Method for verifying security of communication protocol based on quantum key distribution

Abstract

The application relates to the technical field of quantum key distribution and discloses a communication protocol security verification method based on quantum key distribution. The method establishes a quantum communication channel framework, loads protocol parameters to generate an initial security verification model, configures a security state transition rule, combines quantum entity parameters to perform cross-layer data fusion, and obtains a full-process security tracking model. Through the model, security path deduction is performed, a key exchange trajectory chain is generated, security trajectory simulation data is constructed, a quantum conflict resolution mechanism is established, a security strategy optimization model is generated by training, and security governance parameters are output. Based on the security governance parameters and the like, security incremental simulation information is generated, a multi-objective decision model is constructed by combining protocol evolution constraint conditions, optimal security path parameters are adjusted and generated, security verification strategies are verified and updated through a real-time quantum mapping network, and a full-process security matching target is achieved. The method effectively improves the comprehensiveness, accuracy and dynamic adaptability of quantum communication protocol security verification.

Description

Technical Field

[0001] This invention relates to the field of quantum key distribution technology, specifically to a method for secure verification of communication protocols based on quantum key distribution. Background Technology

[0002] With the rapid development of quantum communication technology, quantum key distribution, as a core technology for achieving absolutely secure communication, directly impacts the reliability of information transmission through the security of its communication protocol. However, existing security verification methods for communication protocols have many shortcomings when facing quantum communication scenarios. On the one hand, traditional verification methods struggle to effectively handle the unique quantum state characteristics and cross-layer data interaction issues in quantum communication, making it impossible to establish a comprehensive and accurate security verification model. This results in a lack of effective constraints and tracking of the secure state transition process in the quantum communication channel, hindering the achievement of end-to-end security monitoring.

[0003] Existing technologies lack efficient fusion mechanisms and algorithms when processing cross-layer data fusion of quantum entity parameters. They cannot accurately construct multi-layer quantum correlation equations and perform iterative solutions, resulting in insufficient accuracy in key steps such as generating protocol evolution boundary sets. This makes it difficult to effectively identify regions with low conflict density, thereby affecting the accuracy and reliability of the entire security verification process.

[0004] Traditional methods lack effective conflict resolution mechanisms and security strategy optimization models when dealing with dynamic changes in quantum communication. They cannot be trained and optimized based on security trajectory simulation data, and it is difficult to output accurate security governance parameters, such as quantum correlation weights and security compliance thresholds. This results in insufficient ability to iteratively adjust the security framework, the inability to generate optimal security path parameters, and difficulty in achieving the goal of security matching throughout the entire process.

[0005] Existing technologies have shortcomings in generating secure incremental simulation information and constructing multi-objective decision-making models. They cannot perform effective incremental simulation and global optimization based on information such as security governance parameters, resulting in low protocol coverage efficiency, high quantum conflict density, and failure to meet the requirements of high security and high reliability in quantum communication. Summary of the Invention

[0006] The purpose of this invention is to provide a secure verification method for communication protocols based on quantum key distribution, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a secure verification method for communication protocols based on quantum key distribution, the method comprising:

[0008] Establish a quantum communication channel framework and load a set of quantum key distribution protocol parameters to generate an initial security verification model;

[0009] Based on the initial security verification model, security state transition rules are configured, and cross-layer data fusion is performed by combining quantum entity parameters to obtain a full-process security tracking model.

[0010] Security path deduction is performed by a full-process security tracing model to generate a key exchange trajectory chain, and security trajectory simulation data is constructed by combining quantum state iteration frequency parameters.

[0011] A quantum conflict resolution mechanism is established and trained using security trajectory simulation data to generate a security strategy optimization model, which then outputs security governance parameters. These parameters include at least quantum correlation weights, security compliance thresholds, and protocol optimization priority sequences.

[0012] Based on security governance parameters, a full-process security tracking model, and quantum entity parameters, incremental security simulation information is generated.

[0013] By combining security incremental simulation information with protocol evolution constraints, a multi-objective decision model is constructed and the security framework is iteratively adjusted to generate optimal security path parameters;

[0014] The current secure path parameters are verified using a real-time quantum mapping network, the quantum consistency index is calculated, and the security verification strategy is updated by combining the optimal secure path parameters with the historical trajectory chain to achieve the goal of full-process security matching.

[0015] Preferably, the safety trajectory simulation data includes at least a set of quantum conflict parameters, a set of quantum state constraint parameters, a set of protocol evolution boundaries, and a dynamic optimization priority sequence;

[0016] The security incremental simulation information includes at least the quantum mapping deviation, protocol coverage completeness, and quantum consistency evaluation index.

[0017] Preferably, the step of establishing a quantum communication channel framework and loading a set of quantum key distribution protocol parameters to generate an initial security verification model includes the following steps:

[0018] Structured cleaning and classification of multi-source quantum communication data are performed to generate a standardized set of quantum entities;

[0019] Quantum properties are extracted from a set of quantum entities, wherein the extraction includes one or more of quantum clustering, property mapping, state classification, and quantum state identification;

[0020] Based on the state classification results, an initial security verification model is constructed, wherein the model includes a set of quantum nodes, a set of swapped edges, and quantum constraint rules;

[0021] Quantum correlation strength analysis is performed on the initial security verification model to generate a dynamic correlation weight matrix, and a security state label is assigned to each quantum node.

[0022] Preferably, the step of configuring security state transition rules based on the initial security verification model and performing cross-layer data fusion with quantum entity parameters to obtain a full-process security tracking model includes the following steps:

[0023] The initial security verification model is loaded with security state transition rules to constrain the state transition conditions, thereby generating the first security framework;

[0024] Load cross-layer correlation parameters onto the first security framework to generate a standardized security fusion framework;

[0025] Cross-layer data fusion based on a standardized security fusion framework includes the following specific processes:

[0026] A multi-layer quantum correlation equation is constructed, which includes at least a state similarity equation, an attribute matching equation, and an exchange consensus equation. The multi-layer quantum correlation equation is iteratively solved using a quantum evolution algorithm to obtain a set of quantum conflicts, quantum state constraint parameters, and a set of protocol evolution boundaries.

[0027] The generation of the protocol evolution boundary set includes the following steps:

[0028] Based on the quantum conflict set, the conflict density of each quantum node is calculated;

[0029] Identify regions in the standardized security fusion framework where the conflict density is no greater than a preset threshold, and generate a set of protocol evolution boundaries.

