A dynamic access method for multi-user collaborative learning based on the integration of air, land, and sea

Abstract

This invention discloses a multi-user collaborative learning dynamic access method based on an integrated air-space-ground-sea network for use in the communications field. The method includes the following steps: analyzing the requirements of the integrated air-space-ground-sea information network and designing a comprehensive network architecture including satellites, UAVs, ships, and ground stations; defining unified interfaces and protocols for satellites, UAVs, ships, and ground stations in the comprehensive network architecture and establishing a network coordination mechanism; formulating collaborative strategies and communication protocols among multiple users based on the network coordination mechanism; optimizing the collaborative strategies and communication protocols among multiple users using a particle swarm optimization algorithm; and using a time series prediction model to predict the impact of the optimized collaborative strategies and communication protocols on the requirements of the integrated air-space-ground-sea information network and user behavior. This invention ensures that the network design can meet the diversity and complexity of practical applications by deeply analyzing the needs of different user groups and predicting data traffic and service types.

Description

Technical Field

[0001] The present invention relates to the field of communications, and in particular to a multi-user collaborative learning dynamic access method based on the integration of air, land, and sea. Background Art

[0002] The integrated information network of air, space, land and sea is an advanced network system based on the ground network and extended through the space-based network. It adopts a unified technical architecture, unified technical system and unified standard specifications. It is composed of the interconnection of space-based information network, Internet, mobile communication network and other key components. It has the remarkable characteristics of diversified business carrying capacity, efficient interconnection between heterogeneous networks and comprehensive management of global resources. On this basis, the integrated information network of air, space, land and sea also includes a wide range of applications from satellites to drones and ground stations, forming a true integrated network of sky, land and sea. This expansion not only enhances the network's coverage and service scope, but also improves its application flexibility and responsiveness in various environments and situations.

[0003] The integrated air-ground-sea information network can provide stable and reliable communication services in various complex environments, especially in the integrated applications of air-ground-sea from satellite to drones and ground stations. This network can effectively connect and manage various types of communication equipment and platforms to ensure the fast and accurate transmission of information, thereby improving the overall efficiency of the network and its ability to respond to various emergencies.

[0004] The network design in the existing technology often does not conduct in-depth analysis of the needs of different user groups, resulting in the inability to fully meet the specific needs of users in different scenarios. The lack of targeted network design may lead to poor user experience and inefficient resource utilization. Traditional network design may not fully consider the particularities of the air, land, and sea environments, such as coverage, service capabilities, and adaptability in different application scenarios. As a result, the network may perform poorly in these special environments and cannot effectively cope with various complex scenarios. In multi-component networks, compatibility and coordination issues between different components are a common challenge. Traditional networks may lack unified interfaces and protocols, resulting in inefficient communication and collaboration between different components, affecting the efficiency and reliability of the entire network.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In order to overcome the above problems, the present invention aims to propose a multi-user collaborative learning dynamic access method based on the integration of air, land, and sea. The purpose is to solve the problem that the network design in the prior art often does not deeply analyze the needs of different user groups, resulting in the inability to fully meet the specific needs of users in different situations. The lack of targeted network design may lead to poor user experience and inefficient resource utilization.

[0007] To this end, the specific technical solution adopted by the present invention is as follows:

[0008] A multi-user collaborative learning dynamic access method based on air-space-ground-sea integration, the multi-user collaborative learning dynamic access method comprising the following steps:

[0009] S1. Analyze the requirements of integrated information network for air, land, and sea, and design a comprehensive network architecture including satellites, drones, ships, and ground stations;

[0010] S2. Define unified interfaces and protocols for satellites, drones, ships, and ground stations in an integrated network architecture, and establish a network coordination mechanism;

[0011] S3. Based on the network coordination mechanism, formulate the collaboration strategy and communication protocol among multiple users;

[0012] S4, using particle swarm algorithm to optimize the collaboration strategy and communication protocol among multiple users;

[0013] S5. Use the time series prediction model to predict the impact of the optimized collaboration strategy and communication protocol on the demand and user behavior of the integrated air-space-ground-sea information network, and adjust resource allocation and network configuration.

[0014] Optionally, analyzing the requirements for an integrated air-space-ground-sea information network and designing a comprehensive network architecture including satellites, drones, ships, and ground stations includes the following steps:

[0015] S11. Conduct demand analysis on the needs of different user groups, data traffic forecasts, and service types in the integrated air, land, and sea information network;

[0016] S12. Determine the network topology, node distribution and transmission path based on the results of demand analysis, and design a comprehensive network architecture;

[0017] S13. Select components including satellites, drones, ships and ground stations for the integrated air, land, and sea information network;

[0018] S14. Based on the components of the integrated air-space-land-sea information network, use a network simulator to evaluate the performance indicators of the integrated network architecture.

