Multi-scene adaptive communication protocol software system and optimization method

Abstract

The invention belongs to the technical field of smart city information, and particularly relates to a multi-scene adaptive communication protocol software system and an optimization method. And the whole process of communication protocol adaptation, data transmission and abnormity management and control is covered. Core algorithms such as protocol adaptation modeling, data transmission optimization and abnormal management and control early warning are adopted, the technical bottlenecks of'heavy transmission and light adaptation, heavy rate and light reliability, and heavy response and light pre-judgment 'of a traditional communication protocol software system are broken through, and adaptive adaptation, high-reliability and low-delay data transmission and full-process abnormal real-time management and control of communication protocols under multiple scenes are achieved. The adaptability, reliability and stability of a communication protocol software system are remarkably improved, deep fusion of communication protocol software and multi-scene application is promoted, and a brand new intelligent communication solution is provided for the fields of industrial communication, the Internet of Things, intelligent terminals and the like.

Description

Technical Field

[0001] This invention belongs to the field of information technology, specifically relating to a communication protocol software system and optimization method that adapts to multiple scenarios. Background Technology

[0002] Current communication protocol software systems are widely used in industrial communication, the Internet of Things (IoT), smart terminals, and other fields. However, with the diversification of application scenarios and the increasing demands for data transmission, traditional communication protocol software systems still face prominent problems such as poor adaptability to multiple scenarios, low data transmission reliability, and insufficient real-time anomaly control. Traditional systems often adopt fixed protocol parameters, single transmission paths, and passive anomaly handling modes, lacking the ability to adapt to multiple scenarios, intelligently optimize data transmission, and predict and control anomalies in real time. They are no longer able to meet the communication requirements of multiple scenarios, high reliability, and low latency. In particular, in the three core areas of protocol adaptation, data transmission, and anomaly control, there are three specific and unresolved practical problems, all of which are specific pain points in the manufacturing process. These problems have no overlap with existing or previous communication protocols and large-scale model-related technologies (including large-scale models for cultural activities and education, and general communication protocols), as follows: 1. Poor adaptability to multiple scenarios, lack of dedicated feature extraction and dynamic parameter adaptation algorithms: Existing communication protocol software systems mostly use fixed protocol parameters and adaptation logic, without adaptive adaptation to the differences of different types of communication scenarios (such as industrial communication and IoT); there is no protocol scenario feature adaptive extraction algorithm, which cannot accurately extract the core communication requirements (rate, distance, interference) of different scenarios, resulting in inaccurate scenario feature recognition; there is no protocol parameter dynamic adaptation algorithm, which cannot dynamically adjust protocol parameters according to scenario requirements, resulting in large deviations between protocol and scenario adaptation, and failing to meet the communication needs of multiple scenarios.

[0003] 2. Low data transmission reliability and lack of dedicated path planning and error suppression algorithms: Existing communication protocol software systems mostly use fixed paths for data transmission, lacking real-time awareness of link status and dynamic path adjustment; there is no dynamic data transmission path planning algorithm, which cannot select the optimal transmission path in real time, resulting in high transmission delay and high packet loss rate; there is no adaptive error suppression algorithm, which cannot effectively identify and suppress errors and interference in the transmission process, resulting in low data transmission reliability and failing to meet the requirements of high-reliability communication.

[0004] 3. Insufficient real-time performance of anomaly control, lacking dedicated feature recognition and strategy optimization algorithms: Existing communication protocol software systems mostly adopt a passive response mode for anomaly control, lacking real-time identification and prediction of anomalies; there is no intelligent anomaly feature recognition algorithm, which cannot accurately identify the characteristics of various anomalies (parameter anomalies, link anomalies), resulting in low anomaly identification accuracy and high false negative and false positive rates; there is no dynamic optimization algorithm for anomaly control strategies, which cannot dynamically adjust control strategies according to anomaly type and scenario requirements, resulting in slow anomaly control response and poor effectiveness, and failing to achieve real-time anomaly control throughout the entire process.

[0005] Existing communication protocol technologies largely focus on single-protocol optimization, fixed-scenario transmission, and simple anomaly handling. They lack core algorithmic innovation in multi-scenario adaptive adaptation of communication protocol software systems, intelligent data transmission optimization, and real-time anomaly control. Significant technological gaps exist, particularly in adaptive extraction of protocol scenario features, dynamic transmission path planning, and intelligent anomaly feature recognition, failing to address the aforementioned specific problems and offering no overlap in technical direction or innovation with existing or previous related technologies. There is an urgent need for a multi-scenario adaptable communication protocol software system and optimization method centered on algorithmic innovation. This method should focus on three entirely new technical perspectives: protocol adaptation, data transmission, and anomaly control, emphasizing algorithmic innovation and modeling and solution principles throughout. It should achieve multi-scenario adaptation, highly reliable transmission, and real-time anomaly control for communication protocol software systems, filling the technological gaps in this field and driving the upgrading and iteration of communication protocol software technology. Summary of the Invention