[0030] Preferably, the establishment of a quantum conflict resolution mechanism, training it with security trajectory simulation data, generating a security strategy optimization model, and then outputting security governance parameters includes the following steps:

[0031] A quantum conflict resolution mechanism is constructed based on the initial security verification model;

[0032] The quantum conflict resolution mechanism is trained and verified using safety trajectory simulation data to generate a safety strategy optimization model;

[0033] Input real-time quantum entity parameters into the security strategy optimization model to predict the protocol evolution boundary set;

[0034] Based on the predicted set of protocol evolution boundaries, security governance parameters are output, wherein the security governance parameters include at least quantum correlation weights, security compliance thresholds, and protocol optimization priority sequences.

[0035] Preferably, it also includes feature reconstruction of the safety trajectory simulation data, specifically:

[0036] An initial multi-layer input tensor is constructed based on the set of quantum conflict, quantum state constraint parameters, and protocol evolution boundary set;

[0037] The initial multi-layer input tensor is normalized and feature-enhanced to generate the final multi-layer input tensor.

[0038] Construct a security-optimized label tensor based on a dynamic optimization priority sequence;

[0039] The training sample set is formed by combining the final multi-layer input tensor with the security-optimized label tensor.

[0040] Preferably, the process of outputting security governance parameters based on the predicted protocol evolution boundary set includes the following steps:

[0041] Extract the quantum node with the lowest quantum conflict density from the predicted protocol evolution boundary set, and generate quantum correlation weights;

[0042] Based on the topological connectivity of the predicted protocol evolution boundary set, the distribution structure of the security compliance threshold is fitted to generate a protocol optimization priority sequence;

[0043] The state similarity gradient direction of the predicted protocol evolution boundary set is calculated and normalized into a security baseline vector, which is the security compliance adjustment direction.

[0044] Preferably, the step of generating incremental security simulation information based on security governance parameters, a full-process security tracking model, and quantum entity parameters includes the following steps:

[0045] The quantum correlation weights are mapped to the full-process security tracking model, matching the security compliance threshold and protocol optimization priority sequence. The quantum node density in the conflict area is adjusted, the full-process security tracking model is updated, and the incremental triggering conditions, protocol reconstruction rules and parameter update increments are defined to generate a security incremental simulation model.

[0046] Based on the security incremental simulation model, the multi-layer quantum correlation equation is iteratively solved using a quantum evolution algorithm to generate security incremental simulation information, specifically including:

[0047] When the incremental triggering condition is met, update the quantum mapping deviation, protocol coverage completeness, and quantum consistency evaluation index, and resolve the multi-level quantum correlation equation until the simulation termination condition is reached.

[0048] The incremental triggering condition includes triggering parameter updates when the current protocol coverage completeness rate is not greater than a preset completeness rate threshold; the protocol reconstruction rule includes adjusting the security compliance threshold based on the state similarity gradient direction; the parameter update increment has a piecewise linear relationship with the current quantum consistency evaluation index.

[0049] Preferably, the step of constructing a multi-objective decision model and iteratively adjusting the security framework to generate optimal security path parameters includes the following steps:

[0050] A multi-objective decision-making model is constructed, in which the decision variables include quantum node density, security compliance threshold and quantum state iteration frequency, the decision objectives include maximizing protocol coverage efficiency and minimizing quantum conflict density, and the constraints include protocol evolution boundary constraints and attribute matching accuracy threshold.

[0051] The multi-objective decision model is initially solved using the Bayesian optimization algorithm to generate an initial set of decision paths;

[0052] Based on the initial set of decision paths, the ant colony algorithm is used for global optimization to generate the optimal safe path parameters.

[0053] Preferably, the step of initially solving the multi-objective decision model using the Bayesian optimization algorithm to generate an initial set of decision paths includes the following steps:

[0054] A parameter space structure is constructed based on quantum node density and security compliance thresholds to generate an initial set of sampling points;

[0055] The objective function is calculated based on the protocol coverage efficiency and quantum conflict density. Gaussian process regression and acquisition function optimization are performed on the initial sampling point set to generate a set of intermediate decision paths.

[0056] The set of intermediate decision paths is filtered by confidence intervals and explored locally to generate the initial set of decision paths.

[0057] Compared with the prior art, the beneficial effects of the present invention are:

[0058] The quantum key distribution-based communication protocol security verification method provided by this invention establishes a quantum communication channel framework and loads relevant parameters to generate an initial security verification model, laying a comprehensive and accurate foundation for subsequent security verification. Based on the initial model, secure state transition rules are configured and cross-layer data fusion is performed to obtain a full-process security tracking model, which can effectively constrain state transition conditions, achieve secure tracking of the entire quantum communication process, and improve the comprehensiveness and accuracy of security verification.

[0059] By performing security path deduction through a full-process security tracing model, a key exchange trajectory chain is generated and security trajectory simulation data is constructed, providing rich data support for subsequent security strategy optimization. A quantum conflict resolution mechanism is established and a security strategy optimization model is generated by training with security trajectory simulation data. This model can output accurate security governance parameters, such as quantum correlation weights and security compliance thresholds, improving the system's ability to resolve quantum conflicts and optimize security strategies, thereby enhancing the system's stability and reliability.

[0060] By generating security incremental simulation information based on security governance parameters, the security framework can be dynamically adjusted according to actual conditions, improving the system's adaptability and flexibility. Combining security incremental simulation information with protocol evolution constraints to construct a multi-objective decision model and iteratively adjust it generates optimal security path parameters. This maximizes protocol coverage efficiency and minimizes quantum conflict density, optimizes resource allocation, and improves the security and reliability of the communication protocol.

[0061] Finally, the current secure path parameters are verified and the security verification strategy is updated based on a real-time quantum mapping network, achieving the goal of secure matching throughout the entire process and further ensuring the security and reliability of quantum communication. This method, through the synergistic effect of multiple steps, comprehensively enhances the security verification capability of quantum key distribution-based communication protocols, solves many problems existing in current technologies, and possesses significant technical advantages and application value. Attached Figure Description

[0062] Figure 1 This is a schematic diagram illustrating the working principle of the quantum key distribution-based communication protocol security verification method described in this invention.

[0063] Figure 2 Design diagrams generated for the initial security verification model;

[0064] Figure 3 Design diagrams generated for the end-to-end security tracking model;

[0065] Figure 4 Design diagrams generated for security policy optimization models. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] Please see Figures 1-4 The present invention relates to a secure verification method for communication protocols based on quantum key distribution, the specific implementation steps of which are as follows:

[0068] A quantum communication channel framework is established and a set of quantum key distribution protocol parameters is loaded to generate an initial security verification model.

