A wireless communication network method and system for a mobile emergency rescue station

Abstract

This application provides a wireless communication network method and system for mobile emergency stations. The method includes: real-time monitoring and evaluation of the surrounding environment; selection of the optimal operating frequency band; adjustment of frequency band switching strategies to obtain an adaptive multi-band access mechanism; dynamic adjustment of the bandwidth and connection priority of the wireless communication network; evaluation of task priority to generate a dynamic resource allocation strategy; deployment of a distributed caching and synchronization system to achieve balanced data distribution and rapid location, generating a distributed temporary data cache pool; establishment of a deep reinforcement learning-based intelligent routing algorithm to calculate the optimal transmission path from source to destination, ultimately generating an intelligent routing planning scheme; and pre-setting a redundant path on the path, generating a redundant path planning scheme based on the dynamic resource allocation strategy and the results of the intelligent routing planning. The technical solution provided in this application improves the reliability and response speed of the wireless communication network for mobile emergency stations.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology for mobile emergency stations, and more particularly to a wireless communication network method and system for mobile emergency stations. Background Technology

[0002] The wireless communication network approach for mobile emergency stations is designed to meet the demands for efficient, reliable, and real-time data transmission in emergency rescue scenarios. In complex emergency environments, such as natural disaster sites, traffic accidents, or large-scale public events, the communication network must be able to deploy rapidly and adapt to constantly changing environmental conditions. Specific requirements include: ensuring stable transmission of mission-critical data even under harsh conditions; supporting high-definition video transmission, real-time voice communication, and other high-volume data applications; and dynamically adjusting operating frequency bands and resource allocation according to environmental changes.

[0003] Currently, common wireless communication solutions for mobile emergency stations mainly include the following: using multiple preset frequency bands to improve anti-interference capabilities, but lacking an adaptive adjustment mechanism and unable to optimize frequency band selection in real time; pre-setting bandwidth and connection priorities, making it difficult to cope with resource competition and demand changes in emergencies; relying on a central server for data management and synchronization, leading to single-point failure risks and slow response times; and relying on fixed path selection rules, making it impossible to predict network change trends, resulting in insufficient redundant path planning and affecting fault recovery speed.

[0004] However, while existing solutions meet some of the requirements, they still have the following major drawbacks: Existing multi-band radio systems and static resource allocation strategies cannot monitor and adjust frequency bands and resources in real time, making them ill-suited for complex and ever-changing emergency environments. Centralized caching and synchronization systems are prone to becoming single points of failure; once the central server fails, the performance of the entire system will degrade significantly. Traditional routing algorithms fail to fully consider changes in network topology and node states, lacking effective planning and continuous optimization mechanisms for redundant paths, resulting in slow and inefficient switching during network failures.

[0005] In summary, existing wireless communication solutions have significant shortcomings in terms of flexibility, reliability, and intelligent path planning, failing to fully meet the high-performance communication needs of mobile emergency stations in complex emergency scenarios. Therefore, a more intelligent, adaptive, and reliable wireless communication network method is urgently needed to improve data transmission efficiency and stability, providing strong technical support for emergency rescue. Summary of the Invention

[0006] This application provides a wireless communication network method and system for mobile emergency stations to solve the problems of low reliability and slow response speed in the prior art of wireless communication networks for mobile emergency stations.

[0007] In a first aspect, embodiments of this application provide a wireless communication network method for a mobile emergency station, including:

[0008] By real-time monitoring and evaluation of signal strength, interference level and channel occupancy in the surrounding environment, the optimal operating frequency band is selected and the frequency band switching strategy is adjusted to obtain an adaptive multi-band access mechanism.

[0009] Based on the optimal operating frequency band determined by the adaptive multi-band access mechanism, the bandwidth and connection priority of the wireless communication network are dynamically adjusted, the task priority is evaluated, and the bandwidth demand in the future period is estimated. At the same time, the resource competition between different users is simulated to generate a dynamic resource allocation strategy.

[0010] Based on the task priorities and bandwidth allocation defined in the dynamic resource allocation strategy, a distributed caching and synchronization system is deployed to achieve balanced data distribution and rapid data location. A version vector clock is used to manage concurrent updates, while cross-site data synchronization is achieved, reducing dependence on the central server and generating a distributed temporary data cache pool.

[0011] Using the data in the distributed cache pool, a deep reinforcement learning-based intelligent routing algorithm is established. The intelligent routing algorithm considers the current network topology and node status, predicts network change trends, calculates the optimal transmission path from source to destination, and finally generates an intelligent routing planning scheme.

[0012] Based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path, and the maximum flow minimum cut theorem in graph theory is used to ensure rapid switching to the best backup path in the event of network failure. The ant colony optimization algorithm is used to continuously optimize the path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated.

[0013] Optionally, the step of using data from the distributed cache pool to establish a deep reinforcement learning-based intelligent routing algorithm, which considers the current network topology and node states, predicts network change trends, calculates the optimal transmission path from source to destination, and ultimately generates an intelligent routing planning scheme, including:

[0014] By utilizing historical communication records, node status information, and multi-source heterogeneous data of network topology in a distributed cache pool, the multi-source heterogeneous data is cleaned, transformed, and normalized to obtain feature vectors suitable for input to deep learning models, thereby generating an optimized feature dataset.

[0015] Based on the optimized feature dataset, a hybrid deep reinforcement learning model is constructed that integrates convolutional neural networks for spatial feature extraction and recurrent neural networks for time series analysis. This hybrid deep reinforcement learning model can capture the spatial correlation and time-varying trends of network topology, generating an intelligent decision-making framework suitable for dynamic network environments.

[0016] Based on the intelligent decision-making framework applicable to dynamic network environments, the near-end policy optimization algorithm is adopted as the core of the reinforcement learning framework, and combined with the reward mechanism in the actual network environment, the hybrid deep learning model is trained. The hybrid deep learning model is continuously optimized through interaction with the simulated environment, learns the ability to select the optimal path in different situations, and finally generates a trained intelligent model.

[0017] Using the trained intelligent model, the optimal transmission path from source to destination is calculated based on the current network status and predictions of possible network changes in the future, and an intelligent routing planning scheme is finally generated.

[0018] Optionally, based on the optimized feature dataset, a hybrid deep reinforcement learning model is constructed that integrates convolutional neural networks for spatial feature extraction and recurrent neural networks for time series analysis. This hybrid deep reinforcement learning model can capture the spatial correlation and temporal trends of network topology, generating an intelligent decision-making framework suitable for dynamic network environments, including:

[0019] Using the optimized feature dataset, the spatial distribution of network topology and node states is modeled. Multi-layer convolution operations are performed on the feature dataset through a convolutional neural network to capture the spatial correlation and local patterns between network nodes, thereby obtaining a spatial feature representation.

[0020] Based on the spatial feature representation, and further combined with the time series information of node states, a recurrent neural network is used to process the network state data that changes over time in order to capture the temporal dependencies and dynamic trends, and generate a time series feature representation.

[0021] Based on the spatial feature representation and the time series feature representation, a hybrid model is designed. The hybrid model can process information in both spatial and temporal dimensions simultaneously and introduces an attention mechanism to focus on important spatiotemporal features, thereby improving the accuracy and efficiency of decision-making and obtaining an intelligent decision-making framework that integrates spatiotemporal features.

[0022] By utilizing an intelligent decision-making framework that integrates spatiotemporal features, an intelligent decision-making system suitable for dynamic network environments is constructed. This intelligent decision-making system considers the spatial layout and node status of the current network topology, predicts network change trends over a future period, provides strong support for intelligent routing algorithms, and generates an intelligent decision-making framework suitable for dynamic network environments.

[0023] Optionally, the intelligent decision-making framework suitable for dynamic network environments employs a near-end policy optimization algorithm as the core of the reinforcement learning framework, combined with a reward mechanism in the actual network environment, to train the hybrid deep learning model. This allows the hybrid deep learning model to continuously optimize through interaction with the simulated environment, learning to select the optimal path in different situations, ultimately generating a trained intelligent model, including:

[0024] Based on an intelligent decision-making framework suitable for dynamic network environments, a reinforcement learning framework with a near-end policy optimization algorithm as its core is designed. The reinforcement learning framework continuously adjusts and optimizes model parameters through interaction with the simulated environment, ensuring that the model can make the optimal path selection in complex and ever-changing network environments.

[0025] Based on the intelligent decision-making framework, a reward mechanism that conforms to the communication characteristics of mobile emergency stations is defined. The reward mechanism includes minimizing transmission latency, reducing packet loss rate, and maximizing bandwidth utilization. It is used to evaluate the performance of the model in different scenarios and guide the learning direction of the intelligent model to obtain the optimization objective function.

[0026] Using the aforementioned optimization objective function, a simulation environment is constructed, enabling the hybrid deep learning model to interact with various possible network conditions within the simulation environment. In each interaction, the deep learning model takes action based on the current network state and receives corresponding reward feedback to accumulate experience data.

[0027] Based on the empirical data, the model parameters are updated using a proximal policy optimization algorithm. This algorithm avoids performance instability caused by excessively large update magnitudes by limiting the pace of parameter updates, thereby ensuring the stability and convergence of the deep learning model during training and generating a pre-trained intelligent model.

[0028] The pre-trained intelligent model continues to interact with the simulation environment. The model gradually learns how to select the optimal path in different situations, prioritizing low-latency paths under high load, and finally generating a trained intelligent model.

[0029] Optionally, the step of using the trained intelligent model to calculate the optimal transmission path from the source to the destination based on the current network state and predictions of possible network changes in the future, and ultimately generating an intelligent routing planning scheme, includes:

[0030] Based on the trained intelligent model, the current network status is monitored and data is collected in real time. The data includes node load, connection quality, and traffic patterns to obtain the latest network status information.

[0031] Using the latest network status information and the time series analysis capabilities embedded in the intelligent model, the network change trend in the future is predicted, and network change trend prediction results are generated.

[0032] Based on the network change trend prediction results, the intelligent model evaluates multiple transmission paths. By comprehensively considering the node status on the path, the expected network change trend, and the actual transmission demand, the expected performance index of each path is calculated to obtain the path performance evaluation result.

[0033] Based on the path performance evaluation results, the intelligent model selects a path that meets the transmission requirements and has the best performance as the main path, giving priority to paths that can still maintain efficient transmission under high load or network congestion, and generating the optimal transmission path.

[0034] For the optimal transmission path, the intelligent model initiates a dynamic monitoring mechanism to continuously monitor the real-time performance of the optimal transmission path, including node status, link quality, and traffic changes, and obtains dynamic monitoring results.

[0035] Using the dynamic monitoring results, the intelligent model evaluates the stability and reliability of existing transmission paths. When a performance degradation or potential risk is detected in the transmission path, the intelligent model automatically re-evaluates other transmission paths and obtains the updated optimal transmission path based on the latest network status and prediction results.

[0036] Based on the updated optimal transmission path, a smart routing plan is finally generated. The smart routing plan includes the optimal transmission path from source to destination and provides a mechanism that can dynamically adapt to network changes to ensure the continuity and reliability of data transmission.

[0037] Optionally, based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path, and the maximum flow minimum cut theorem in graph theory is used to ensure rapid switching to the best backup path in the event of a network failure. Ant colony optimization algorithm is used to continuously optimize path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated, including:

[0038] Using the optimal path information determined in the intelligent routing planning scheme, the current network topology and node status are analyzed. Based on the characteristics of the optimal path, one or more potential redundant paths are pre-selected as backup options to obtain a list of pre-selected redundant paths.

[0039] Based on the pre-selected redundant path list, the maximum flow and minimum cut theorem in graph theory are applied to calculate the maximum flow of the network, identify the key nodes and links that cause network interruption, and ensure that the network can be quickly switched to a redundant path when the main path fails, thereby generating a redundant path switching strategy.

[0040] Based on the redundant path switching strategy and combined with the dynamic resource allocation strategy, the bandwidth availability and connection priority on the redundant path are evaluated. Based on the task priority and the bandwidth demand forecast for a period of time in the future, the resource allocation of the redundant path is adjusted to generate an optimized redundant path configuration.

[0041] Using the optimized redundant path configuration, the ant colony optimization algorithm is used to continuously optimize the redundant paths. The ant colony optimization algorithm finds the best alternative path from the source to the destination through iterative search and generates an optimized alternative path list.

