] Network structure data, key performance data, qubit error rate (BER), fourth weight, and data transmission data. Together, these data form a comprehensive foundation for assessing the status of a QKD network. Using this data, a specific mathematical algorithm performs a comprehensive calculation. This calculation considers each data item and its corresponding weight to derive one or more comprehensive impact factors. These factors comprehensively reflect the overall performance of the QKD network in multiple aspects, including structure, key performance, transmission quality, and data transmission. The comprehensive impact factor is an important indicator for evaluating QKD network performance. By analyzing and comparing the comprehensive impact factors at different times or under different network conditions, potential network issues, optimization points, or security risks can be identified, providing a scientific basis for network management and optimization. Furthermore, considering the comprehensive impact factor of QBER can help assess network security and reliability, which is crucial for ensuring the stable operation of the QKD network.

[0112] In one embodiment, the data transmission data includes a data receiving rate and a data forwarding rate, and step 102 includes the following sub-steps:

[0113] The data reception rate is a measure of a network node or system's ability to receive data, indicating the amount of data successfully received per unit time. A high reception rate means the network can process incoming data streams more quickly, which is crucial for real-time communications and large data transmission.

[0114] In one example, the calculation formula for the data reception rate may be:

[0115] Where T is the unit time, It represents the total amount of received data from the first port to the nth port of the target node, and R represents the data receiving rate.

[0116] The data forwarding rate is a measure of a network node or system's ability to forward or transmit data. It indicates the amount of data successfully forwarded per unit time. A high forwarding rate means the network can more efficiently transfer data from one node to another, which is crucial for maintaining network fluidity and reducing latency.

[0117] In one example, the data forwarding rate may be calculated as follows:

[0118] Where T is the unit time, It represents the total amount of forwarded data from the first port to the nth port of the target node, and f represents the data forwarding rate.

[0119] Sub-step S41, determining a fifth weight according to the data receiving rate;

[0120] Based on the importance of data reception rate in network performance evaluation, a weight, the fifth weight, is assigned to it. This weight reflects the relative importance of data reception rate in the calculation of the comprehensive impact factor. Generally, the higher the data reception rate, the greater its corresponding weight, as it directly affects the overall network throughput and responsiveness.

[0121] Sub-step S42, determining a sixth weight according to the data forwarding rate;

[0122] Based on the importance of data forwarding rate, a weight is assigned to it, namely the sixth weight. This weight reflects the relative influence of data forwarding rate in the calculation of the comprehensive impact factor. Generally, the faster the data forwarding rate, the greater its corresponding weight, as it is directly related to network transmission efficiency and coverage.

[0123] Sub-step S43, determining a comprehensive impact factor based on the network structure data, the key performance data, the communication quality data and the data receiving rate, the fifth weight, the data forwarding rate and the sixth weight.

[0124] Network structure data, key performance data, communication quality data, as well as data reception rate, fifth weight, data forwarding rate, and sixth weight. Together, these data form the comprehensive foundation for evaluating network performance. Using this data, a specific mathematical algorithm performs a comprehensive calculation. This calculation considers each data item and its corresponding weight to derive one or more comprehensive impact factors. These factors comprehensively reflect the overall performance of the network in multiple aspects, including structure, key performance, communication quality, and data reception and forwarding. The comprehensive impact factor is a key indicator for evaluating network performance. By analyzing and comparing the comprehensive impact factors over time or under different network conditions, potential network issues, optimization points, or performance bottlenecks can be identified, providing a scientific basis for network management, optimization, and upgrades.