[0069] Based on the initial security verification model, security state transition rules are configured, and cross-layer data fusion is performed using quantum entity parameters to obtain a full-process security tracking model.

[0070] The security path is simulated by performing a full-process security tracing model, generating a key exchange trajectory chain, and constructing security trajectory simulation data by combining quantum state iteration frequency parameters.

[0071] A quantum conflict resolution mechanism is established and trained using security trajectory simulation data to generate a security strategy optimization model, which in turn outputs security governance parameters. These parameters include at least quantum correlation weights, security compliance thresholds, and protocol optimization priority sequences.

[0072] Based on security governance parameters, a full-process security tracking model, and quantum entity parameters, incremental security simulation information is generated.

[0073] By combining security incremental simulation information with protocol evolution constraints, a multi-objective decision model is constructed and the security framework is iteratively adjusted to generate optimal security path parameters.

[0074] The current secure path parameters are verified using a real-time quantum mapping network, the quantum consistency index is calculated, and the security verification strategy is updated by combining the optimal secure path parameters with the historical trajectory chain to achieve the goal of full-process security matching.

[0075] Example 1:

[0076] In quantum key distribution-based communication protocol security verification methods, generating an initial security verification model is one of the core steps. This process involves the structured processing of quantum communication data, deep extraction of quantum properties, and the construction and optimization of the security verification model.

[0077] Quantum communication data typically originates from multiple heterogeneous network nodes, including quantum key distribution devices, quantum repeaters, and end-user nodes. This data may be affected by noise interference or protocol incompatibility during transmission, thus requiring structured cleaning and classification. The data cleaning process includes removing redundant information, repairing missing values, and standardizing the data format to ensure the integrity and consistency of quantum entity parameters. The classification process, based on the characteristics of the quantum communication data, such as quantum state type, transmission protocol version, and key distribution mode, divides the data into different standardized sets of quantum entities.

[0078] Quantum attribute extraction is a crucial step in constructing the initial security verification model. Quantum clustering algorithms are used to identify similarity features within a set of quantum entities, grouping nodes with similar quantum states or key exchange patterns into one class. Attribute mapping transforms abstract parameters in quantum communication data into quantifiable security metrics, such as qubit error rate, channel transmission efficiency, and key generation rate. State classification, based on the superposition and entanglement of quantum states, distinguishes different quantum communication stages, such as key negotiation, quantum state preparation, and quantum measurement. Quantum state identification assigns a unique security label to each quantum node, facilitating subsequent correlation analysis and state tracking.

[0079] Based on the state classification results, an initial security verification model is constructed. This model consists of a set of quantum nodes, a set of exchange edges, and quantum constraint rules. The set of quantum nodes represents the quantum devices or terminals participating in the communication, and each node contains quantum state parameters, a security label, and an association weight. The set of exchange edges describes the quantum key distribution path between nodes, including channel type, transmission efficiency, and security level. Quantum constraint rules are used to restrict the state transition conditions during quantum communication, such as the maximum number of key distribution attempts and the error tolerance threshold for quantum state measurement.

[0080] Quantum correlation strength analysis is performed on the initial security verification model to assess the security dependencies between nodes. A dynamic correlation weight matrix is ​​generated by calculating the quantum state similarity, key exchange frequency, and collision probability between nodes. Each element of the weight matrix reflects the security correlation strength between two nodes; a higher value indicates a stronger security dependency. Based on the dynamic correlation weight matrix, a security state label is assigned to each quantum node, with label types including secure, potentially risky, and high-collision.

[0081] The generation of secure trajectory simulation data relies on the extrapolation capabilities of the full-process secure tracing model. The quantum conflict set records anomalous events detected during communication, such as inconsistent quantum state measurements or key distribution failures. Quantum state constraint parameters are used to limit the dynamic behavior of quantum communication, ensuring that the key exchange process conforms to preset security standards. The protocol evolution boundary set identifies regions in the network with conflict densities below a preset threshold by analyzing quantum conflict density generation; these regions are considered feasible for protocol optimization. The dynamic optimization priority sequence determines the order of protocol adjustments based on the security state labels and association weights of quantum nodes.

[0082] Security incremental simulation information is used to quantify the effectiveness of protocol optimization. Quantum mapping deviation reflects the difference between actual quantum communication data and simulation model predictions; a smaller deviation indicates higher model accuracy. Protocol coverage completeness measures the extent to which security policies cover the quantum communication network; a higher completeness indicates more comprehensive security governance. Quantum consistency evaluation metrics are used to verify whether the key distribution process conforms to quantum mechanical principles, such as the quantum no-cloning theorem and the Heisenberg uncertainty principle.

[0083] Solving the multi-layer quantum correlation equations is the core of cross-layer data fusion. The state similarity equation compares the security state differences between different quantum nodes; the smaller the difference, the stronger the cooperation between nodes. The attribute matching equation assesses the compatibility of quantum entity parameters with security policies, ensuring that protocol optimization does not break the existing security framework. The exchange consensus equation detects logical conflicts in the key distribution process, such as the risk of key reuse or quantum state leakage.

[0084] The generation of the protocol evolution boundary set is based on the calculation of quantum conflict density. Conflict density is defined as the ratio of the number of quantum conflict events in a given region to the total number of nodes in that region. By setting a conflict density threshold, low-conflict regions suitable for protocol optimization are selected. These regions typically have relatively stable topologies, enabling gradual adjustments to security strategies.

[0085] The establishment of a quantum conflict resolution mechanism relies on training with secure trajectory simulation data. The training process employs a supervised learning method, with input data including a set of quantum conflicts, quantum state constraint parameters, and a set of protocol evolution boundaries. The security policy optimization model iteratively learns to gradually reduce the probability of quantum conflicts and improve key distribution efficiency. The model's output consists of security governance parameters, including quantum correlation weights, security compliance thresholds, and a protocol optimization priority sequence.

[0086] Quantum correlation weights reflect the importance of security dependencies between nodes; higher weights indicate a more urgent need for collaborative optimization among nodes. Security compliance thresholds determine whether quantum communication behavior complies with security standards; operations exceeding these thresholds are marked as high-risk. Protocol optimization priority sequences guide the implementation order of security policies, ensuring that critical nodes are optimized first.

