Polar code resource allocation optimization method and system in multi-user scene

Abstract

The invention discloses a Polar code resource allocation optimization method and system in a multi-user scene, and relates to the technical field of channel coding resource optimization, and the method comprises the steps: generating a plurality of user channels; performing multi-mode communication accident feature deduction to obtain a communication accident portrait group; performing a Polar code resource adjustment decision to obtain a Polar code resource adjustment domain; performing guarantee priority calculation to obtain a communication guarantee priority matrix; establishing a multi-level resource adjustment optimizing framework; and executing multi-dimensional evolution joint optimization, and carrying out Polar code resource allocation optimization. The technical problems that in the prior art, Polar code resource allocation in a multi-user scene lacks pertinence and is single in risk management and control, so that communication quality is unstable, and multi-user differentiation requirements are difficult to adapt are solved, and the technical effects that Polar code resource allocation optimization in the multi-user scene is achieved, the communication quality is improved, and the multi-user requirements are adapted are achieved.

Description

Technical Field

[0001] This invention relates to the field of channel coding resource optimization technology, specifically to a method and system for optimizing Polar code resource allocation in multi-user scenarios. Background Technology

[0002] In multi-user communication scenarios, with the widespread application of short-range communication technologies such as Polar code modules, the simultaneous access of multiple user devices intensifies channel resource competition, leading to increasingly prominent issues such as unstable communication quality, large latency fluctuations, and significant security risks. Traditional Polar code resource allocation methods often employ single-dimensional resource adjustment strategies, failing to fully consider the differences in communication accident risks among different user channels and lacking a comprehensive consideration of user service types and service protocol priorities, resulting in insufficient targeted resource allocation. Furthermore, existing methods offer relatively simplistic management of communication coupling risks, making it difficult to cover scenarios with overlapping multi-dimensional risks. They also lack a dynamically evolving resource optimization architecture, failing to adapt to the dynamically changing communication needs of multiple users. Ultimately, this results in low resource utilization, frequent communication accidents, and an inability to meet the demands for high-quality communication services in multi-user scenarios.

[0003] In existing technologies, the allocation of Polar code resources in multi-user scenarios lacks specificity, and risk management is simplistic, resulting in unstable communication quality and difficulty in adapting to the differentiated needs of multiple users. Summary of the Invention

[0004] This application provides a method and system for optimizing Polar code resource allocation in multi-user scenarios, which addresses the technical problems in existing technologies where Polar code resource allocation in multi-user scenarios lacks specificity, risk management is singular, resulting in unstable communication quality and difficulty in adapting to the differentiated needs of multiple users.

[0005] In view of the above problems, this application provides a method and system for optimizing Polar code resource allocation in multi-user scenarios.

[0006] The first aspect of this application provides a method for optimizing Polar code resource allocation in multi-user scenarios, the method comprising: Multiple user channels are generated based on multiple user equipment connected to the StarSpark module. Multimodal communication accident feature deduction is performed on these user channels to obtain a communication accident profile group. Polar code resource adjustment decisions are made for the multiple user channels based on the communication accident profile group to obtain a Polar code resource adjustment domain. Priority calculation is performed on the multiple user channels to obtain a communication guarantee priority matrix. Based on the communication guarantee priority matrix, multidimensional communication coupling risk optimization is performed on the Polar code resource adjustment domain according to the multiple user channels to establish a multi-level resource adjustment optimization architecture. Multi-dimensional evolutionary joint optimization is executed based on the Polar code resource adjustment domain to obtain Polar code resource adjustment results, and Polar code resource allocation optimization is performed on the multiple user channels in conjunction with the StarSpark module.

[0007] A second aspect of this application provides a Polar code resource allocation optimization system for multi-user scenarios, the system comprising: The user channel generation module generates multiple user channels based on multiple user equipment connected to the StarSpark module; the communication accident profile acquisition module performs multimodal communication accident feature deduction on the multiple user channels to obtain a communication accident profile; the resource adjustment domain acquisition module performs Polar code resource adjustment decisions on the multiple user channels based on the communication accident profile to obtain a Polar code resource adjustment domain; the priority calculation module calculates the guarantee priority based on the multiple user channels to obtain a communication guarantee priority matrix; the risk optimization module performs multidimensional communication coupling risk optimization on the Polar code resource adjustment domain based on the communication guarantee priority matrix and the multiple user channels to establish a multi-level resource adjustment optimization architecture; and the resource allocation optimization module performs multi-dimensional evolutionary joint optimization of the multi-level resource adjustment optimization architecture based on the Polar code resource adjustment domain to obtain Polar code resource adjustment results, and optimizes Polar code resource allocation for the multiple user channels in conjunction with the StarSpark module.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Based on multiple user equipment connected to the StarSpark module, multiple user channels are generated; multimodal communication accident feature inference is performed to obtain a communication accident profile group; Polar code resource adjustment decisions are made for the multiple user channels to obtain the Polar code resource adjustment domain; guarantee priority is calculated based on the multiple user channels to obtain a communication guarantee priority matrix; multi-dimensional communication coupling risk optimization is performed on the Polar code resource adjustment domain based on the multiple user channels to establish a multi-level resource adjustment optimization architecture; multi-dimensional evolutionary joint optimization of the multi-level resource adjustment optimization architecture is executed to obtain the Polar code resource adjustment result, and the Polar code resource allocation of the multiple user channels is optimized in conjunction with the StarSpark module. This achieves the technical effect of optimizing Polar code resource allocation in multi-user scenarios, improving communication quality, and adapting to the needs of multiple users. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic diagram of the Polar code resource allocation optimization method in a multi-user scenario provided in an embodiment of this application; Figure 2 This is a schematic diagram of the Polar code resource allocation optimization system structure provided in the embodiments of this application.

[0011] Explanation of reference numerals in the attached diagram: User channel generation module 10, Communication accident profile group acquisition module 20, Resource adjustment domain acquisition module 30, Priority calculation module 40, Risk optimization module 50, Resource allocation optimization module 60. Detailed Implementation

[0012] This application provides a method and system for optimizing Polar code resource allocation in multi-user scenarios, which addresses the technical problems in existing technologies where Polar code resource allocation in multi-user scenarios lacks specificity, risk management is singular, resulting in unstable communication quality and difficulty in adapting to the differentiated needs of multiple users.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] Example 1, as Figure 1 As shown, this application provides a method for optimizing Polar code resource allocation in multi-user scenarios, the method comprising: Step S100: Generate multiple user channels based on multiple user equipment connected to the StarScan module.

[0015] Specifically, the core process involves multiple user devices connected to the StarShine module, such as smart terminals, IoT sensing devices, and industrial control equipment. Leveraging the StarShine module's multi-device access and channel management capabilities, a user channel generation process is initiated. First, the StarShine module identifies and analyzes the communication needs of all connected user devices, obtaining key parameters such as the service type (e.g., real-time data transmission, high-definition multimedia interaction, low-latency control command transmission), data volume, and transmission rate requirements. Then, based on StarShine's channel allocation protocol and resource scheduling rules, and considering the differences in device parameters, a dedicated communication frequency band, transmission time slot, and signal modulation method are allocated to each user device to ensure that communication data from different devices does not interfere with each other during transmission. Finally, through the StarShine module's channel establishment mechanism, an independent user channel tailored to the communication needs of each user device is built, forming multiple parallel user channels.

[0016] Step S200: Perform multimodal communication accident feature deduction on the multiple user channels to obtain a communication accident profile group.

[0017] Specifically, for the generated multiple user channels, communication accident feature inference is carried out in a multi-dimensional, channel-specific manner, ultimately constructing a communication accident profile group. The specific process is as follows: First, target channels are selected one by one from the multiple user channels, denoted as the h-th user channel (h is a positive integer). Key operating parameters of this channel, such as signal strength, data packet loss rate, transmission delay fluctuation, and encrypted link status, are collected in real time through the channel monitoring module, forming a continuous h-th channel monitoring sequence. Next, based on this monitoring sequence, three types of accident feature inference are performed. In the communication quality dimension, combined with the inference model trained on historical channel quality accident sets, the types and probabilities of possible quality accidents such as signal attenuation and data loss are predicted, yielding the h-th communication quality accident inference result. In the communication delay dimension, delay analysis is performed... The matching degree between the fluctuation pattern and the service latency requirements is used to deduce the risk of latency accidents such as exceeding the latency threshold and sudden latency changes, generating the h-th communication latency accident deduction result; in the communication security dimension, the integrity of channel data encryption and access permission verification records are checked to identify security risks such as data tampering and unauthorized access, forming the h-th communication security accident deduction result; finally, the three types of accident deduction results of the h-th user channel are integrated to clarify the core information such as the accident type, risk level, and scope of impact of the channel, construct the h-th communication accident profile, and include it in the set. After the accident profiles of all user channels are generated, a complete communication accident profile group is formed.

[0018] Step S300: Based on the communication accident profile group, make Polar code resource adjustment decisions for the multiple user channels to obtain the Polar code resource adjustment domain.

[0019] Specifically, a deep analysis of the incident profile for each user channel in the communication incident profile group is conducted to extract the incident characteristics and risk levels of each channel in three dimensions: communication quality, communication latency, and communication security. For example, it is identified that a certain user channel has a "quality incident risk caused by a high packet loss rate," another user channel has a "latency incident risk of transmission latency exceeding the threshold," and yet another user channel has a "security incident risk of data being easily tampered with." Subsequently, based on the resource allocation characteristics of Polar codes, such as code rate adjustment, code block length selection, power resource allocation, and error correction capability configuration, differentiated Polar code resource adjustment strategies are formulated for different incident risk types of channels: for channels with high packet loss rates, a Polar code rate configuration with higher error correction capability is adopted; for latency-sensitive channels, a shorter code block length is selected to reduce encoding and decoding latency; and for channels with high security risks, encryption-enhanced Polar code resource parameters are used. Finally, the Polar code resource adjustment strategies corresponding to all user channels are summarized, and the configuration range of Polar code resources under each adjustment strategy is clarified, such as the adjustable range of code rate, the selectable value of code block length, and the power allocation threshold. These sets, which include adjustment strategies and resource configuration ranges, are integrated to form a Polar code resource adjustment domain that can cover the needs of multi-user channel accident risk response.