[0125] In one embodiment, the calculation of the comprehensive impact factor can also be obtained based on the comprehensive calculation of the above embodiments. Specifically:

[0126] The calculation formula of the comprehensive factor can be:

[0127] I=w1·C D +w2·r+w3·c+w4·E+w5·R+w6·f, where w1-w6 represent the first to sixth weights, respectively. By default, the sum of w1-w6 is 1. Initially, the distribution of each weight can be set based on experience or the historical situation of the target node. Generally, the first to sixth weights are gradually reduced in the initial situation. Then, based on subsequent data, the weight corresponding to the data type is dynamically adjusted. The comprehensive impact factor calculated based on data from multiple dimensions and their corresponding weights has the advantages of comprehensiveness, accuracy, flexibility, and decision support. This calculation method helps to more comprehensively evaluate the performance of the network or system and provides a scientific basis for optimization and management.

[0128] Step 103: Determine the target quantum key distribution network status based on the performance data, the comprehensive impact factor, and the evaluation model.

[0129] Performance data, comprehensive impact factors, and evaluation models enable real-time monitoring and evaluation of the quantum key distribution network situation. This helps to promptly identify problems or potential risks in the network and take appropriate measures for optimization and management.

[0130] In one embodiment, the evaluation model is a neural network model optimized by a cuckoo search algorithm, and step 103 includes the following sub-steps:

[0131] The Cuckoo Search (CS) algorithm is a heuristic optimization algorithm proposed by Yang Xin-She and S. Deb of the University of Cambridge in 2009. The algorithm is inspired by the reproductive behavior of cuckoos in nature, particularly their nest parasitism and Lévy flight mechanism. It has the advantages of strong global search capabilities, few parameters, and ease of implementation.

[0132] The cuckoo algorithm performs a global search by simulating the process of a cuckoo bird searching for a host nest. The algorithm assumes that each cuckoo lays only one egg at a time and randomly selects a nest for incubation. Furthermore, the number of available nests is fixed, and the probability that a nest owner will discover an alien egg (i.e., a cuckoo egg) is constant. The algorithm uses Levy Flight as its search strategy, a random walk process with a step size that follows a Levy distribution. This helps achieve a balance between global exploration and local exploitation during the search process.

[0133] A Lévy flight is a special random walk model characterized by a heavy-tailed probability distribution of step lengths. A heavy-tailed distribution is a probability distribution model in which the tail probability decays much more slowly than an exponential distribution. This means that extreme or outliers are more likely to occur in a heavy-tailed distribution. This, in turn, means that the probability of relatively large step lengths, or long-distance movements, is much higher in a Lévy flight than in a normal random walk. This step length distribution typically follows a power law, where the probability of a step length is inversely proportional to some power of the step length. Due to this heavy-tailed distribution, the trajectory of a Lévy flight exhibits the characteristic of intermittent flight, as it can quickly jump from one location to another distant location. This property makes Lévy flight very effective when exploring unknown areas or searching for sparse resources, as it can quickly cover large areas.

[0134] The key difference between a Lévy flight and a regular random walk is the heavy-tailed nature of its step-size distribution. While regular random walks typically have short steps and fast decay, a Lévy flight allows for larger steps, allowing it to explore a wider range of space in fewer steps.

[0135] Neural networks (NNs) are computational models that mimic the structure and function of biological neural networks, designed to approximate complex nonlinear functions through learning and training. Neural networks consist of a large number of simple processing units (neurons) interconnected by weighted connections. Each neuron receives input signals from other neurons and performs calculations based on the input signals and its own weights, ultimately outputting a result. Neural networks possess characteristics such as massively parallel processing, distributed storage and computing, self-organization, self-adaptation, and self-learning capabilities. They are particularly well-suited for handling imprecise and ambiguous information processing problems that require simultaneous consideration of many factors and conditions.

[0136] During neural network training, a large number of weights and bias parameters must be adjusted to minimize prediction error or maximize performance metrics. This process is essentially an optimization problem, and traditional optimization algorithms such as gradient descent can easily become stuck in local optimal solutions. The cuckoo search algorithm offers advantages such as strong global search capabilities, a small number of parameters, simple operation, and ease of implementation. It utilizes Lévy flights to perform efficient random search, helping to escape local optimal solutions during neural network training and find globally optimal or near-globally optimal weight and bias parameters. Applying the cuckoo search algorithm to neural network training can be used as a global optimization algorithm to guide the adjustment of the neural network's weights and bias parameters. By iteratively generating new parameter combinations and evaluating their performance, the cuckoo algorithm can gradually approach the optimal neural network model.