[0087] Example 2:

[0088] The configuration of secure state transition rules and cross-layer data fusion are key steps in achieving end-to-end secure tracing. This process involves extending the initial security verification model, constructing and solving multi-layer quantum correlation equations, and establishing and training a quantum conflict resolution mechanism.

[0089] The process of loading secure state transition rules into the initial security verification model requires full consideration of the unique characteristics of quantum communication. These rules define the conditions and constraints for quantum nodes to transition between different secure states. These rules are formulated based on the fundamental principles of quantum key distribution protocols and the characteristics of actual network environments. State transition conditions include the validity verification of quantum state measurement results, the success probability threshold for key distribution, and limitations on channel noise levels. By loading these rules, the initial security verification model is extended into a first security framework, which can more accurately describe the various secure state changes that may occur during quantum communication.

[0090] The loading of cross-layer correlation parameters further enriches the information dimensions of the security framework. These parameters include the quantum channel characteristics of the physical layer, the key management rules of the protocol layer, and the security requirements indicators of the application layer. During the generation of the standardized security fusion framework, parameters at different levels need to be normalized to ensure that data from each layer can be compared and fused under a unified metric. The normalization process considers the unique parameter characteristics of quantum communication, such as the non-replicability of qubits and the perturbation of quantum measurements, ensuring that cross-layer data fusion conforms to the principles of quantum mechanics while also meeting the needs of practical security verification.

[0091] The construction of multi-layer quantum correlation equations is a core technical means for cross-layer data fusion. The state similarity equation is used to evaluate the consistency of security states of different quantum nodes in the same communication phase. This evaluation needs to consider the special effects brought about by the superposition and entanglement of quantum states. The attribute matching equation focuses on the adaptability between quantum entity parameters and security policies, especially maintaining the effectiveness of security policies in dynamically changing network environments. The exchange consensus equation focuses on analyzing the temporal relationships and logical constraints in the key distribution process, ensuring that each stage of key exchange meets protocol requirements. These equations are solved using a quantum evolutionary algorithm, which can effectively handle the high dimensionality and nonlinearity of quantum communication data.

[0092] During the solution process, the quantum evolutionary algorithm automatically adjusts its search strategy based on the characteristics of the equations. For the state similarity equation, the algorithm prioritizes the phase relationship between quantum states and the statistical properties of measurement results. When solving the attribute matching equation, the algorithm focuses on analyzing the functional correlation and constraint relationships between parameters. Solving the exchange consensus equation emphasizes the temporal logic and the continuity of state transitions. Through multiple iterations, the algorithm ultimately outputs important data such as the set of quantum conflicts, quantum state constraint parameters, and the set of protocol evolution boundaries.

[0093] The generation process of the quantum conflict set employs a dynamic monitoring mechanism. This mechanism tracks abnormal events in the quantum communication process in real time, including quantum state measurement deviations exceeding the allowable range and key distribution success rates falling below a threshold. For each detected conflict event, the system records its occurrence time, the quantum nodes involved, the conflict type, and the potential scope of its impact. This information is stored in a structured manner, forming a complete quantum conflict set, providing a data foundation for subsequent conflict analysis and resolution.

[0094] The determination of quantum state constraint parameters is based on the analysis of the performance limits of quantum communication systems. These parameters include the maximum allowable qubit error rate, the minimum acceptable channel transmission efficiency, and the security lower bound on the key generation rate. In determining these parameters, not only were the physical limitations of the quantum device considered, but also performance trade-offs under different security requirements were comprehensively evaluated. These constraint parameters will serve as important boundary conditions for security strategy optimization, ensuring that the optimized protocol satisfies both security requirements and practical feasibility.

[0095] The generation of the protocol evolution boundary set employs a conflict density analysis method. This method first calculates the conflict density of each quantum node, which is the ratio of the number of conflict events occurring per unit time to the total communication volume processed by that node. Then, a spatial clustering algorithm is used to identify characteristic regions of conflict density distribution in the network, marking regions with conflict densities consistently below a preset threshold as the safe boundaries of protocol evolution. These boundary regions possess relatively stable communication performance and security states, making them suitable as experimental areas for protocol optimization.

[0096] The quantum conflict resolution mechanism employs machine learning methods. Using a set of quantum conflicts and a set of protocol evolution boundaries as training data, the mechanism learns the characteristics and solutions of historical conflict events to establish a mapping relationship from conflict detection to resolution strategies. The training process utilizes incremental learning; as new conflict data accumulates, the mechanism continuously optimizes its decision-making capabilities. The trained quantum conflict resolution mechanism can quickly classify real-time detected conflict events and recommend appropriate resolution strategies based on conflict type and severity.

[0097] The generation of the security strategy optimization model is an iterative feedback process. This model takes real-time quantum entity parameters as input and predicts potential protocol evolution requirements by analyzing the differences between the current network state and historical data. The model's predictive power is based on a deep understanding of the dynamic characteristics of quantum communication systems, enabling it to accurately identify the impact trends of network state changes on protocol performance. The prediction results include the range of parameters that need to be adjusted for the protocol, possible optimization directions, and the expected performance improvements.

[0098] The output process for security governance parameters employs a multi-dimensional evaluation method. The calculation of quantum correlation weights comprehensively considers factors such as communication frequency between nodes, security dependency, and historical conflict records. The determination of security compliance thresholds is based on statistical analysis of the overall system security status, ensuring that threshold settings effectively prevent risks without excessively restricting normal communication. The generation of the protocol optimization priority sequence uses a risk-benefit ratio-based ranking algorithm, prioritizing protocol parameters with high improvement potential and low implementation difficulty.

[0099] These security governance parameters form a dynamically adjusted closed-loop system in practical applications. Quantum correlation weights guide resource allocation priorities, ensuring critical communication links receive greater security. Security compliance thresholds serve as a benchmark for risk warning, helping the system promptly identify potential security vulnerabilities. Protocol optimization priority sequences provide a clear roadmap for system upgrades, enabling limited optimization resources to generate maximum security benefits.

[0100] Example 3:

[0101] In the security verification system of quantum key distribution communication protocols, feature reconstruction of security trajectory simulation data is a key technical step in achieving efficient security strategy optimization. This process constructs a high-quality training sample set for machine learning models through multi-dimensional analysis and structured recombination of quantum conflict characteristics, laying a data foundation for the accurate prediction of security governance parameters.