[0020] Step S400: Calculate the guarantee priority based on the multiple user channels to obtain the communication guarantee priority matrix.

[0021] Specifically, priority evaluation is performed on all user channels from the service type perspective: Based on the service scenarios carried by the channels, such as real-time control, high-definition multimedia, and ordinary data transmission, service types are divided into different priority levels. For example, real-time control services for industrial equipment have a higher priority than ordinary text transmission services for consumers. According to the preset service type priority standards, each user channel is assigned a corresponding service type priority evaluation score, forming a service type priority evaluation sequence. Next, priority evaluation is performed from the service protocol perspective: The communication protocols followed by each user channel are analyzed, such as low-latency, high-reliability protocols and general data transmission protocols. Priority rules are set based on the differences in the protocols' requirements for transmission reliability and latency sensitivity. For example, channels corresponding to low-latency, high-reliability protocols have a higher priority than general protocol channels. Based on this, a service protocol priority evaluation score is assigned to each user channel, generating a service protocol priority evaluation sequence. Finally, the preset priority weight configuration is invoked, including service type priority weight and service protocol priority weight. The weight values ​​are preset according to the communication needs of multi-user scenarios. The service type priority evaluation score and service protocol priority evaluation score of each user channel are weighted and summed to obtain the comprehensive guarantee priority of each user channel. The identifiers of all user channels and their corresponding comprehensive guarantee priorities are arranged in an orderly matrix to obtain the communication guarantee priority matrix, which provides a priority basis for risk optimization in subsequent resource adjustment.

[0022] Step S500: Based on the communication guarantee priority matrix, perform multi-dimensional communication coupling risk optimization on the Polar code resource adjustment domain according to the multiple user channels, and establish a multi-level resource adjustment optimization architecture.

[0023] Specifically, based on the communication assurance priority matrix, and focusing on the actual communication needs of multiple user channels, the Polar code resource adjustment domain is optimized for multi-dimensional communication coupling risks from three core dimensions: communication quality, communication delay, and communication security, thereby constructing a multi-level resource adjustment optimization architecture. The specific process is as follows: First, in the communication quality dimension, based on the guarantee priority of each user channel in the communication guarantee priority matrix, resource adjustment schemes that can reduce the coupling impact of multi-channel quality accidents are selected from the Polar code resource adjustment domain. For example, to avoid the quality problems of high-priority channels from affecting other channels, such as prioritizing the code rate configuration of high-priority channels to improve their anti-interference capability, the schemes that meet the requirements are integrated to form the first resource adjustment optimization layer. Second, in the communication delay dimension, based on the guarantee priority matrix, adjustment schemes that can balance the delay of multiple channels and avoid delay superposition are selected. For example, to allocate better time slots and shorter code lengths for high-priority, low-latency demand channels, the second resource adjustment optimization layer is formed. Then, in the communication security dimension, based on priority ranking, adjustment schemes that can enhance the overall security protection capability of multiple channels and reduce the transmission of security risks are retained. For example, to strengthen the encryption-related Polar code resource configuration for high-priority channels, the third resource adjustment optimization layer is established. Finally, the first, second, and third resource adjustment optimization layers are connected in parallel to form a multi-level resource adjustment optimization architecture that can simultaneously cover quality, delay, and security risks and adapt to guarantee priorities.

[0024] Step S600: Perform multi-dimensional evolutionary joint optimization of the multi-level resource adjustment optimization architecture according to the Polar code resource adjustment domain to obtain the Polar code resource adjustment result, and combine it with the star flash module to optimize the Polar code resource allocation of the multiple user channels.

[0025] Specifically, based on the Polar code resource adjustment domain, evolutionary optimization is carried out sequentially for the first, second, and third resource adjustment optimization layers in the multi-level resource adjustment optimization architecture, corresponding to the dimensions of communication quality, communication latency, and communication security, to expand the resource adjustment space of each dimension: For the first resource adjustment optimization layer, the differences between it and the Polar code resource adjustment domain are analyzed first, and the first resource adjustment difference feature group is extracted. The first adjustment evolutionary feature group is generated through random mutation. Based on this feature group, evolutionary adjustment is performed on the Polar code resource adjustment domain to generate the first resource adjustment evolutionary decision group. Then, the decision group is optimized for communication quality coupling risk by combining the communication assurance priority matrix, expanding to form a first resource adjustment space covering more high-quality solutions; Using the same logic, evolutionary optimization is performed on the second and third resource adjustment optimization layers respectively to generate second and third resource adjustment spaces that adapt to communication latency and communication security requirements. Subsequently, the intersection of the first, second, and third resource adjustment spaces is identified, and a fourth resource adjustment space that simultaneously meets the basic requirements of quality, latency, and security is selected. Based on preset communication quality coupling risk weights, communication latency coupling risk weights, and communication security coupling risk weights, the weight configuration is adapted to the resource optimization priorities of multi-user scenarios. A joint communication risk assessment is performed on all schemes within the fourth resource adjustment space, calculating the comprehensive risk value of each scheme across the three dimensions. The scheme with the lowest comprehensive risk and that meets the high-priority channel guarantee requirements is selected as the Polar code resource adjustment result. Finally, the Polar code resource adjustment result is synchronized to the StarSpark module. The StarSpark module then uses parameters such as code rate configuration, code block length, and power allocation from the result to precisely allocate and dynamically adjust Polar code resources for multiple user channels. For example, short code length configurations are implemented for high-priority and latency-sensitive channels, and high error correction code rate schemes are enabled for channels with high quality risk, ultimately achieving optimized allocation of Polar code resources in multi-user scenarios.

[0026] In one possible implementation, step S200 further includes: Step S210: Extract the h-th user channel based on the multiple user channels, and monitor the h-th user channel in real time to obtain the h-th channel monitoring sequence, where h is a positive integer.

[0027] Step S220: Based on the h-th channel monitoring sequence, perform communication quality incident feature deduction on the h-th user channel to obtain the h-th communication quality incident deduction result.

[0028] Step S230: Based on the h-th channel monitoring sequence, perform communication delay incident feature deduction on the h-th user channel to obtain the h-th communication delay incident deduction result.

[0029] Step S240: Deduce the characteristics of communication security accidents for the h-th user channel based on the h-th channel monitoring sequence, and obtain the h-th communication security accident deduction result.

[0030] Step S250: Construct the h-th communication accident portrait based on the h-th communication quality accident deduction result, the h-th communication delay accident deduction result, and the h-th communication security accident deduction result, and add the h-th communication accident portrait to the communication accident portrait group.

[0031] Specifically, first, among the multiple user channels generated by the XingFlash module, any target channel is extracted according to the principle of one-by-one analysis and defined as the h-th user channel, where h is a positive integer, used to distinguish different user channels to ensure that each channel can be analyzed separately. Subsequently, start the channel real-time monitoring module supporting the XingFlash module, and continuously collect the key operating parameters of the h-th user channel. The monitoring content covers core indicators such as the signal strength change, data transmission rate fluctuation, packet loss rate, transmission delay value, delay jitter amplitude, and the real-time state of the data encryption link of this channel. Record the specific values and change trends of each parameter at a fixed time interval (such as millisecond level). Structurally organize all the collected parameter data in the order of monitoring time to form a sequence data containing timestamp, parameter type, and parameter value, and this sequence data is the h-th channel monitoring sequence that can completely reflect the real-time operating state of the h-th user channel.

[0032] Retrieve the historical channel quality accident set, and use the accident tree tracing method to sort out the occurrence causes of past quality accidents, such as signal attenuation, data packet loss, transmission interruption, etc., the development path and the variation law of associated parameters, to form a channel quality accident tracing sequence set containing various types of quality accident characteristics; then, use the adversarial sample generator to perform data perturbation on this tracing sequence set to simulate complex scenarios such as abnormal fluctuations of channel parameters and superposition of interference signals, and generate a quality accident tracing perturbation sequence set to improve the adaptability of the subsequent model to extreme working conditions; subsequently, use the channel quality accident tracing sequence set and the quality accident tracing perturbation sequence set as training data respectively to train the first communication quality accident deduction model and the second communication quality accident deduction model, and optimize the model parameters through the adversarial training of the two to generate a third communication quality accident deduction model with both the ability to fit conventional scenarios and the ability to generalize abnormal scenarios; finally, input the obtained h-th channel monitoring sequence, including real-time parameters such as signal strength and packet loss rate, into the third communication quality accident deduction model. The model predicts the possible types of quality accidents that may occur in the h-th user channel, such as mild packet loss, severe signal attenuation, occurrence probability, and influence range by comparing the similarity between the monitoring sequence and the historical accident characteristics, and finally outputs the h-th communication quality accident deduction result.