[0042] Based on the optimized list of backup paths, and taking into account the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, the configuration of the redundant paths is continuously adjusted, taking into account network change trends and real-time performance monitoring data. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant paths and re-evaluates and optimizes the path selection based on the latest network status, generating a redundant path planning scheme.

[0043] Optionally, based on the optimized list of backup paths, and considering the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, the configuration of the redundant paths is continuously adjusted, taking into account network change trends and real-time performance monitoring data. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant paths and re-evaluates and optimizes path selection based on the latest network status to generate a redundant path planning scheme, including:

[0044] Based on the optimized list of alternative paths, combined with the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, the network change trend is predicted, and the network change trend prediction result is obtained.

[0045] Using the network change trend prediction results, the redundant paths are pre-adjusted to ensure that the redundant paths have sufficient communication capabilities when needed, and a pre-adjusted redundant path configuration is generated.

[0046] Based on the pre-adjusted redundant path configuration, a real-time performance monitoring mechanism is activated to continuously monitor the performance of the main path and redundant paths and collect real-time performance monitoring data.

[0047] Based on the real-time performance monitoring data, the intelligent model assesses the health status of the main path. If a performance degradation or potential risk is detected in the main path, the best backup path is immediately activated to obtain the activated redundant path.

[0048] Using the activated redundant path, the intelligent model continues to monitor the performance of the redundant path and further optimizes the path by combining the ant colony optimization algorithm to ensure the high efficiency and stability of the redundant path and generate an optimized redundant path configuration.

[0049] Finally, a redundant path planning scheme is generated, which includes preset redundant paths and their switching strategies, as well as the optimized configuration for activating redundant paths, to ensure that efficient communication capabilities are maintained even when network conditions change.

[0050] Secondly, embodiments of this application provide a wireless communication network system for a mobile emergency station, comprising:

[0051] The monitoring and evaluation module is used to monitor and evaluate the signal strength, interference level and channel occupancy in the surrounding environment in real time, select the optimal operating frequency band, and adjust the frequency band switching strategy to obtain an adaptive multi-band access mechanism.

[0052] The adjustment and estimation module is used to dynamically adjust the bandwidth and connection priority of the wireless communication network according to the optimal operating frequency band determined by the adaptive multi-band access mechanism, evaluate task priority, and estimate bandwidth demand in the future period of time. At the same time, it simulates resource competition between different users and generates dynamic resource allocation strategies.

[0053] The deployment synchronization module is used to deploy a distributed caching and synchronization system based on the task priority and bandwidth allocation defined in the dynamic resource allocation strategy, so as to achieve balanced data distribution and fast location, and use version vector clock to manage concurrent updates, while achieving cross-site data synchronization, reducing dependence on the central server, and generating a distributed temporary data cache pool.

[0054] The prediction calculation module is used to establish a deep reinforcement learning-based intelligent routing algorithm using the data in the distributed cache pool. The intelligent routing algorithm considers the current network topology and node status, predicts network change trends, calculates the optimal transmission path from source to destination, and finally generates an intelligent routing planning scheme.

[0055] The optimization generation module is used to pre-define a redundant path on the path based on the optimal path information determined in the intelligent routing planning scheme. It also uses the maximum flow minimum cut theorem in graph theory to ensure a rapid switch to the best backup path in the event of a network failure. The ant colony optimization algorithm is used to continuously optimize the path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated.

[0056] Thirdly, embodiments of this application provide a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are to be invoked and executed by the processing component to implement a wireless communication network method for a mobile emergency station as described in any of the first aspects.

[0057] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which, when executed by a computer, implements a wireless communication network method for a mobile emergency station as described in any of the first aspects.

[0058] In this embodiment, the signal strength, interference level, and channel occupancy rate in the surrounding environment are monitored and evaluated in real time. The optimal operating frequency band is selected, and the frequency band switching strategy is adjusted to obtain an adaptive multi-band access mechanism. Based on the optimal operating frequency band determined by the adaptive multi-band access mechanism, the bandwidth and connection priority of the wireless communication network are dynamically adjusted, task priorities are evaluated, and bandwidth requirements in the future are estimated. At the same time, resource competition between different users is simulated to generate a dynamic resource allocation strategy. Based on the task priorities and bandwidth allocation defined in the dynamic resource allocation strategy, a distributed caching and synchronization system is deployed to achieve balanced data distribution and rapid location. Version vector clocks are used to manage concurrent updates, while achieving cross-site data... To reduce reliance on a central server, a distributed temporary data cache pool is generated. Using the data in this distributed cache pool, a deep reinforcement learning-based intelligent routing algorithm is established. This algorithm considers the current network topology and node states, predicts network change trends, calculates the optimal transmission path from source to destination, and ultimately generates an intelligent routing planning scheme. Based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path. The maximum flow minimum cut theorem in graph theory is used to ensure a rapid switch to the best backup path in case of network failure. Ant colony optimization is used to continuously optimize path selection. Based on the dynamic resource allocation strategy and the results of the intelligent routing planning, a redundant path planning scheme is generated.

[0059] The technical solution of this application has the following beneficial effects:

[0060] By real-time monitoring and evaluation of signal strength, interference levels, and channel occupancy in the surrounding environment, an adaptive multi-band access mechanism is implemented by selecting the optimal operating frequency band and adjusting the frequency band switching strategy. This significantly enhances the network's anti-interference capability and stability, reducing the risk of communication interruptions. Based on the optimal operating frequency band determined by the adaptive multi-band access mechanism, the bandwidth and connection priority of the wireless communication network are dynamically adjusted, task priorities are evaluated, and bandwidth requirements for a future period are predicted. Simultaneously, resource competition between different users is simulated to generate a dynamic resource allocation strategy. This method effectively improves bandwidth utilization, ensures the priority processing of critical tasks, and avoids resource waste. Based on the task priorities and bandwidth allocation defined in the dynamic resource allocation strategy, a distributed caching and synchronization system is deployed to achieve balanced data distribution and rapid data location. Version vector clocks are used to manage concurrent updates, while cross-site data synchronization is achieved, reducing dependence on the central server and generating a distributed temporary data cache pool. This design not only accelerates data access speed but also improves the system's fault tolerance and scalability. Utilizing data from the distributed cache pool, a deep reinforcement learning-based intelligent routing algorithm is established. Considering the current network topology and node states, it predicts network change trends, calculates the optimal transmission path from source to destination, and ultimately generates an intelligent routing plan. This intelligent path selection mechanism can flexibly respond to network changes, ensuring efficient and reliable data transmission. Based on the optimal path information determined in the intelligent routing plan, a redundant path is pre-defined on the path. The maximum flow minimum cut theorem in graph theory ensures a rapid switch to the best backup path in the event of a network failure. Ant colony optimization continuously optimizes path selection, generating a redundant path planning scheme based on dynamic resource allocation strategies and the results of intelligent routing planning. This redundant path planning scheme can immediately activate the backup path when the primary path fails, greatly shortening fault recovery time and ensuring communication continuity.

[0061] Furthermore, using historical communication records, node status information, and multi-source heterogeneous data of network topology from a distributed cache pool, the data is cleaned, transformed, and normalized to generate feature vectors suitable for input to the deep learning model, forming an optimized feature dataset. Based on the optimized feature dataset, a hybrid deep reinforcement learning model is constructed, integrating convolutional neural networks for spatial feature extraction and recurrent neural networks for time series analysis. This model can capture the spatial correlation and temporal trends of network topology, generating an intelligent decision-making framework suitable for dynamic network environments. A near-end policy optimization algorithm is used as the core of the reinforcement learning framework, combined with a reward mechanism in a real network environment, to train the hybrid deep learning model. Through continuous optimization via interaction with a simulated environment, the model learns to select the optimal path in different scenarios, ultimately generating a trained intelligent model. Using the trained intelligent model, based on the current network state and predictions of potential network changes over a future period, the optimal transmission path from source to destination is calculated, generating an intelligent routing plan. Based on the optimal path information determined in the intelligent routing plan, one or more potential redundant paths are pre-selected as backup options, resulting in a pre-selected redundant path list. Applying the maximum flow and minimum cut theorem from graph theory, this algorithm calculates the maximum flow of the network to identify critical nodes and links causing network outages. This ensures a rapid switch to redundant paths when the primary path fails, generating a redundant path switching strategy. Based on this strategy and a dynamic resource allocation strategy, the algorithm evaluates bandwidth availability and connection priorities on redundant paths. According to task priorities and predicted bandwidth demands over a future period, resource allocation for redundant paths is adjusted, generating an optimized redundant path configuration. Using this optimized configuration, an ant colony optimization algorithm continuously optimizes the redundant paths, iteratively searching for the best alternative path from source to destination, generating an optimized alternative path list. Based on this list, and considering network trends and real-time performance monitoring data, the redundant path configuration is continuously adjusted. When a performance degradation or potential risk is detected on the primary path, the intelligent model automatically activates redundant paths and re-evaluates and optimizes path selection based on the latest network status, generating a redundant path planning scheme.

[0062] By introducing a deep reinforcement learning model, the system can automatically generate optimal transmission paths in complex and ever-changing network environments, significantly improving the intelligence and adaptability of path selection. This not only enhances data transmission efficiency but also strengthens the system's flexibility and response speed. Utilizing redundant path planning and a rapid switching mechanism, the system can quickly switch to the best backup path when the primary path fails, greatly shortening fault recovery time and ensuring communication continuity and reliability. Simultaneously, through continuous path selection optimization, the system can cope with various emergencies, reducing the risk of network outages. Combined with a dynamic resource allocation strategy, the system can rationally allocate bandwidth resources based on task priority and bandwidth demand prediction, avoiding resource waste and ensuring the priority processing of critical tasks. Furthermore, the deployment of a distributed caching and synchronization system further improves data access speed, reduces dependence on the central server, and enhances the overall performance and stability of the system.

[0063] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 A flowchart illustrating a wireless communication network method for a mobile emergency station provided in an embodiment of this application;

[0066] Figure 2 A schematic diagram of the wireless communication network system of a mobile emergency station provided in an embodiment of this application;

[0067] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0068] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0069] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0070] 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 some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0071] Figure 1 A flowchart of a wireless communication network method for a mobile emergency station is provided in this application embodiment, as shown below. Figure 1 As shown, the method includes:

[0072] 101. Monitor and evaluate the signal strength, interference level and channel occupancy in the surrounding environment in real time, select the optimal operating frequency band, and adjust the frequency band switching strategy to obtain an adaptive multi-band access mechanism.

[0073] In this step, real-time monitoring and evaluation refers to the continuous collection of data on signal strength, interference levels, and channel occupancy through a sensor network deployed in and around the mobile emergency station. This data includes, but is not limited to, the received power of wireless signals, the level of interference from adjacent frequencies, and the usage of each communication channel. This process is used to identify the most stable and efficient communication frequency bands in the current environment, thereby ensuring reliable data transmission and low latency. By dynamically adjusting the frequency band switching strategy, the system can automatically select the optimal operating frequency band under different environmental conditions, achieving an adaptive multi-band access mechanism.

[0074] First, the system collects environmental data in real time using sensors installed at the emergency station and its surrounding facilities. Next, data analysis algorithms process this data to evaluate the quality of each frequency band and select the most suitable operating frequency band for the current environment. Finally, based on the evaluation results, the frequency band switching strategy is adjusted to enable the system to respond quickly to environmental changes and ensure optimal communication quality. This step lays a solid foundation for subsequent resource allocation and path planning.

[0075] In an emergency rescue scenario, suppose a mobile first aid station is located near a large fire. Due to the presence of numerous wireless devices and other wireless communication activities at the scene, certain frequency bands are severely interfered with. Using sensors deployed on the first aid station and surrounding vehicles, the system monitors in real time that the 2.4 GHz band experiences significant interference, while the 5 GHz band is relatively idle. Based on this information, the system automatically switches to the 5 GHz band for primary communication tasks, while reserving the 2.4 GHz band as a backup. This not only improves communication efficiency but also reduces the possibility of data transmission errors.

[0076] 102. Based on the optimal operating frequency band determined by the adaptive multi-band access mechanism, dynamically adjust the bandwidth and connection priority of the wireless communication network, evaluate task priority, and predict bandwidth demand in the future. At the same time, simulate resource competition between different users and generate a dynamic resource allocation strategy.