[0102] The construction of the initial multi-layer input tensor begins with a deep analysis of the quantum conflict set. Each conflict event recorded in the quantum conflict set is deconstructed into multiple feature dimensions, including conflict type encoding, spatiotemporal distribution coordinates, feature vectors of involved quantum nodes, and environmental parameter snapshots. The conflict type encoding adopts a hierarchical classification system, dividing possible anomalies in quantum communication into several major categories such as measurement deviation, timing misalignment, and protocol mismatch, with each major category further subdivided into several specific subcategories. The spatiotemporal distribution coordinates not only record the physical location and time of the conflict but also include the hierarchical location information of the event in the network topology. The quantum node feature vectors extract a complete state description of each node involved in the conflict at the time of the event, covering core attributes such as quantum state parameters, security labels, and correlation weights. The environmental parameter snapshots capture the instantaneous values ​​of environmental factors such as channel noise level, device temperature, and synchronization accuracy at the time of the conflict.

[0103] Tensor quantization of quantum state constraint parameters employs feature embedding techniques. This technique transforms the originally discrete constraints into continuous vector representations, preserving the semantic information of the original constraints while adapting to the input requirements of deep learning models. During processing, different types of constraints are assigned to different embedding spaces; for example, qubit error rate constraints and channel transmission efficiency constraints are transformed using independent embedding matrices. This approach ensures that the differences between various constraints are fully preserved, avoiding feature confusion.

[0104] Feature extraction of the protocol evolution boundary set focuses on the topological characteristics and dynamic changes of the boundary regions. Each boundary region is represented as a data structure with multiple attributes, including a region shape descriptor, node density distribution, and historical stability index. The region shape descriptor is generated using graph theory-based methods, accurately depicting the spatial distribution characteristics of the boundary region in the network topology. The node density distribution is calculated using a kernel density estimation algorithm, reflecting the degree of clustering of quantum nodes within the boundary region. The historical stability index is derived by analyzing the conflict density fluctuations of the region over multiple past time windows, and is used to assess the reliability of the boundary region.

[0105] The characterization process of dynamically optimizing priority sequences incorporates time series analysis methods. This method not only considers the priority ranking at the current moment but also analyzes the patterns and trends of priority sequence changes over time. Statistical, frequency domain, and time domain features of the sequence are extracted using a sliding window technique, constructing a feature set that comprehensively reflects the dynamic changes in priority. These features are strictly aligned with quantum conflict features and constraint parameter features in the time dimension, ensuring temporal consistency for subsequent feature fusion.

[0106] The initial multi-layer input tensor standardization process employs a hierarchical normalization strategy. For different types of input features, the most suitable normalization method is designed. Numerical features utilize an improved RobustScaling method, which is more robust to outliers and particularly suitable for handling extreme values ​​that may exist in quantum communication data. Categorical features are converted into low-dimensional dense vectors through embedding layers before normalization. Temporal features employ a sliding window normalization technique to ensure that the normalization process does not disrupt the continuity of the time series. This hierarchical processing approach preserves the effective information of the original data to the greatest extent possible while eliminating the negative impact of differences in feature scales.

[0107] Feature enhancement is primarily achieved through two approaches: data transformation and feature interaction. Data transformation includes nonlinear transformations, polynomial expansions, and kernel method mappings of the original features, which can reveal hidden high-order patterns in the data. Feature interaction calculates the correlation weights between different features using an attention mechanism, and generates more discriminative combined features based on these weights. In particular, considering the unique characteristics of quantum communication data, quantum state-aware transformation operations are specifically designed in the feature enhancement process. These operations preserve the invariance of the physical meaning of quantum features.

[0108] The construction of the security optimization label tensor employs a multi-task learning framework. This framework simultaneously considers multiple optimization objectives, including conflict resolution efficiency, protocol execution performance, and resource utilization. Each optimization objective is quantified into an independent label channel, and information exchange between channels is achieved through a gating mechanism. The label values ​​are determined not only based on the current system state but also referencing the effectiveness evaluations of historical optimization cases, ensuring that the label information reflects both immediate needs and experiential wisdom. The temporal resolution of the label tensor is strictly synchronized with the input features, ensuring that each time step has a corresponding description of the optimization objective.

[0109] The training sample set is organized using a time-slice-based storage scheme. Each sample unit contains all feature and label data within a complete time window, with the window length dynamically adjusted according to the characteristics of the quantum communication protocol. Overlapping sampling maintains temporal continuity between samples, while stratified sampling ensures a balanced distribution of samples with different collision types. The sample set also maintains a complete metadata index, including data source, acquisition time, and preprocessing records, providing comprehensive background information for subsequent model training and validation.

[0110] Quality control of training samples is maintained throughout the entire feature reconstruction process. The online data cleaning module detects and repairs outliers and missing values ​​in the feature data in real time, dynamically selecting the repair strategy based on the feature type and data distribution characteristics. A consistency verification mechanism periodically checks the logical relationship between features and labels to ensure the internal consistency of the sample data. The sample weighting system automatically calculates the training weights of each sample based on its information content and representativeness, enabling the model to focus more on data with higher learning value.

[0111] The feature reconstruction process also considers the dynamic evolution characteristics of the quantum communication system. An adaptive feature update mechanism continuously monitors changes in the system state, automatically triggering adjustments to the feature space when significant changes are detected. This adjustment is not a simple recalculation, but rather a method based on incremental learning, gradually adapting to the new data distribution while preserving existing knowledge. An evolution-aware feature selection algorithm periodically evaluates the importance of each feature, dynamically adjusting the composition of the feature set to ensure that the input data always contains the most predictive information.

[0112] The feature reconstruction system collaborates closely with other modules of the security verification platform. Real-time interaction with the quantum conflict detection module ensures the acquisition of the latest conflict data; feedback loops with the protocol evolution prediction module help optimize feature selection strategies; and collaborative work with the security policy execution module enables feature design to better align with practical application needs. This comprehensive collaboration ensures that feature reconstruction work remains synchronized with actual security requirements.

[0113] Example 4:

[0114] In the dynamic security maintenance of quantum key distribution communication systems, the generation of security incremental simulation information constitutes the core mechanism for continuous protocol optimization. This process, through the establishment of a responsive parameter update system, enables real-time adaptation and adjustment of the quantum communication network state, and in practice, it manifests as a multi-level, multi-stage collaborative operation mode.