[0019] Optionally, formulating a collaboration strategy and a communication protocol among multiple users based on a network coordination mechanism includes the following steps:

[0020] S31. Analyze the way in which network coordination mechanisms handle resource allocation, data transmission, and network security;

[0021] S32. Formulate a collaboration strategy among multiple users based on their interaction and communication needs;

[0022] S33. Build a communication protocol that adapts to multi-user collaboration and is compatible with the network coordination mechanism;

[0023] S34. Integrate the collaboration strategy and communication protocol into the network coordination mechanism for testing;

[0024] S35. Analyze the test results and optimize the collaboration strategy and communication protocol.

[0025] Optionally, optimizing the collaboration strategy and communication protocol among multiple users using a particle swarm algorithm includes the following steps:

[0026] S41, defining the optimization objectives of the collaboration strategy and communication protocol among multiple users, and setting the parameters of the particle swarm algorithm;

[0027] S42, randomly initialize the position and speed of each particle in the particle swarm, where the position represents different cooperation strategies and communication protocol schemes, and the speed represents the trend and amplitude of the scheme adjustment;

[0028] S43, for each collaboration strategy and communication protocol scheme, calculating the fitness according to the position of the collaboration strategy and communication protocol scheme, and evaluating the efficiency of the current collaboration strategy and communication protocol scheme;

[0029] S44, setting the individual optimal solution of each particle as the initial particle position, and obtaining the global optimal solution according to the particle comparison criterion;

[0030] S45. If the fitness of the current cooperation strategy and communication protocol scheme is better than the historical optimal fitness, the individual optimal position is updated, and the particle with the best fitness is found among all particles to update the global optimal position;

[0031] S46, adjusting the speed and position of each particle according to the speed and position update formula of the particle swarm optimization algorithm;

[0032] S47, check whether the preset maximum number of iterations is reached, if so, execute step S48; if not, return to step S44;

[0033] S48. Output the final optimal particle position and obtain the optimal multi-user collaboration strategy and communication protocol solution.

[0034] Optionally, for each collaboration strategy and communication protocol scheme, calculating the fitness according to the position of the collaboration strategy and communication protocol scheme, and evaluating the efficiency of the current collaboration strategy and communication protocol scheme includes the following steps:

[0035] S431, constructing a fitness function;

[0036] S432, for each cooperation strategy and communication protocol scheme in the particle swarm algorithm, using the fitness function to calculate the fitness value of the cooperation strategy and communication protocol scheme;

[0037] S433, analyzing the fitness values ​​of the collaboration strategies and communication protocol solutions, and evaluating the efficiency of the fitness values ​​in the integrated information network of air, land, and sea;

[0038] S434. Adjust the fitness value according to the performance result of the evaluated efficiency.

[0039] Optionally, setting the individual optimal solution of each particle as the initial particle position and obtaining the global optimal solution according to the particle comparison criterion includes the following steps:

[0040] S441, setting the initial position of the particle as the optimal solution of the individual particle;

[0041] S442, obtaining the fitness values ​​of the cooperation strategy and the communication protocol scheme, and evaluating the quality of the particles according to the particle comparison criterion;

[0042] S443, obtaining the particle with the highest fitness by comparing the fitness values ​​of all particles;

[0043] S444. The position of the particle with the highest fitness is taken as the current global optimal solution.

[0044] Optionally, if the fitness of the current cooperation strategy and communication protocol scheme is better than the historical optimal fitness, the individual optimal position is updated, and the particle with the best fitness is found among all particles. Updating the global optimal position includes the following steps:

[0045] S451. If the current fitness of a particle is better than its historical optimal fitness, the current position of the particle is updated to a new individual optimal solution;

[0046] S452. In the entire particle swarm, compare the current individual optimal solutions of all particles;

[0047] S453, find the particle with the highest fitness among the particles, and obtain the current global optimal solution;

[0048] S454. Record the update status of the individual optimal solution and the global optimal solution of each particle.

[0049] Optionally, the speed and position update formula according to the particle swarm optimization algorithm is:

[0050] ;

[0051] ;

[0052] In the formula, Indicates the trend and magnitude of parameter adjustments of collaboration strategies or communication protocols;

[0053] Parameters representing collaboration strategies or communication protocols;

[0054] represents the inertia weight;

[0055] , All represent learning factors;

[0056] Parameters representing the current collaboration strategy or communication protocol;

[0057] represents the current individual optimal solution;

[0058] represents the current global optimal solution;

[0059] Represents the parameters of an updated collaboration policy or communication protocol.

[0060] Optionally, using a time series prediction model to predict the impact of the optimized collaboration strategy and communication protocol on the air-space-ground-sea integrated information network demand and user behavior, and adjusting resource allocation and network configuration includes the following steps:

[0061] S51. Collect historical data of the integrated information network of air, land, and sea;

[0062] S52, selecting a time series prediction model, and setting the attenuation factor, lag factor and index of the time series prediction model;

[0063] S53, inputting the attenuation factor, the lag factor and the index into the time series prediction model, and fitting the time series prediction model using historical data;

[0064] S54, verifying the performance of the time series prediction model by comparing the predicted values ​​of the time series prediction model with the actual observed values;

[0065] S55. Use the fitted model to predict network demand and user behavior within the next day;

[0066] S56. Adjust the collaboration strategy and communication protocol among multiple users according to the network demand and user behavior predicted by the model;

[0067] S57. Adjust resource allocation based on prediction results to optimize the performance of the integrated air-space-ground-sea information network.