[0033] Based on historical channel delay incident sets, including incident records such as delay timeouts and excessive delay fluctuations, an incident tree tracing is performed. Causal analysis is used to analyze the triggering factors of delay incidents, such as the correlation between channel load, signal interference intensity, and incident outcomes, generating a channel delay incident tracing sequence set. Each sequence contains time-series data of triggering factor parameters and the corresponding delay incident level. Next, an adversarial example generator is used to slightly perturb the triggering factor parameters in the tracing sequence set, such as adding ±5% random perturbation to the channel load data, generating a quality incident tracing perturbation sequence set to enhance the model's robustness to anomalous data. Finally, using the tracing sequence set as training data, a Long Short-Term Memory (LSTM) network is used to train the first communication delay incident inference model, learning normal data... Based on the inference patterns of delay accidents under different distributions, and using a set of perturbation sequences as training data, a second communication delay accident inference model is trained using a long short-term memory network to learn the inference logic under abnormal data distributions. Then, the two models are trained adversarially. By minimizing the inference error of the first model and maximizing the interference error of the second model on the first model, the model parameters are dynamically adjusted, and finally fused to generate a third communication delay accident inference model. Finally, the real-time acquired h-th channel monitoring sequence, including real-time channel load, interference intensity and other parameters, is input into the third model. The model outputs the probability of delay accidents occurring in the h-th user channel in the future within a preset time period, the estimated delay exceedance duration, and other information, which is the h-th communication delay accident inference result.

[0034] A historical set of communication security incidents is retrieved, encompassing records of past incidents in multi-user scenarios, including data tampering, unauthorized access, and encrypted link failures on user channels. This set also includes security-related parameters of the channel at the time of the incident, such as the encryption algorithm's running status, access permission verification logs, and data integrity verification results. An incident tree tracing method is used to analyze the triggering factors, abnormal parameter patterns, and propagation paths of various security incidents, forming a channel security incident tracing sequence set. Next, an adversarial sample generator is used to perturb the channel security incident tracing sequence set, simulating malicious attacks such as brute-force attacks, man-in-the-middle attacks, device security vulnerability triggers, and environmental interference causing encryption failures. This generates a security incident tracing perturbation sequence set to improve the subsequent model's ability to identify extreme security risk scenarios. Subsequently, using the channel security incident tracing sequence set as training data, a Long Short-Term Memory (LSTM) network model was constructed and trained as the first communication security incident inference model to learn the temporal evolution law of security incidents under normal data distribution. Simultaneously, using the perturbation sequence set as training data, a second communication security incident inference model was trained based on the same LSM network structure to learn the incident inference logic under abnormal data distribution. Then, the first and second models were subjected to adversarial training, with the goal of minimizing the security incident prediction error of the first model and maximizing the prediction interference of the second model on the first model. The model parameters were iteratively adjusted, and finally, a third communication security incident inference model with stronger generalization ability was generated through fusion. Finally, the h-th channel monitoring sequence, including real-time encryption status, access request timing, and interference signal strength, was input into the third communication security incident inference model. The model outputs the probability of a security incident occurring in the h-th user channel within a preset time period, the estimated incident type, and the degree of impact, i.e., the h-th communication security incident inference result.

[0035] Using the h-th communication quality incident simulation results, h-th communication delay incident simulation results, and h-th communication security incident simulation results as data sources, the construction and integration of the h-th communication incident profile is carried out: First, the simulation results of the three types of incidents are analyzed in a structured manner. From the quality incident simulation results, incident types, such as signal attenuation, data packet loss, probability of occurrence, and degree of impact, are extracted. From the delay incident simulation results, delay incident types, such as delay exceeding threshold, delay mutation, expected duration, and scope of impact on business, are extracted. From the security incident simulation results, security threat types, such as data tampering, unauthorized access, risk level, and weak points in protection, are extracted. Next, following the pre-defined profile construction specifications, the parsed information is categorized and integrated to form a structured data framework containing incident dimensions, incident details, and risk parameters. This framework clarifies the overall incident risk of the h-th user channel in terms of quality, delay, and security, thereby constructing a h-th communication incident profile that comprehensively reflects the incident characteristics of the channel. Finally, the constructed h-th communication incident profile is marked by user channel number and h value and added to an initially empty communication incident profile set. Steps S210-S250 are then repeated to construct incident profiles for other user channels and incorporate them into the set one by one, ultimately forming a communication incident profile group covering all target user channels.

[0036] In one possible implementation, step S220 further includes: Step S221: Perform fault tree tracing based on the historical channel quality incident set to obtain a channel quality incident tracing sequence set.

[0037] Step S222: Perturb the channel quality incident tracing sequence set according to the adversarial sample generator to obtain the quality incident tracing perturbation sequence set.

[0038] Step S223: Train a first communication quality incident inference model based on the channel quality incident tracing sequence set, and train a second communication quality incident inference model based on the quality incident tracing disturbance sequence set.

[0039] Step S224: Perform adversarial training based on the first communication quality incident simulation model and the second communication quality incident simulation model to generate a third communication quality incident simulation model.

[0040] Step S225: Input the h-th channel monitoring sequence into the third communication quality incident simulation model to generate the h-th communication quality incident simulation result.

[0041] Specifically, the system first retrieves a pre-set historical channel quality incident set from the file. This set contains records of communication quality-related incidents that occurred on each user channel in scenarios where the StarSpark module is connected to multiple user devices. It covers typical quality incident types such as signal attenuation, data packet loss, sudden drop in transmission rate, and abnormal signal-to-noise ratio. Each record contains real-time channel parameters at the time of the incident, such as signal strength values, packet loss rate change curves, transmission rate fluctuation data, incident trigger time, incident duration, and incident impact range. Subsequently, an in-depth analysis of the historical channel quality incident set was conducted using the fault tree tracing method. Taking each type of quality incident as the top event, the direct causes leading to the incident were broken down layer by layer, such as signal interference and insufficient equipment power, and indirect causes, such as multi-channel resource competition and environmental electromagnetic interference. A complete logical chain of cause parameters - incident symptoms - incident occurrence - incident development was identified. The parameter change time sequence and cause correlation corresponding to each incident were transformed into structured sequence data in chronological order, including timestamps, parameter types, parameter values, and incident stage identifiers. The structured sequence data of all incidents were summarized and integrated to finally form a channel quality incident tracing sequence set that clearly reflects the evolution law and parameter correlation characteristics of quality incidents.

[0042] Using the acquired channel quality incident tracing sequence set as the processing object, data perturbation operations are carried out based on an adversarial example generator to expand the coverage of sequence scenarios. First, the core parameter dimensions in the channel quality incident tracing sequence set are identified, including key parameters directly related to communication quality incidents such as signal strength fluctuation values, data packet loss rate changes, instantaneous peak transmission rate, and dynamic range of signal-to-noise ratio. These parameters are the core indicators reflecting channel quality anomalies and are also the key targets of perturbation operations. Subsequently, the adversarial example generator was activated. Based on the actual communication environment characteristics of the StarSpark module connection in a multi-user scenario, reasonable perturbation rules were set: For the signal strength parameter, scenarios such as sudden electromagnetic interference and signal superposition from multiple devices were simulated, and random fluctuations of ±5% to ±15% were superimposed on the original sequence parameter values. The fluctuation range was determined according to the communication performance threshold of the StarSpark module. For the packet loss rate parameter, scenarios such as sudden increases in network load and temporary preemption of channel resources were simulated, and abnormal data points with short-term surges were inserted into the original packet loss rate sequence, such as an instantaneous increase from the normal 1% packet loss rate to 8% to 12%. For the transmission rate and signal-to-noise ratio parameters, corresponding perturbation amplitudes were also set in combination with the actual possible interference scenarios to ensure that the perturbed parameters not only conform to the physical laws of communication but also cover extreme or abnormal conditions not included in the original sequence. Finally, each sequence in the channel quality incident tracing sequence set was perturbed according to the above rules to generate a new sequence set containing various potential abnormal scenarios, namely the quality incident tracing perturbation sequence set.

[0043] For the training of the first and second communication quality incident inference models, a long short-term memory network algorithm adapted to the characteristics of sequence data was used. The training was carried out in combination with the temporal evolution characteristics of channel quality incidents in multi-user scenarios. First, the training data was processed. The channel quality incident tracing sequence set and the quality incident tracing disturbance sequence set were divided into training subset and validation subset in a 7:3 ratio. The input features of each sequence were set as time-series data of signal strength, packet loss rate, transmission rate and signal-to-noise ratio, with a time step of 10ms. The output label was set as the corresponding quality incident type and incident occurrence probability. When training the first communication quality incident simulation model, a training subset of the channel quality incident tracing sequence set is used as input to initialize a long short-term memory network structure containing two hidden layers, each with 64 neurons. The activation function is ReLU. The model's incident prediction results for the sequence data are calculated through forward propagation, and the error between the prediction results and the actual incident labels is calculated using the cross-entropy loss function. The Adam optimizer is used with a learning rate of 0.001 to update the network weights through backpropagation. After each round of training, the model's prediction accuracy is verified using a validation subset. Training is stopped when the accuracy fluctuation of the validation set is less than 0.5% for five consecutive rounds and the loss value converges stably, thus obtaining the first communication quality incident simulation model. When training the second communication quality incident simulation model, the same long short-term memory network structure and hyperparameter settings as the first model are used. Only the input data is replaced with a training subset of the quality incident tracing perturbation sequence set. The training is carried out through the same iterative process of forward propagation, loss calculation, and back optimization. The generalization ability of the model is verified with the corresponding validation subset until the model's incident prediction accuracy on the perturbation sequence data reaches the standard and the loss converges. Finally, a second communication quality incident simulation model that can adapt to extreme and abnormal scenarios is generated.