[0115] The mapping process for quantum correlation weights is implemented using a distributed computing architecture. When the system detects fluctuations in the key exchange success rate on a quantum channel, the weight allocation module immediately retrieves the corresponding node correlation records from the full-process security tracking model. For example, for a core quantum relay node connecting Beijing and Shanghai, the system analyzes its quantum state transmission stability index over the past 24 hours, compares this historical data with the real-time collected quantum error rate, and generates new weight coefficients using predefined correlation calculation rules. These coefficients are synchronously updated in the security assessment matrix of all network nodes, triggering a state reassessment process for the relevant nodes. This dynamic weight adjustment ensures that security strategies can respond promptly to changes in network conditions, especially in cross-border quantum communication scenarios, where differences in regulatory requirements across different regions can be effectively balanced through the weight system.

[0116] The security compliance threshold matching mechanism operates using a case-based reasoning approach. The system maintains a case library containing various network anomaly scenarios. When the conflict characteristics of the current quantum node are found to be similar to historical cases, the corresponding security threshold configuration is automatically retrieved. Taking a quantum memory node as an example, if its quantum state retention time is detected to exhibit periodic decay, the system compares it with records of quantum memory performance degradation in the case library and selects the closest case as a reference for threshold adjustment. Simultaneously, the system fine-tunes the threshold based on the actual operating environment parameters of the current node (such as temperature and electromagnetic interference levels) to ensure that it meets security standards without causing unnecessary communication interruptions due to excessive stringency.

[0117] The generation process of the protocol optimization priority sequence incorporates a multi-factor decision-making algorithm. In a regional quantum network upgrade project, the system needs to simultaneously handle the optimization requirements of multiple protocol parameters, including key update frequency, quantum state encoding method, and error correction scheme. The decision-making algorithm first assesses the impact range of these parameters, such as analyzing how many quantum channels an adjustment to the key update frequency will affect; then, it performs dependency detection to determine which parameter modifications must be implemented in a specific order; finally, it combines resource availability analysis to calculate the expected execution cost of each optimization operation. Through this comprehensive evaluation, the system generates a dynamic priority queue, ensuring that limited optimization resources are allocated to the most critical protocol improvement points.

[0118] The density adjustment of quantum nodes in conflict zones employs a gradual optimization strategy. When the system identifies a persistent measurement basis mismatch problem among quantum nodes within a data center, it first analyzes the physical layout and communication patterns of these nodes, and then gradually implements the density adjustment scheme. In the initial stage, only the location distribution of a few key nodes may be adjusted to observe the changing trend of conflict indicators; after confirming effectiveness, the optimization strategy is then extended to adjacent areas. This phased adjustment approach avoids network oscillations that may be caused by large-scale topology changes, making it particularly suitable for the smooth upgrading of security strategies in operating quantum communication networks.

[0119] The incremental triggering conditions reflect a thorough consideration of system stability. Taking protocol coverage integrity monitoring as an example, the system not only sets a threshold for overall network coverage but also sets differentiated triggering standards for different types of quantum services. For the backbone link undertaking the core key distribution task, the monitoring frequency and trigger sensitivity of its coverage integrity are significantly higher than those of ordinary user access links. When the protocol coverage integrity of a quantum exchange node falls below the threshold for three consecutive monitoring cycles, the system initiates a parameter update process for that node while maintaining the normal operation of other nodes. This refined triggering mechanism ensures the accuracy and minimal interference of security maintenance operations.

[0120] The execution process of protocol refactoring rules emphasizes compatibility with existing systems. When upgrading the communication protocol of a quantum satellite ground station, the refactoring engine first verifies the compatibility of the new rules with existing hardware, including physical layer parameters such as the response characteristics of quantum detectors and the control precision of modulators. Only after confirming that the new rules can be supported by existing equipment will they be deployed to the actual system. For rule improvements that require hardware upgrades, the system automatically generates a phased implementation plan to ensure uninterrupted service. This cautious refactoring approach is particularly important in the upgrade of quantum encrypted communication systems in the financial industry, as it can prevent business interruptions caused by protocol changes.

[0121] The calculation of parameter update increments employs an adaptive adjustment mechanism. When the quantum consistency evaluation metric indicates a decline in the state stability of a quantum channel, the system does not immediately apply the maximum parameter adjustment. Instead, it dynamically determines the increment size based on the rate and extent of the metric deterioration. For example, for slowly developing performance degradation, the system will schedule multiple small-amplitude parameter fine-tunings and observe the system response after each adjustment; while for sudden severe anomalies, a preset maximum safety increment may be applied directly. This differentiated increment strategy ensures rapid response in emergencies while avoiding system fluctuations caused by over-adjustment.

[0122] Quantum evolutionary algorithms exhibit unique adaptability in solving multi-level quantum correlation equations. When dealing with the impact of atmospheric turbulence in satellite-to-ground quantum communication, the algorithm prioritizes optimizing parameters most sensitive to channel disturbances. By analyzing key generation efficiency under different weather conditions in historical communication data, the algorithm automatically adjusts the parameter search direction, improving the system's environmental adaptability while ensuring security. This optimization approach based on practical operational experience enables security strategies to better cope with various complex real-world environmental challenges.

[0123] The determination of simulation termination conditions comprehensively considers multiple factors. In addition to conventional iteration limits and convergence thresholds, the system also monitors actual operational indicators such as quantum node load changes and network energy consumption trends during the optimization process. If the optimization direction is found to potentially cause certain critical nodes to exceed their operating capacity, the current simulation cycle will be terminated early and a warning message will be output, even if the algorithm has not yet reached its theoretical optimum. This pragmatic termination strategy prevents the practical operational risks that pure mathematical optimization may bring, reflecting the safety-first principle in engineering implementation.

[0124] The output information from the security incremental simulation model provides a comprehensive reference for subsequent decision-making. The quantum mapping deviation not only provides numerical differences but also indicates the spatial distribution characteristics of the deviations; the protocol coverage completeness rate includes a detailed gap analysis report, indicating which specific protocol clauses need strengthening; and the quantum consistency assessment index distinguishes the weight of different quantum effects. This structured output information enables network administrators to accurately understand the system status and make targeted management decisions.

[0125] Example 5:

[0126] In the optimization decision-making process of quantum key distribution networks, the construction and solution of a multi-objective decision model constitute the core decision engine for protocol optimization. The implementation of this system embodies a hierarchical and progressive intelligent decision-making mechanism, which achieves secure path planning in complex quantum communication environments by integrating the advantages of multiple optimization algorithms.