[0137] Weights represent the strength of the connections between neurons in a neural network. During the forward propagation process, input data is multiplied by the neuron's input using the weights, and the sum is accumulated to form the neuron's total input. This total input is then processed by the activation function to produce the neuron's output. The size and sign of the weights determine the degree and direction of the input data's influence on the neuron's output. During the training process, the neural network continuously adjusts these weights to better fit the data and learning task.

[0138] A bias is an additional parameter for neurons in a neural network that adjusts the neuron's output threshold. After the neuron's total input is calculated, the bias is added to the total input before both are processed by the activation function. The bias allows the neuron to produce a non-zero output even when all inputs are zero. This increases the flexibility of neural networks, allowing them to better adapt to different data and tasks.

[0139] Sub-step S51, determining the target quantum key distribution network status based on the performance data, the comprehensive impact factor and the neural network model optimized by the cuckoo search algorithm.

[0140] Performance data for the target quantum key distribution network is collected and organized. Simultaneously, based on previous calculations, a comprehensive impact factor is obtained, which integrates information from multiple dimensions, including network structure, key performance, and communication quality. These performance data and comprehensive impact factors are fed into a neural network model optimized by the cuckoo search algorithm to determine the state of the QKD network.

[0141] In one embodiment, sub-step S51 includes the following sub-steps:

[0142] Sub-step S511, determining a step size adjustment parameter of the cuckoo algorithm in the neural network model optimized by the cuckoo search algorithm according to the comprehensive influencing factor;

[0143] The previously calculated comprehensive impact factor is used to determine the step size adjustment parameter for the cuckoo search algorithm during the neural network model optimization process. The step size adjustment parameter in the cuckoo search algorithm is crucial for search efficiency and result accuracy. A larger step size allows the search process to cover the entire search space more quickly, but may also miss the optimal solution; a smaller step size allows for a more precise search of a local area, but the search speed is slower. Therefore, it is necessary to dynamically adjust the step size parameter based on the comprehensive impact factor according to the specific conditions and requirements of the QKD network to achieve the best search results.

[0144] In one example, the calculation expression for determining the step size adjustment parameter according to the comprehensive impact factor I may be:

[0145] a=e -γ·I, where a is the step size adjustment parameter and γ is the adjustment coefficient, which defaults to 1.

[0146] In one example, the process of adjusting the step size according to the step size adjustment parameter may be:

[0147] α = α0a, where α is the adjusted step size and α0 is the step size before adjustment;

[0148] Sub-step S512: determining the target quantum key distribution network state based on the performance data, the step size adjustment parameter, and the neural network model optimized by the cuckoo search algorithm.

[0149] In one embodiment, sub-step S512 includes the following sub-steps:

[0150] Sub-step S5111, obtaining initial model parameters of the neural network model in the neural network model optimized by the cuckoo search algorithm;

[0151] Get the initial parameter model of the neural network;

[0152] In one example, the parameters may be weights and biases;

[0153] Sub-step S5112, determining optimized model parameters according to the step size adjustment parameter, the cuckoo algorithm and the initial model parameters;

[0154] Adjust the parameters according to the previously determined step size, adjust the step size of the cuckoo search algorithm, and use the global search capability of the cuckoo search algorithm to search in the parameter space of the neural network model to find the weight and bias parameter combination that makes the neural network output the best.

[0155] Sub-step S5113, determining the target quantum key distribution network state based on the performance data, the optimization model parameters and the neural network model.

