Application program data interaction method based on TCP-IP protocol

Abstract

The invention relates to the technical field of data exchange, in particular to a TCP-IP protocol-based application program data interaction method, which comprises the following steps of: collecting a signal quality index of application program data in a physical layer, capturing signal quality data of each node through real-time network monitoring, and performing time sequence analysis; and extracting a signal quality trend and an abnormal point, and generating an initial signal analysis result. According to the invention, through real-time analysis and trend prediction, potential problems in the network path can be effectively predicted, network path optimization is realized, the data are analyzed through the reinforcement learning model, the network path is predicted and optimized in real time, the adaptive adjustment capability of the network is enhanced, and the data transmission efficiency is greatly improved. Through simulation testing and real-time monitoring, delay reduction of data transmission and bandwidth utilization maximization are ensured, and then through dynamic adjustment of the size of a TCP window, adjustment is performed according to real-time network congestion conditions, and the overall performance of the network is greatly optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of data exchange, and in particular to an application data interaction method based on TCP-IP protocol. Background Art

[0002] The field of data exchange technology involves various methods and technologies for transmitting and processing data between different computer systems, networks and platforms. The key part is to ensure the security, accuracy and efficiency of data during transmission from the source to the destination. Common technologies include standardization of various data formats, use of encryption technology to protect data transmission, and data compression technology to improve transmission efficiency. Data exchange technology is widely used in e-commerce, online transaction processing, big data transmission and cloud computing services, and is an indispensable part of the modern digital economy.

[0003] Among them, the application data interaction method implemented by the TCP-IP protocol refers to the technology that uses the Transmission Control Protocol-Internet Protocol (TCP-IP) as the basis for data exchange and communication between applications. TCP-IP is a network communication protocol widely used worldwide, allowing devices on different computer networks to exchange data securely and reliably through virtual connections. Data interaction based on TCP-IP is mainly used to achieve interoperability of network services, such as email transmission, file sharing, and web page data exchange, and is the cornerstone of network communication and data processing. Summary of the invention

[0004] In order to solve the problems of network congestion and path selection efficiency in the prior art, although the existing data exchange methods are widely used in many fields, they face many challenges in the data transmission process, especially in network congestion and path selection efficiency. Traditional methods rely on static routing tables and standard TCP window adjustment mechanisms, which limit the response speed and flexibility of the network when encountering emergencies. The lack of real-time network performance monitoring and analysis tools leads to the inability to respond in time when the network is congested or the quality is degraded, which is particularly problematic in large-scale or high-demand network environments. For example, during the peak period of e-commerce, network delays and data loss lead to transaction failures, affecting user experience and commercial benefits. These deficiencies show that although the prior art provides a basic framework for data exchange, in a dynamic network environment, more flexible and efficient solutions are still needed to cope with complex and changeable network conditions. An embodiment of the present invention provides an application data interaction method and system based on the TCP-IP protocol. The technical solution is as follows: On the one hand, a method for application data interaction based on TCP-IP protocol is provided, the method comprising: S1: Collect signal quality indicators of application data at the physical layer, capture signal quality data of each node through real-time network monitoring, perform time series analysis, extract signal quality trends and abnormal points, and generate initial signal analysis results; S2: Input the initial signal analysis result into the reinforcement learning model, predict the bottleneck and optimal path in the network path by analyzing the real-time signal quality trend, and output the path optimization result; S3: using the path optimization result, adjusting the routing table of the router through the TCP-IP protocol, adjusting the flow direction of the application data to the predicted optimal path, and performing simulation tests to obtain the routing configuration update result; S4: Based on the routing configuration update result, monitor the data transmission efficiency after the new routing configuration, including delay and bandwidth usage, and output the transmission efficiency comparison result by comparing the performance indicators before and after the adjustment; S5: adjusting the TCP window size according to the transmission efficiency comparison result, dynamically adjusting the window size parameter according to the real-time network congestion data, evaluating the impact by using the network simulation environment, and outputting the window adjustment result; S6: Using the window adjustment result, by applying new parameters and monitoring the overall network performance, verifying the implementation effect of the optimization measure, and generating a network performance evaluation result.

[0005] As a further solution of the present invention, the initial signal analysis results include time series data of signal strength, quality fluctuation and packet loss rate indicators, the path optimization results include predicted minimum delay path, highest bandwidth path and minimum packet loss path, the routing configuration update results include routing path, priority and associated protocol settings, the transmission efficiency comparison results include delay changes, bandwidth utilization and data transmission rate before and after adjustment, the window adjustment results include adjusted TCP window size parameters and the impact of parameters on network traffic control, and the network performance evaluation results include optimized overall network delay, data transmission efficiency and network stability indicators.