[0044] Based on the first and second communication quality incident prediction models that have been trained, an adversarial training framework is used to optimize the models and generate a third communication quality incident prediction model that can generalize to both normal and abnormal scenarios. First, an adversarial training system is constructed: the first and second models are used as predictors for normal and abnormal scenarios, respectively. They share an input layer, receiving channel monitoring sequence data, but maintain independent hidden and output layers. The training objective is to make the two models complementary in their prediction results. The first model needs to accurately identify the characteristics of normal quality incidents, while the second model needs to accurately capture the characteristics of abnormal quality incidents. Simultaneously, mutual feedback is used to correct and reduce prediction bias. During training, a mixed sample is randomly selected from the channel quality incident tracing sequence set and the quality incident tracing perturbation sequence set, containing 60% normal sequences and 40% perturbation sequences as input data. The mixed sample is simultaneously input into two models to obtain the normal incident prediction results of the first model and the abnormal incident prediction results of the second model. The total loss value of the prediction results of the two models and the real incident label is calculated using the cross-entropy loss function. For normal sequence samples, the focus is on optimizing the prediction accuracy of the first model, and for perturbation sequence samples, the focus is on optimizing the prediction accuracy of the second model. The hidden layer parameters of the two models are updated synchronously through backpropagation using the Adam optimizer, so that the first model is more accurate in predicting normal scenarios, the second model is more sensitive in predicting abnormal scenarios, and the prediction results of the two models can be mutually calibrated for fuzzy boundary scenarios. After every 10 rounds of adversarial training, an additional 20% of data is extracted from the historical channel quality incident set using an independent test set. This test set includes both routine and abnormal scenarios to verify the joint prediction accuracy of the two models. When the joint prediction accuracy consistently exceeds 92% and shows no significant improvement for five consecutive rounds, the adversarial training is stopped. Finally, the parameters and prediction logic of the two models are merged to generate a third communication quality incident inference model. After receiving a channel monitoring sequence, this model can automatically identify the scenario type of the sequence and call the appropriate prediction module. For routine scenarios, the model calls the core parameters of the original first model, and for abnormal scenarios, it calls the core parameters of the original second model, outputting more comprehensive and accurate quality incident inference results.

[0045] The acquired channel h monitoring sequence, containing time-series parameters such as real-time signal strength, packet loss rate, transmission rate, and signal-to-noise ratio of the h-th user channel, is structured and arranged in the order of monitoring time as input data and imported into the third communication quality incident simulation model generated by adversarial training. This model first extracts features from the input channel h monitoring sequence, automatically identifying the changing trends of parameters in the sequence, such as whether the signal strength continuously weakens or whether the packet loss rate exhibits abnormal fluctuations. Based on the sequence features, it matches the pre-stored rules for identifying normal / abnormal scenarios to determine the communication scenario type of the current sequence. If identified as a normal scenario, the model calls the core parameters of the original first communication quality incident simulation model, combines them with historical normal quality incident feature sequences, calculates the feature similarity between the current monitoring sequence and various types of normal quality incidents, and outputs the probability of the corresponding incident occurring. If identified as an abnormal scenario, it calls the core parameters of the original second communication quality incident simulation model, compares the quality incident characteristics under extreme scenarios, and generates a type judgment and risk level assessment of the abnormal quality incident. Finally, the model integrates the scene identification results, accident type judgment, occurrence probability, risk level, and impact range on the h-th user channel-bearing services, such as whether it affects real-time data transmission, and outputs them in the form of a structured report, thus forming a complete h-th communication quality accident simulation result.

[0046] In one possible implementation, step S500 further includes: Step S510: Based on the communication guarantee priority matrix, perform communication quality coupling risk optimization on the Polar code resource adjustment domain according to the multiple user channels to obtain the first resource adjustment optimization layer.

[0047] Step S520: Based on the communication guarantee priority matrix, optimize the communication delay coupling risk of the Polar code resource adjustment domain according to the multiple user channels to obtain the second resource adjustment optimization layer.

[0048] Step S530: Based on the communication guarantee priority matrix, optimize the communication security coupling risk of the Polar code resource adjustment domain according to the multiple user channels to obtain the third resource adjustment optimization layer.

[0049] Step S540: Connect the first resource adjustment and optimization layer, the second resource adjustment and optimization layer, and the third resource adjustment and optimization layer in parallel to generate the multi-level resource adjustment and optimization architecture.

[0050] Specifically, based on the communication assurance priority matrix, and focusing on the communication quality requirements of multiple user channels, the first resource adjustment optimization layer is obtained by optimizing the communication quality coupling risk in the Polar code resource adjustment domain. First, the U-th scheme for Polar code resource adjustment is extracted one by one from the Polar code resource adjustment domain. Each scheme includes resource parameters related to communication quality, such as code rate configuration and error correction capability parameters. For each U-th scheme, Polar code resource allocation is fitted to multiple user channels, generating a U-th resource adjustment fitting dataset that reflects the quality performance of each channel after the scheme is applied. Next, based on the U-th resource adjustment fitting dataset, communication quality risk is predicted for each user channel, resulting in a U-th communication quality risk sequence containing the probability and risk level of quality incidents for each channel. Then, based on the communication assurance priority matrix, the proportion is calculated to obtain the priority assurance entropy weight sequence, where higher priority channels correspond to higher entropy weight values. Finally, using the priority assurance entropy weight sequence as weight, the U-th communication quality risk sequence is weighted to obtain the U-th communication quality coupling risk coefficient, which reflects the overall correlation of quality risks across multiple channels. Finally, the U-th communication quality coupling risk coefficient is compared with the preset communication quality coupling risk threshold. If the coefficient is less than the threshold, it indicates that the scheme can effectively reduce the multi-channel quality coupling risk while ensuring the quality of high-priority channels. Therefore, the U-th Polar code resource adjustment scheme is added to the candidate set. After all schemes have been optimized, all qualified candidate schemes are integrated to form the first resource adjustment optimization layer for communication quality coupling risk management.

[0051] The U-th scheme for Polar code resource adjustment is extracted sequentially from the Polar code resource adjustment domain, where U is a positive integer. Each scheme includes resource parameters directly related to communication delay, such as code block length, time slot allocation, and modulation scheme. Using a delay fitting algorithm, the U-th scheme is applied to multiple user channels to simulate Polar code resource allocation. The transmission delay, delay jitter, and other indicators of each channel after the scheme application are recorded, forming the U-th resource adjustment fitting dataset. Next, a delay risk prediction model is constructed using a Long Short-Term Memory (LSTM) network algorithm. The delay-related indicators of each channel in the U-th resource adjustment fitting dataset are used as input. The model learns the correlation between historical delay incidents and real-time delay parameters, outputting prediction results such as the probability of delay incidents and the duration of delay exceeding the threshold for each user channel. These results are integrated to form the U-th communication delay risk sequence. Finally, based on the communication guarantee priority matrix, the priority guarantee ratio of each user channel is calculated using the entropy weight method, generating a priority guarantee entropy weight sequence. Higher priority channels correspond to higher entropy weights, ensuring that their delay requirements are given priority consideration. Subsequently, using the priority guarantee entropy sequence as weight, the U-th communication delay risk sequence is weighted and summed to obtain the U-th communication delay coupling risk coefficient. This coefficient comprehensively reflects the superposition and propagation degree of delay risks among multiple channels after the application of the scheme. Finally, the U-th communication delay coupling risk coefficient is compared with the preset communication delay coupling risk threshold. If the coefficient is less than the threshold, it indicates that the scheme can effectively reduce the multi-channel delay coupling risk while meeting the low delay requirements of high-priority channels. It is then included in the candidate scheme set. After all schemes have been optimized, the candidate schemes are integrated to form the second resource adjustment optimization layer.

[0052] The U-th scheme for Polar code resource adjustment is extracted sequentially from the Polar code resource adjustment domain, where U is a positive integer. Each scheme includes parameters directly related to communication security, such as the encrypted enhanced code structure, the proportion of security verification resources, and the code resource configuration associated with the key update cycle. Using a security coupling simulation algorithm, the U-th scheme is simultaneously applied to multiple user channels for Polar code resource allocation simulation. Security indicators such as encrypted link stability, data integrity verification pass rate, and unauthorized access interception rate are recorded for each channel after the scheme application, forming the U-th resource adjustment fitting dataset. Next, a security risk prediction model based on a convolutional neural network is used. The time-series data of security indicators for each channel in the U-th resource adjustment fitting dataset are used as input. The model learns the mapping relationship between historical security incidents and real-time security parameters, outputting prediction results such as the probability of security incidents and the risk level of security vulnerabilities for each user channel, integrating them to form the U-th communication security risk sequence. Then, based on the communication assurance priority matrix, the security assurance priority proportion of each user channel is calculated using the entropy weight method. Higher priority channels, carrying important services, correspond to a higher proportion, generating a priority assurance entropy weight sequence. Subsequently, using the priority protection entropy sequence as weight, the U-th communication security risk sequence is weighted and summed to obtain the U-th communication security coupling risk coefficient. This coefficient comprehensively reflects the transmission probability and superposition degree of security risks between multiple channels after the application of the scheme. Finally, the U-th communication security coupling risk coefficient is compared with the preset communication security coupling risk threshold. If the coefficient is less than the threshold, it indicates that the scheme can effectively reduce the hidden dangers of multi-channel security risk coupling while strengthening the security protection of high-priority channels. It is included in the candidate scheme set. After all schemes have completed the optimization, the candidate schemes are integrated to form the third resource adjustment optimization layer.

[0053] Based on the obtained first, second, and third resource adjustment optimization layers, a multi-layered resource adjustment optimization architecture is generated using a parallel connection architecture design logic. First, independent input interfaces and data processing channels are configured for the three optimization layers to ensure that each layer can synchronously receive the original resource adjustment scheme data from the Polar code resource adjustment domain, and that each layer does not interfere with each other during risk optimization calculations. The first resource adjustment optimization layer can independently assess the quality coupling risk of the scheme, the second resource adjustment optimization layer simultaneously performs delay coupling risk analysis, and the third resource adjustment optimization layer completes the security coupling risk judgment in parallel, avoiding the impact of single-level operation delays on the overall optimization efficiency. Simultaneously, a cross-layer data interaction mechanism is constructed, enabling the three optimization layers to share priority parameters related to the communication guarantee priority matrix in real time while operating independently. These parameters include the quality, delay, and security requirement thresholds for high-priority user channels, ensuring that each layer uses the priority matrix as a unified guide during the risk optimization process, guaranteeing that the resource requirements of high-priority channels are met first. Finally, the outputs of the three optimization layers are integrated to form a unified architecture output interface, which can synchronously output the risk assessment results of each layer for the same Polar code resource adjustment scheme, and finally generate a multi-level resource adjustment optimization architecture that has multi-dimensional risk management capabilities, high computational efficiency and adaptability to priority requirements.