[0156] In one embodiment, the evaluation model can be a CS-BP model, that is, a BP neural network model optimized by the cuckoo algorithm. The BP neural network (Back Propagation Neural Network) is a multi-layer feedforward neural network trained based on the back propagation algorithm. It calculates the error between the output layer and the expected output and backpropagates the error to each layer in the network, thereby adjusting the weights and bias parameters of each layer. Introducing the cuckoo search algorithm for optimization during the BP neural network training process can significantly improve the training efficiency and performance of the network. Through the optimization of the cuckoo search algorithm, the BP neural network can converge to the global optimal or approximate global optimal solution more quickly, thereby improving the prediction accuracy and generalization ability of the network. In addition, the optimization of the cuckoo algorithm also helps to avoid overfitting during the network training process and improve the stability and robustness of the network.

[0157] In one example, the specific process of using the evaluation model to predict network status can be:

[0158] Floating-point encoding is a way of representing floating-point numbers in computers. It is based on the principle of scientific notation and decomposes floating-point numbers into three parts: sign bit, exponent (or exponent) and mantissa (or base) for encoding.

[0159] First, initialize a certain number of cuckoo individuals. Each individual represents a candidate solution, that is, a set of initial weights and biases for the BP neural network. Floating-point encoding can better reflect the physical meaning of the parameters. We can encode the weights and biases into cuckoo individuals using floating-point encoding. Each cuckoo individual can only lay one egg at a time. Randomly generate n nest locations as initial solutions, denoted as: And calculate the fitness value of each bird's nest initial position.

[0160] Update the locations of all nests. The process of an individual cuckoo searching for a nest to lay eggs is essentially the algorithm's search for the optimal solution in n-dimensional space. Based on the initial solution, the individual cuckoo performs a random walk through Levy flight to obtain a new solution, thus retaining the better solution for the next iteration. During this process, the random walk formula for the individual cuckoo, i.e., the formula for finding the next generation of nests, is:

[0161] in, It is the location of the next generation bird's nest, is the nest position of this generation, α represents the step size used to control the random search range, Levy(λ) is the levy flight function, which obeys the Levy distribution: Levy(λ)~u=t -λAmong them, t represents the flight time of the cuckoo, λ represents the power coefficient with a value of 1.5, and u represents the random step size. The step size is adjusted according to the comprehensive influence factor to ensure that the step size matches the real-time nature and complexity of the network situation. The formula: α = α0e -γ·I Among them, α is the adjusted step size, α0 is the initial step size, γ is the adjustment coefficient with a default value of 1, and I is the comprehensive influence factor.

[0162] The updated nest position of the cuckoo is denoted as:

[0163] Calculate the fitness value. The quality of individuals in the population is measured by the fitness value. The mean absolute percentage error (MAPE) function can be used as the fitness function, and the calculation formula is as follows:

[0164] Among them, N is the number of samples, is the test value of the i-th sample, y i is the actual value of the i-th sample.

[0165] Subsequently, an elimination operation needs to be performed. Generate a random number R between [0, 1], compare the size of R and the discovery probability P, and determine whether it is discovered. If R ≥ P, it is regarded as not discovered, and the cuckoo nest position remains unchanged. If R < P, it is regarded as discovered, the egg is discovered and discarded, the cuckoo looks for a new nest to lay eggs, and the nest position is updated. The elimination operation is to keep the population always in the optimal state, and n×P individuals with the worst fitness values will be eliminated; to keep the population size unchanged, n×P solutions will be randomly generated; at the same time, for individuals with better fitness values, they will be directly passed to the next generation. The cuckoo eggs successfully hatch and then grow up, and the original cuckoo will die. Evaluate the fitness value of the new cuckoo individuals. If it is better than the best fitness recorded previously, update the best fitness value. Judge whether the optimal cuckoo meets the conditions or whether the number of iteration generations reaches the requirements. If so, decode the optimal cuckoo to obtain the optimal weights and biases for output; otherwise, continue to find the optimum.

[0166] Put the optimal weights and biases into the BP neural network for BP neural network training:

[0167] Initialize the parameters of the BP neural network, the number of iterations N, the allowable error ε, the learning rate δ, the activation function (here the Sigmoid function is selected), the loss function, and at the same time assign the optimal weights and biases found by the cuckoo search algorithm to the BP neural network model. Among them, the number of iterations N, the allowable error ε, and the learning rate δ are empirical values set according to experience.