[0006] As a further solution of the present invention, the steps of collecting signal quality indicators of application data at the physical layer, capturing signal quality data of each node through real-time network monitoring, and performing time series analysis to extract signal quality trends and abnormal points and generate initial signal analysis results are specifically as follows: S101: Based on the application data, configure the network monitoring tool to capture the signal quality data of multiple nodes in real time, set the data collection frequency and threshold to adjust the data capture speed, and generate a node signal data set; S102: Using the node signal data set, using time series analysis to draw a trend graph of the data, by comparing short-term and long-term data fluctuations, identifying changes and abnormal points in signal quality, and generating a signal quality trend analysis result; S103: According to the signal quality trend analysis result, the signal trend graph and abnormal point information of each node are integrated, and iterative technical adjustments and network optimization are performed to generate an initial signal analysis result.

[0007] As a further solution of the present invention, the initial signal analysis result is input into the reinforcement learning model, and the bottleneck and optimal path in the network path are predicted by analyzing the real-time signal quality trend, and the steps of outputting the path optimization result are specifically as follows: S201: Using the initial signal analysis result, configuring a reinforcement learning model, inputting node signal trend data and abnormal point information, setting model parameters, including learning rate and reward mechanism, adjusting data input frequency, and generating a model configuration data set; S202: Based on the model configuration data set, using the Q learning algorithm, performing iterative analysis of the signal quality data, identifying bottleneck nodes and potential optimization paths in the network, and generating an optimized network path efficiency value; S203: Using the optimized network path efficiency value, a reinforcement learning model is used to predict and recommend the optimal network path, optimize the overall network performance and application data transmission efficiency, and generate a path optimization result.

[0008] As a further solution of the present invention, the formula of the Q learning algorithm is as follows: in, is the optimized network path efficiency value, Represents the current network status. Represents the routing adjustment and bandwidth allocation in the current state, is the learning rate, Representatives take action Back from state Transfer to state Instant rewards, is the discount factor, Represents the maximum value.

[0009] As a further solution of the present invention, the path optimization result is used to adjust the routing table of the router through the TCP-IP protocol, adjust the flow direction of the application data to the predicted optimal path, and perform simulation tests to obtain the routing configuration update result. Specifically, the steps are as follows: S301: Based on the path optimization result, through the TCP-IP protocol interface, the application data flow direction is set to the predicted optimal path, the target IP address and subnet mask are adjusted, and a routing table update configuration is generated; S302: According to the routing table update configuration, apply the updated routing table to the network environment, monitor and record the load and traffic changes of the router through actual network traffic steering test, and generate routing configuration test results; S303: Using the routing configuration test result and adopting a gradient descent algorithm, the network efficiency and data transmission speed before and after routing optimization are recorded to obtain a routing configuration update result.

[0010] As a further solution of the present invention, the formula of the gradient descent algorithm is as follows: in, is the performance index of the optimized network. represents the average routing response time, Represents the packet loss rate counted during the routing test. represents the current load level of the network, , and is the adjustment parameter.

[0011] As a further solution of the present invention, based on the routing configuration update result, the data transmission efficiency after the new routing configuration is monitored, including delay and bandwidth utilization, and the steps of outputting the transmission efficiency comparison result by comparing the performance indicators before and after the adjustment are specifically as follows: S401: using the routing configuration update result, configuring a network monitoring tool to monitor the data transmission efficiency under the new routing setting, collecting data on delay and bandwidth usage, setting a monitoring time interval and data sampling rate, and generating a transmission efficiency monitoring data set; S402: Based on the transmission efficiency monitoring data set, evaluate the impact of the route adjustment on the network performance, and perform data integration and deviation analysis by comparing the delay and bandwidth usage before and after the adjustment to generate a network performance comparison analysis result; S403: Analyze the improved efficiency indicators and potential problem points according to the network performance comparison and analysis results, record and extract performance improvement and efficiency difference data, and generate transmission efficiency comparison results.

[0012] As a further solution of the present invention, according to the transmission efficiency comparison result, the TCP window size is adjusted, the window size parameter is dynamically adjusted according to the real-time network congestion data, the impact is evaluated by using the network simulation environment, and the steps of outputting the window adjustment result are specifically as follows: S501: adjusting the TCP window size setting according to the transmission efficiency comparison result, dynamically modifying the window size parameter according to the actual network congestion data, setting the frequency and threshold of parameter adjustment, and generating a TCP window adjustment configuration; S502: Based on the TCP window adjustment configuration, apply the new window size setting in the network simulation environment, monitor the data transmission efficiency and network response changes by simulating differentiated network traffic and congestion scenarios, and generate a window size test result; S503: Using the window size test results, evaluate the actual impact of TCP window adjustment on network transmission efficiency, analyze network performance data under differentiated settings, and output window adjustment results.

[0013] As a further solution of the present invention, the steps of using the window adjustment result to verify the implementation effect of the optimization measure by applying new parameters and monitoring the overall network performance to generate the network performance evaluation result are specifically as follows: S601: applying the new TCP window size parameter to the actual network environment based on the window adjustment result, monitoring the real-time impact of the parameter change, recording the data changes of delay, packet loss rate and throughput, setting the sampling interval to verify the integrity of the data, and generating a network performance monitoring data set; S602: Analyze the network performance monitoring data set, evaluate network performance changes, compare the delay, throughput and detection packet loss rate before and after optimization, evaluate the impact of TCP window size adjustment, and generate performance impact analysis results; S603: Using the performance impact analysis results, integrating key performance indicators, comparing network performance differences before and after optimization, recording network optimization effects and potential improvement measures, and generating network performance evaluation results.