[0068] Optionally, inputting the attenuation factor, the lag factor and the index into the time series prediction model, and fitting the time series prediction model using historical data includes the following steps:

[0069] S531, inputting the attenuation factor, the lag factor and the index into the time series prediction model;

[0070] S532, dividing the historical data into a training set and a test set;

[0071] S533, fitting the time series prediction model using the training set data;

[0072] S534. Check the output of the time series prediction model;

[0073] S535. Perform a preliminary evaluation based on the model fitting results, and adjust the attenuation factor, lag factor and index of the time series prediction model based on the evaluation results;

[0074] S536. Use the test set data to verify the adjusted time series prediction model.

[0075] Compared with the prior art, this application has the following beneficial effects:

[0076] 1. The present invention ensures that the network design can meet the diversity and complexity of actual applications by deeply analyzing the needs of different user groups and predicting data traffic and service types. The detailed demand analysis provides a solid foundation for network design, ensuring that the network can effectively meet the actual needs of users. Taking into account the particularities of the air, land, and sea environments, a variety of components including satellites, drones, ships, and ground stations are selected during the design. The combination not only improves the coverage and service capabilities of the network, but also enhances the adaptability of the network in different application scenarios. The comprehensive network architecture is evaluated through a network simulator, and key indicators such as the network's load capacity, response speed, and data transmission rate are tested before actual deployment, which helps to discover potential problems early and make necessary adjustments.

[0077] 2. The present invention defines a unified interface and protocol to ensure that all components in the network can communicate using a common language and standard, which helps reduce compatibility issues and improve the efficiency and reliability of the entire network. The established network coordination mechanism can ensure that the various components in the network work together effectively, especially when dealing with complex data transmission and resource allocation. Based on the network coordination mechanism, the multi-user collaboration strategy and communication protocol formulated take into account the interaction and communication needs between multiple users, improve user experience and network efficiency, and ensure the flexibility and adaptability of the communication protocol; particle swarm optimization can efficiently find the optimal solution or approximate optimal solution to the problem, and in the collaboration In the optimization of strategies and communication protocols, it can quickly converge to the optimal solution and improve the efficiency of the optimization process. By constructing a fitness function and defining the evaluation criteria for collaborative strategies and communication protocol solutions, the strategies can be adjusted and optimized according to specific network performance indicators and user needs. In the particle swarm algorithm, each collaborative strategy and communication protocol solution will be evaluated to ensure that each possible solution is fully considered and the comprehensiveness of the selection is enhanced. By setting the initial position of the particle to the individual optimal solution and obtaining the global optimal solution based on the particle comparison criterion, the particle swarm algorithm can effectively avoid falling into the local optimal solution and increase the possibility of finding the global optimal solution.

[0078] 3. The present invention can accurately predict the future demand and user behavior of the network through the time series prediction model, which helps to improve the efficiency of network resource utilization. By analyzing and fitting historical data, the changing trends of network demand and user behavior can be captured, so that the network can dynamically adapt to these changes. According to the data predicted by the model, resource allocation and network configuration can be performed more efficiently to ensure that network resources are optimally used when needed and reduce resource waste. By adjusting the collaboration strategies and communication protocols among multiple users, the user's network experience can be optimized according to the prediction results. For example, by predicting high-traffic periods and adjusting the network configuration accordingly, the stability and response speed of the network can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] The above characteristics, features and advantages of the present invention and their implementation methods and methods will become more clearly understood in conjunction with the following description of the embodiments, which are described in detail in conjunction with the accompanying drawings. Herein, a schematic diagram is shown:

[0080] Figure 1 It is a flow chart of a multi-user collaborative learning dynamic access method based on the integration of air, land, and sea according to an embodiment of the present invention. DETAILED DESCRIPTION

[0081] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0082] According to an embodiment of the present invention, a multi-user collaborative learning dynamic access method based on the integration of air, land, and sea is provided.

[0083] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the multi-user collaborative learning dynamic access method based on air-space-ground-sea integration according to an embodiment of the present invention, the multi-user collaborative learning dynamic access method includes the following steps:

[0084] S1. Analyze the needs of integrated air, land, and sea information networks, and design a comprehensive network architecture including satellites, drones, ships, and ground stations.

[0085] Preferably, analyzing the needs of an integrated air-space-ground-sea information network and designing an integrated network architecture including satellites, drones, ships, and ground stations includes the following steps:

[0086] S11. Conduct demand analysis on the needs of different user groups, data traffic forecasts, and service types in the integrated air, land, and sea information network;

[0087] S12. Determine the network topology, node distribution and transmission path based on the results of demand analysis, and design a comprehensive network architecture;

[0088] S13. Select components including satellites, drones, ships and ground stations for the integrated air, land, and sea information network;

[0089] S14. Based on the components of the integrated air-space-land-sea information network, use a network simulator to evaluate the performance indicators of the integrated network architecture.