[0168] Sigmoid is used for data normalization processing. At the same time, the Sigmoid function is continuous, which helps the stability of the gradient descent algorithm. The Sigmoid function is:

[0169] The error formula is: Where N is the number of samples, is the situation test value of the i-th sample, z i For the i-th

[0170] The number of neurons in the input layer is the number of QKD network state factors. The neuron input signal corresponds to the QKD network topology, QKD key generation rate, QKD key consumption rate, quantum bit error rate, data reception rate, and data forwarding rate. The result of the output layer is used as the final state value, so the number of neurons in the output layer is 1. The number of neurons in the hidden layer is generally calculated by an empirical formula, as follows: Where n is the number of neurons in the input layer, m is the number of neurons in the output layer, and μ is a constant between [1,10].

[0171] During the forward propagation process, the output value of each layer is calculated. Each neuron in the input layer directly receives external input without any processing. Therefore, the output value of each neuron is the input value itself, which is a i , i represents the i-th neuron in the input layer. The output calculation expression of each neuron in the hidden layer is as follows:

[0172]

[0173] The output calculation expression of each neuron in the output layer is as follows:

[0174] Through the gradient descent algorithm, the loss function is used to adjust the error and bias, thereby reducing the error and achieving iterative optimization solution.

[0175] According to the error output result, determine whether to terminate the iteration

[0176] According to the optimized weights and biases, the situation test value is calculated, and the error between the situation test value and the actual situation value is calculated to determine whether the error is less than the allowable error ε:

[0177] 1) When the error is less than ε, it means that the condition is met and the iteration is terminated;

[0178] 2) When the error is greater than ε and the number of iterations of the BP neural network is less than the set number of iterations N, return to the step of training the neural network;

[0179] 3) When the error is greater than ε and the number of iterations of the BP neural network is greater than the set number of iterations N, return to the process of regenerating the optimal weights and biases;

[0180] Finally, the QKD network status value is calculated based on the final output weight and bias values and the BP neural network and network performance values.

[0181] The embodiment of the present invention obtains the performance data of the quantum key distribution network, including network structure data, key performance data, communication quality data, data transmission data, etc., to provide a comprehensive and accurate information basis for subsequent situation assessment. On the basis of obtaining the performance data, the comprehensive influencing factors are further determined. These factors reflect the importance of different performance data to the situation of the quantum key distribution network. By introducing comprehensive influencing factors, the network situation can be evaluated more accurately and the impact of key factors can be highlighted. Combining performance data, comprehensive influencing factors and evaluation models, the situation of the target quantum key distribution network can be accurately determined. By comprehensively, accurately and in real time evaluating the QKD network situation, the embodiment of the present invention significantly improves the security and reliability of the QKD network. Through the evaluation of the network situation, potential security vulnerabilities and attack risks can be discovered and responded to in a timely manner, ensuring the security and efficiency of the key distribution process.

[0182] Reference Figure 2 , showing a flow chart of an embodiment of a quantum key distribution network situation assessment method of the present invention;

[0183] The BP neural network weights and biases are initialized. This is the starting point of the entire process, setting the initial weights and biases for the BP neural network. These initial values are randomly assigned and serve as the basis for subsequent optimization adjustments, essentially giving the neural network an initial state to begin learning and adjusting to the task of QKD network situation assessment.

[0184] Using floating-point encoding, a method for representing numerical values in floating-point form, the weights and biases in the BP neural network are converted into individuals in the cuckoo search algorithm. In the cuckoo search algorithm, each individual represents a possible solution, equivalent to a specific set of neural network weights and biases. The cuckoo search algorithm then screens and optimizes these individuals to find the optimal weight and bias combination for evaluating the QKD network status.