[0014] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: Through real-time network monitoring technology, the signal quality data of each node is captured and time series analysis is performed to extract signal quality trends and anomalies, significantly improving the accuracy and security of data exchange. Through real-time analysis and trend prediction, potential problems in the network path can be effectively foreseen and network path optimization can be achieved. Through reinforcement learning models to analyze these data, real-time prediction and optimization of network paths can not only enhance the network's adaptive adjustment capabilities, but also greatly improve the efficiency of data transmission. Based on the optimized network path, the router's routing table is adjusted to make the data transmission path more efficient. These optimization measures ensure that data transmission delays are reduced and bandwidth utilization is maximized through simulation tests and real-time monitoring. Then, by dynamically adjusting the TCP window size and adjusting according to the real-time network congestion situation, the overall performance of the network is greatly optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 This is a detailed flow chart of S1 of the present invention; Figure 3 This is a detailed flow chart of S2 of the present invention; Figure 4 This is a detailed flow chart of S3 of the present invention; Figure 5 This is a detailed flow chart of S4 of the present invention; Figure 6 This is a detailed flow chart of S5 of the present invention; Figure 7 This is a detailed flow chart of S6 of the present invention. DETAILED DESCRIPTION

[0016] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0017] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and-or" can be both, or it can be either of the two.

[0018] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0019] See also Figure 1 The embodiment of the present invention provides an application data interaction method based on the TCP-IP protocol. The processing flow of the method may include the following steps: S1: Collect signal quality indicators of application data at the physical layer, including signal-to-noise ratio and bit error rate, capture signal quality data of each node through real-time network monitoring, and perform time series analysis to extract signal quality trends and abnormal points to generate initial signal analysis results; S2: Input the initial signal analysis results into the reinforcement learning model, analyze the real-time signal quality trend, predict the bottleneck and optimal path in the network path, and output the path optimization results; S3: Using the path optimization results, the routing table of the router is adjusted through the TCP-IP protocol to adjust the flow of application data to the predicted optimal path, and a simulation test is performed to verify the effectiveness of the new configuration to obtain the routing configuration update result; S4: Based on the routing configuration update results, monitor the application data transmission efficiency after the new routing configuration, including latency and bandwidth usage, compare the performance indicators before and after the adjustment, record the performance improvement data, and output the transmission efficiency comparison results; S5: Adjust the TCP window size based on the transmission efficiency comparison results, dynamically adjust the window size parameters based on real-time network congestion data, use the network simulation environment to test the impact of the new window size, and output the window adjustment results; S6: Use the new window size parameters in the window adjustment result to optimize the network. By applying the new parameters and monitoring the overall network performance, the implementation effect of the optimization measures is verified and the network performance evaluation results are generated.

[0020] The initial signal analysis results include time series data of signal strength, quality fluctuation and packet loss rate indicators. The path optimization results include the predicted lowest delay path, highest bandwidth path and minimum packet loss path. The routing configuration update results include routing paths, priorities and associated protocol settings. The transmission efficiency comparison results include the delay change, bandwidth utilization and data transmission rate before and after adjustment. The window adjustment results include the adjusted TCP window size parameters and the impact of the parameters on network traffic control. The network performance evaluation results include the optimized overall network delay, data transmission efficiency and network stability indicators.

[0021] See also Figure 2 , collect the signal quality indicators of application data at the physical layer, capture the signal quality data of each node through real-time network monitoring, and perform time series analysis to extract signal quality trends and abnormal points. The specific steps to generate initial signal analysis results are as follows: S101: Based on the application data, configure the network monitoring tool to capture the signal quality data of multiple nodes in real time, set the data collection frequency and threshold to adjust the data capture speed, and generate the node signal data set. The execution process is as follows; Configuring network monitoring tools based on application data involves real-time monitoring of multiple nodes and capturing signal quality data. This process ensures that the frequency and threshold of data collection are scientifically set to adjust the data capture speed. Monitoring parameters need to be set in detail, including the time interval for data capture and the threshold for signal quality. These parameters are set based on the performance requirements of the application and the network status. By monitoring the signal quality of multiple nodes, the operating status of the network can be understood in real time, and the network configuration can be adjusted in time to optimize performance. The network monitoring tool analyzes the data of each node, comprehensively evaluates the overall signal quality of the network, and generates a node signal data set.