[0054] In one possible implementation, step S510 further includes: Step S511: Extract the U-th Polar code resource adjustment scheme based on the Polar code resource adjustment domain, where U is a positive integer.

[0055] Step S512: Fit the Polar code resource allocation to the multiple user channels according to the U-th scheme of Polar code resource adjustment to obtain the U-th resource adjustment fitting dataset.

[0056] Step S513: Based on the U-th resource adjustment fitting dataset, perform communication quality risk prediction for each user channel to obtain the U-th communication quality risk sequence.

[0057] Step S514: Calculate the proportion based on the communication guarantee priority matrix to obtain the priority guarantee entropy reorder sequence.

[0058] Step S515: Perform a weighted calculation on the U-th communication quality risk sequence according to the priority guarantee entropy reordering sequence to obtain the U-th communication quality coupling risk coefficient.

[0059] Step S516: If the U-th communication quality coupling risk coefficient is less than the communication quality coupling risk threshold, add the U-th Polar code resource adjustment scheme to the first resource adjustment optimization layer.

[0060] Specifically, using the obtained Polar code resource adjustment domain as the data source, all Polar code resource adjustment schemes stored within this domain are extracted one by one. Each extracted scheme corresponds to a complete set of Polar code resource configuration parameters, covering core aspects directly related to communication quality optimization, such as code rate configuration, error correction capability parameters, and power allocation ratios. Each extracted scheme is defined as the U-th Polar code resource adjustment scheme, where U is a positive integer used to uniquely identify different resource adjustment schemes, ensuring that subsequent operations such as fitting and risk prediction for each scheme can be accurately performed.

[0061] Based on the extracted Polar code resource adjustment scheme U, a Polar code resource allocation fitting operation was performed on multiple user channels connected to the star-speed module. During the fitting process, considering the current communication status of each user channel, such as data transmission requirements and basic signal strength, resource parameters from the Polar code resource adjustment scheme U, including code rate configuration, error correction capability parameters, and power allocation ratio, were matched to each user channel one by one, and the resource allocation effect was simulated. Simultaneously, real-time monitoring and fitting data related to communication quality for each user channel under this scheme adaptation were recorded, including key indicators such as signal integrity changes, packet loss rate fitting curves, and signal-to-noise ratio dynamic trends. These monitoring and fitting data for all user channels were organized into a structured dataset according to channel number, ultimately forming the U-th resource adjustment fitting dataset.

[0062] A communication quality risk prediction algorithm based on Long Short-Term Memory (LSTM) networks is adopted. Using the U-th resource adjustment fitting dataset as input, communication quality risk prediction is performed for each user channel. First, the monitoring fitting data of each user channel in the U-th resource adjustment fitting dataset, such as signal integrity changes, packet loss rate fitting curves, and signal-to-noise ratio dynamic trends, undergoes time-series preprocessing. The data is converted into a time-series feature matrix with uniform dimensions at a fixed time step, where each row corresponds to the quality parameters of a single user channel at consecutive time steps. Then, the LSM network structure is initialized, containing an input layer, two hidden layers, and an output layer. Each hidden layer... The network consists of 64 neurons, with ReLU as the activation function. The preprocessed temporal feature matrix is ​​input into the network, and the predicted quality risk value of each user channel under the U-th scheme of Polar code resource adjustment is calculated through forward propagation. During the network training phase, historical channel quality incident data, including the temporal parameters at the time of the incident and the corresponding risk level optimization parameters, are used to accurately learn the correlation between quality parameter changes and risk. Finally, the network outputs the communication quality risk prediction coefficient for each user channel; the larger the coefficient value, the higher the risk. These coefficients are arranged sequentially according to the user channel number to form the U-th communication quality risk sequence.

[0063] The communication assurance priority value for each user channel is extracted from the communication assurance priority matrix. These values ​​are calculated based on the service type priority and service protocol priority of each channel, directly reflecting the importance of each channel's assurance. Then, the sum of the communication assurance priorities of all user channels within the communication assurance priority matrix is ​​calculated and used as the denominator for the percentage calculation. Next, for each user channel, its corresponding communication assurance priority value is used as the numerator, and divided by the above sum to obtain the priority assurance entropy weight of that channel, i.e., priority assurance entropy weight = communication assurance priority of that channel / sum of communication assurance priorities of all channels within the matrix. Finally, the priority assurance entropy weights of all channels are arranged sequentially according to the user channel number, forming a priority assurance entropy weight sequence containing multiple priority assurance entropy weights.

[0064] The risk prediction coefficient of each user channel in the U-th communication quality risk sequence corresponds one-to-one with the priority guarantee entropy weight of that channel in the priority guarantee entropy weight sequence, ensuring that the weights can be accurately matched to the corresponding risk data. Subsequently, a weighted calculation method of multiplying and summing each item is adopted: the communication quality risk prediction coefficient of each user channel is multiplied by its corresponding priority guarantee entropy weight to obtain the weighted risk value of that channel; then the weighted risk values ​​of all user channels are accumulated, and the final accumulated result is the U-th communication quality coupling risk coefficient.

[0065] The logic for setting the communication quality coupling risk threshold is clearly defined. This threshold is determined by combining the communication quality standards of the Polar code module in multi-user scenarios, the minimum quality requirements of high-priority user channels, and historical experience in multi-channel quality risk management. It is used to determine whether the multi-channel quality coupling risk is within an acceptable range after the application of the scheme. Subsequently, the U-th communication quality coupling risk coefficient is compared with this threshold: if the U-th communication quality coupling risk coefficient is less than the communication quality coupling risk threshold, it means that when the Polar code resource adjustment U-th scheme is applied to multiple user channels, it can not only ensure the stable communication quality of high-priority channels, but also effectively control the superposition and transmission of quality risks between multiple channels, which meets the core requirements of the first resource adjustment optimization layer for low quality coupling risk. Therefore, this scheme is included and added to the first resource adjustment optimization layer; if the U-th communication quality coupling risk coefficient is greater than or equal to the communication quality coupling risk threshold, it indicates that the application of the scheme may cause the multi-channel quality risk to exceed the standard. Therefore, this scheme is removed and not included in the first resource adjustment optimization layer.

[0066] In one possible implementation, step S600 further includes: Step S610: Perform evolutionary optimization of the first resource adjustment optimization layer according to the Polar code resource adjustment domain to obtain the first resource adjustment space.

[0067] Step S620: Perform evolutionary optimization of the second resource adjustment optimization layer according to the Polar code resource adjustment domain to obtain the second resource adjustment space.

[0068] Step S630: Perform evolutionary optimization of the third resource adjustment optimization layer according to the Polar code resource adjustment domain to obtain the third resource adjustment space.

[0069] Step S640: Perform intersection identification on the first resource adjustment space, the second resource adjustment space and the third resource adjustment space to obtain the fourth resource adjustment space.

[0070] Step S650: Perform joint risk assessment and optimization of the fourth resource adjustment space based on the communication quality coupling risk weight, communication delay coupling risk weight, and communication security coupling risk weight, and generate the Polar code resource adjustment result.

[0071] Specifically, the resource allocation differences between the first resource adjustment optimization layer and the Polar code resource adjustment domain are analyzed to extract a first resource adjustment difference feature group that reflects the direction of quality risk optimization and is not fully covered in the existing optimization layer. Then, the difference feature group is randomly mutated according to a preset mutation rule to generate a first adjustment evolution feature group containing more possibilities for quality risk management, thus broadening the optimization dimension of the scheme. Subsequently, the resource allocation in the Polar code resource adjustment domain is evolutionarily adjusted according to the first adjustment evolution feature group to simulate the resource allocation effect under different feature combinations, generating a first resource adjustment evolution decision group. Then, based on the communication assurance priority matrix, communication quality coupling risk optimization is performed on each scheme in the first resource adjustment evolution decision group, and schemes with coupling risk coefficients less than the quality risk threshold are selected to form a fourth resource adjustment optimization layer. Finally, the schemes in the fourth resource adjustment optimization layer are integrated with the schemes in the original first resource adjustment optimization layer, and schemes with duplicates and poor risk management effects are eliminated, ultimately generating a first resource adjustment space with more comprehensive coverage and better quality risk management capabilities.

[0072] The resource configuration differences between the second resource adjustment optimization layer and the Polar code resource adjustment domain are analyzed to extract second resource adjustment difference feature groups that reflect the direction of delay risk optimization and are not fully covered by the existing optimization layer. These feature groups include differences in key parameters related to delay optimization, such as code block length and time slot allocation. Then, the second resource adjustment difference feature groups are randomly mutated according to preset mutation rules to generate a second adjustment evolution feature group that covers more possibilities for delay risk management, thus broadening the exploration scope of delay optimization schemes. Subsequently, the resource configuration in the Polar code resource adjustment domain is evolutionarily adjusted according to the second adjustment evolution feature group to simulate the delay optimization effect under different feature combinations, generating a second resource adjustment evolution decision group. Then, based on the communication guarantee priority matrix, the communication delay coupling risk optimization is performed on the second resource adjustment evolution decision group for multiple user channels, and schemes with delay coupling risk coefficients less than the delay risk threshold are selected to form the fifth resource adjustment optimization layer. Finally, the schemes in the fifth resource adjustment optimization layer are integrated with the schemes in the original second resource adjustment optimization layer, and schemes that are duplicated and have poor delay risk management effects are eliminated, ultimately generating a second resource adjustment space with more comprehensive coverage and better delay risk management capabilities.