[0185] The collected data on various situations of the QKD network are input into the system. These data carry the actual operation status of the QKD network.

[0186] Based on the principle of the cuckoo search algorithm, the flight behavior of the cuckoo is simulated to update the nest position. The nest position here corresponds to the weights and biases of the neural network previously encoded as the cuckoo individual. During the update process, the Levy flight mechanism is used to allow the cuckoo individual to explore new possible positions in the solution space, that is, the value space of weights and biases, and find a better solution. At the same time, for each updated nest position, that is, a new set of weights and biases, its fitness value is calculated. The fitness value reflects the quality of the neural network corresponding to this set of weights and biases in evaluating the QKD network status.

[0187] Based on the fitness values calculated in the previous step, the various nest locations (i.e. different weight and bias combinations) are selected and eliminated. Nest locations with high fitness values are considered to be better solutions and are more likely to be retained, while those with low fitness values will be eliminated.

[0188] For example, if the fitness value does not increase significantly after multiple iterations or the diversity of the population decreases to a certain level, if such termination conditions are met, it means that the cuckoo search algorithm has found it difficult to find a better combination of weights and biases. At this time, the optimal weights and biases found so far will be output. If the termination conditions are not met, it is necessary to return to the iteration process, that is, repeat the cuckoo flight to update the nest position and continue to explore better solutions in the solution space.

[0189] When the termination condition is met, the optimal set of weights and biases is determined and output from the numerous nest positions (weight and bias combinations) that have been screened and optimized through multiple rounds. This optimal set of parameters is the result of the cuckoo search algorithm optimization and is then fed into the subsequent BP neural network.

[0190] Assign the optimal weight and bias values output previously to the BP neural network, replacing the previous initial values or parameter values of the previous round.

[0191] Compare the evaluation results output by the BP neural network with the actual QKD network status and calculate the error between the two. Common metrics such as mean square error and mean absolute error can be used to calculate the error. This error value intuitively reflects the accuracy of the current neural network evaluation results and is an important basis for determining whether the model has achieved the expected results.

[0192] An acceptable error range is pre-set as the error condition. If the calculated model output error is within this acceptable error range, it means that the current evaluation model obtained through the CS-BP network is accurate enough to meet the actual requirements for QKD network status assessment. At this point, the network status assessment can be carried out. If the error does not meet the condition, that is, the error exceeds the acceptable range, it means that the current model needs further optimization. At this time, it is necessary to use the cuckoo search algorithm again to find a better combination of weights and biases to reduce the error and improve the accuracy of the assessment.

[0193] If the error condition is not met, the model's iteration number condition will be judged. If the iteration number condition is not met, new weights and biases will be obtained for training. If the iteration number condition is met, the model returns to the step of generating weights and biases according to the cuckoo algorithm and repeats the iteration.

[0194] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0195] Reference Figure 3 , shows a structural block diagram of an embodiment of a quantum key distribution network situation assessment device of the present invention, which may specifically include the following modules:

[0196] A network data acquisition module 201 is used to acquire performance data of the quantum key distribution network; the performance data includes network structure data, key performance data, communication quality data, data transmission data and an evaluation model;

[0197] An impact factor determination module 202 is configured to determine a comprehensive impact factor based on the performance data; the comprehensive impact factor is configured to reflect the importance of the performance data to the quantum key distribution network situation;

[0198] In the network status acquisition module 203, the user determines the target quantum key distribution network status based on the performance data, the comprehensive impact factor and the evaluation model.

[0199] In one embodiment, the evaluation model is a neural network model optimized by a cuckoo search algorithm, and the network situation acquisition module includes:

[0200] The first network situation acquisition submodule is used to determine the target quantum key distribution network situation based on the performance data, the comprehensive influencing factor and the neural network model optimized by the cuckoo search algorithm.