[0022] S102: Using the node signal data set, using time series analysis to draw a trend graph of the data, by comparing short-term and long-term data fluctuations, identifying changes and abnormal points in signal quality, and generating the signal quality trend analysis results. The execution process is as follows; Use time series analysis to draw trend graphs of node signal data. According to the formula , calculate the changing trend of node signal quality. In the formula, Represents the signal quality, represents the time variable, represents the initial signal quality, represents the linear trend coefficient, Represents the acceleration coefficient. Detailed explanation of the formula and the process of formula calculation: Considering the signal quality Over time The change in setting can be simulated by a quadratic equation, where Indicated in =0 signal quality, represents the linear trend coefficient over time, and This indicates the acceleration or deceleration of the trend. For example, If is a positive value, the signal quality will increase linearly with time. is also positive, this increase accelerates over time. If it is a negative value, the increase speed will slow down over time. Set at a certain time point , signal quality Through actual measurement, =50dBm, assuming =1, set =45dBm, =3dBm-month, =0.5dBm-month 2 , then we can obtain =45+3*1+0.5*12=48.5dBm, which is close to the actual measured value, indicating that the model is relatively accurate.

[0023] S103: According to the signal quality trend analysis result, the signal trend graph and abnormal point information of each node are integrated, and iterative technical adjustments and network optimization are performed to generate the initial signal analysis result. The execution process is as follows; According to the signal quality trend analysis results, the signal trend graph and abnormal point information of each node are integrated to iteratively adjust and optimize the network. This process includes analyzing the signal quality data of each node, identifying nodes with weak signals and abnormal fluctuations, and making technical adjustments to these nodes, such as adjusting the transmission power, replacing unstable hardware or updating firmware. At the same time, the optimization algorithm will also adjust the operating parameters of the network according to real-time data to reduce delays and data packet loss. It not only reflects the improvement effect of the network after adjustment, but also provides a basis for further optimization and generates initial signal analysis results.

[0024] See also Figure 3 , the initial signal analysis results are input into the reinforcement learning model, and the bottlenecks and optimal paths in the network path are predicted by analyzing the real-time signal quality trend. The specific steps of outputting the path optimization results are as follows: S201: Using the initial signal analysis results, configuring the reinforcement learning model, inputting the node signal trend data and abnormal point information, setting the model parameters, including the learning rate and reward mechanism, adjusting the data input frequency, and generating the model configuration data set. The execution process is as follows; Using the initial signal analysis results, configure the reinforcement learning model, set the model parameters, adjust the learning rate and reward mechanism, and optimize the model to better respond to the input node signal trend data and anomaly information. In the model parameter configuration, the learning rate controls the speed at which the model adapts to new information, and the reward mechanism guides the model to balance exploration and utilization. The frequency adjustment ensures that the data flow matches the model update speed. The model continuously receives new input data, such as the changing trend of node signals and detected anomalies, and dynamically adjusts internal parameters to optimize performance. For example, when frequent anomalies are observed, the model increases the learning rate to quickly adapt to changes in network conditions, or adjusts the reward mechanism to reduce the occurrence of incorrect predictions. In this way, the reinforcement learning model can be optimized in the actual network environment, continuously improve the quality of decision-making, and generate a model configuration data set.

[0025] S202: Based on the model configuration data set, the Q learning algorithm is used to perform iterative analysis of the signal quality data, identify bottleneck nodes and potential optimization paths in the network, and generate the optimized network path efficiency value. The execution process is as follows; The formula for the Q-learning algorithm is as follows: in, is the optimized network path efficiency value, Represents the current network status. Represents the routing adjustment and bandwidth allocation in the current state, is the learning rate, Representatives take action Back from state Transfer to state Instant rewards, is the discount factor, Represents the maximum value.

[0026] Detailed explanation of the formula and the process of formula calculation: This formula is the basic update rule in Q learning, which is used to update the state in a specific state. Take specific actions The value of Here, is the learning rate, It's a reward. is the discount factor used to calculate the updated value taking into account future rewards. The following are the quantitative processing and specific calculation steps based on actual data: state Represents the current configuration of the network, such as node connectivity, latency, and bandwidth usage. Latency is continuously monitored and recorded via network monitoring tools, such as SNMP (Simple Network Management Protocol) tools. Milliseconds, bandwidth usage .

[0027] action is to change the route or adjust the bandwidth. In this case, To adjust bandwidth allocation.

[0028] : Learning rate, set to the effectiveness of adjustment in previous training , ensuring a reasonable balance between new and old knowledge, this value is obtained through repeated experiments to optimize the learning process.

[0029] : Immediate reward, due to bandwidth adjustment the delay is reduced to milliseconds, the reward is calculated as .

[0030] : Discount factor, set to , indicating that future rewards are given more consideration. This value is evaluated in multiple simulations to balance current and future rewards.

[0031] In the new state The maximum Q value of all actions under the setting is the maximum Q value of all actions under the setting. .

[0032] Substitute these parameters into the formula for calculation: The results show that the updated Value is , reflected in the current state and actions This indicates that the network performance has improved due to bandwidth adjustment. Add display action In Status The following is valid, and taking the same action in similar conditions in the future has higher priority.