[0077] In this step, the dynamic resource allocation strategy refers to flexibly adjusting the allocation of network resources based on the currently selected operating frequency band, combined with task priorities and future bandwidth demand forecasts. This strategy aims to maximize resource utilization while ensuring that critical tasks are prioritized. The system simulates resource competition among different users to plan resource allocation schemes in advance, avoiding service interruptions or performance degradation due to insufficient resources.

[0078] Based on the selected optimal operating frequency band, the system analyzes the current network status and task requirements, assesses the priority of various tasks, and predicts bandwidth demands over a future period. Then, by simulating resource competition among different users, a reasonable resource allocation strategy is developed. This process involves complex mathematical modeling and simulation techniques to ensure the fairness and efficiency of resource allocation.

[0079] Continuing with the fire scene example above, the emergency station needs to support multiple communication tasks simultaneously, including high-definition video transmission, voice calls, and data reporting. The system allocates more bandwidth resources to high-priority tasks and less to low-priority tasks based on their importance and urgency. Furthermore, the system anticipates bandwidth demand changes over the next 10 minutes and adjusts resource allocation accordingly to ensure sufficient bandwidth is available in critical moments. When multiple users simultaneously request large bandwidth resources, the system simulates resource contention to optimize the allocation ratio for each user, ensuring smooth overall communication.

[0080] 103. Based on the task priority and bandwidth allocation defined in the dynamic resource allocation strategy, deploy a distributed caching and synchronization system to achieve balanced data distribution and rapid data location, and use version vector clock to manage concurrent updates, while achieving cross-site data synchronization, reducing dependence on the central server, and generating a distributed temporary data cache pool.

[0081] In this step, a distributed caching and synchronization system is a crucial mechanism for improving data access speed and reliability. By deploying cache nodes across different nodes in the network, it allows data to be retrieved from the nearest available location, reducing reliance on a central server. A version vector clock is used to manage concurrent updates, ensuring data consistency and integrity, and maintaining data synchronization even under network instability. This design is particularly suitable for highly distributed and frequently changing work environments such as mobile first-aid stations.

[0082] Based on the generated dynamic resource allocation strategy, the system deploys a distributed caching and synchronization system. This system caches frequently used data across various nodes according to task priority and bandwidth allocation, achieving balanced data distribution and rapid data location. Simultaneously, a version vector clock is used to manage concurrent updates, ensuring data consistency across all nodes. Furthermore, a cross-site data synchronization mechanism further enhances the system's fault tolerance and scalability.

[0083] At the fire scene, the emergency medical station deployed multiple distributed cache nodes, distributed among different ambulances and the command center. These nodes stored important data such as frequently used medical records, map information, and command and dispatch instructions. When an ambulance needs to access a specific patient's medical records, it can quickly retrieve them through the nearest cache node without waiting to download them from the central server. If multiple nodes are updating the same data simultaneously (e.g., the latest fire spread information), a version vector clock ensures that all update operations are performed in the correct order. Even if a node temporarily loses connection, other nodes can continue to function normally and automatically synchronize data once the connection is restored.

[0084] 104. Using the data in the distributed cache pool, a deep reinforcement learning-based intelligent routing algorithm is established. The intelligent routing algorithm considers the current network topology and node status, predicts network change trends, calculates the optimal transmission path from source to destination, and finally generates an intelligent routing planning scheme.

[0085] In this step, the intelligent routing algorithm based on deep reinforcement learning is an advanced path selection method. It utilizes multi-source heterogeneous data, including historical communication records, node state information, and network topology from a distributed cache pool, to construct a hybrid deep learning model. This model extracts spatial features through convolutional neural networks and analyzes time-series data through recurrent neural networks, capturing the spatial correlation and temporal trends of network topology, thereby generating an intelligent decision-making framework suitable for dynamic network environments. Ultimately, the system can predict future trends based on the current network state and calculate the optimal transmission path.

[0086] The system first cleans, transforms, and normalizes the multi-source heterogeneous data in the distributed cache pool to generate feature vectors suitable for input to the deep learning model. Next, a hybrid deep reinforcement learning model integrating convolutional neural networks (CNNs) is constructed and trained to capture the spatial correlation and temporal trends of network topology. Through interaction with a simulated environment, the model parameters are continuously optimized, enabling it to learn the ability to select the optimal path in different scenarios. Finally, based on the current network state and predicted future changes, the system calculates the optimal transmission path from source to destination, generating an intelligent routing plan.

[0087] At the fire scene, the system utilized data from a previously deployed distributed cache pool, including past communication records, node states, and network topology, to establish an intelligent routing algorithm. By extracting spatial features of the current network topology through a convolutional neural network (CNN), and analyzing time-series data, the model predicted potential network changes within the next few minutes. For example, if the system predicted that signal strength in a certain area might weaken due to increased smoke, it would adjust communication paths in advance to bypass that area, ensuring the continuity and stability of data transmission. In this way, the system can maintain efficient data transmission even in complex and ever-changing environments.

[0088] Optionally, step 104, which involves using data from the distributed cache pool to establish an intelligent routing algorithm based on deep reinforcement learning, considers the current network topology and node states, predicts network change trends, calculates the optimal transmission path from source to destination, and ultimately generates an intelligent routing planning scheme. This includes: using historical communication records, node state information, and multi-source heterogeneous data of the network topology from the distributed cache pool to clean, transform, and normalize the multi-source heterogeneous data to obtain feature vectors suitable for input to the deep learning model, generating an optimized feature dataset; and based on the optimized feature dataset, constructing a hybrid deep reinforcement learning model that integrates convolutional neural networks for spatial feature extraction and recurrent neural networks for time series analysis. A hybrid deep reinforcement learning model can capture the spatial correlation and temporal trends of network topology, generating an intelligent decision-making framework suitable for dynamic network environments. Based on this intelligent decision-making framework, a near-end policy optimization algorithm is used as the core of the reinforcement learning framework, combined with a reward mechanism in a real network environment, to train the hybrid deep learning model. This allows the hybrid deep learning model to continuously optimize through interaction with a simulated environment, learning to select the optimal path in different situations, ultimately generating a trained intelligent model. Using this trained intelligent model, based on the current network state and predictions of potential network changes in the future, the optimal transmission path from source to destination is calculated, ultimately generating an intelligent routing planning scheme.

[0089] The step described above involves constructing a hybrid deep reinforcement learning model based on the optimized feature dataset. This model integrates convolutional neural networks for spatial feature extraction and recurrent neural networks for time series analysis. The hybrid deep reinforcement learning model can capture the spatial correlation and time-varying trends of network topology, generating an intelligent decision-making framework suitable for dynamic network environments. This includes: modeling the spatial distribution of network topology and node states using the optimized feature dataset; performing multi-layer convolution operations on the feature dataset using a convolutional neural network to capture the spatial correlation and local patterns between network nodes, obtaining a spatial feature representation; and further combining the spatial feature representation with the time-series information of node states, using a recurrent neural network to process the network changes over time. State data is used to capture temporal dependencies and dynamic trends, generating time-series feature representations. Based on these spatial and time-series feature representations, a hybrid model is designed. This hybrid model can simultaneously process information in both spatial and temporal dimensions and incorporates an attention mechanism, enabling it to focus on important spatiotemporal features, thereby improving the accuracy and efficiency of decision-making and resulting in an intelligent decision-making framework that integrates spatiotemporal features. Utilizing this intelligent decision-making framework, an intelligent decision-making system suitable for dynamic network environments is constructed. This system considers the spatial layout and node states of the current network topology, predicts network change trends over a future period, provides strong support for intelligent routing algorithms, and generates an intelligent decision-making framework suitable for dynamic network environments.

[0090] In this step, the optimized feature dataset includes heterogeneous data from multiple sources, such as historical communication records, node state information, and network topology, which have been cleaned, transformed, and normalized. This data is used to generate feature vectors suitable for input to the deep learning model, ensuring that the model can accurately capture key features in the network environment. Convolutional neural networks (CNNs) are used for spatial feature extraction. By performing multi-layer convolution operations on the optimized feature dataset, they capture the spatial correlations and local patterns between network nodes, obtaining spatial feature representations. This enables the model to understand the spatial layout of the network topology and identify which nodes have close connections or potential bottlenecks. Recurrent neural networks (RNNs) are used for time series analysis. Combining the time series information of node states, they process network state data that changes over time to capture temporal dependencies and dynamic trends, generating time series feature representations. RNNs are particularly suitable for processing data with temporal properties and can predict future network trends. Hybrid models combine the advantages of CNNs and RNNs to design a model that can simultaneously process spatial and temporal information. This model introduces an attention mechanism, allowing it to focus on important spatiotemporal features, improving the accuracy and efficiency of decision-making. This design is particularly suitable for complex routing decision-making tasks in dynamic network environments.

[0091] First, the spatial distribution of the network topology and node states is modeled using the optimized feature dataset. Multiple convolutional operations are then performed on the feature dataset using a convolutional neural network to capture the spatial correlations and local patterns between network nodes, resulting in a spatial feature representation. This process is similar to using convolutional kernels to extract edge and texture features from an image in image processing, but it is applied here to the network topology.

[0092] Secondly, based on the spatial feature representation obtained above, the temporal series information of node states is further combined. A recurrent neural network is used to process the network state data that changes over time to capture temporal dependencies and dynamic trends, generating a time series feature representation. This step helps the model predict network change trends over a future period, providing a basis for path selection.

[0093] Next, based on spatial and temporal feature representations, a hybrid model is designed. This model can simultaneously process information in both spatial and temporal dimensions and incorporates an attention mechanism, enabling it to focus on important spatiotemporal features and improve the accuracy and efficiency of decision-making. The attention mechanism allows the model to automatically adjust its focus on different features according to the importance of the current task, thus better coping with complex and ever-changing network environments.

[0094] Finally, an intelligent decision-making system suitable for dynamic network environments is constructed using an intelligent decision-making framework that integrates spatiotemporal features. This system considers the spatial layout of the current network topology and the state of nodes, predicts network change trends over a future period, provides strong support for intelligent routing algorithms, and generates an intelligent decision-making framework suitable for dynamic network environments.

[0095] In this embodiment of the application, in a wireless communication scenario of a mobile emergency station, it is assumed that an emergency station needs to transmit a large amount of high-definition video and medical data in real time while performing a rescue mission. To ensure the efficiency and reliability of data transmission, the system adopts the intelligent routing algorithm in the above-mentioned optional scheme 104.

[0096] The system first uses an optimized feature dataset to model the current network topology and node states. Through a convolutional neural network, the system captures spatial correlations and local patterns among nodes. For example, the system identifies that some nodes have formed stable communication links due to geographical proximity, while other nodes may have weaker signals due to the presence of obstacles.

[0097] Next, the system combines the time-series information of node states and uses a recurrent neural network to process the network state data that changes over time. Through this process, the system predicts that the signal in a certain area may weaken due to increased smoke in the next few minutes, and therefore adjusts the communication path in advance to bypass that area.

[0098] Based on the aforementioned spatial and temporal features, a hybrid model was designed, incorporating an attention mechanism. This model automatically focuses on important spatiotemporal features, improving the accuracy and efficiency of path selection. For example, in emergency situations, the system can quickly identify the most reliable communication path, ensuring that critical tasks are prioritized.

[0099] Ultimately, the system utilizes an intelligent decision-making framework that integrates spatiotemporal features to construct an intelligent decision-making system suitable for dynamic network environments. This system not only considers the spatial layout and node states of the current network topology but also predicts network change trends over a future period, providing robust support for intelligent routing algorithms. Throughout the rescue operation, regardless of environmental changes, the system can adjust routes in a timely manner, ensuring efficient and reliable data transmission.

[0100] Through the above steps, the system can maintain efficient path selection capabilities in complex and ever-changing environments, significantly improving the reliability and stability of data transmission and providing strong technical support for emergency rescue.