[0090] It needs to be explained that the first priority is to conduct a demand analysis for the integrated air, land, and sea information network, to have an in-depth understanding of the needs of different user groups, to predict data traffic, and to analyze the needs of various service types, to ensure that the network design can meet the needs of the real world; based on the analysis results, determine the network's topology, node distribution, and transmission path. Decisions will directly affect the network's coverage, data transmission efficiency, and overall performance. Select necessary components for the network, including satellites, drones, ships, and ground sites. Each component has its unique advantages and uses. For example, satellites can provide a wide coverage area, drones and ships can provide enhanced service capabilities in specific areas, and ground sites are the basic support for this network. Use a network simulator to evaluate the performance of this integrated network architecture, test key indicators such as the network's load capacity, response speed, and data transmission rate, and predict the performance of the network through simulation before actual deployment, and make necessary adjustments accordingly.

[0091] S2. Define unified interfaces and protocols for satellites, drones, ships, and ground stations in an integrated network architecture, and establish a network coordination mechanism.

[0092] It needs to be explained that, first of all, the work of defining unified interfaces and protocols involves ensuring that all network components can communicate using a common language and standards. Whether it is data format, transmission rate or security standards, they need to be unified among the various components of the network. Unification helps reduce compatibility issues and improve the efficiency and reliability of the entire network; establishing a network coordination mechanism is to ensure that the various components in the network can work together effectively, especially when dealing with complex data transmission and resource allocation. The network coordination mechanism includes a central control system for monitoring network status, adjusting resource allocation, and adjusting the behavior of each component when necessary. For example, when data demand in a certain area increases, the coordination mechanism can dynamically adjust the deployment of drones or ships to provide additional support.

[0093] S3. Based on the network coordination mechanism, formulate collaboration strategies and communication protocols among multiple users.

[0094] Preferably, based on the network coordination mechanism, formulating a collaboration strategy and communication protocol among multiple users includes the following steps:

[0095] S31. Analyze the way in which network coordination mechanisms handle resource allocation, data transmission, and network security;

[0096] S32. Formulate a collaboration strategy among multiple users based on their interaction and communication needs;

[0097] S33. Build a communication protocol that adapts to multi-user collaboration and is compatible with the network coordination mechanism;

[0098] S34. Integrate the collaboration strategy and communication protocol into the network coordination mechanism for testing;

[0099] S35. Analyze the test results and optimize the collaboration strategy and communication protocol.

[0100] What needs to be explained is that we need to analyze how the network coordination mechanism deals with key issues such as resource allocation, data transmission and network security, understand the working principles of existing mechanisms and how they support different components and users in the network, and formulate collaboration strategies based on the interaction and communication needs between multiple users, taking into account aspects such as data sharing, task collaboration and resource utilization between users to ensure that all users can work together efficiently while also meeting their respective needs. At the same time, we build communication protocols that are compatible with multi-user collaboration strategies. The protocols are compatible with the network coordination mechanism to ensure that they can operate seamlessly in the entire network architecture, integrate collaboration strategies and communication protocols into the network coordination mechanism for testing, verify the effectiveness of these strategies and protocols in actual or simulated network environments, and check whether they can meet the expected performance standards. Analyze the test results and optimize the collaboration strategies and communication protocols based on these results, to adjust the parameters of the strategy, improve the design of the protocol, or solve any problems found during the testing process.

[0101] S4. Use particle swarm algorithm to optimize the collaboration strategy and communication protocol among multiple users.

[0102] Preferably, using a particle swarm algorithm to optimize the collaboration strategy and communication protocol among multiple users includes the following steps:

[0103] S41, defining the optimization objectives of the collaboration strategy and communication protocol among multiple users, and setting the parameters of the particle swarm algorithm;

[0104] S42, randomly initialize the position and speed of each particle in the particle swarm, where the position represents different cooperation strategies and communication protocol schemes, and the speed represents the trend and amplitude of the scheme adjustment;

[0105] S43, for each collaboration strategy and communication protocol scheme, calculating the fitness according to the position of the collaboration strategy and communication protocol scheme, and evaluating the efficiency of the current collaboration strategy and communication protocol scheme;

[0106] S44, setting the individual optimal solution of each particle as the initial particle position, and obtaining the global optimal solution according to the particle comparison criterion;

[0107] S45. If the fitness of the current cooperation strategy and communication protocol scheme is better than the historical optimal fitness, the individual optimal position is updated, and the particle with the best fitness is found among all particles to update the global optimal position;

[0108] S46, adjusting the speed and position of each particle according to the speed and position update formula of the particle swarm optimization algorithm;

[0109] S47, check whether the preset maximum number of iterations is reached, if so, execute step S48; if not, return to step S44;

[0110] S48. Output the final optimal particle position and obtain the optimal multi-user collaboration strategy and communication protocol solution.