[0033] S203: Using the optimized network path efficiency value, the reinforcement learning model is used to predict and recommend the optimal network path, optimize the overall network performance and application data transmission efficiency, and the execution process of generating the path optimization result is as follows; Through the optimized network path efficiency value, the reinforcement learning model predicts and recommends the optimal network path. During the process, the model will comprehensively evaluate the connection quality, data transmission speed and network congestion between each node. The input data includes the signal trend and abnormal point information of each node in the network. The model calculates the efficiency value of each network path, uses these data for prediction, and continuously adjusts the decision-making strategy through the set reward mechanism and learning rate to optimize the overall network performance and application data transmission efficiency, providing a scientific basis for network operators or IT departments to adjust network configuration and optimize data flow, improve the overall network service quality, and generate path optimization results.

[0034] See also Figure 4 , using the path optimization results, through the TCP-IP protocol, adjust the router's routing table, adjust the flow of application data to the predicted optimal path, and conduct simulation tests. The specific steps to obtain the routing configuration update results are as follows: S301: Based on the path optimization result, through the TCP-IP protocol interface, the application data flow direction is set to the predicted optimal path, the target IP address and subnet mask are adjusted, and the execution process of generating the routing table update configuration is as follows; Based on the path optimization results, the application data flow is set to the predicted optimal path through the TCP-IP protocol interface. This process involves adjustments to the target IP address and subnet mask. These adjustments ensure that data packets can be transmitted along the predetermined optimal path, reducing the probability of delays and data loss. Based on the latest network traffic analysis and path optimization predictions, the updated routing table will include changed network nodes and related configurations. The changes are aimed at improving the overall efficiency of the network and the performance of the application, and generating an updated routing table configuration.

[0035] S302: According to the routing table update configuration, the updated routing table is applied to the network environment, and the load and traffic changes of the router are monitored and recorded through the actual network traffic steering test, and the execution process of generating the routing configuration test result is as follows; Update the configuration according to the routing table and apply the updated routing table to the network environment. The process includes implementing the new routing configuration on the network devices and monitoring the effect through actual network traffic steering tests. This includes monitoring the load and traffic changes of the routers, detecting the speed and efficiency of the data flow through the new path, ensuring that there is no data transmission interruption or significant delay, and providing data on whether the update is successful and the specific impact of the new routing settings on network performance. This information is crucial for network administrators to continue to adjust and optimize the network structure and generate routing configuration test results.

[0036] S303: Using the routing configuration test results, adopting the gradient descent algorithm, recording the network efficiency and data transmission speed before and after routing optimization, and obtaining the routing configuration update result, the execution process is as follows; The formula for the gradient descent algorithm is as follows: in, is the performance index of the optimized network. represents the average routing response time, Represents the packet loss rate counted during the routing test. represents the current load level of the network, , and is the adjustment parameter.

[0037] Parameter settings and data sources: Routing response time :Acquired through real-time monitoring by network monitoring tools, set to 150 milliseconds. This is the average time from receiving a data packet to sending it out by the router under the current network load.

[0038] Packet loss rate : Also measured by the network monitoring tool, the calculated loss rate is 0.02 (2%). This reflects the stability of the network under a certain load.

[0039] Network Load :The average load value of the network is obtained through the data provided by the network management system, which is 2000 units. This represents the average data processing volume of the network during the measurement period.

[0040] Weight coefficient : Set to 1.5. This value is determined based on the high sensitivity of routing response time to network performance.

[0041] Weight coefficient : Set to 0.5, considering that packet loss has little impact on the overall network performance.

[0042] Weight coefficient : Set to 0.75 to adjust the relative importance of the remaining variables in the formula to balance the calculation of network performance.

[0043] Formula derivation process Calculating routing response time and packet loss rate The weighted difference of: Calculate the absolute value of the weighted difference and take the square root: Using Network Load and adjustment coefficient Calculate the formula: The result shows that under the given network load and current network status, the optimized network performance index is 0.00998. This value represents the comprehensive performance of network efficiency and data transmission speed after routing configuration optimization. A lower value indicates that the network is more efficient and stable in processing data packets. This result is obtained through the measurement and precise calculation of actual data, providing network administrators with a quantitative way to evaluate the actual effect of routing optimization.

[0044] See also Figure 5 ,Based on the routing configuration update results, the data transmission efficiency after the new routing configuration is monitored, including delay and bandwidth utilization. By comparing the performance indicators before and after the adjustment, the steps of outputting the transmission efficiency comparison results are as follows: S401: Using the routing configuration update result, configuring the network monitoring tool to monitor the data transmission efficiency under the new routing setting, collecting data on delay and bandwidth usage, setting the monitoring time interval and data sampling rate, and generating the transmission efficiency monitoring data set. The execution process is as follows; Using the routing configuration update results, configure the network monitoring tool to monitor the data transmission efficiency under the new routing settings. The process includes setting the time interval and data sampling rate of the monitoring tool in detail to ensure that the network status information at each time point can be captured. The collected data includes latency and bandwidth utilization, which are key indicators for evaluating the effectiveness of the new routing settings. The monitoring tool will periodically record the network operation data according to the set parameters. This data will be used to analyze the performance of the new routing configuration and its impact on the overall network efficiency, and generate a transmission efficiency monitoring data set.