[0101] Optionally, step 104, based on the intelligent decision-making framework suitable for dynamic network environments, employs a proximal policy optimization algorithm as the core of the reinforcement learning framework and combines it with a reward mechanism in the actual network environment to train the hybrid deep learning model. This allows the hybrid deep learning model to continuously optimize through interaction with the simulated environment, learning to select the optimal path in different situations, ultimately generating a trained intelligent model. This includes: designing a reinforcement learning framework with the proximal policy optimization algorithm as its core, based on the intelligent decision-making framework suitable for dynamic network environments. This reinforcement learning framework continuously adjusts and optimizes model parameters through interaction with the simulated environment, ensuring the model can make the optimal path selection in complex and ever-changing network environments; and defining a reward mechanism that conforms to the communication characteristics of mobile emergency stations, based on the intelligent decision-making framework. This reward mechanism includes minimizing transmission latency, reducing packet loss rate, and maximizing bandwidth utilization, used to evaluate the model in different situations. The performance of the model is analyzed to guide the learning direction of the intelligent model, resulting in an optimization objective function. Using this objective function, a simulation environment is constructed, enabling the hybrid deep learning model to interact with various possible network conditions. In each interaction, the deep learning model takes action based on the current network state and receives corresponding reward feedback to accumulate experience data. Based on this experience data, the model parameters are updated using a proximal policy optimization algorithm. This algorithm limits the pace of parameter updates, avoiding performance instability caused by excessively large update magnitudes, thus ensuring the stability and convergence of the deep learning model during training, generating a pre-trained intelligent model. The pre-trained intelligent model continues to interact with the simulation environment, gradually learning how to select the optimal path in different situations, prioritizing low-latency paths under high load, ultimately generating a fully trained intelligent model.

[0102] The process of using the trained intelligent model to calculate the optimal transmission path from source to destination based on the current network status and predictions of potential network changes over a future period, and ultimately generating an intelligent routing plan, includes: real-time monitoring and data collection of the current network status based on the trained intelligent model, including node load, connection quality, and traffic patterns, to obtain the latest network status information; using the latest network status information, combined with the time series analysis capabilities embedded in the intelligent model, to predict network changes over a future period, generating a network change trend prediction result; based on the network change trend prediction result, the intelligent model evaluates multiple transmission paths, calculating the expected performance indicators for each path by comprehensively considering the node status on the path, the expected network change trend, and the actual transmission requirements, to obtain a path performance evaluation result; based on the path performance evaluation result, the intelligent model... The model selects a path that meets transmission requirements and has the best performance as the main path, prioritizing paths that can maintain efficient transmission even under high load or network congestion, thus generating an optimal transmission path. For this optimal transmission path, the intelligent model initiates a dynamic monitoring mechanism to continuously monitor its real-time performance, including node status, link quality, and traffic changes, obtaining dynamic monitoring results. Using these results, the intelligent model evaluates the stability and reliability of existing transmission paths. When a performance degradation or potential risk is detected in the transmission path, the intelligent model automatically re-evaluates other transmission paths and obtains an updated optimal transmission path based on the latest network status and prediction results. Based on the updated optimal transmission path, a smart routing plan is finally generated. This plan includes the optimal transmission path from source to destination and provides a mechanism that dynamically adapts to network changes, ensuring the continuity and reliability of data transmission.

[0103] In this step, the proximal policy optimization algorithm, a reinforcement learning algorithm, avoids performance instability caused by excessively large update increments by limiting the pace of parameter updates, ensuring stability and convergence during model training. In this scheme, proximal policy optimization serves as the core algorithm, used to adjust and optimize the parameters of the hybrid deep learning model, enabling it to make optimal path selections in complex and ever-changing network environments. The reward mechanism includes metrics such as minimizing transmission latency, reducing packet loss rate, and maximizing bandwidth utilization, used to evaluate the model's performance in different scenarios and guide the learning direction of the intelligent model. These metrics reflect the key requirements of mobile emergency station communication, ensuring that the system can provide efficient and reliable communication services in practical applications. The simulation environment is a virtualized network simulation platform that allows the hybrid deep learning model to interact with various possible network conditions. In each interaction, the model takes action based on the current network state and receives corresponding reward feedback to accumulate experience data. This interactive approach helps the model gradually learn how to select the optimal path in different scenarios. The dynamic monitoring mechanism refers to real-time monitoring of the selected optimal transmission path, continuously collecting information such as node status, link quality, and traffic changes. This data is used to assess the stability and reliability of existing transmission paths. When a path performance degradation or potential risk is detected, the intelligent model automatically re-evaluates other transmission paths and dynamically adjusts the optimal path based on the latest network status and prediction results.

[0104] First, based on an intelligent decision-making framework suitable for dynamic network environments, a reinforcement learning framework with a proximal policy optimization algorithm at its core is designed. This framework continuously adjusts and optimizes model parameters through interaction with the simulated environment, ensuring that the model can make optimal path selections in complex and ever-changing network environments.

[0105] Secondly, based on the intelligent decision-making framework, a reward mechanism is defined that conforms to the communication characteristics of mobile emergency stations. These reward mechanisms include minimizing transmission latency, reducing packet loss rate, and maximizing bandwidth utilization, which are used to evaluate the model's performance in different scenarios and guide the learning direction of the intelligent model to obtain the optimization objective function.

[0106] Next, using the aforementioned optimization objective function, a simulation environment is constructed, enabling the hybrid deep learning model to interact with various possible network conditions within this environment. In each interaction, the model takes action based on the current network state and receives corresponding reward feedback to accumulate empirical data.

[0107] Furthermore, based on accumulated empirical data, the proximal policy optimization algorithm is used to update the model parameters. By limiting the pace of parameter updates, the proximal policy optimization algorithm ensures the stability and convergence of the model training process, generating a pre-trained intelligent model. This pre-trained intelligent model continues to interact with the simulation environment, gradually learning how to select the optimal path in different scenarios, prioritizing low-latency paths under high load, ultimately generating a fully trained intelligent model.

[0108] Finally, the current network status is monitored and data is collected in real time to obtain the latest network status information, including node load, connection quality, and traffic patterns. Combining the time series analysis capabilities embedded in the intelligent model, the network's future trend is predicted, generating network trend prediction results. Based on these predictions, multiple transmission paths are evaluated, comprehensively considering node status, expected network trends, and actual transmission demands. The expected performance indicators for each path are calculated, yielding path performance evaluation results. The path that meets transmission requirements and has the best performance is selected as the primary path, prioritizing paths that can maintain efficient transmission under high load or network congestion, thus generating the optimal transmission path. A dynamic monitoring mechanism is activated to continuously monitor the real-time performance of the optimal transmission path, evaluating its stability and reliability. When a path performance degradation or potential risk is detected, the intelligent model automatically re-evaluates other transmission paths and dynamically adjusts the optimal path based on the latest network status and prediction results, ultimately generating an intelligent routing plan.

[0109] In this embodiment of the application, in a wireless communication scenario of a mobile emergency station, it is assumed that the emergency station needs to transmit high-definition video streams and a large amount of medical data in real time while performing emergency rescue missions. To ensure the efficiency and reliability of data transmission, the system employs the aforementioned intelligent routing algorithm.

[0110] The system first designs a reinforcement learning framework based on a near-end policy optimization algorithm, using an intelligent decision-making framework suitable for dynamic network environments. This framework continuously adjusts and optimizes model parameters through interaction with the simulated environment, ensuring that the model can make optimal path selections in complex and ever-changing network environments.

[0111] Secondly, the system defines a reward mechanism that conforms to the communication characteristics of mobile emergency stations, including minimizing transmission latency, reducing packet loss rate, and maximizing bandwidth utilization. These reward mechanisms are used to evaluate the model's performance in different scenarios and guide the learning direction of the intelligent model, resulting in an optimized objective function.

[0112] Next, using the aforementioned optimization objective function, the system constructs a simulation environment that enables the hybrid deep learning model to interact with various possible network conditions within this environment. In each interaction, the model takes action based on the current network state and receives corresponding reward feedback to accumulate experience data.

[0113] Furthermore, based on accumulated empirical data, the system uses a proximal policy optimization algorithm to update model parameters. By limiting the pace of parameter updates, the proximal policy optimization algorithm ensures the stability and convergence of the model training process, generating a pre-trained intelligent model. Continuing to interact with the simulated environment using this pre-trained intelligent model, the model gradually learns how to select the optimal path in different scenarios, prioritizing low-latency paths under high load, ultimately generating a fully trained intelligent model.

[0114] Furthermore, during actual rescue operations, the system monitors and collects data on the current network status in real time, acquiring the latest network condition information, including node load, connection quality, and traffic patterns. Combining this with the time-series analysis capabilities embedded in the intelligent model, the system predicts network trends over a future period, generating network trend prediction results. Based on these predictions, the system evaluates multiple transmission paths, comprehensively considering node status, expected network trends, and actual transmission needs, calculating the expected performance indicators for each path, and obtaining path performance evaluation results. Ultimately, the system selects the path that meets transmission requirements and has the best performance as the primary path, prioritizing paths that can maintain efficient transmission even under high load or network congestion conditions, thus generating the optimal transmission path.

[0115] Finally, the system activates a dynamic monitoring mechanism to continuously monitor the real-time performance of the optimal transmission path and evaluate its stability and reliability. When a path performance degradation or potential risk is detected, the system automatically re-evaluates other transmission paths and dynamically adjusts the optimal path based on the latest network status and prediction results to ensure the continuity and reliability of data transmission.

[0116] Through the above steps, the system can maintain efficient path selection capabilities in complex and ever-changing environments, significantly improving the reliability and stability of data transmission and providing strong technical support for emergency rescue.

[0117] This application considers that the efficiency and reliability of data transmission are crucial in the wireless communication environment of mobile emergency stations. Due to the complex and ever-changing network environment in emergency scenarios, traditional static routing algorithms struggle to cope with dynamically changing needs. Therefore, the research team has developed an intelligent routing model based on a near-end policy optimization algorithm, aiming to enable the model to automatically select the optimal path in complex and ever-changing network environments through a reinforcement learning framework. Thus, a new alternative scheme is proposed, which includes:

[0118] Optionally, in step 104, based on the intelligent decision-making framework suitable for dynamic network environments, the near-end policy optimization algorithm is used as the core of the reinforcement learning framework, and combined with the reward mechanism in the actual network environment, to train the hybrid deep learning model. This allows the hybrid deep learning model to continuously optimize through interaction with the simulated environment, learning the ability to select the optimal path in different situations, ultimately generating a trained intelligent model, including:

[0119] Based on an intelligent decision-making framework suitable for dynamic network environments, a reinforcement learning framework with a proximal policy optimization algorithm as its core is designed. The reinforcement learning framework continuously adjusts and optimizes model parameters through interaction with the simulated environment, ensuring that the model can make the optimal path selection in complex and ever-changing network environments.

[0120]

[0121] Where L(θ) is the loss function; Represents the expected value at time step t; clip(r) t (θ), 1-∈, 1+∈) are clipping operations, restricting r to... t The range of (θ) is within [1-∈, 1+∈], to prevent excessive parameter updates from causing performance instability; ∈ is the pruning range of the near-end policy optimization algorithm, controlling the pace of parameter updates; A t It is the action advantage function, representing the action advantage in state s. t Take action a t Advantage, which measures the degree of advantage of taking a particular action relative to other actions, is defined as:

[0122] A t =Q(s) t a t )-V(s t )

[0123] Where Q(s) t a t ) is to take action a t The expected return after V(s) t ) is state s t The value function;

[0124] r t (θ) is the ratio of the old and new strategies, representing the choice of action a under the current parameter θ. t The probability and the old parameter θ old The ratio of the probabilities of choosing the same action is given by the formula:

[0125]

[0126] Where π θ (a t |s t )and These represent actions taken under the old and new strategies, respectively. t The probability of;

[0127] Based on the requirements of the intelligent decision-making framework, a reward mechanism that conforms to the communication characteristics of mobile emergency stations is defined. The reward mechanism includes minimizing transmission latency, reducing packet loss rate, and maximizing bandwidth utilization. It is used to evaluate the performance of the model in different scenarios and guide the learning direction of the intelligent model to obtain the optimization objective function.

[0128] R(s t a t )=w1·(1-d t )+w2·(1-p t )+w3·u t

[0129] Wherein, R(s) t a t ) is a reward mechanism, s t This refers to the current network status; a t It refers to the action at the current moment; d t It is the transmission delay; p t It's the packet loss rate; u t It is bandwidth utilization; w1, w2, and w3 are the weights of each indicator, used to balance the importance of different objectives.