[0127] The construction of the multi-objective decision-making model begins with a comprehensive analysis of the characteristics of quantum networks. Taking the quantum encrypted communication network of a multinational financial institution as an example, the decision-making system first digitally models its infrastructure, abstracting the quantum nodes distributed across 12 data centers globally as vertices in the network topology graph. Each vertex contains more than 50 feature dimensions, including the coherence time of the quantum memory at the physical layer, the key refresh frequency at the protocol layer, and the node connectivity at the network layer. Decision variables undergo special encoding processing, such as converting the quantum node density into spatial distribution coefficients based on the Voronoi diagram, transforming the discrete node deployment problem into a continuous optimization problem. Security compliance thresholds are expressed as multi-dimensional constraints, including data compliance requirements for each jurisdiction and security standards for different business levels.

[0128] The parameter space structure was constructed using adaptive grid technology. In an upgrade project of a government quantum secure communication network, the system identified the correlations of key parameters based on historical operation and maintenance data, reducing the originally high-dimensional parameter space to several main feature directions. For example, quantum state iteration frequency and channel bit error rate were identified as strongly correlated parameters, and the system merged them into a composite optimization dimension. This intelligent dimensionality reduction allows subsequent sampling processes to focus on the most influential parameter combinations, significantly improving optimization efficiency. The generation of the initial sampling point set not only considers uniform coverage of the parameter range but also pays special attention to sensitive areas discovered in past operations and maintenance, ensuring sufficient sampling density in these key areas.

[0129] The objective function calculation integrates multiple performance dimensions of quantum communication. When optimizing a certain seabed quantum repeater system, the system simultaneously considers two core indicators: protocol coverage efficiency and quantum conflict density. The calculation of protocol coverage efficiency not only counts the number of supported services but also evaluates the quality level and priority weight of each service. The measurement of quantum conflict density adopts a multi-scale analysis method, examining both the macroscopic overall network conflict rate and the microscopic critical path conflict distribution. These indicators are integrated into a comprehensive objective function through a weighted system based on business requirements, ensuring that the optimization direction aligns with actual operational requirements.

[0130] The application of Gaussian process regression demonstrates its advantages in handling quantum uncertainty. When optimizing the ground station layout of a satellite quantum communication system, the system utilizes Gaussian processes to establish a probabilistic model of the relationship between parameters and performance. This method is particularly suitable for quantum communication environments because it can naturally handle quantum noise and observation errors in measurements. The regression model not only predicts the expected values ​​of performance indicators but also provides the confidence intervals for the predictions, providing a basis for subsequent risk assessment. When dealing with periodic parameters such as the quantum satellite's overhead time, the system employs a periodic kernel function to better capture the temporal correlation of the parameters.

[0131] The sampling function optimization phase achieved a balance between exploration and utilization. In the frequency planning of a city's quantum government network, the system dynamically adjusted its sampling strategy: during nighttime hours when network load is low, it favored exploratory sampling, trying new parameter combinations; during peak business hours, it favored utilization sampling, selecting parameter settings that have proven effective. This adaptive strategy ensured that the optimization process could discover new optimization directions without significantly impacting existing services. The calculation of the sampling function also considered the operational costs of adjusting different parameters, prioritizing optimization directions that were easier to implement but yielded greater benefits.

[0132] The confidence interval screening mechanism provides risk assessment for decision-making. When optimizing a quantum protection communication network for a power system, the system pays special attention to parameter combinations with excellent predictive performance but wide confidence intervals. For these combinations, the system arranges additional confirmatory sampling to reduce prediction uncertainty. Simultaneously, the system maintains a risk parameter knowledge base, recording parameter characteristics that have historically led to sudden performance drops, automatically avoiding combinations with similar characteristics during the screening process. This conservative and rigorous screening strategy is particularly important in the optimization of critical infrastructure.

[0133] The local exploration process employs gradient-aware intelligent search. When adjusting the fiber optic length parameters of a quantum data center, the system determines the most promising search direction by analyzing the local gradient of the performance surface. Unlike traditional optimization methods, the gradient calculation here considers the non-local characteristics unique to quantum communication, such as the cross-node effects of long-distance quantum entanglement. The system also identifies flat regions in the parameter space, which typically correspond to multiple near-optimal solutions, providing operators with flexible options.

[0134] Ant colony optimization (ACO) exhibits unique advantages in the global optimization phase. When planning the upgrade path of a national-level quantum backbone network, the algorithm simulates "ants" that explore various possible optimization paths on the network topology. Each "ant" carries specific optimization preferences; some prioritize security improvements, while others focus on cost reduction. These exploration results are shared through a pheromone mechanism, ultimately merging into a comprehensive optimization scheme. The algorithm features a specially designed quantum-sensing pheromone update rule, which can correctly handle the unique non-classical correlation characteristics of quantum networks.

[0135] The generation of optimal security path parameters emphasizes feasibility. The system outputs not only theoretically optimal parameter values ​​but also detailed implementation roadmaps. For example, when optimizing the security protocol of a bank's quantum trading system, the solution clearly distinguishes between critical modifications that must be implemented immediately and enhancements that can be carried out in stages. Each parameter adjustment is accompanied by an impact assessment report, explaining the system components that may be affected and the necessary supporting measures. This engineered output format greatly facilitates the practical operation of the operations and maintenance team.

[0136] The interaction between the decision-making system and the actual quantum network forms a continuous improvement loop. After each parameter adjustment, the system monitors the network performance in real time, comparing the actual operating data with the predicted results. The discrepancies discovered are used to calibrate the optimization model, continuously improving the accuracy of subsequent decisions. The system also maintains a case knowledge base, recording the decision-making process and implementation effects of each optimization, providing experience for new optimization tasks. This self-improving mechanism enables the system to adapt to the rapid development of quantum network technology.