[0045] S402: Based on the transmission efficiency monitoring data set, the impact of the route adjustment on the network performance is evaluated, and the delay and bandwidth utilization before and after the adjustment are compared to perform data integration and deviation analysis to generate the network performance comparison analysis results. The execution process is as follows; Based on the transmission efficiency monitoring data set, the impact of route adjustment on network performance is evaluated. This process involves comparing the latency and bandwidth utilization before and after the adjustment. Through data integration and deviation analysis, the actual effect of route configuration changes on network performance can be revealed. These analyses help the technical team understand the effectiveness of network adjustments and provide decision-making information. During the evaluation process, the performance data at different time points and under different network conditions will be recorded in detail, the specific changes in performance before and after the network adjustment will be shown in detail, and the optimization results will be pointed out to generate network performance comparison analysis results.

[0046] S403: According to the network performance comparison and analysis results, analyzing the improved efficiency indicators and potential problem points, recording and extracting the performance improvement and efficiency difference data, and generating the transmission efficiency comparison results. The execution process is as follows; Analyze the improved efficiency indicators and potential problem points according to the formula , calculate the rate of change of transmission efficiency. In the formula, represents the efficiency improvement rate, represents the performance index before adjustment, Represents the adjusted performance indicator. Formula explanation and formula calculation derivation process: This formula is used to calculate the percentage change of performance improvement, where and The performance data before and after the network adjustment (such as bandwidth utilization or latency) are shown in Figure 1. For example, if the bandwidth utilization before adjustment is 70% and after adjustment is 85%, the efficiency improvement rate is , which is a 21.43% improvement. This calculation method is simple and intuitive, which helps to quickly evaluate the actual effect of network adjustment measures and provide a basis for further network optimization.

[0047] See also Figure 6 ,According to the transmission efficiency comparison results, adjust the TCP window size, dynamically adjust the window size parameters according to the real-time network congestion data, use the network simulation environment to evaluate the impact, and output the window adjustment results. The specific steps are: S501: Adjust the TCP window size setting based on the transmission efficiency comparison result, dynamically modify the window size parameter according to the actual network congestion data, set the frequency and threshold of parameter adjustment, and generate the execution flow of TCP window adjustment configuration as follows; By comparing the transmission efficiency results, the TCP window size settings are adjusted. In this process, the window size parameters are dynamically modified according to the actual network congestion data, including setting the frequency and threshold of parameter adjustment. This adjustment is to optimize congestion control during data transmission. Dynamic adjustment of the TCP window size can adjust the data packet sending rate according to real-time changes in network conditions, reduce network congestion and data transmission delays. The set frequency and threshold determine the sensitivity and response speed of the window size adjustment, providing network administrators with a strategy for adjusting the window size in real time according to network conditions to maintain the efficiency and stability of the data flow and generate a TCP window adjustment configuration.

[0048] S502: Based on the TCP window adjustment configuration, a new window size setting is applied in a network simulation environment, and the execution process of generating a window size test result by simulating differentiated network traffic and congestion scenarios, monitoring data transmission efficiency and network response changes, is as follows; Based on the TCP window adjustment configuration, the new window size setting is applied in a network simulation environment. This operation includes monitoring data transmission efficiency and network response changes by simulating differentiated network traffic and congestion scenarios. The process enables network engineers to test the effects of different window sizes in a controlled environment and predict the performance of these adjustments in the actual network. The simulation test includes a variety of network conditions, such as high and low bandwidth utilization and different degrees of network congestion, to help analyze network response and data transmission efficiency under different settings. This information is critical for optimizing TCP window settings and generating window size test results.

[0049] S503: Using the window size test results, evaluate the actual impact of TCP window adjustment on network transmission efficiency, analyze network performance data under differentiated settings, and output the window adjustment results. The execution process is as follows; To evaluate the actual impact of TCP window adjustment on network transmission efficiency, we use the formula , calculate the impact of window size adjustment on transmission efficiency. Where, represents the change in efficiency, Represents the adjusted window size, Represents the original window size, Represents the transmission time. Detailed explanation of the formula and the process of formula calculation: This formula is used to measure the direct impact of window size adjustment on transmission efficiency, where and Indicates the TCP window size before and after adjustment. is the total transmission time during the observation period. For example, if the original window size is 1024 bytes and is adjusted to 2048 bytes, and the transmission time is 2 seconds, then the efficiency change is Byte-second. This means that window adjustment increases the amount of data transmitted by 512 bytes per second, proving that adjusting the window size has a direct impact on improving network transmission efficiency. This analysis helps confirm whether the effect of window adjustment is as expected and further guides network optimization strategies.