[0111] In addition, it should be noted that the optimization goal is defined and the parameters of the particle swarm algorithm are set. The optimization goal is usually to improve the efficiency or performance of the collaboration strategy and communication protocol. The parameters of the algorithm include the number of particles, the maximum number of iterations, the learning factor, etc.; the position and speed of each particle in the particle swarm are randomly initialized. Here, each particle represents a potential collaboration strategy and communication protocol scheme, and its position and speed represent the specific content of the scheme and its adjustment trend respectively; each scheme is evaluated, its fitness is calculated, and the effectiveness of each scheme is measured according to standards such as network performance and resource utilization efficiency. The individual optimal solution of each particle is set, and the global optimal solution is found. This process is the core of the particle swarm optimization algorithm. The best solution is determined by comparing the performance of different particles. If the fitness of the current solution is better than the previous best solution, the individual and global optimal positions are updated. This ensures that the algorithm can continue to evolve towards a better solution. The speed and position of each particle are adjusted according to the rules of the particle swarm optimization algorithm. This process simulates the group behavior of organisms in nature and guides the entire group to move towards the optimal solution through information sharing between individuals.

[0112] Preferably, for each collaboration strategy and communication protocol scheme, calculating the fitness according to the position of the collaboration strategy and communication protocol scheme, and evaluating the efficiency of the current collaboration strategy and communication protocol scheme comprises the following steps:

[0113] S431, constructing a fitness function;

[0114] S432, for each cooperation strategy and communication protocol scheme in the particle swarm algorithm, using the fitness function to calculate the fitness value of the cooperation strategy and communication protocol scheme;

[0115] S433, analyzing the fitness values ​​of the collaboration strategies and communication protocol solutions, and evaluating the efficiency of the fitness values ​​in the integrated information network of air, land, and sea;

[0116] S434. Adjust the fitness value according to the performance result of the evaluated efficiency.

[0117] Preferably, setting the individual optimal solution of each particle as the initial particle position and obtaining the global optimal solution according to the particle comparison criterion comprises the following steps:

[0118] S441, setting the initial position of the particle as the optimal solution of the individual particle;

[0119] S442, obtaining the fitness values ​​of the cooperation strategy and the communication protocol scheme, and evaluating the quality of the particles according to the particle comparison criterion;

[0120] S443, obtaining the particle with the highest fitness by comparing the fitness values ​​of all particles;

[0121] S444. The position of the particle with the highest fitness is taken as the current global optimal solution.

[0122] Preferably, if the fitness of the current cooperation strategy and communication protocol scheme is better than the historical optimal fitness, the individual optimal position is updated, and the particle with the best fitness is found among all particles. Updating the global optimal position includes the following steps:

[0123] S451. If the current fitness of a particle is better than its historical optimal fitness, the current position of the particle is updated to a new individual optimal solution;

[0124] S452. In the entire particle swarm, compare the current individual optimal solutions of all particles;

[0125] S453, find the particle with the highest fitness among the particles, and obtain the current global optimal solution;

[0126] S454. Record the update status of the individual optimal solution and the global optimal solution of each particle.

[0127] Preferably, the speed and position update formula according to the particle swarm optimization algorithm is:

[0128] ;

[0129] ;

[0130] In the formula, Indicates the trend and magnitude of parameter adjustments of collaboration strategies or communication protocols;

[0131] Parameters representing collaboration strategies or communication protocols;

[0132] represents the inertia weight;

[0133] , All represent learning factors;

[0134] Parameters representing the current collaboration strategy or communication protocol;

[0135] represents the current individual optimal solution;

[0136] represents the current global optimal solution;

[0137] Represents the parameters of an updated collaboration policy or communication protocol.

[0138] It needs to be explained that the fitness of each collaboration strategy and communication protocol scheme is calculated and evaluated. The fitness value of each scheme is calculated through a pre-defined fitness function. This function is based on the performance of the scheme in a specific network environment, such as processing efficiency, data transmission speed, resource utilization, etc. The evaluation process is crucial because it directly determines which collaboration strategies and communication protocol schemes may perform better in the actual network environment. By analyzing these fitness values, we can effectively identify and select strategies and protocols that can improve the overall performance of the network and user collaboration efficiency.

[0139] Determine and update the individual optimal solution of each particle in the particle swarm algorithm, and further find the global optimal solution of the entire particle swarm. In this process, the initial position of each particle is regarded as the starting point of its individual optimal solution, and the global optimal solution is obtained by comparing the fitness values ​​of all particles. This step is the core of the particle swarm optimization algorithm because it not only involves tracking the performance of each particle, but also involves identifying the most effective strategies and protocol schemes in the entire group to ensure that the algorithm can evolve in the direction of improving the overall network performance.