[0130] Using the aforementioned optimization objective function, a simulation environment is constructed, enabling the hybrid deep learning model to interact with various possible network conditions within the simulation environment. In each interaction, the deep learning model takes action based on the current network state and receives corresponding reward feedback to accumulate experience data.

[0131]

[0132] Where τ is a complete trajectory; π θ J(θ) is the policy distribution with parameter θ; J(θ) is the policy gradient objective function, which represents the expected cumulative reward that can be obtained from a series of interactions from the initial state to the final state given the policy parameter θ. Let represent the expected value of all possible trajectories τ, where τ is the expected value according to the current policy π. θ Generated; R(s) represents the cumulative discount reward from time step t = 0 to the final time step T; γ is the discount factor, ranging from [0, 1]; t a t ) is in state s at time step t. t And take action a t The instant rewards received;

[0133] Based on accumulated empirical data, the model parameters are updated using a proximal policy optimization algorithm. The proximal policy optimization algorithm avoids performance instability caused by excessive update magnitude by limiting the pace of parameter updates, thereby ensuring the stability and convergence of the deep learning model during training and generating an intelligent model that has undergone preliminary training.

[0134]

[0135] Where α is the learning rate, which controls the step size of each parameter update; It is the gradient of the loss function L(θ) with respect to θ; θ new It is the parameter update formula; θ old These are the model parameters before the update; θ new These are the updated model parameters;

[0136] By continuing to interact with the simulated environment using the initially trained intelligent model, the model gradually learns how to select the optimal path in different situations, prioritizing low-latency paths under high load, and finally generating a fully trained intelligent model.

[0137]

[0138] Among them, f θ (s t ) is the unnormalized probability value output by the policy network; softmax converts the output into a probability distribution, allowing the model to select the optimal path based on the current network state; It is based on the new parameters In state s t Choose action a t The probability distribution; θ refers to the model parameters, which remain consistent throughout all instances involving model updates.

[0139] The following are detailed annotations for the parameters:

[0140] In the formula for the loss function L(θ), E t A represents the expected value at time step t, used to measure the average performance of the model at different time points; tThe definition of A t =Q(s) t a t )-V(s t ), indicating that in state s t Take action a t The advantage of `min` is that by comparing the advantages of taking a specific action relative to other actions, it helps the model select the optimal path; `min` is used to limit the impact range of parameter updates, preventing performance instability caused by large adjustments. It ensures that the updated policy does not deviate too far from the old policy; `clip` limits `r`. t The range of (θ) is within [1-∈, 1+∈], in order to control the pace of parameter updates and avoid excessively large update magnitudes;

[0141] The ratio of new to old strategies r t In the formula (θ), π θ (a t |s t ) indicates taking action a under the current parameter θ. t The probability of; This indicates that in the old parameter θ old The probability of taking the same action;

[0142] In the reward mechanism R(s) t a t In the formula, s t This refers to the current network status; a t It refers to the action at the current moment; d t Indicates the data transmission time from source to destination; u t Indicates the efficiency of network bandwidth utilization; p t This indicates the proportion of data packets lost during data transmission; w1, w2, and w3 are used to balance the importance of different objectives, and these weights can be adjusted according to specific application scenarios.

[0143] In the formula for the policy gradient objective function J(θ), τ is a complete trajectory; π θ J(θ) is the policy distribution with parameter θ; J(θ) is the policy gradient objective function, which represents the expected cumulative reward that can be obtained from a series of interactions from the initial state to the final state given the policy parameter θ. Let represent the expected value of all possible trajectories τ, where τ is the expected value according to the current policy π. θ Generated; R(s) represents the cumulative discount reward from time step t = 0 to the final time step T; γ is the discount factor, ranging from [0, 1]; t a t ) is in state s at time step t. t And take action a t The instant rewards received;

[0144] In parameter update θ new In the formula, α controls the step size of each parameter update, which determines the learning speed of the model; the loss function... The gradient with respect to θ indicates the direction of parameter updates; θ old These are the model parameters before the update;

[0145] In action selection probability In the formula, f θ (s t ) is the unnormalized probability value output by the policy network; softmax converts the output into a probability distribution, allowing the model to select the optimal path based on the current network state;

[0146] The following is a brief introduction to the design rationale behind each term of the formula:

[0147] In the reward mechanism R(s) t a t In the formula, w1·(1-d) t The reason for this sub-item's design is the transmission delay d. t It is a key metric for measuring data transmission speed. To encourage models to choose low-latency paths, 1-d is used. t To calculate this part of the reward. When d t When approaching 0, 1-d t A value close to 1 indicates that the path has a low latency, thus warranting a higher reward. Conversely, if d... t If it is higher, then 1-d t The lower the value, the lower the reward. Weight w1 controls the degree to which transmission delay affects the total reward; w2·(1-p t The reason for designing this sub-item is the packet loss rate p. t This represents the proportion of data packets lost during data transmission. To encourage the model to choose reliable paths, 1-p is used. t To calculate this part of the reward. When p t When approaching 0, 1-p t A value close to 1 indicates a low packet loss rate for the path, thus warranting a higher reward. Conversely, if p t If it is higher, then 1-p t The lower the packet loss rate, the lower the reward. Weight w2 controls the degree of impact of packet loss rate on total reward; w3·u t The reason for designing this sub-item is bandwidth utilization u t This represents the efficiency of network bandwidth utilization. To encourage models to make full use of available bandwidth, u is used directly. t To calculate this part of the reward. When u tA value close to 1 indicates high bandwidth utilization, warranting a higher reward; conversely, if u t Lower bandwidth utilization results in lower rewards. Weight w3 controls the degree to which bandwidth utilization affects the total reward.

[0148] The reason for adding up the individual items is as follows:

[0149] By adding these metrics together, we can comprehensively consider three key indicators: transmission delay, packet loss rate, and bandwidth utilization. Each component represents an independent but important performance metric, and the sum of these metrics forms a comprehensive reward value, which fully evaluates the overall performance of the model in taking a certain action under the current state.

[0150] The above formula allows for the construction of a comprehensive reward mechanism to guide the learning direction of the intelligent routing model. Each component is designed to optimize a specific network performance metric, while their sum provides a comprehensive evaluation of the overall system performance. This approach not only improves the accuracy of model selection but also ensures its efficiency and reliability in practical applications.

[0151] The following is a brief introduction to the design rationale behind each term of the formula:

[0152] The updated model parameters θ new In the formula, The reason for this design is that the learning rate α controls the pace of parameter updates, preventing instability caused by excessively large gradients. By multiplying, the magnitude of each update can be flexibly adjusted, ensuring that the model maintains an appropriate update speed at different stages. Different parameters may have different gradient scales, and directly using the gradient may cause some parameters to update too quickly or too slowly. By introducing a learning rate, these updates can be standardized, allowing each parameter to be adjusted at an appropriate rate.

[0153] The reason for adding up the individual items is as follows:

[0154] By using the old parameter θ old Add an increment proportional to the gradient. The parameters were updated. This update method allows the model to move in the direction of reducing the loss function in each iteration, thereby gradually optimizing the model performance.

[0155] The above formula enables efficient updating of model parameters. This method not only ensures that the model can gradually reduce the value of the loss function, but also provides a mechanism through the learning rate α to control the magnitude of the update, thereby guaranteeing the stability and efficiency of the training process. This approach is widely used in the training of various machine learning and deep learning models and is one of the core elements of optimization algorithms.

[0156] Suppose a mobile emergency station at a large fire scene needs to simultaneously support the transmission of high-definition video streams, voice calls, and large amounts of medical data. To ensure the efficiency and reliability of data transmission for these critical tasks, the above-mentioned formula scheme is used for the development and training of an intelligent routing model. The following are the implementation steps and calculation examples:

[0157] Set transmission delay d t For 0.5 seconds, the packet loss rate p t The bandwidth utilization is 0.05, u t It is 0.9.

[0158] The weights w1 = 0.4, w2 = 0.3, and w3 = 0.3 represent the degree of importance attached to transmission delay, packet loss rate, and bandwidth utilization.

[0159] Calculate the immediate reward R(s) t a t ):

[0160] R(s t a t )=w1·(1-d t )+w2·(1-p t )+w3·u t

[0161] R(s t a t = 0.4·(1-0.5)+0.3·(1-0.05)+0.3·0.9

[0162] R(s t a t ) = 0.4·0.5 + 0.3·0.95 + 0.3·0.9

[0163] R(s t a t = 0.2 + 0.285 + 0.27 = 0.755

[0164] Construct a simulated environment in which the hybrid deep learning model can interact with various possible network states. In each interaction, the model takes action based on the current network state and receives corresponding reward feedback, accumulating experience data.

[0165] Assuming a discount factor γ = 0.9, a time step T = 10, and a cumulative reward... for:

[0166]

[0167] If the instantaneous reward at each time step R(s) t a t If both are 0.755, then:

[0168]

[0169] Using the formula for summation of geometric series Where r = 0.9 and n = 10:

[0170]

[0171] J(θ)≈0.755·6.862≈5.178

[0172] Assuming the old parameter θ old The probability of taking the action is The probability of taking the same action under the new parameter θ is π. θ (a t |s t If ) = 0.8, and the clipping range ∈ = 0.2, then:

[0173]

[0174] Calculate the loss function L(θ):

[0175] L(θ)=E t [A t ·min(r t (θ)·A t ,clip(r t (θ), 1-∈, 1+∈)·A t )]

[0176] Assume action advantage function A t =0.5:

[0177] L(θ)=E t [0.5·min(1.333·0.5, clip(1.333, 0.8, 1.2)·0.5)]

[0178] L(θ)=E t [0.5·min(0.6665,0.6·0.5)]

[0179] L(θ)=E t [0.5·0.3]=0.15

[0180] Assuming the learning rate α = 0.01, then:

[0181]

[0182] If θ old =0.5, and

[0183] θnew =0.5 + 0.01·(-0.3) = 0.5 - 0.003 = 0.497

[0184] By continuing to interact with the simulated environment using the initially trained intelligent model, the model gradually learns how to select the optimal path in different situations, prioritizing low-latency paths under high load, and finally generating a fully trained intelligent model.

[0185] Based on the above calculations, the following conclusion can be drawn: the immediate reward R(s) t a t The value of θ = 0.755 indicates that the current path selection strikes a good balance between transmission delay, packet loss rate, and bandwidth utilization. The cumulative reward J(θ) ≈ 5.178 shows that the model performs well in this simulation environment and is expected to achieve a high cumulative reward. The new parameter θ... new =0.497, which is slightly lower than the old parameter, indicating that the model is gradually optimizing its decision-making process to avoid instability caused by large-scale updates.

[0186] Overall, this solution effectively improves the adaptability and stability of the intelligent routing model by introducing a near-end policy optimization algorithm, ensuring that the optimal path can always be found in complex and ever-changing network environments. This significantly improves the efficiency and reliability of data transmission and provides strong technical support for emergency rescue.

[0187] 105. Based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path, and the maximum flow minimum cut theorem in graph theory is used to ensure that the best backup path is quickly switched when the network fails. The ant colony optimization algorithm is used to continuously optimize the path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated.

[0188] In this step, redundant path planning refers to pre-setting one or more backup paths in addition to the primary path, so that the system can quickly switch to the optimal backup path in the event of a network failure. By applying the maximum flow and minimum cut theorem from graph theory, the system can identify critical nodes and links that may cause network outages, ensuring a rapid switch to redundant paths when the primary path fails. Furthermore, ant colony optimization is used to continuously optimize the redundant paths, ensuring that path selection is always optimal. This method greatly improves the system's fault tolerance and reliability.

[0189] Based on the optimal path information determined in the intelligent routing planning scheme, the system pre-selects one or more potential redundant paths as backup options. By applying the maximum flow minimum cut theorem, the maximum flow of the network is calculated, and key nodes and links are identified to ensure rapid switching to redundant paths when the primary path fails. According to the redundant path switching strategy, combined with a dynamic resource allocation strategy, the bandwidth availability and connection priority on the redundant paths are evaluated, and the resource allocation of the redundant paths is adjusted to generate an optimized redundant path configuration. Finally, the ant colony optimization algorithm is used to continuously optimize the redundant paths, ensuring that the path selection is always in an optimal state.