[0050] See also Figure 7 , using the window adjustment results, verify the effectiveness of the optimization measures by applying new parameters and monitoring the overall network performance. The steps to generate the network performance evaluation results are as follows: S601: Apply the new TCP window size parameters to the actual network environment based on the window adjustment results, monitor the real-time impact of parameter changes, record the data changes of delay, packet loss rate and throughput, set the sampling interval to verify the integrity of the data, and generate the network performance monitoring data set. The execution process is as follows; Based on the window adjustment results, the new TCP window size parameters are applied to the actual network environment. The process includes monitoring the real-time impact of parameter changes and recording key network performance indicators such as latency, packet loss rate, and throughput. Setting the sampling interval to verify the integrity of the data is crucial because it ensures that the collected data can accurately reflect the network status. These data changes will be used to evaluate the effect of the new window size setting, including performance data at multiple time points, providing a real-time and dynamic view of the network status, and generating a network performance monitoring data set.

[0051] S602: Analyze the network performance monitoring data set, evaluate the network performance change, compare the delay, throughput and detection packet loss rate before and after optimization, evaluate the impact of TCP window size adjustment, and generate the performance impact analysis results. The execution process is as follows; Analyze the network performance monitoring data set and evaluate the changes in network performance. During the analysis, compare the latency, throughput and packet loss rate before and after optimization. These indicators can accurately assess the impact of TCP window size adjustment. Analysts will use statistical methods and charts to show performance changes, making performance comparisons intuitive and easy to understand. Through these data analysis, the actual effect of window adjustment can be clarified, whether it meets the expected performance improvement, and the changes in various performance indicators are explained in detail to provide a basis for further network optimization and generate performance impact analysis results.

[0052] S603: Using the performance impact analysis results, integrating key performance indicators, comparing the network performance differences before and after optimization, recording the network optimization effects and potential improvement measures, and generating the network performance evaluation results. The execution process is as follows; Integrate key performance indicators according to the formula , calculate the actual difference in network performance. Represents performance differences, Represents the optimized performance index, Represents the performance index before optimization. Formula explanation and formula calculation derivation process: This formula is used to measure the difference in performance indicators before and after the implementation of network optimization measures. For example, the throughput before optimization is 200Mbps, and after optimization it increases to 250Mbps. The performance difference is This result directly shows the specific impact of TCP window size adjustment on throughput. Further analysis can reveal the impact of this change on the overall network experience, such as reduced latency and reduced packet loss, confirming the effectiveness of network optimization and potential further improvement measures.

[0053] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for application data interaction based on TCP-IP protocol, characterized in that: The method comprises: Collect signal quality indicators of application data at the physical layer, capture signal quality data of each node through real-time network monitoring, and perform time series analysis to extract signal quality trends and abnormal points to generate initial signal analysis results; Inputting the initial signal analysis result into the reinforcement learning model, predicting the bottleneck and optimal path in the network path by analyzing the real-time signal quality trend, and outputting the path optimization result; Adopting the path optimization result, adjusting the routing table of the router through the TCP-IP protocol, adjusting the flow direction of the application data to the predicted optimal path, and performing simulation tests to obtain the routing configuration update result; Based on the routing configuration update result, monitoring the data transmission efficiency after the new routing configuration, including delay and bandwidth utilization, and outputting the transmission efficiency comparison result by comparing the performance indicators before and after the adjustment; According to the transmission efficiency comparison result, adjust the TCP window size, dynamically adjust the window size parameters according to the real-time network congestion data, use the network simulation environment to evaluate the impact, and output the window adjustment result; Using the window adjustment results, the implementation effect of the optimization measures is verified by applying new parameters and monitoring the overall network performance, thereby generating a network performance evaluation result.

2. The method for application data interaction based on TCP-IP protocol according to claim 1, characterized in that: The initial signal analysis results include time series data of signal strength, quality fluctuation and packet loss rate indicators, the path optimization results include the predicted minimum delay path, highest bandwidth path and minimum packet loss path, the routing configuration update results include routing paths, priorities and associated protocol settings, the transmission efficiency comparison results include delay changes before and after adjustment, bandwidth utilization and data transmission rate, the window adjustment results include adjusted TCP window size parameters and the impact of parameters on network traffic control, and the network performance evaluation results include optimized overall network delay, data transmission efficiency and network stability indicators.

3. The method for application data interaction based on TCP-IP protocol according to claim 1, characterized in that: The steps to collect signal quality indicators of application data at the physical layer, capture the signal quality data of each node through real-time network monitoring, and perform time series analysis to extract signal quality trends and abnormal points and generate initial signal analysis results are as follows: Based on the application data, configure the network monitoring tool to capture the signal quality data of multiple nodes in real time, set the data collection frequency and threshold to adjust the data capture speed, and generate the node signal data set; Using the node signal data set, a time series analysis is used to plot a trend graph of the data, and by comparing short-term and long-term data fluctuations, changes in signal quality and abnormal points are identified, and a signal quality trend analysis result is generated; According to the signal quality trend analysis results, the signal trend graph and abnormal point information of each node are integrated, and iterative technical adjustments and network optimization are performed to generate initial signal analysis results.