[0140] Update individual and global optimal solutions under specific conditions. When the current fitness of a particle exceeds its previous best fitness, the position of the particle will be updated to the new individual optimal solution. At the same time, this step also includes finding the particle with the highest fitness in the entire particle swarm and marking its position as the current global optimal solution. The update mechanism ensures that the particle swarm algorithm can continuously adapt to and respond to changes in the network environment, and then continuously optimize and improve the collaboration strategy and communication protocol scheme to find the solution that best suits the current network conditions.

[0141] S5. Use the time series prediction model to predict the impact of the optimized collaboration strategy and communication protocol on the demand and user behavior of the integrated air-space-ground-sea information network, and adjust resource allocation and network configuration.

[0142] Preferably, using a time series prediction model to predict the impact of the optimized collaboration strategy and communication protocol on the air-space-ground-sea integrated information network demand and user behavior, and adjusting resource allocation and network configuration includes the following steps:

[0143] S51. Collect historical data of the integrated information network of air, land, and sea;

[0144] S52, selecting a time series prediction model, and setting the attenuation factor, lag factor and index of the time series prediction model;

[0145] S53, inputting the attenuation factor, the lag factor and the index into the time series prediction model, and fitting the time series prediction model using historical data;

[0146] S54, verifying the performance of the time series prediction model by comparing the predicted values ​​of the time series prediction model with the actual observed values;

[0147] S55. Use the fitted model to predict network demand and user behavior within the next day;

[0148] S56. Adjust the collaboration strategy and communication protocol among multiple users according to the network demand and user behavior predicted by the model;

[0149] S57. Adjust resource allocation based on prediction results to optimize the performance of the integrated air-space-ground-sea information network.

[0150] Preferably, inputting the attenuation factor, the lag factor and the index into the time series prediction model, and fitting the time series prediction model using historical data comprises the following steps:

[0151] S531, inputting the attenuation factor, the lag factor and the index into the time series prediction model;

[0152] S532, dividing the historical data into a training set and a test set;

[0153] S533, fitting the time series prediction model using the training set data;

[0154] S534, checking the output of the time series prediction model;

[0155] S535. Perform a preliminary evaluation based on the model fitting results, and adjust the attenuation factor, lag factor and index of the time series prediction model based on the evaluation results;

[0156] S536. Use the test set data to verify the adjusted time series prediction model.

[0157] It should be explained that the time series prediction model is used to predict the potential impact of the optimized multi-user collaboration strategy and communication protocol on the demand and user behavior of the integrated air-space-land-sea information network. First, the historical data of the network is collected, which provides basic data support for the prediction model. Then, a suitable time series prediction model is selected and key parameters are set for it, such as attenuation factor, lag factor and exponent, so that the model can more accurately reflect the characteristics of the network and the dynamics of user behavior. Next, the parameters are input into the model and fitted with historical data. The purpose is to enable the model to capture important trends and patterns in the data, and to verify the performance of the model by comparing the predicted values ​​with the actual observed values ​​to ensure its accuracy and reliability.

[0158] Using verified models to predict network demand and user behavior in the future helps to plan and allocate network resources in advance. Subsequently, the collaboration strategies and communication protocols among multiple users are adjusted according to the results of the model prediction to better adapt to the expected network conditions and user needs. Finally, resource allocation is adjusted according to the prediction results to optimize the performance of the entire integrated air-space-land-sea information network.

[0159] Specifically, in order to facilitate a better understanding by those skilled in the art, the technical terms or some nouns that may be involved in the present application are explained in the following embodiments:

[0160] The time series prediction model in the present invention is an improved financial time series analysis that enhances the analysis capability of financial time series data by integrating data and feedback from multiple users. Specifically, it can more accurately predict financial data related to the integrated information network of air, land, and sea, such as tariffs and service costs, thereby providing stronger data support for decision-making.

[0161] The time series forecasting model integrates data from different users, who may be market participants, analysts or other relevant parties. This collaborative approach helps to obtain a more comprehensive and diverse data perspective and improve the accuracy of forecasts. Using the method of time series analysis, the model can capture the trends and patterns of data changes over time, which is particularly suitable for processing and predicting the dynamic changes of financial markets. The model includes the setting of attenuation factors, lag factors and indexes. The optimization selection of parameters is based on a detailed analysis of comprehensive historical data. By adjusting these parameters, the model can better adapt to the characteristics of specific financial data, thereby improving the accuracy and reliability of forecasts.