[0190] At the fire scene, the system pre-sets several redundant paths based on the optimal path determined by the intelligent routing planning scheme. Using the maximum flow minimum cut theorem, the system identifies critical nodes and links that may cause network interruptions, ensuring a rapid switch to redundant paths when the primary path fails. For example, when a primary path is interrupted due to building collapse, the system immediately activates a pre-set redundant path, ensuring communication continuity. Furthermore, the system continuously optimizes redundant paths using an ant colony optimization algorithm, ensuring that path selection is always optimal. Throughout the rescue process, regardless of environmental changes, the system can adjust paths promptly, ensuring efficient and reliable data transmission.

[0191] Optionally, in step 105, based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path, and the maximum flow minimum cut theorem in graph theory is used to ensure a rapid switch to the best backup path in the event of a network failure. Ant colony optimization algorithm is used to continuously optimize path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated, including: using the optimal path information determined in the intelligent routing planning scheme to analyze the current network topology and node status; pre-selecting one or more potential redundant paths as backup options based on the characteristics of the optimal path, thus obtaining a list of pre-selected redundant paths; and based on the list of pre-selected redundant paths, applying the maximum flow minimum cut theorem in graph theory to calculate the maximum flow of the network, identifying the key nodes and links that cause network interruption, ensuring a rapid switch to a redundant path in the event of a primary path failure, and generating a redundant path switching strategy. Based on the redundant path switching strategy and combined with the dynamic resource allocation strategy, the bandwidth availability and connection priority on the redundant paths are evaluated. According to task priority and bandwidth demand predictions for a future period, the resource allocation of the redundant paths is adjusted to generate an optimized redundant path configuration. Using the optimized redundant path configuration, an ant colony optimization algorithm is employed to continuously optimize the redundant paths. The ant colony optimization algorithm iteratively searches for the best alternative path from source to destination, generating an optimized alternative path list. Based on the optimized alternative path list, and considering the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, as well as network change trends and real-time performance monitoring data, the configuration of the redundant paths is continuously adjusted. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant path and re-evaluates and optimizes path selection based on the latest network status, generating a redundant path planning scheme.

[0192] Optionally, step 105, based on the optimized backup path list, and considering the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, comprehensively taking into account network change trends and real-time performance monitoring data, continuously adjusts the configuration of the redundant paths. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant paths and re-evaluates and optimizes path selection based on the latest network status to generate a redundant path planning scheme. This includes: predicting network change trends based on the optimized backup path list, combined with the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, to obtain network change trend prediction results; and using the network change trend prediction results to pre-adjust the redundant paths to ensure that the redundant paths have sufficient communication capabilities when needed, generating pre-adjusted redundant paths. The system configures redundant paths. Based on the pre-adjusted redundant path configuration, a real-time performance monitoring mechanism is activated to continuously monitor the performance of the main path and redundant paths, and collect real-time performance monitoring data. Based on the real-time performance monitoring data, the intelligent model evaluates the health status of the main path. If a performance degradation or potential risk is detected in the main path, the optimal backup path is immediately activated, resulting in an activated redundant path. Using the activated redundant path, the intelligent model continues to monitor the performance of the redundant path and further optimizes the path using an ant colony optimization algorithm to ensure the high efficiency and stability of the redundant path, generating an optimized redundant path configuration. Finally, a redundant path planning scheme is generated, which includes preset redundant paths and their switching strategies, as well as the optimized activated redundant path configuration, ensuring that efficient communication capabilities are maintained even when network conditions change.

[0193] In this step, the pre-selected redundant path list includes one or more potential redundant paths pre-selected as backup options based on the optimal path information determined in the intelligent routing planning scheme. These paths are used for rapid switching in the event of network failure, ensuring the continuity and reliability of communication. The maximum flow minimum cut theorem is a graph theory algorithm that identifies critical nodes and links causing network outages by calculating the maximum flow of the network. This theorem ensures rapid switching to redundant paths when the primary path fails, generating a redundant path switching strategy, thereby improving the network's fault tolerance. The dynamic resource allocation strategy refers to rationally adjusting the bandwidth availability and connection priority on redundant paths based on task priorities and bandwidth demand predictions over a future period. This strategy ensures efficient resource utilization and rapid response in case of emergencies. The ant colony optimization algorithm is a heuristic search algorithm that iteratively searches for the best backup path from source to destination by simulating the behavior of ants searching for food. This algorithm can continuously optimize path selection in complex and changing environments, improving path stability and efficiency. The real-time performance monitoring mechanism refers to continuously monitoring the primary and redundant paths, collecting real-time performance monitoring data, such as node status, link quality, and traffic changes. This data is used to assess the stability and reliability of existing transmission paths and to guide the decision-making of intelligent models.

[0194] First, using the optimal path information determined in the intelligent routing planning scheme, the current network topology and node status are analyzed. Based on the characteristics of the optimal path, one or more potential redundant paths are pre-selected as backup options, resulting in a list of pre-selected redundant paths. This step ensures that the system has alternative paths available when needed.

[0195] Secondly, based on the pre-selected redundant path list, the maximum flow and minimum cut theorem in graph theory are applied to identify critical nodes and links that may cause network outages by calculating the maximum flow of the network. This step ensures a rapid switch to redundant paths when the primary path fails, generating a redundant path switching strategy and enhancing the system's fault tolerance.

[0196] Next, based on the redundant path switching strategy and combined with the dynamic resource allocation strategy, the bandwidth availability and connection priority on the redundant paths are evaluated. Based on task priorities and bandwidth demand forecasts for the near future, the resource allocation of the redundant paths is adjusted to generate an optimized redundant path configuration. This process ensures efficient resource utilization and enables rapid response in case of emergencies.

[0197] Furthermore, leveraging the optimized redundant path configuration, an ant colony optimization algorithm is employed to continuously optimize the redundant paths. Through iterative search, the best alternative path from the source to the destination is found, generating an optimized list of alternative paths. This step ensures that path selection is always optimal, improving path stability and efficiency.

[0198] Furthermore, based on the optimized list of backup paths, combined with the results of dynamic resource allocation strategies and intelligent routing planning schemes, network change trends are predicted, yielding network change trend prediction results. Using these prediction results, redundant paths are pre-adjusted to ensure sufficient communication capacity when needed, generating a pre-adjusted redundant path configuration. A real-time performance monitoring mechanism is initiated to continuously monitor the performance of the primary and redundant paths, collecting real-time performance monitoring data. Based on this data, the intelligent model assesses the health status of the primary path. If a performance degradation or potential risk is detected in the primary path, the best backup path is immediately activated, resulting in the activated redundant path. Using the activated redundant path, the intelligent model continues to monitor its performance and further optimizes the path using an ant colony optimization algorithm, ensuring the high efficiency and stability of the redundant path, generating an optimized redundant path configuration.

[0199] The final redundant path planning scheme includes preset redundant paths and their switching strategies, as well as optimized configurations for activating redundant paths, ensuring efficient communication capabilities even when network conditions change.

[0200] In this embodiment of the application, in a wireless communication scenario of a mobile emergency station, it is assumed that the emergency station needs to ensure the continuity and reliability of communication when performing emergency rescue missions. To cope with possible network failures, the system adopts the redundant path planning and continuous optimization method in the above-mentioned optional scheme 105.

[0201] The system first utilizes the optimal path information determined in the intelligent routing planning scheme to analyze the current network topology and node status, pre-selecting one or more potential redundant paths as backup options, thus obtaining a list of pre-selected redundant paths. For example, in a fire scene, the system selects several different backup paths to ensure that there are alternative paths available if the primary path fails.

[0202] Secondly, based on the pre-selected redundant path list, the system applies the maximum flow and minimum cut theorem from graph theory to calculate the maximum flow of the network and identify critical nodes and links that may cause network interruption. For example, by identifying certain critical nodes and links, the system ensures that it can quickly switch to redundant paths when the main path fails, thus enhancing the system's fault tolerance.

[0203] Next, based on the redundancy path switching strategy, the system combines a dynamic resource allocation strategy to evaluate bandwidth availability and connection priority on the redundant paths. For example, the system adjusts the resource allocation of redundant paths based on task priorities and bandwidth demand forecasts for a future period, generating an optimized redundant path configuration. If a redundant path is expected to carry a large amount of video data in the next few minutes, the system will prioritize allocating more bandwidth resources to it.

[0204] Furthermore, leveraging the optimized redundant path configuration, the system employs an ant colony optimization algorithm to continuously optimize the redundant paths. For example, it iteratively searches for the best alternative path from the source to the destination, generating an optimized list of alternative paths. When a redundant path is found to have higher transmission efficiency, the system automatically updates the path selection to ensure that the path selection is always in an optimal state.

[0205] Furthermore, based on the optimized list of backup paths, the system combines the results of dynamic resource allocation strategies and intelligent routing planning to predict network change trends, thus obtaining network change trend prediction results. For example, if the system predicts that the signal in a certain area may weaken due to increased smoke, it will adjust the resource allocation of redundant paths in advance. After activating the real-time performance monitoring mechanism, the system continuously monitors the performance of the main path and redundant paths, collecting real-time performance monitoring data. When a performance degradation of the main path or a potential risk is detected, the intelligent model immediately activates the best backup path to ensure communication continuity. For example, if the main path is interrupted due to a building collapse, the system automatically switches to a pre-set redundant path to ensure uninterrupted communication. Subsequently, the system continues to monitor the performance of redundant paths and further optimizes the paths using ant colony optimization algorithms to ensure the high efficiency and stability of redundant paths, ultimately generating a redundant path planning scheme.

[0206] Through the above steps, the system not only maintains efficient path selection capabilities in complex and ever-changing environments, but also significantly improves the reliability and stability of data transmission, providing strong technical support for emergency rescue.

[0207] This application considers that ensuring the continuity and reliability of data transmission is crucial in the wireless communication environment of mobile emergency stations. Due to the complex and ever-changing network environment in emergency scenarios, traditional static routing algorithms struggle to cope with dynamically changing demands. Therefore, the research team developed an intelligent redundant path planning scheme based on graph theory and ant colony optimization algorithms. This scheme aims to enable the system to quickly switch to the optimal redundant path when the primary path fails, and to continuously optimize path selection, through dynamic resource allocation strategies and real-time performance monitoring. Therefore, a new alternative scheme is proposed, which includes:

[0208] Optionally, in step 105, based on the optimized list of backup paths, and according to the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, the configuration of the redundant paths is continuously adjusted by comprehensively considering network change trends and real-time performance monitoring data. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant paths and re-evaluates and optimizes path selection based on the latest network status to generate a redundant path planning scheme, including:

[0209] Using the optimal path information determined in the intelligent routing planning scheme, the current network topology and node status are analyzed. Based on the characteristics of the optimal path, one or more potential redundant paths are pre-selected as backup options, resulting in a pre-selected redundant path list P. redundant ;

[0210] P redundant ={p1, p2, ..., p i}

[0211] Among them, P redundant : Pre-selected redundant path list; p i It is the i-th potentially redundant path;

[0212] Based on a pre-selected list of redundant paths, and applying the maximum flow and minimum cut theorem in graph theory, the maximum flow C of the network is calculated. max It identifies the key nodes and links that cause network outages, ensures that it can quickly switch to a redundant path when the primary path fails, and generates a redundant path switching strategy.

[0213]

[0214] Among them, C max The maximum flow of a network; S is a set of nodes in the network; It is the complement of S, that is, the set of nodes that are not in S; c(u, v) is the capacity of edge (u, v);

[0215] Based on the redundant path switching strategy and the dynamic resource allocation strategy, evaluate the bandwidth availability B on the redundant path. i and connection priority P i Based on task priority and bandwidth requirements in the near future, predict D future Adjust the resource allocation of redundant paths to generate an optimized redundant path configuration;

[0216] R i =f(B i P i D future )

[0217] Among them, R i It is a redundant path p i Resource allocation; B i It is a redundant path p i Bandwidth availability on P; i It is a redundant path p i Connection priority; D future This is a forecast of bandwidth demand over a period of time.

[0218] Using the optimized redundant path configuration, the ant colony optimization algorithm is used to continuously optimize the redundant paths. The ant colony optimization algorithm finds the best alternative path from the source to the destination through iterative search and generates an optimized alternative path list.