[0201] In one embodiment, the first network situation acquisition submodule includes:

[0202] a step size adjustment parameter acquisition unit, configured to determine a step size adjustment parameter of the cuckoo algorithm in the neural network model optimized by the cuckoo search algorithm according to the comprehensive influencing factor;

[0203] The second network situation acquisition unit is used to determine the target quantum key distribution network situation based on the performance data, the step size adjustment parameter and the neural network model optimized by the cuckoo search algorithm.

[0204] In one embodiment, the network structure data includes network structure degree centrality data, and the impact factor determination module includes:

[0205] A first weight acquisition submodule, configured to acquire a first weight according to the network structure centrality data;

[0206] The first impact factor determination submodule is used to determine a comprehensive impact factor based on the network structure centrality data, the first weight, the key performance data, the communication quality data and the data transmission data.

[0207] In one embodiment, the key performance data includes a key generation rate and a key consumption rate, and the impact factor determination module includes:

[0208] A second weight acquisition submodule, configured to acquire a second weight according to the key generation rate;

[0209] A third weight acquisition submodule, configured to acquire a third weight according to the key consumption rate;

[0210] The second influencing factor determination submodule is used to determine a comprehensive influencing factor based on the network structure data, the key generation rate, the second weight, the key consumption rate, the third weight, the communication quality data and the data transmission data.

[0211] In one embodiment, the communication quality data includes a quantum bit error rate, and the impact factor determination module includes:

[0212] a fourth weight acquisition submodule, configured to acquire a fourth weight according to the quantum bit error rate;

[0213] The third influencing factor determination submodule is used to determine the comprehensive influencing factor based on the network structure data, the key performance data, the quantum bit error rate, the fourth weight and the data transmission data.

[0214] In one embodiment, the data transmission data includes a data receiving rate and a data forwarding rate, and the impact factor determination module includes:

[0215] a fifth weight obtaining submodule, configured to determine a fifth weight according to the data receiving rate;

[0216] a sixth weight obtaining submodule, configured to determine a sixth weight according to the data forwarding rate;

[0217] The fourth impact factor determination submodule is used to determine a comprehensive impact factor based on the network structure data, the key performance data, the communication quality data and the data receiving rate, the fifth weight, the data forwarding rate and the sixth weight.

[0218] In one embodiment, the second network situation acquisition unit includes:

[0219] A model parameter acquisition subunit, used to obtain initial model parameters of the neural network model in the neural network model optimized by the cuckoo search algorithm;

[0220] an optimization parameter determination subunit, configured to determine optimization model parameters according to the step size adjustment parameter, the cuckoo algorithm, and the initial model parameters;

[0221] The third network situation acquisition subunit is used to determine the target quantum key distribution network situation based on the performance data, the optimization model parameters and the neural network model.

[0222] The embodiment of the present invention obtains the performance data of the quantum key distribution network, including network structure data, key performance data, communication quality data, data transmission data, etc., to provide a comprehensive and accurate information basis for subsequent situation assessment. On the basis of obtaining the performance data, the comprehensive influencing factors are further determined. These factors reflect the importance of different performance data to the situation of the quantum key distribution network. By introducing comprehensive influencing factors, the network situation can be evaluated more accurately and the impact of key factors can be highlighted. Combining performance data, comprehensive influencing factors and evaluation models, the situation of the target quantum key distribution network can be accurately determined. By comprehensively, accurately and in real time evaluating the QKD network situation, the embodiment of the present invention significantly improves the security and reliability of the QKD network. Through the evaluation of the network situation, potential security vulnerabilities and attack risks can be discovered and responded to in a timely manner, ensuring the security and efficiency of the key distribution process.

[0223] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0224] An embodiment of the present invention further provides an electronic device, including:

[0225] The present invention includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned quantum key distribution network situation assessment method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0226] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned quantum key distribution network situation assessment method embodiment are implemented, and the same technical effects can be achieved. To avoid repetition, they will not be described here.