[0162] In summary, with the help of the above technical solutions of the present invention, the present invention ensures that the network design can meet the diversity and complexity of actual applications by deeply analyzing the needs of different user groups, predicting data traffic and service types. The detailed demand analysis provides a solid foundation for network design, ensuring that the network can effectively meet the actual needs of users; considering the particularity of the air, land, and sea environment, a variety of components including satellites, drones, ships, and ground stations are selected during the design. The combination not only improves the coverage and service capabilities of the network, but also enhances the adaptability of the network in different application scenarios. The comprehensive network architecture is evaluated through a network simulator, and the load capacity of the network is tested before actual deployment. , response speed, data transmission rate and other key indicators, which help to detect potential problems early and make necessary adjustments; define unified interfaces and protocols to ensure that all components in the network can communicate using a common language and standards, which helps to reduce compatibility issues and improve the efficiency and reliability of the entire network. The established network coordination mechanism can ensure that the various components in the network work together effectively, especially when dealing with complex data transmission and resource allocation. Based on the network coordination mechanism, the multi-user collaboration strategy and communication protocol formulated take into account the interaction and communication needs between multiple users, improve user experience and network efficiency, and ensure the flexibility and adaptability of the communication protocol; the use of particle swarm optimization can efficiently It can quickly converge to the optimal solution or approximate optimal solution of the problem in the optimization of cooperation strategies and communication protocols, and improve the efficiency of the optimization process. By constructing a fitness function and defining the evaluation criteria of cooperation strategies and communication protocol solutions, the strategies are adjusted and optimized according to specific network performance indicators and user needs. In the particle swarm algorithm, each cooperation strategy and communication protocol solution will be evaluated, ensuring that each possible solution is fully considered and enhancing the comprehensiveness of the selection. By setting the initial position of the particle to the individual optimal solution and obtaining the global optimal solution according to the particle comparison criterion, the particle swarm algorithm can effectively avoid falling into the local optimal solution and improve the efficiency of finding the global optimal solution. possibility; the present invention can accurately predict the future demand and user behavior of the network through the time series prediction model, which is helpful to improve the efficiency of network resource utilization. By analyzing and fitting historical data, the changing trend of network demand and user behavior can be captured, so that the network can dynamically adapt to these changes. According to the data predicted by the model, resource allocation and network configuration can be performed more efficiently to ensure that network resources are optimally used when needed and reduce resource waste. By adjusting the collaboration strategy and communication protocol among multiple users, the user's network experience can be optimized according to the prediction results. For example, by predicting high-traffic periods and adjusting the network configuration accordingly, the stability and response speed of the network can be improved.

[0163] Although the present invention has been disclosed as above with preferred embodiments, the embodiments are merely examples for the convenience of description and are not intended to limit the present invention. Those skilled in the art may make several changes and modifications without departing from the spirit and scope of the present invention. The scope of protection claimed by the present invention shall be based on the claims.

Claims

1. A multi-user collaborative learning dynamic access method based on the integration of air, land, and sea, characterized in that: include: S1. Analyze the requirements of integrated information network for air, land, and sea, and design a comprehensive network architecture including satellites, drones, ships, and ground stations; S2. Define unified interfaces and protocols for satellites, drones, ships, and ground stations in an integrated network architecture, and establish a network coordination mechanism; S3. Based on the network coordination mechanism, formulate the collaboration strategy and communication protocol among multiple users; S4, using particle swarm algorithm to optimize the collaboration strategy and communication protocol among multiple users; S5. Use the time series prediction model to predict the impact of the optimized collaboration strategy and communication protocol on the demand and user behavior of the integrated air-space-ground-sea information network, and adjust resource allocation and network configuration; The use of the time series prediction model to predict the impact of the optimized collaboration strategy and communication protocol on the demand for the integrated air-space-ground-sea information network and user behavior, and adjusting resource allocation and network configuration includes: S51. Collect historical data of the integrated information network of air, land, and sea; S52, selecting a time series prediction model, and setting the attenuation factor, lag factor and index of the time series prediction model; S53, inputting the attenuation factor, the lag factor and the index into the time series prediction model, and fitting the time series prediction model using historical data; S54, verifying the performance of the time series prediction model by comparing the predicted values ​​of the time series prediction model with the actual observed values; S55. Use the fitted model to predict network demand and user behavior within the next day; S56. Adjust the collaboration strategy and communication protocol among multiple users according to the network demand and user behavior predicted by the model; S57. Adjust resource allocation based on prediction results to optimize the performance of the integrated air-space-ground-sea information network.

2. According to claim 1, a multi-user collaborative learning dynamic access method based on air-space-ground-sea integration is characterized in that: The analysis of the requirements for the integrated air-space-ground-sea information network and the design of a comprehensive network architecture including satellites, drones, ships and ground stations includes the following steps: S11. Conduct demand analysis on the needs of different user groups, data traffic forecasts, and service types in the integrated air, land, and sea information network; S12. Determine the network topology, node distribution and transmission path based on the results of demand analysis, and design a comprehensive network architecture; S13. Select components including satellites, drones, ships and ground stations for the integrated air, land, and sea information network; S14. Based on the components of the integrated air-space-land-sea information network, use a network simulator to evaluate the performance indicators of the integrated network architecture.

3. According to claim 1, a multi-user collaborative learning dynamic access method based on air-space-ground-sea integration is characterized in that: The method of formulating a collaboration strategy and communication protocol among multiple users based on a network coordination mechanism includes the following steps: S31. Analyze the way in which network coordination mechanisms handle resource allocation, data transmission, and network security; S32. Formulate a collaboration strategy among multiple users based on their interaction and communication needs; S33. Build a communication protocol that adapts to multi-user collaboration and is compatible with the network coordination mechanism; S34, integrating the collaboration strategy and the communication protocol into a network coordination mechanism for testing; S35. Analyze the test results and optimize the collaboration strategy and communication protocol.