[0073] The resource allocation differences between the third resource adjustment optimization layer and the Polar code resource adjustment domain are analyzed to extract third resource adjustment difference feature groups that reflect the direction of security risk optimization and are not fully covered by the existing optimization layer. These feature groups include key parameter differences related to security optimization, such as the encryption enhancement code structure and the proportion of security verification resources. Then, the third resource adjustment difference feature groups are randomly mutated according to preset mutation rules to generate third adjustment evolution feature groups that cover more possibilities for security risk management, thus broadening the scope of security optimization scheme exploration. Subsequently, the Polar code resource adjustment domain is adjusted based on the third adjustment evolution feature groups. The resource allocation within the system is evolved and adjusted to simulate the security optimization effect under different feature combinations, generating a third resource adjustment evolutionary decision group. Then, based on the communication assurance priority matrix, the third resource adjustment evolutionary decision group is optimized for communication security coupling risks for multiple user channels, and schemes with security coupling risk coefficients less than the security risk threshold are selected to form a sixth resource adjustment optimization layer. Finally, the schemes in the sixth resource adjustment optimization layer are integrated with the schemes in the original third resource adjustment optimization layer, and schemes that are duplicated and have poor security risk control effects are eliminated, ultimately generating a third resource adjustment space with more comprehensive coverage and better security risk control capabilities.

[0074] Using the first, second, and third resource adjustment spaces as the operational objects, an intersection identification operation is performed to obtain a fourth resource adjustment space. The first resource adjustment space contains high-quality solutions focusing on communication quality coupling risk management; the second resource adjustment space covers solutions meeting communication delay coupling risk management requirements; and the third resource adjustment space includes solutions conforming to communication security coupling risk management standards. First, through a solution parameter comparison mechanism, the core configuration parameters of Polar code resource adjustment solutions in each of the three spaces are extracted, such as code rate, code block length, and encryption structure, to establish a parameter feature library for each solution. Then, the parameter feature libraries of the three spaces are cross-matched to select solutions whose core configuration parameters exist in all three feature libraries. These solutions meet the quality risk management requirements of the first resource adjustment space, the delay risk management standards of the second resource adjustment space, and the security risk management conditions of the third resource adjustment space. Finally, all selected co-occurring solutions are integrated to form a fourth resource adjustment space with multi-dimensional risk collaborative management capabilities.

[0075] Based on the obtained fourth resource adjustment space, the core object is the set of Polar code resource adjustment schemes that simultaneously meet the requirements of communication quality, delay, and security coupling risk control. Combined with the preset communication quality coupling risk weight, communication delay coupling risk weight, and communication security coupling risk weight, the weights of the three are set according to the degree of impact of each dimension of risk on the communication stability of the StarSpark module in multi-user scenarios, and the total weight is 1. A joint communication risk assessment optimization operation is carried out to generate Polar code resource adjustment results. First, for each Polar code resource adjustment scheme within the fourth resource adjustment space, the corresponding risk assessment model is invoked to calculate the communication quality coupling risk coefficient, communication delay coupling risk coefficient, and communication security coupling risk coefficient of the scheme under the current resource configuration. Next, following the formula: Communication Joint Risk Evaluation Coefficient = Communication Quality Coupling Risk Weight × Communication Quality Coupling Risk Coefficient + Communication Delay Coupling Risk Weight × Communication Delay Coupling Risk Coefficient + Communication Security Coupling Risk Weight × Communication Security Coupling Risk Coefficient, the joint risk evaluation coefficient is calculated for each scheme individually. Subsequently, the joint risk evaluation coefficients of all schemes are numerically sorted, and the scheme with the smallest coefficient is selected. This scheme represents the optimal balance in risk management across the three dimensions of communication quality, delay, and security, maximizing the protection requirements of high-priority channels while comprehensively controlling the overall risk of multi-user channels. Finally, the scheme with the smallest coefficient is determined as the Polar code resource adjustment result.

[0076] In one possible implementation, step S610 further includes: Step S611: Perform difference analysis on the Polar code resource adjustment domain according to the first resource adjustment optimization layer to obtain the first resource adjustment difference feature group.

[0077] Step S612: Randomly mutate the first resource regulation difference feature group to obtain the first regulatory evolution feature group.

[0078] Step S613: Perform evolutionary regulation of the Polar code resource regulation domain according to the first regulatory evolutionary feature group to generate the first resource regulation evolutionary decision group.

[0079] Step S614: Based on the communication guarantee priority matrix, perform communication quality coupling risk optimization on the first resource adjustment evolutionary decision group according to the multiple user channels to obtain the fourth resource adjustment optimization layer.

[0080] Step S615: Expand the first resource adjustment optimization layer according to the fourth resource adjustment optimization layer to generate the first resource adjustment space.

[0081] Specifically, a difference analysis operation is performed on the generated Polar code resource adjustment domain. During the analysis, the focus is on comparing the numerical and logical differences in core configuration parameters related to communication quality, such as code rate setting, error correction capability level, and power allocation ratio, between all schemes in the first resource adjustment optimization layer and other unselected schemes in the Polar code resource adjustment domain. Parameter differences that are not covered by the first resource adjustment optimization layer but have potential quality risk optimization value are selected, such as code rate combinations that are more suitable for high-priority channels and error correction parameter configurations that can better reduce packet loss risk among the unselected schemes. These selected differences are categorized and organized according to parameter type, ultimately forming the first resource adjustment difference feature group.

[0082] The obtained first resource adjustment difference feature group, including parameter difference points not covered by the first resource adjustment optimization layer but possessing potential quality risk optimization value, is used as the operation object. Feature mutation operations are carried out according to preset random mutation rules. The mutation rules are set in combination with the communication quality adaptation range and resource adjustment flexibility of the Polar code module in multi-user scenarios. For example, for the code rate parameter, random numerical adjustments are made within a reasonable range of ±8%; for the error correction capability level, random switching is made between adjacent levels; for the power allocation ratio, the remaining resource ratio is randomly fine-tuned by ±5% while ensuring the basic requirements of high-priority channels. By performing such random mutations on each parameter difference point in the first resource adjustment difference feature group one by one, more diverse feature combinations with greater potential for quality risk optimization are generated. Finally, these mutated feature combinations are sorted and classified according to parameter type to form the first adjustment evolution feature group, providing rich feature selections for subsequent evolutionary adjustment of the Polar code resource adjustment domain.

[0083] Based on the obtained first adjustment evolutionary feature group, evolutionary adjustment operations are carried out on the basic Polar code resource adjustment schemes stored in the Polar code resource adjustment domain. During the adjustment process, for each basic scheme in the adjustment domain, different evolutionary features in the first adjustment evolutionary feature group are selected one by one for adaptation and integration. For example, the code rate parameters adapted to high-priority channels in the feature group are updated to the code rate module of the basic scheme, the optimized error correction capability level is integrated into the quality assurance mechanism of the scheme, and the adjusted power allocation ratio is applied to the resource allocation logic of the scheme. This ensures that each basic scheme retains its original compliance while upgrading its communication quality risk management capabilities through the integration of evolutionary features. At the same time, the complete configuration parameters and expected quality risk management effects of each evolved scheme are recorded in real time, and invalid schemes with parameter conflicts or those that cannot adapt to the multi-user communication scenario of the StarSpark module are eliminated. Finally, all effective and practically applicable adjusted schemes are compiled and summarized to generate the first resource adjustment evolutionary decision group.

[0084] For each Polar code resource adjustment scheme within the first resource adjustment evolutionary decision group, a resource allocation fitting tool is invoked to simulate and fit Polar code resource allocation for multiple user channels according to the scheme parameters. Fitted data such as resource occupancy rate and signal attenuation rate for each channel are output, forming a single-scheme multi-channel fitting dataset. Next, the fitted dataset is input into a pre-trained communication quality risk prediction model, outputting the predicted communication quality risk value for each user channel, forming a single-scheme quality risk sequence. Subsequently, based on the communication assurance priority matrix, the priority assurance entropy weight of each user channel is calculated using the entropy weight method: priority assurance entropy weight = channel assurance priority / sum of all channel assurance priorities within the matrix. The single-scheme quality risk sequence is then weighted and summed using the entropy weight as the weight to obtain the communication quality coupling risk coefficient of the scheme. Finally, the coupling risk coefficient of each scheme is numerically compared with a preset communication quality coupling risk threshold. Schemes with coefficients less than the threshold are selected, sorted by channel adaptability, and integrated and stored to generate the fourth resource adjustment optimization layer.

[0085] Using the obtained fourth resource adjustment optimization layer and the generated first resource adjustment optimization layer as the operation objects, a layer expansion operation is carried out to generate the first resource adjustment space. First, using a scheme parameter comparison tool, the core configuration parameters of the schemes in the fourth resource adjustment optimization layer and the first resource adjustment optimization layer are compared one by one to identify new high-quality schemes in the fourth resource adjustment optimization layer that do not exist in the first resource adjustment optimization layer. Next, these new schemes are subjected to a second validity verification to ensure that they meet the requirements in terms of adapting to multi-user channel communication needs and being compatible with the resource configuration logic of the star flash module. Subsequently, the new schemes that pass the verification are classified according to parameter similarity and added to the corresponding classification modules of the first resource adjustment optimization layer in an orderly manner, while retaining the schemes in the original optimization layer that do not duplicate the new schemes and whose risk control effect meets the standards. Finally, the schemes in the expanded first resource adjustment optimization layer are deduplicated and sorted, and sorted from low to high according to the communication quality coupling risk coefficient to form a scheme set with a wider coverage and more comprehensive quality risk control capability, namely the first resource adjustment space.

[0086] In one possible implementation, step S400 further includes: Step S410: Perform service type priority evaluation on the multiple user channels to obtain a service type priority evaluation sequence.