[0227] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0228] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0229] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0230] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0231] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0232] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0233] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0234] The above is a detailed introduction to the quantum key distribution network situation assessment method, device, equipment and medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A quantum key distribution network situation assessment method, characterized in that: The method comprises: Obtaining performance data of a quantum key distribution network; the performance data includes network structure data, key performance data, communication quality data, data transmission data, and an evaluation model; Determining a comprehensive impact factor based on the performance data; the comprehensive impact factor is used to reflect the importance of the performance data to the quantum key distribution network situation; Determine the target quantum key distribution network situation based on the performance data, the comprehensive influencing factors and the evaluation model.

2. The method according to claim 1, characterized in that The evaluation model is a neural network model optimized by a cuckoo search algorithm, and determining the target quantum key distribution network situation based on the performance data, the comprehensive influencing factors, and the evaluation model includes: The target quantum key distribution network situation is determined based on the performance data, the comprehensive influencing factors and the neural network model optimized by the cuckoo search algorithm.

3. The method according to claim 2, characterized in that Determining the target quantum key distribution network situation according to the performance data, the comprehensive impact factor, and the neural network model optimized by the cuckoo search algorithm includes: Determining a step size adjustment parameter of a cuckoo algorithm in a neural network model optimized by the cuckoo search algorithm according to the comprehensive influencing factor; A target quantum key distribution network state is determined based on the performance data, the step size adjustment parameter, and a neural network model optimized by a cuckoo search algorithm.

4. The method according to claim 1, wherein The network structure data includes network structure degree centrality data, and determining the comprehensive impact factor based on the performance data includes: Obtaining a first weight according to the network structure centrality data; A comprehensive impact factor is determined based on the network structure centrality data, the first weight, the key performance data, the communication quality data and the data transmission data.

5. The method according to claim 1, wherein The key performance data includes a key generation rate and a key consumption rate. Determining a comprehensive impact factor based on the performance data includes: Obtaining a second weight according to the key generation rate; Obtaining a third weight according to the key consumption rate; A comprehensive impact factor is determined based on the network structure data, the key generation rate, the second weight, the key consumption rate, the third weight, the communication quality data, and the data transmission data.

6. The method according to claim 1, characterized in that The communication quality data includes a quantum bit error rate, and determining a comprehensive impact factor based on the performance data includes: Obtaining a fourth weight according to the quantum bit error rate; A comprehensive influencing factor is determined based on the network structure data, the key performance data, the quantum bit error rate, the fourth weight and the data transmission data.

7. The method according to claim 1, characterized in that The data transmission data includes a data receiving rate and a data forwarding rate. The determining of a comprehensive impact factor based on the performance data includes: determining a fifth weight according to the data receiving rate; determining a sixth weight according to the data forwarding rate; A comprehensive impact factor is determined based on the network structure data, the key performance data, the communication quality data and the data receiving rate, the fifth weight, the data forwarding rate and the sixth weight.

8. The method according to claim 3, characterized in that Determining the target quantum key distribution network situation based on the performance data, the step size adjustment parameter, and the neural network model optimized by the cuckoo search algorithm includes: Obtaining initial model parameters of the neural network model in the neural network model optimized by the cuckoo search algorithm; Determining optimized model parameters according to the step size adjustment parameter, the cuckoo algorithm and the initial model parameters; A target quantum key distribution network state is determined based on the performance data, the optimization model parameters, and the neural network model.

9. A quantum key distribution network situation assessment device, characterized in that: The device comprises: A network data acquisition module is used to obtain performance data of the quantum key distribution network; the performance data includes network structure data, key performance data, communication quality data, data transmission data and evaluation model; An impact factor determination module is used to determine a comprehensive impact factor based on the performance data; the comprehensive impact factor is used to reflect the importance of the performance data to the status of the quantum key distribution network; The network situation acquisition module allows the user to determine the target quantum key distribution network situation based on the performance data, the comprehensive influencing factors, and the evaluation model.

10. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of a quantum key distribution network situation assessment method as described in any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the quantum key distribution network situation assessment method as described in any one of claims 1 to 8 are implemented.

Images