[0219] Update path quality using the following formula:

[0220] q(t+1) = Q(t) + ΔQ(t)

[0221] Where Q(t+1) is the updated path quality at time step t+1; Q(t) is the path quality at time step t; and ΔQ(t) is the path quality increment between time step t and t+1.

[0222] The pheromone concentration is updated using the following formula:

[0223] τ ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij (t)

[0224] Where, τ ij (t+1) is the updated pheromone concentration at time step t+1; τ ij (t) is the pheromone concentration on edge (i, j) at time step t; ρ is the pheromone evaporation rate; Δτ ij (t) is the amount of pheromone added on edge (i, j) between time step t and t+1;

[0225] Based on the optimized list of backup paths, and taking into account network change trends and real-time performance monitoring data, the configuration of redundant paths is continuously adjusted. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant path and re-evaluates and optimizes the path selection according to the latest network status, ultimately generating a redundant path planning scheme.

[0226] The following are detailed annotations for the parameters:

[0227] In the pre-selected redundant path list P redundant In the formula, P redundant It is a pre-selected list of redundant paths, representing a pre-selected set of potential redundant paths; p i This is the i-th potential redundant path. Each path is determined based on network topology and node state analysis, serving as a backup option when the primary path fails.

[0228] In calculating the maximum flow C of the network max In the formula, C max S is the maximum flow in the network, representing the maximum possible flow from the source to the destination; S is a set of nodes in the network. It is the complement of S, that is, the set of nodes not in S; c(u, v) is the capacity of edge (u, v), which represents the maximum amount of data that the link connecting nodes u and v can carry;

[0229] In redundant path resource allocation R i In the formula, R i It is a redundant path p i Resource allocation is expressed as a function of bandwidth availability, connection priority, and future bandwidth demand forecasts; B i It is a redundant path p i Bandwidth availability on a path indicates the bandwidth resources that the path can currently provide; P i It is a redundant path p i The connection priority reflects the importance and preference of the path among all redundant paths; D future It is a forecast of bandwidth demand over a period of time in the future, used to assess the bandwidth resources required for future tasks and ensure the forward-looking nature of resource allocation;

[0230] In the formula for updating path quality Q(t+1), Q(t+1) is the updated path quality at time step t+1, representing the overall performance of the path after one iteration; Q(t) is the path quality at time step t, representing the current performance level of the path; ΔQ(t) is the path quality increment between time step t and t+1, representing the performance improvement or decline brought about by adjusting the path through the optimization algorithm.

[0231] The following is a brief introduction to the design rationale behind each term of the formula:

[0232] In updating pheromone concentration τ ij In the formula (t+1), (1-ρ)·τ ij (t) The design of this sub-item stems from the ability to precisely control the evaporation rate of pheromones through multiplication. A larger ρ value leads to more pheromone evaporation, while a smaller ρ value results in more pheromone retention. This flexibility allows for adjustments to pheromone persistence in different application scenarios to meet varying needs. Multiplication ensures the standardization of the pheromone renewal process, ensuring each renewal occurs within a controllable range and avoiding instability caused by excessively high or low pheromone concentrations. Δτ ij (t) This component is designed so that whenever an ant successfully finds a valid path, it leaves pheromones on the path to mark its quality. This is achieved by increasing Δτ. ij (t) can reinforce proven effective paths, making subsequent ants more likely to choose these paths. The increase in pheromones provides a positive feedback mechanism, making high-performing paths more popular in future selections, thereby gradually optimizing path selection.

[0233] Here are the reasons for adding up the individual items:

[0234] By using an additive approach, both pheromone evaporation and new additions can be considered simultaneously. This maintains a memory of historical paths while incorporating feedback on the latest path quality. This helps the algorithm find a balance between exploring new paths and utilizing existing ones. After each iteration, the pheromone concentration is updated based on the current path quality and historical performance. This method allows the algorithm to dynamically respond to network changes and continuously optimize path selection.

[0235] The above formula enables efficient updating of pheromone concentration. This method not only simulates the behavior of pheromones in nature but also provides a mechanism to balance the memory of historical paths with the exploration of new paths, thereby ensuring that the ant colony optimization algorithm can continuously optimize path selection in complex and ever-changing environments. This approach is widely used in various path optimization problems, such as routing and logistics distribution, significantly improving the accuracy and efficiency of path selection.

[0236] Suppose a mobile emergency station at a large fire scene needs to simultaneously support the transmission of high-definition video streams, voice calls, and large amounts of medical data. To ensure the efficiency and reliability of data transmission for these critical tasks, the above-mentioned formula scheme is used for the research and training of intelligent redundant path planning.

[0237] The following are the implementation steps and calculation examples:

[0238] Suppose a mobile emergency station at a large fire scene needs to simultaneously support the transmission of high-definition video streams, voice calls, and large amounts of medical data. To ensure the efficiency and reliability of data transmission for these critical tasks, the above-mentioned formula scheme is used for the research and training of intelligent redundant path planning.

[0239] Analyze the current network topology and node status, pre-select one or more potential redundant paths as backup options, and obtain a list of pre-selected redundant paths P. redundant ={p1, p2, ..., p i}

[0240] Suppose three potentially redundant paths are chosen: p1, p2, and p3.

[0241] Calculate the maximum flow C of the network max :

[0242]

[0243] Assuming that C is obtained through calculation max =50Mbps. This means that at any split point in the network, the maximum possible traffic from source to destination is 50Mbps.

[0244] Based on the redundant path switching strategy and the dynamic resource allocation strategy, evaluate the bandwidth availability B on the redundant path. i and connection priority P i Based on task priority and bandwidth requirements in the near future, predict D future Adjust the resource allocation of redundant paths and generate an optimized redundant path configuration R. i :

[0245] R i =f(B i P i D future )

[0246] Assuming for path p1, B1 = 40 Mbps, P1 = 0.8 (high priority), D future =35Mbps, then R1 may be set to a bandwidth allocation of 35Mbps.

[0247] The ant colony optimization algorithm is used to continuously optimize redundant paths. The best alternative path from the source to the destination is found through iterative search, and an optimized alternative path list is generated.

[0248] Update path quality Q(t):

[0249] Q(t+1) = Q(t) + ΔQ(t)

[0250] Assuming the initial path quality Q(0) = 0.7, and the path quality increment ΔQ(0) = 0.1 after one iteration, then the updated path quality is:

[0251] Q(1) = 0.8.

[0252] Update pheromone concentration τ ij (t):

[0253] τ ij (t+1)=(1-ρ)·τ ij (T)+Δτ ij (T)

[0254] Assuming the pheromone evaporation rate ρ = 0.1, and the initial pheromone concentration τ ij (0) = 0.5, the increase in pheromone amount Δτ after one iteration ij If (0) = 0.2, then the updated pheromone concentration τ ij (1) = (1-0.1)·0.5+0.2 = 0.65.

[0255] When a performance degradation or potential risk is detected in the main path, the intelligent model automatically activates several redundant paths and re-evaluates and optimizes path selection based on the latest network status, ultimately generating a redundant path planning scheme.

[0256] If the performance of the main path degrades, the system automatically activates the redundant path p1 and re-evaluates other paths, such as p2 and p3, based on the latest network status and prediction results to ensure that the optimal path is selected.

[0257] Through the above calculations, a set of potential redundant paths can be pre-selected by analyzing the network topology and node status, ensuring that alternative paths are available when the primary path fails. The calculated C... max =50Mbps indicates the network's maximum carrying capacity, helping to identify critical nodes and links that may cause network outages. By evaluating the bandwidth availability and connection priority of redundant paths and combining this with future bandwidth demand forecasts, resources are rationally allocated to ensure the effective utilization of redundant paths. By continuously updating path quality and pheromone concentration, the ant colony optimization algorithm can iteratively find the best backup path, improving the accuracy and efficiency of path selection. When a performance degradation of the primary path or a potential risk is detected, the intelligent model can automatically activate redundant paths and re-evaluate and optimize path selection based on the latest network status, ensuring the continuity and reliability of data transmission.

[0258] Overall, by introducing graph theory and ant colony optimization algorithms, this scheme effectively improves the adaptability and stability of intelligent redundant path planning, ensuring that the optimal path can always be found in complex and ever-changing network environments. This significantly improves the efficiency and reliability of data transmission, providing strong technical support for emergency rescue.

[0259] Figure 2 This application provides a schematic diagram of the wireless communication network system for a mobile emergency station, as shown in the embodiment. Figure 2 As shown, the system includes:

[0260] The monitoring and evaluation module 21 is used to monitor and evaluate the signal strength, interference level and channel occupancy in the surrounding environment in real time, select the optimal operating frequency band, and adjust the frequency band switching strategy to obtain an adaptive multi-band access mechanism.

[0261] The adjustment and estimation module 22 is used to dynamically adjust the bandwidth and connection priority of the wireless communication network according to the optimal operating frequency band determined by the adaptive multi-band access mechanism, evaluate the task priority, and estimate the bandwidth demand in the future period of time. At the same time, it simulates the resource competition between different users and generates a dynamic resource allocation strategy.

[0262] Deployment synchronization module 23 is used to deploy a distributed cache and synchronization system based on the task priority and bandwidth allocation defined in the dynamic resource allocation strategy, to achieve balanced data distribution and fast location, and to use version vector clock to manage concurrent updates, while achieving cross-site data synchronization, reducing dependence on the central server, and generating a distributed temporary data cache pool.

[0263] The prediction calculation module 24 is used to establish a deep reinforcement learning intelligent routing algorithm using the data in the distributed cache pool. The intelligent routing algorithm considers the current network topology and node status, predicts network change trends, calculates the optimal transmission path from source to destination, and finally generates an intelligent routing planning scheme.

[0264] The optimization generation module 25 is used to pre-define a redundant path on the path based on the optimal path information determined in the intelligent routing planning scheme, and to ensure rapid switching to the best backup path in the event of network failure through the maximum flow minimum cut theorem in graph theory algorithm. It also uses ant colony optimization algorithm to continuously optimize path selection and generate a redundant path planning scheme based on the dynamic resource allocation strategy and the results of intelligent routing planning.

[0265] Figure 2 The wireless communication network system of the mobile emergency station can perform... Figure 1 The implementation principle and technical effects of the wireless communication network method for mobile emergency stations described in the illustrated embodiments will not be repeated here. The specific methods by which each module and unit of the wireless communication network system for mobile emergency stations in the above embodiments perform operations have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0266] In one possible design, Figure 2 The wireless communication network system of the mobile emergency station in the illustrated embodiment can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0267] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0268] The processing component 32 is used to: monitor and evaluate the signal strength, interference level, and channel occupancy rate in the surrounding environment in real time; select the optimal operating frequency band and adjust the frequency band switching strategy to obtain an adaptive multi-band access mechanism; dynamically adjust the bandwidth and connection priority of the wireless communication network according to the optimal operating frequency band determined by the adaptive multi-band access mechanism; evaluate task priorities and predict bandwidth requirements in the future; simulate resource competition between different users to generate a dynamic resource allocation strategy; and deploy a distributed caching and synchronization system based on the task priorities and bandwidth allocation defined in the dynamic resource allocation strategy to achieve balanced data distribution and rapid location, and use a version vector clock to manage concurrent updates while achieving cross-site... Data synchronization reduces reliance on a central server, generating a distributed temporary data cache pool. Using the data in this distributed cache pool, a deep reinforcement learning-based intelligent routing algorithm is established. This algorithm considers the current network topology and node states, predicts network change trends, calculates the optimal transmission path from source to destination, and ultimately generates an intelligent routing planning scheme. Based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path. The maximum flow minimum cut theorem in graph theory ensures a rapid switch to the best backup path in case of network failure. Ant colony optimization continuously optimizes path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated.

[0269] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0270] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0271] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0272] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0273] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0274] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0275] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The wireless communication network method for a mobile emergency station shown in the embodiment.