[0087] Step S420: Perform service protocol priority evaluation on the multiple user channels to obtain a service protocol priority evaluation sequence.

[0088] Step S430: Calculate the guarantee priority of the service type priority evaluation sequence and the service protocol priority evaluation sequence according to the guarantee priority weight configuration, and generate the communication guarantee priority matrix.

[0089] Specifically, multiple user channels connected to the StarSpark module are used as evaluation objects. Priority evaluation is conducted based on the service type currently carried by each channel to obtain a service type priority evaluation sequence. First, considering the urgency and real-time requirements of communication needs in multi-user scenarios, a service type priority evaluation standard is established: service types with extremely high requirements for communication stability and timeliness, such as emergency communication, real-time voice, and video conferencing, are classified as high priority, assigned an evaluation score of 8-10 points; service types with moderate real-time requirements, such as ordinary data transmission and non-real-time information interaction, are classified as medium priority, assigned an evaluation score of 4-7 points; and service types with tolerable latency, such as background tasks, are classified as low priority, assigned an evaluation score of 1-3 points. Then, the specific service type currently carried by each user channel is identified, and the service type priority score for each channel is determined according to the above evaluation standard. Finally, the service type priority scores of all channels are arranged sequentially according to the user channel number, forming a service type priority evaluation sequence.

[0090] Evaluation criteria are established based on the QoS indicators stipulated in the Service Level Agreement (SLA) of the service agreement, such as bandwidth guarantee, latency cap, and packet loss rate threshold. For channels with high-level SLAs (e.g., enterprise users, VIP customers), if the agreement explicitly stipulates a bandwidth of no less than 100Mbps, latency of no more than 50ms, and packet loss rate of less than 0.1%, these are classified as high-priority protocols and assigned an evaluation score of 8-10 points. For standard SLA channels signed by ordinary individual users, with agreed bandwidth of 30-100Mbps, latency of 50-100ms, and packet loss rate of 0.1%-0.5%, these are classified as medium-priority protocols and assigned an evaluation score of 4-7 points. For channels without explicit SLA stipulations or only basic service guarantees, these are classified as low-priority protocols and assigned an evaluation score of 1-3 points. Next, the service agreement text corresponding to each user channel is checked one by one, and the QoS indicator parameters are extracted. The service agreement priority score for each channel is determined by comparing it with the evaluation criteria. Finally, according to the user channel number order, the service agreement priority scores of all channels are arranged sequentially to form a service agreement priority evaluation sequence.

[0091] Using the obtained service type priority evaluation sequence, service protocol priority evaluation sequence, and preset guarantee priority weight configuration (including service type priority weight and service protocol priority weight, with the sum of their weights being 1; for example, the service type priority weight is set to 0.6 and the service protocol priority weight to 0.4), guarantee priority calculation is performed to generate a communication guarantee priority matrix. First, for each user channel, its communication guarantee priority is calculated using the formula: Communication Guarantee Priority = Service Type Priority Weight × Service Type Priority Score of the Channel + Service Protocol Priority Weight × Service Protocol Priority Score of the Channel. Next, according to the user channel number order, the scores of each channel in the service type priority evaluation sequence and the service protocol priority evaluation sequence are extracted one by one, substituted into the formula for weighted calculation, and the specific numerical value of the communication guarantee priority for each channel is obtained. Finally, all user channel numbers are used as matrix row indices, and the corresponding communication guarantee priority values ​​are used as matrix elements, arranged in a row-column structure to form a communication guarantee priority matrix containing multi-user channel guarantee priority information.

[0092] In one possible implementation, step S400 further includes: The priority weight configuration includes service type priority weight and service agreement priority weight.

[0093] Specifically, the priority weight configuration is a key parameter setting used to calculate the communication assurance priority matrix. Its core components include two parts: service type priority weight and service protocol priority weight. The service type priority weight quantifies the impact of service type on channel assurance priority. For example, for high real-time services such as emergency communication and real-time voice, this weight can be increased, such as setting it to 0.6, to give these services a higher weight in the assurance priority calculation. The service protocol priority weight reflects the role of the service protocol in assurance priority, especially the QoS indicators agreed upon in the SLA. For scenarios involving enterprise users and VIP customers who have signed high-level service agreements, this weight can be appropriately increased, such as setting it to 0.4, to match the high-quality assurance requirements stipulated in the agreement. Simultaneously, the sum of the service type priority weight and the service protocol priority weight is 1, ensuring a reasonable weight allocation in the assurance priority calculation. This together supports the subsequent comprehensive priority calculation based on the service type priority evaluation sequence and the service protocol priority evaluation sequence, providing a clear weight basis for generating the communication assurance priority matrix.

[0094] Example 2, based on the same inventive concept as the Polar code resource allocation optimization method in the multi-user scenario in the foregoing examples, such as... Figure 2 As shown, this application provides a Polar code resource allocation optimization system for multi-user scenarios. The system and method embodiments in this application are based on the same inventive concept. The system includes: User channel generation module 10 is used to generate multiple user channels based on multiple user equipment connected to the StarShine module.

[0095] The communication accident profile acquisition module 20 is used to perform multimodal communication accident feature deduction on the multiple user channels to obtain a communication accident profile.

[0096] The resource adjustment domain acquisition module 30 is used to make Polar code resource adjustment decisions on the multiple user channels based on the communication accident profile group, and obtain the Polar code resource adjustment domain.

[0097] The priority calculation module 40 is used to perform guarantee priority calculation based on the multiple user channels to obtain a communication guarantee priority matrix.

[0098] The risk optimization module 50 is used to perform multi-dimensional communication coupling risk optimization on the Polar code resource adjustment domain based on the communication guarantee priority matrix and the multiple user channels, and to establish a multi-level resource adjustment optimization architecture.

[0099] The resource allocation optimization module 60 is used to perform multi-dimensional evolutionary joint optimization of the multi-level resource adjustment optimization architecture according to the Polar code resource adjustment domain, obtain the Polar code resource adjustment result, and combine the Star Flash module to optimize the Polar code resource allocation of the multiple user channels.

[0100] Furthermore, the system is also used to implement the following functions: The h-th user channel is extracted based on the multiple user channels, and the h-th user channel is monitored in real time to obtain the h-th channel monitoring sequence, where h is a positive integer. Based on the h-th channel monitoring sequence, communication quality incident characteristics are inferred for the h-th user channel to obtain the h-th communication quality incident inference result. Based on the h-th channel monitoring sequence, communication delay incident characteristics are inferred for the h-th user channel to obtain the h-th communication delay incident inference result. Based on the h-th channel monitoring sequence, communication security incident characteristics are inferred for the h-th user channel to obtain the h-th communication security incident inference result. Based on the h-th communication quality incident inference result, the h-th communication delay incident inference result, and the h-th communication security incident inference result, an h-th communication incident profile is constructed, and the h-th communication incident profile is added to the communication incident profile group.

[0101] Furthermore, the system is also used to implement the following functions: Accident tree tracing is performed based on the historical channel quality incident set to obtain a channel quality incident tracing sequence set; the channel quality incident tracing sequence set is perturbed using an adversarial example generator to obtain a quality incident tracing perturbation sequence set; a first communication quality incident inference model is trained based on the channel quality incident tracing sequence set, and a second communication quality incident inference model is trained based on the quality incident tracing perturbation sequence set; adversarial training is performed based on the first and second communication quality incident inference models to generate a third communication quality incident inference model; the h-th channel monitoring sequence is input into the third communication quality incident inference model to generate the h-th communication quality incident inference result.

[0102] Furthermore, the system is also used to implement the following functions: Based on the communication guarantee priority matrix, a first resource adjustment optimization layer is obtained by optimizing the communication quality coupling risk of the Polar code resource adjustment domain according to the multiple user channels; a second resource adjustment optimization layer is obtained by optimizing the communication delay coupling risk of the Polar code resource adjustment domain according to the multiple user channels; a third resource adjustment optimization layer is obtained by optimizing the communication security coupling risk of the Polar code resource adjustment domain according to the multiple user channels; the first resource adjustment optimization layer, the second resource adjustment optimization layer, and the third resource adjustment optimization layer are connected in parallel to generate the multi-level resource adjustment optimization architecture.

[0103] Furthermore, the system is also used to implement the following functions: The U-th Polar code resource adjustment scheme is extracted based on the Polar code resource adjustment domain, where U is a positive integer. The U-th Polar code resource adjustment scheme is then used to fit Polar code resource allocation to the multiple user channels, resulting in a U-th resource adjustment fitting dataset. Communication quality risk is predicted for each user channel based on the U-th resource adjustment fitting dataset, resulting in a U-th communication quality risk sequence. A priority guarantee entropy reordering sequence is obtained by calculating the proportion of the communication guarantee priority matrix. The U-th communication quality risk sequence is then weighted based on the priority guarantee entropy reordering sequence to obtain a U-th communication quality coupling risk coefficient. If the U-th communication quality coupling risk coefficient is less than the communication quality coupling risk threshold, the U-th Polar code resource adjustment scheme is added to the first resource adjustment optimization layer.

[0104] Furthermore, the system is also used to implement the following functions: Evolutionary optimization of the first resource adjustment optimization layer is performed according to the Polar code resource adjustment domain to obtain a first resource adjustment space; evolutionary optimization of the second resource adjustment optimization layer is performed according to the Polar code resource adjustment domain to obtain a second resource adjustment space; evolutionary optimization of the third resource adjustment optimization layer is performed according to the Polar code resource adjustment domain to obtain a third resource adjustment space; intersection identification is performed on the first resource adjustment space, the second resource adjustment space, and the third resource adjustment space to obtain a fourth resource adjustment space; communication joint risk assessment optimization is performed on the fourth resource adjustment space according to communication quality coupling risk weight, communication delay coupling risk weight, and communication security coupling risk weight to generate the Polar code resource adjustment result.