4. According to claim 1, a multi-user collaborative learning dynamic access method based on air-space-ground-sea integration is characterized in that: The method of optimizing the collaboration strategy and communication protocol among multiple users by using the particle swarm algorithm comprises the following steps: S41, defining the optimization objectives of the collaboration strategy and communication protocol among multiple users, and setting the parameters of the particle swarm algorithm; S42, randomly initialize the position and speed of each particle in the particle swarm, where the position represents different cooperation strategies and communication protocol schemes, and the speed represents the trend and amplitude of the scheme adjustment; S43, for each collaboration strategy and communication protocol scheme, calculating the fitness according to the position of the collaboration strategy and communication protocol scheme, and evaluating the efficiency of the current collaboration strategy and communication protocol scheme; S44, setting the individual optimal solution of each particle as the initial particle position, and obtaining the global optimal solution according to the particle comparison criterion; S45. If the fitness of the current cooperation strategy and communication protocol scheme is better than the historical optimal fitness, the individual optimal position is updated, and the particle with the best fitness is found among all particles to update the global optimal position; S46, adjusting the speed and position of each particle according to the speed and position update formula of the particle swarm optimization algorithm; S47, check whether the preset maximum number of iterations is reached, if so, execute step S48; if not, return to step S44; S48. Output the final optimal particle position and obtain the optimal multi-user collaboration strategy and communication protocol solution.

5. The method for dynamic access of multi-user collaborative learning based on the integration of air, land, and sea according to claim 4 is characterized in that: The step of calculating the fitness of each cooperation strategy and communication protocol scheme according to the position of the cooperation strategy and communication protocol scheme and evaluating the efficiency of the current cooperation strategy and communication protocol scheme includes the following steps: S431, constructing a fitness function; S432, for each cooperation strategy and communication protocol scheme in the particle swarm algorithm, using the fitness function to calculate the fitness value of the cooperation strategy and communication protocol scheme; S433, analyzing the fitness values ​​of the collaboration strategies and communication protocol solutions, and evaluating the efficiency of the fitness values ​​in the integrated information network of air, land, and sea; S434. Adjust the fitness value according to the performance result of the evaluated efficiency.

6. The method for dynamic access of multi-user collaborative learning based on the integration of air, land, and sea according to claim 5 is characterized in that: The step of setting the individual optimal solution of each particle as the initial particle position and obtaining the global optimal solution according to the particle comparison criterion comprises the following steps: S441, setting the initial position of the particle as the optimal solution of the individual particle; S442, obtaining the fitness values ​​of the cooperation strategy and the communication protocol scheme, and evaluating the quality of the particles according to the particle comparison criterion; S443, obtaining the particle with the highest fitness by comparing the fitness values ​​of all particles; S444. The position of the particle with the highest fitness is taken as the current global optimal solution.

7. The method for dynamic access of multi-user collaborative learning based on the integration of air, land, and sea according to claim 6 is characterized in that: If the fitness of the current cooperation strategy and communication protocol scheme is better than the historical optimal fitness, the individual optimal position is updated, and the particle with the best fitness is found among all particles. Updating the global optimal position includes the following steps: S451. If the current fitness of a particle is better than its historical optimal fitness, the current position of the particle is updated to a new individual optimal solution; S452. In the entire particle swarm, compare the current individual optimal solutions of all particles; S453, find the particle with the highest fitness among the particles, and obtain the current global optimal solution; S454. Record the update status of the individual optimal solution and the global optimal solution of each particle.

8. The multi-user collaborative learning dynamic access method based on the integration of air, land, and sea according to claim 7 is characterized in that: The speed and position update formula according to the particle swarm optimization algorithm is: ； ; In the formula, Indicates the trend and magnitude of parameter adjustments of collaboration strategies or communication protocols; Parameters representing collaboration strategies or communication protocols; represents the inertia weight; , All represent learning factors; Parameters representing the current collaboration strategy or communication protocol; represents the current individual optimal solution; represents the current global optimal solution; Represents the parameters of an updated collaboration policy or communication protocol.

9. The method for dynamic access of multi-user collaborative learning based on the integration of air, land, and sea according to claim 1, characterized in that: The step of inputting the attenuation factor, the lag factor and the index into the time series prediction model and fitting the time series prediction model using historical data comprises the following steps: S531, inputting the attenuation factor, the lag factor and the index into the time series prediction model; S532, dividing the historical data into a training set and a test set; S533, fitting the time series prediction model using the training set data; S534. Check the output of the time series prediction model; S535. Perform a preliminary evaluation based on the model fitting results, and adjust the attenuation factor, lag factor and index of the time series prediction model based on the evaluation results; S536. Use the test set data to verify the adjusted time series prediction model.

Images