[0137] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0138] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for verifying security of a communication protocol based on quantum key distribution, characterized by, The method comprises the following steps: establishing a quantum communication channel framework and loading a quantum key distribution protocol parameter set to generate an initial security verification model; configuring a security state transition rule based on the initial security verification model, performing cross-layer data fusion combined with quantum entity parameters to obtain a full-process security tracking model; performing security path deduction through the full-process security tracking model to generate a key exchange trajectory chain, and constructing a security trajectory simulation data combined with quantum state iteration frequency parameters; establishing a quantum conflict resolution mechanism and training through the security trajectory simulation data to generate a security policy optimization model, and then outputting security governance parameters, wherein the security governance parameters at least include a quantum correlation degree weight, a security compliance threshold and a protocol optimization priority sequence; generating security incremental simulation information based on the security governance parameters, the full-process security tracking model and the quantum entity parameters; constructing a multi-objective decision model combined with the security incremental simulation information and the protocol evolution constraint condition, and iteratively adjusting the security framework to generate optimal security path parameters; verifying the current security path parameters based on a real-time quantum mapping network, calculating a quantum consistency index, combining the optimal security path parameters and the historical trajectory chain, and updating the security verification strategy to achieve the full-process security matching goal; the security trajectory simulation data at least includes a quantum conflict set, quantum state constraint parameters, a protocol evolution boundary set and a dynamic optimization priority sequence; the security incremental simulation information at least includes a quantum mapping deviation, a protocol coverage completeness rate and a quantum consistency evaluation index; The method of establishing a quantum communication channel framework and loading a quantum key distribution protocol parameter set to generate an initial security verification model comprises the following steps: structurally cleaning and classifying multi-source quantum communication data to generate a standardized quantum entity set; extracting quantum attributes from the quantum entity set, wherein the extraction includes one or more of quantum clustering, attribute mapping, state classification and quantum state identification; based on the state classification result, an initial security verification model is constructed, wherein the model includes a quantum node set, an exchange edge set and quantum constraint rules; performing quantum correlation strength analysis on the initial security verification model to generate a dynamic correlation weight matrix, and assigning a security state label to each quantum node; The method of configuring a security state transition rule based on the initial security verification model, performing cross-layer data fusion combined with quantum entity parameters to obtain a full-process security tracking model comprises the following steps: loading a security state transition rule to the initial security verification model to constrain state conversion conditions to generate a first security framework; loading cross-layer correlation parameters to the first security framework to generate a standardized security fusion framework; based on the standardized security fusion framework, cross-layer data fusion is performed, and the specific process includes: constructing a multi-layer quantum correlation equation, which at least includes a state similarity equation, an attribute matching equation and an exchange consistency equation, iteratively solving the multi-layer quantum correlation equation through a quantum evolution algorithm to obtain a quantum conflict set, quantum state constraint parameters and a protocol evolution boundary set; the generation of the protocol evolution boundary set comprises the following steps: based on the quantum conflict set, the conflict density of each quantum node is calculated; Identify the region with a conflict density not greater than a preset threshold in the standardized security fusion framework, and generate a protocol evolution boundary set; The establishment of quantum conflict resolution mechanism and training through security trajectory simulation data, generating security policy optimization model, and then outputting security governance parameters, including the following steps: Based on the initial security verification model, a quantum conflict resolution mechanism is constructed. Train and verify the quantum conflict resolution mechanism through security trajectory simulation data to generate a security policy optimization model. Input real-time quantum entity parameters into the security policy optimization model to predict the protocol evolution boundary set. Based on the predicted protocol evolution boundary set, output the security governance parameters, including at least quantum correlation degree weight, security compliance threshold, and protocol optimization priority sequence.

2. The method of claim 1, wherein the quantum key distribution based communication protocol security verification method is characterized by, It also includes feature reconstruction of security trajectory simulation data, specifically: Based on the quantum conflict set, quantum state constraint parameters, and protocol evolution boundary set, an initial multi-layer input tensor is constructed. Standardize and enhance the initial multi-layer input tensor to generate a final multi-layer input tensor. Based on the dynamic optimization priority sequence, a security optimization label tensor is constructed. Combine the final multi-layer input tensor and the security optimization label tensor to form a training sample set.

3. The method of claim 2, wherein the quantum key distribution based communication protocol security verification method is characterized by, The security governance parameters are output based on the predicted protocol evolution boundary set, including the following steps: Extract the quantum node with the lowest quantum conflict density from the predicted protocol evolution boundary set to generate the quantum correlation degree weight. According to the topological connection relationship of the predicted protocol evolution boundary set, fit the distribution structure of the security compliance threshold to generate the protocol optimization priority sequence. Calculate the state similarity gradient direction of the predicted protocol evolution boundary set and normalize it to a security benchmark vector, which is the security compliance adjustment direction.

4. The method of claim 1, wherein the quantum key distribution based communication protocol security verification method is characterized by, Based on the security governance parameters, the whole-process security tracking model, and the quantum entity parameters, security incremental simulation information is generated, including the following steps: Map the quantum correlation degree weight to the whole-process security tracking model, match the security compliance threshold and the protocol optimization priority sequence, adjust the quantum node density in the conflict area, update the whole-process security tracking model, define the incremental trigger condition, the protocol reconstruction rule and the parameter update increment, and generate the security incremental simulation model; Based on the security incremental simulation model, the multi-layer quantum correlation equation is iteratively solved by quantum evolution algorithm to generate security incremental simulation information, specifically including: When the incremental trigger condition is met, update the quantum mapping deviation, the protocol coverage completeness rate and the quantum consistency evaluation index, and re-solve the multi-layer quantum correlation equation until the simulation termination condition is reached. The incremental trigger condition includes triggering parameter update when the current protocol coverage completeness rate is not greater than a preset completeness rate threshold; the protocol reconstruction rule includes adjusting the security compliance threshold based on the state similarity gradient direction; the parameter update increment has a segmented linear relationship with the current quantum consistency evaluation index.

5. The method of claim 1, wherein the quantum key distribution based communication protocol security verification method is characterized by, The multi-objective decision model is constructed and the security framework is iteratively adjusted to generate optimal security path parameters, including the following steps: A multi-objective decision model is constructed, wherein the decision variables include quantum node density, security compliance threshold and quantum state iteration frequency, the decision objectives include maximizing protocol coverage efficiency and minimizing quantum conflict density, and the constraint conditions include protocol evolution boundary constraint and attribute matching accuracy threshold; An initial decision path set is generated by performing preliminary solution on the multi-objective decision model through a Bayesian optimization algorithm; Global optimization is performed on the initial decision path set based on an ant colony algorithm to generate optimal security path parameters.

6. The method of claim 5, wherein the quantum key distribution based communication protocol security verification method is characterized by, The preliminary solution on the multi-objective decision model through the Bayesian optimization algorithm to generate the initial decision path set includes the following steps: A parameter space structure is constructed based on quantum node density and security compliance threshold to generate an initial sampling point set; An intermediate decision path set is generated by performing Gaussian process regression and acquisition function optimization on the initial sampling point set according to a target function calculated based on protocol coverage efficiency and quantum conflict density; The initial decision path set is generated by performing confidence interval screening and local exploration on the intermediate decision path set.

Images