[0105] Furthermore, the system is also used to implement the following functions: The first resource regulation optimization layer performs difference analysis on the Polar code resource regulation domain to obtain a first resource regulation difference feature group; random mutation is performed on the first resource regulation difference feature group to obtain a first regulation evolution feature group; evolutionary regulation of the Polar code resource regulation domain is performed according to the first regulation evolution feature group to generate a first resource regulation evolution decision group; based on the communication guarantee priority matrix, communication quality coupling risk optimization is performed on the first resource regulation evolution decision group according to the multiple user channels to obtain a fourth resource regulation optimization layer; the first resource regulation optimization layer is expanded according to the fourth resource regulation optimization layer to generate the first resource regulation space.

[0106] Furthermore, the system is also used to implement the following functions: Service type priority evaluation is performed on the multiple user channels to obtain a service type priority evaluation sequence; service protocol priority evaluation is performed on the multiple user channels to obtain a service protocol priority evaluation sequence; and guarantee priority is calculated on the service type priority evaluation sequence and the service protocol priority evaluation sequence according to the guarantee priority weight configuration to generate the communication guarantee priority matrix.

[0107] Furthermore, the system is also used to implement the following functions: The priority weight configuration includes service type priority weight and service agreement priority weight.

[0108] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0109] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0110] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for optimizing Polar code resource allocation in multi-user scenarios, characterized in that, The method includes: Multiple user channels are generated based on multiple user equipment connected to the StarShine module; Multimodal communication accident feature deduction is performed on the multiple user channels to obtain a communication accident profile group; Based on the communication accident profile group, Polar code resource adjustment decisions are made for the multiple user channels to obtain the Polar code resource adjustment domain; Based on the multiple user channels, a guarantee priority calculation is performed to obtain a communication guarantee priority matrix; Based on the communication guarantee priority matrix, a multi-dimensional communication coupling risk optimization is performed on the Polar code resource adjustment domain according to the multiple user channels to establish a multi-level resource adjustment optimization architecture. The multi-dimensional evolutionary joint optimization of the multi-level resource adjustment optimization architecture is performed according to the Polar code resource adjustment domain to obtain the Polar code resource adjustment result, and the Polar code resource allocation of the multiple user channels is optimized in conjunction with the Star Flash module.

2. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 1, characterized in that, Multimodal communication incident feature deduction is performed on the multiple user channels to obtain a communication incident profile group, including: The h-th user channel is extracted based on the multiple user channels, and the h-th user channel is monitored in real time to obtain the h-th channel monitoring sequence, where h is a positive integer; Based on the h-th channel monitoring sequence, the h-th user channel is used to deduce the characteristics of communication quality accidents and obtain the h-th communication quality accident deduction result. Based on the h-th channel monitoring sequence, the h-th user channel is used to deduce the characteristics of communication delay accidents and obtain the h-th communication delay accident deduction result. Based on the h-th channel monitoring sequence, the h-th user channel is used to deduce the characteristics of communication security incidents and obtain the h-th communication security incident deduction result. Based on the simulation results of the h-th communication quality incident, the h-th communication delay incident, and the h-th communication security incident, a h-th communication incident profile is constructed, and the h-th communication incident profile is added to the communication incident profile group.

3. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 2, characterized in that, Based on the h-th channel monitoring sequence, the h-th user channel is used to extrapolate the characteristics of communication quality incidents, and the extrapolation results of the h-th communication quality incident are obtained, including: Based on the historical channel quality incident set, an incident tree tracing is performed to obtain a channel quality incident tracing sequence set; Based on the adversarial sample generator, the channel quality incident tracing sequence set is perturbed to obtain the quality incident tracing perturbation sequence set; A first communication quality incident inference model is trained based on the channel quality incident tracing sequence set, and a second communication quality incident inference model is trained based on the quality incident tracing disturbance sequence set. Adversarial training is performed based on the first communication quality incident simulation model and the second communication quality incident simulation model to generate a third communication quality incident simulation model; The h-th channel monitoring sequence is input into the third communication quality incident simulation model to generate the h-th communication quality incident simulation result.

4. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 1, characterized in that, Based on the communication guarantee priority matrix, a multi-dimensional communication coupling risk optimization is performed on the Polar code resource adjustment domain according to the multiple user channels, establishing a multi-level resource adjustment optimization architecture, including: Based on the communication guarantee priority matrix, the first resource adjustment optimization layer is obtained by performing communication quality coupling risk optimization on the Polar code resource adjustment domain according to the multiple user channels. Based on the communication guarantee priority matrix, the Polar code resource adjustment domain is optimized for communication delay coupling risk according to the multiple user channels to obtain the second resource adjustment optimization layer. Based on the communication guarantee priority matrix, the Polar code resource adjustment domain is optimized for communication security coupling risk according to the multiple user channels to obtain the third resource adjustment optimization layer. The first resource adjustment and optimization layer, the second resource adjustment and optimization layer, and the third resource adjustment and optimization layer are connected in parallel to generate the multi-level resource adjustment and optimization architecture.

5. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 4, characterized in that, Based on the communication guarantee priority matrix, a first resource adjustment optimization layer is obtained by optimizing the communication quality coupling risk of the Polar code resource adjustment domain according to the multiple user channels, including: Based on the Polar code resource adjustment field, extract the U-th Polar code resource adjustment scheme, where U is a positive integer; Based on the U-th scheme for Polar code resource adjustment, the multiple user channels are fitted with Polar code resource allocation to obtain the U-th resource adjustment fitting dataset. Based on the U-th resource adjustment fitting dataset, the communication quality risk prediction is performed on each user channel to obtain the U-th communication quality risk sequence; The priority guarantee entropy sequence is obtained by calculating the proportion based on the communication guarantee priority matrix. The U-th communication quality risk sequence is weighted according to the priority guarantee entropy sequence to obtain the U-th communication quality coupling risk coefficient. If the U-th communication quality coupling risk coefficient is less than the communication quality coupling risk threshold, the U-th Polar code resource adjustment scheme is added to the first resource adjustment optimization layer.

6. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 1, characterized in that, Based on the Polar code resource adjustment domain, the multi-dimensional evolutionary joint optimization of the multi-level resource adjustment optimization architecture is performed to obtain the Polar code resource adjustment result, including: Based on the Polar code resource adjustment domain, perform evolutionary optimization of the first resource adjustment optimization layer to obtain the first resource adjustment space; Based on the Polar code resource adjustment domain, perform evolutionary optimization of the second resource adjustment optimization layer to obtain the second resource adjustment space; Based on the Polar code resource adjustment domain, perform evolutionary optimization of the third resource adjustment optimization layer to obtain the third resource adjustment space; The intersection of the first resource adjustment space, the second resource adjustment space, and the third resource adjustment space is identified to obtain the fourth resource adjustment space. Based on the communication quality coupling risk weight, communication delay coupling risk weight, and communication security coupling risk weight, a joint communication risk assessment is performed on the fourth resource adjustment space to optimize the resource adjustment results of the Polar code.

7. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 6, characterized in that, Based on the Polar code resource adjustment domain, perform evolutionary optimization of the first resource adjustment optimization layer to obtain the first resource adjustment space, including: Based on the first resource adjustment optimization layer, the Polar code resource adjustment domain is analyzed for differences to obtain the first resource adjustment difference feature group; Random mutations are performed on the first resource regulation difference feature group to obtain the first regulatory evolution feature group; Based on the first regulatory evolutionary feature group, the evolutionary regulation of the Polar code resource regulation domain is performed to generate the first resource regulation evolutionary decision group; Based on the communication guarantee priority matrix, the first resource adjustment evolutionary decision group is optimized for communication quality coupling risk according to the multiple user channels to obtain the fourth resource adjustment optimization layer. The first resource adjustment optimization layer is expanded according to the fourth resource adjustment optimization layer to generate the first resource adjustment space.

8. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 1, characterized in that, Based on the multiple user channels, a guarantee priority calculation is performed to obtain a communication guarantee priority matrix, including: Service type priority evaluation is performed on the multiple user channels to obtain a service type priority evaluation sequence; Service protocol priority evaluation is performed on the multiple user channels to obtain a service protocol priority evaluation sequence; Based on the priority weight configuration, the priority of the service type and the priority of the service protocol are calculated to generate the communication guarantee priority matrix.

9. The Polar code resource allocation optimization method in a multi-user scenario as described in claim 8, characterized in that, The priority weight configuration includes service type priority weight and service agreement priority weight.

10. A Polar code resource allocation optimization system for multi-user scenarios, characterized in that, The system is used to implement the Polar code resource allocation optimization method in a multi-user scenario as described in any one of claims 1-9, and the system includes: The user channel generation module is used to generate multiple user channels based on multiple user equipment connected to the StarShine module; The communication accident profile group acquisition module is used to perform multimodal communication accident feature deduction on the multiple user channels to obtain a communication accident profile group. The resource adjustment domain acquisition module is used to make Polar code resource adjustment decisions on the multiple user channels based on the communication accident profile group, and obtain the Polar code resource adjustment domain. The priority calculation module is used to calculate the guarantee priority based on the multiple user channels to obtain a communication guarantee priority matrix; The risk optimization module is used to perform multi-dimensional communication coupling risk optimization on the Polar code resource adjustment domain based on the communication guarantee priority matrix and according to the multiple user channels, and to establish a multi-level resource adjustment optimization architecture. The resource allocation optimization module is used to perform multi-dimensional evolutionary joint optimization of the multi-level resource adjustment optimization architecture according to the Polar code resource adjustment domain, obtain the Polar code resource adjustment result, and combine the Star Flash module to optimize the Polar code resource allocation of the multiple user channels.

Images