[0276] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0277] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0278] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0279] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A wireless communication network method for a mobile emergency station, characterized in that, include: By real-time monitoring and evaluation of signal strength, interference level and channel occupancy in the surrounding environment, the optimal operating frequency band is selected and the frequency band switching strategy is adjusted to obtain an adaptive multi-band access mechanism. Based on the optimal operating frequency band determined by the adaptive multi-band access mechanism, the bandwidth and connection priority of the wireless communication network are dynamically adjusted, the task priority is evaluated, and the bandwidth demand in the future period is estimated. At the same time, the resource competition between different users is simulated to generate a dynamic resource allocation strategy. Based on the task priorities and bandwidth allocation defined in the dynamic resource allocation strategy, a distributed caching and synchronization system is deployed to achieve balanced data distribution and rapid data location. A version vector clock is used to manage concurrent updates, while cross-site data synchronization is achieved, reducing dependence on the central server and generating a distributed temporary data cache pool. Using the data in the distributed temporary data cache pool, a deep reinforcement learning-based intelligent routing algorithm is established. The intelligent routing algorithm considers the current network topology and node status, predicts network change trends, calculates the optimal transmission path from source to destination, and finally generates an intelligent routing planning scheme. Based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path, and the maximum flow minimum cut theorem in graph theory is used to ensure rapid switching to the best backup path in the event of network failure. The ant colony optimization algorithm is used to continuously optimize the path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated.

2. The method according to claim 1, characterized in that, The method utilizes data from the distributed temporary data cache pool to establish a deep reinforcement learning-based intelligent routing algorithm. This intelligent routing algorithm considers the current network topology and node states, predicts network change trends, calculates the optimal transmission path from source to destination, and ultimately generates an intelligent routing planning scheme, including: By utilizing historical communication records, node status information, and multi-source heterogeneous data of network topology in a distributed temporary data cache pool, the multi-source heterogeneous data is cleaned, transformed, and normalized to obtain the feature vector input to the hybrid deep reinforcement learning model, and an optimized feature dataset is generated. Based on the optimized feature dataset, a hybrid deep reinforcement learning model is constructed that integrates convolutional neural networks for spatial feature extraction and recurrent neural networks for time series analysis. This hybrid deep reinforcement learning model can capture the spatial correlation and time-varying trends of network topology, generating an intelligent decision-making framework suitable for dynamic network environments. Based on the intelligent decision-making framework applicable to dynamic network environments, the near-end policy optimization algorithm is adopted as the core of the reinforcement learning framework, and combined with the reward mechanism in the actual network environment, the hybrid deep reinforcement learning model is trained. The hybrid deep reinforcement learning model is continuously optimized through interaction with the simulated environment, learns the ability to select the optimal path in different situations, and finally generates a trained intelligent model. Using the trained intelligent model, the optimal transmission path from source to destination is calculated based on the current network status and predictions of possible network changes in the future, and an intelligent routing planning scheme is finally generated.

3. The method according to claim 2, characterized in that, Based on the optimized feature dataset, a hybrid deep reinforcement learning model is constructed, which integrates convolutional neural networks for spatial feature extraction and recurrent neural networks for time series analysis. This hybrid deep reinforcement learning model can capture the spatial correlation and temporal trends of network topology, generating an intelligent decision-making framework suitable for dynamic network environments, including: Using the optimized feature dataset, the spatial distribution of network topology and node states is modeled. Multi-layer convolution operations are performed on the feature dataset through a convolutional neural network to capture the spatial correlation and local patterns between network nodes, thereby obtaining a spatial feature representation. Based on the spatial feature representation, and further combined with the time series information of node states, a recurrent neural network is used to process the network state data that changes over time in order to capture the temporal dependencies and dynamic trends, and generate a time series feature representation. Based on the spatial feature representation and the time series feature representation, a hybrid model is designed. The hybrid model can process information in both spatial and temporal dimensions simultaneously and introduces an attention mechanism to focus on important spatiotemporal features, thereby improving the accuracy and efficiency of decision-making and obtaining an intelligent decision-making framework that integrates spatiotemporal features. By utilizing an intelligent decision-making framework that integrates spatiotemporal features, an intelligent decision-making system suitable for dynamic network environments is constructed. This intelligent decision-making system considers the spatial layout and node status of the current network topology, predicts network change trends over a future period, provides strong support for intelligent routing algorithms, and generates an intelligent decision-making framework suitable for dynamic network environments.

4. The method according to claim 2, characterized in that, The intelligent decision-making framework applicable to dynamic network environments employs a near-end policy optimization algorithm as the core of the reinforcement learning framework, combined with reward mechanisms in real-world network environments, to train the hybrid deep reinforcement learning model. This allows the hybrid deep reinforcement learning model to continuously optimize through interaction with a simulated environment, learning to select the optimal path in different situations, ultimately generating a trained intelligent model, including: Based on an intelligent decision-making framework suitable for dynamic network environments, a reinforcement learning framework with a near-end policy optimization algorithm as its core is designed. The reinforcement learning framework continuously adjusts and optimizes model parameters through interaction with the simulated environment, ensuring that the model can make the optimal path selection in complex and ever-changing network environments. Based on the intelligent decision-making framework, a reward mechanism that conforms to the communication characteristics of mobile emergency stations is defined. The reward mechanism includes minimizing transmission latency, reducing packet loss rate, and maximizing bandwidth utilization. It is used to evaluate the performance of the model in different scenarios and guide the learning direction of the intelligent model to obtain the optimization objective function. Using the aforementioned optimization objective function, a simulation environment is constructed, enabling the hybrid deep reinforcement learning model to interact with various possible network conditions within the simulation environment. In each interaction, the hybrid deep reinforcement learning model takes action based on the current network state and receives corresponding reward feedback to accumulate experience data. Based on the empirical data, the model parameters are updated using a proximal policy optimization algorithm. This algorithm avoids performance instability caused by excessively large update magnitudes by limiting the pace of parameter updates, thereby ensuring the stability and convergence of the hybrid deep reinforcement learning model during training and generating an intelligent model that has undergone preliminary training. The pre-trained intelligent model continues to interact with the simulation environment. The model gradually learns how to select the optimal path in different situations, prioritizing low-latency paths under high load, and finally generating a trained intelligent model.

5. The method according to claim 2, characterized in that, The process involves using the trained intelligent model to calculate the optimal transmission path from source to destination based on the current network state and predictions of potential network changes over a future period, ultimately generating an intelligent routing plan, including: Based on the trained intelligent model, the current network status is monitored and data is collected in real time. The data includes node load, connection quality, and traffic patterns to obtain the latest network status information. Using the latest network status information and the time series analysis capabilities embedded in the intelligent model, the network change trend in the future is predicted, and network change trend prediction results are generated. Based on the network change trend prediction results, the intelligent model evaluates multiple transmission paths. By comprehensively considering the node status on the path, the expected network change trend, and the actual transmission demand, the expected performance index of each path is calculated to obtain the path performance evaluation result. Based on the path performance evaluation results, the intelligent model selects a path that meets the transmission requirements and has the best performance as the main path, giving priority to paths that can still maintain efficient transmission under high load or network congestion, and generating the optimal transmission path. For the optimal transmission path, the intelligent model initiates a dynamic monitoring mechanism to continuously monitor the real-time performance of the optimal transmission path, including node status, link quality, and traffic changes, and obtains dynamic monitoring results. Using the dynamic monitoring results, the intelligent model evaluates the stability and reliability of existing transmission paths. When it detects that the performance of the existing transmission path has deteriorated or there is a potential risk, the intelligent model automatically re-evaluates other transmission paths and obtains the updated optimal transmission path based on the latest network status and prediction results. Based on the updated optimal transmission path, a smart routing plan is finally generated. The smart routing plan includes the optimal transmission path from source to destination and provides a mechanism that can dynamically adapt to network changes to ensure the continuity and reliability of data transmission.

6. The method according to claim 1, characterized in that, Based on the optimal path information determined in the intelligent routing planning scheme, a redundant path is pre-defined on the path, and the maximum flow minimum cut theorem in graph theory is used to ensure rapid switching to the best backup path in the event of network failure. Ant colony optimization algorithm is used to continuously optimize path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated, including: Using the optimal path information determined in the intelligent routing planning scheme, the current network topology and node status are analyzed. Based on the characteristics of the optimal path, one or more potential redundant paths are pre-selected as backup options to obtain a list of pre-selected redundant paths. Based on the pre-selected redundant path list, the maximum flow and minimum cut theorem in graph theory are applied to calculate the maximum flow of the network, identify the key nodes and links that cause network interruption, and ensure that the network can be quickly switched to a redundant path when the main path fails, thereby generating a redundant path switching strategy. Based on the redundant path switching strategy and combined with the dynamic resource allocation strategy, the bandwidth availability and connection priority on the redundant path are evaluated. Based on the task priority and the bandwidth demand forecast for a period of time in the future, the resource allocation of the redundant path is adjusted to generate an optimized redundant path configuration. Using the optimized redundant path configuration, the ant colony optimization algorithm is used to continuously optimize the redundant paths. The ant colony optimization algorithm finds the best alternative path from the source to the destination through iterative search and generates an optimized alternative path list. Based on the optimized list of backup paths, and taking into account the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, the configuration of the redundant paths is continuously adjusted, taking into account network change trends and real-time performance monitoring data. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant paths and re-evaluates and optimizes the path selection based on the latest network status, generating a redundant path planning scheme.

7. The method according to claim 6, characterized in that, Based on the optimized list of backup paths, and considering the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, the system continuously adjusts the configuration of redundant paths, taking into account network change trends and real-time performance monitoring data. When a performance degradation of the primary path or a potential risk is detected, the intelligent model automatically activates the redundant paths and re-evaluates and optimizes path selection based on the latest network status, generating a redundant path planning scheme, including: Based on the optimized list of alternative paths, combined with the results of the dynamic resource allocation strategy and the intelligent routing planning scheme, the network change trend is predicted, and the network change trend prediction result is obtained. Using the network change trend prediction results, the redundant paths are pre-adjusted to ensure that the redundant paths have sufficient communication capabilities when needed, and a pre-adjusted redundant path configuration is generated. Based on the pre-adjusted redundant path configuration, a real-time performance monitoring mechanism is activated to continuously monitor the performance of the main path and redundant paths and collect real-time performance monitoring data. Based on the real-time performance monitoring data, the intelligent model assesses the health status of the main path. If a performance degradation or potential risk is detected in the main path, the best backup path is immediately activated to obtain the activated redundant path. The intelligent model is used to continue monitoring the performance of the activated redundant paths, and the paths are further optimized by combining the ant colony optimization algorithm to ensure the high efficiency and stability of the redundant paths and generate an optimized redundant path configuration. Finally, a redundant path planning scheme is generated, which includes preset redundant paths and their switching strategies, as well as the optimized configuration for activating redundant paths, to ensure that efficient communication capabilities are maintained even when network conditions change.

8. A wireless communication network system for a mobile emergency station, characterized in that, include: The monitoring and evaluation module is used to monitor and evaluate the signal strength, interference level and channel occupancy in the surrounding environment in real time, select the optimal operating frequency band, and adjust the frequency band switching strategy to obtain an adaptive multi-band access mechanism. The adjustment and estimation module is used to dynamically adjust the bandwidth and connection priority of the wireless communication network according to the optimal operating frequency band determined by the adaptive multi-band access mechanism, evaluate task priority, and estimate bandwidth demand in the future period of time. At the same time, it simulates resource competition between different users and generates dynamic resource allocation strategies. The deployment synchronization module is used to deploy a distributed caching and synchronization system based on the task priority and bandwidth allocation defined in the dynamic resource allocation strategy, so as to achieve balanced data distribution and fast location, and use version vector clock to manage concurrent updates, while achieving cross-site data synchronization, reducing dependence on the central server, and generating a distributed temporary data cache pool. The prediction calculation module is used to establish a deep reinforcement learning-based intelligent routing algorithm using data in the distributed temporary data cache pool. The intelligent routing algorithm considers the current network topology and node status, predicts network change trends, calculates the optimal transmission path from source to destination, and finally generates an intelligent routing planning scheme. The optimization generation module is used to pre-define a redundant path on the path based on the optimal path information determined in the intelligent routing planning scheme. It also uses the maximum flow minimum cut theorem in graph theory to ensure a rapid switch to the best backup path in the event of a network failure. The ant colony optimization algorithm is used to continuously optimize the path selection. Based on the dynamic resource allocation strategy and the results of intelligent routing planning, a redundant path planning scheme is generated.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a wireless communication network method for a mobile emergency station as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a wireless communication network method for a mobile emergency station as described in any one of claims 1 to 7.

Images