4. The method for application data interaction based on TCP-IP protocol according to claim 1, characterized in that: The initial signal analysis result is input into the reinforcement learning model, and the bottleneck and optimal path in the network path are predicted by analyzing the real-time signal quality trend, and the steps of outputting the path optimization result are specifically as follows: Using the initial signal analysis results, configuring a reinforcement learning model, inputting node signal trend data and abnormal point information, setting model parameters, including learning rate and reward mechanism, adjusting data input frequency, and generating a model configuration data set; Based on the model configuration data set, a Q learning algorithm is used to perform iterative analysis of signal quality data, identify bottleneck nodes and potential optimization paths in the network, and generate optimized network path efficiency values; Through the optimized network path efficiency value, the reinforcement learning model is used to predict and recommend the optimal network path, optimize the overall network performance and application data transmission efficiency, and generate a path optimization result.

5. The method for application data interaction based on TCP-IP protocol according to claim 4, characterized in that: The formula of the Q-learning algorithm is as follows: in, is the optimized network path efficiency value, Represents the current network status. Represents the routing adjustment and bandwidth allocation in the current state, is the learning rate, Representatives take action Back from state Transfer to state Instant rewards, is the discount factor, Represents the maximum value.

6. The method for application data interaction based on TCP-IP protocol according to claim 1, characterized in that: The steps of using the path optimization result to adjust the routing table of the router through the TCP-IP protocol, adjusting the flow direction of the application data to the predicted optimal path, and performing simulation tests to obtain the routing configuration update result are as follows: Based on the path optimization result, the application data flow direction is set to the predicted optimal path through the TCP-IP protocol interface, the target IP address and subnet mask are adjusted, and the routing table update configuration is generated; According to the routing table update configuration, apply the updated routing table to the network environment, monitor and record the load and traffic changes of the router through actual network traffic steering test, and generate routing configuration test results; The routing configuration test result is used, a gradient descent algorithm is adopted, the network efficiency and data transmission speed before and after routing optimization are recorded, and the routing configuration update result is obtained.

7. The method for application data interaction based on TCP-IP protocol according to claim 6, characterized in that: The formula of the gradient descent algorithm is as follows: in, is the performance index of the optimized network. represents the average routing response time, Represents the packet loss rate counted during the routing test. represents the current load level of the network, , and is the adjustment parameter.

8. The method for application data interaction based on TCP-IP protocol according to claim 1, characterized in that: Based on the routing configuration update result, the steps of monitoring the data transmission efficiency after the new routing configuration, including delay and bandwidth usage, and outputting the transmission efficiency comparison result by comparing the performance indicators before and after the adjustment are specifically as follows: Using the routing configuration update result, configuring a network monitoring tool to monitor the data transmission efficiency under the new routing setting, collecting data on delay and bandwidth usage, setting a monitoring time interval and data sampling rate, and generating a transmission efficiency monitoring data set; Based on the transmission efficiency monitoring data set, the impact of route adjustment on network performance is evaluated, and by comparing the delay and bandwidth utilization before and after the adjustment, data integration and deviation analysis are performed to generate network performance comparison analysis results; According to the network performance comparison and analysis results, the improved efficiency indicators and potential problem points are analyzed, the performance improvement and efficiency difference data are recorded and extracted, and the transmission efficiency comparison results are generated.

9. The method for application data interaction based on TCP-IP protocol according to claim 1, characterized in that: According to the transmission efficiency comparison result, the steps of adjusting the TCP window size, dynamically adjusting the window size parameter according to the real-time network congestion data, evaluating the impact by using the network simulation environment, and outputting the window adjustment result are specifically as follows: According to the transmission efficiency comparison result, the TCP window size setting is adjusted, the window size parameter is dynamically modified according to the actual network congestion data, the frequency and threshold of the parameter adjustment are set, and the TCP window adjustment configuration is generated; Based on the TCP window adjustment configuration, apply the new window size setting in the network simulation environment, monitor the data transmission efficiency and network response changes by simulating differentiated network traffic and congestion scenarios, and generate window size test results; The window size test results are used to evaluate the actual impact of TCP window adjustment on network transmission efficiency, analyze network performance data under differentiated settings, and output window adjustment results.

10. The method for application data interaction based on TCP-IP protocol according to claim 1, characterized in that: Using the window adjustment results, the steps of verifying the implementation effect of the optimization measures by applying new parameters and monitoring the overall network performance and generating the network performance evaluation results are as follows: Apply the new TCP window size parameters to the actual network environment through the window adjustment results, monitor the real-time impact of parameter changes, record data changes in latency, packet loss rate, and throughput, set sampling intervals to verify data integrity, and generate a network performance monitoring data set; Analyze the network performance monitoring data set, evaluate network performance changes, compare latency, throughput, and detected packet loss rate before and after optimization, assess the impact of TCP window size adjustment, and generate performance impact analysis results; The performance impact analysis results are used to integrate key performance indicators, compare network performance differences before and after optimization, record the effects of network optimization and potential improvement measures, and generate network performance evaluation results.

Images