[0006] To address the three specific problems raised in the background technology, the present invention aims to provide a multi-scenario adaptable communication protocol software system and optimization method, achieving accurate adaptation between multiple scenarios and communication protocols, high-reliability and low-latency data transmission, and real-time anomaly control throughout the entire process. This solves the problems of poor multi-scenario adaptability, low data transmission reliability, and insufficient real-time anomaly control. The entire process emphasizes algorithm innovation and modeling solution, without involving rules of intellectual activity, thereby improving the adaptability, reliability, and stability of the communication protocol software system. It promotes the deep integration of communication protocol software with multi-scenario applications, further improves the communication protocol software technology system, and has no duplication with existing or previous technologies, focusing on the principles of algorithm efficiency enhancement and modeling innovation.

[0007] The present invention is implemented through the following specific technical solution: (I) Protocol Multi-Scenario Adaptive Module The core of this module is to achieve accurate adaptation of multiple scenarios and communication protocols, construct a multi-scenario adaptive adaptation model of protocols, solve the problem of poor adaptability in multiple scenarios, and realize a closed loop of "scenario data acquisition - protocol parameter acquisition - feature extraction - parameter adaptation - adaptation result output", providing accurate protocol support for intelligent optimization of data transmission. The core highlights algorithm innovation and modeling and solution principles.

[0008] Modeling Approach: Abandoning the traditional approach of "fixed protocol parameters and lack of precise scenario adaptation," this approach constructs an integrated modeling logic encompassing "scenario data acquisition - protocol parameter acquisition - data preprocessing - feature extraction - parameter adaptation - verification and optimization." It combines multi-scenario communication requirement data (rate, distance, interference, data type), protocol operating parameters (baud rate, parity bit, protocol type), and historical adaptation data to establish data acquisition, preprocessing, feature extraction, parameter adaptation, and verification and optimization models. Adaptive feature extraction algorithms and dynamic parameter adaptation algorithms for protocol scenarios are designed. Through algorithmic innovation, precise extraction of scenario features is achieved; through modeling optimization, dynamic adaptation of protocol parameters is realized, highlighting the principles of algorithm efficiency enhancement and modeling innovation.

[0009] Solution Process: First, deploy multi-source data acquisition terminals to simultaneously collect data from various communication scenarios, including communication rate requirements, data transmission distance, environmental interference intensity, and data types (real-time and non-real-time data) for different types of scenarios such as industrial communication, IoT, smart terminals, and vehicle communication. Simultaneously, collect communication protocol operating parameters, including baud rate, parity, transmission protocol type (TCP / IP, UDP, Modbus), and data frame format, to establish a raw dataset of scenarios and protocols. Preprocess the collected data: use data cleaning algorithms to remove missing, abnormal, and invalid data; use standardization to unify data dimensions and eliminate the influence of units; and map scenario data to protocol parameters to establish a standardized scenario-protocol dataset. Then, an adaptive feature extraction algorithm for protocol scenarios was designed to establish a communication scenario feature system. This system integrates the rate, distance, interference, and data type features of standardized scenario data. An algorithm combining an improved recurrent neural network (RNN) with an attention mechanism is adopted. The RNN extracts the temporal features of the scenario (such as the dynamic changes in interference intensity), while the attention mechanism strengthens the weight of core requirement features of the scenario (such as the high reliability of industrial communication and the low power consumption of the Internet of Things), suppresses irrelevant interference features, and adaptively extracts the core features of different types of scenarios. The type, weight, and representation rules of scenario features are clarified. The algorithm's efficiency enhancement principle lies in the fact that by combining the improved RNN with the attention mechanism, it breaks through the limitations of traditional scenario feature extraction, which is inaccurate and untargeted. It can accurately capture the core requirement differences of different communication scenarios, and significantly improves the recognition accuracy and targeting of scenario features compared with the fixed feature extraction mode of existing technologies. Simultaneously, a dynamic protocol parameter adaptation algorithm is designed, establishing a protocol parameter adaptation system. This system integrates core scenario features with protocol operating parameters and employs an improved Particle Swarm Optimization (PSO) algorithm to construct a dynamic protocol parameter adaptation model. Using the matching degree between scenario requirements and protocol parameters as the objective function, the algorithm dynamically adjusts protocol parameters (baud rate, parity, protocol type) through iterative optimization of the PSO algorithm. This quantifies the matching degree between scenario requirements and protocol parameters, selecting the protocol parameter adaptation scheme with the highest matching degree, thus achieving dynamic adaptation of protocol parameters. The innovative modeling principle lies in constructing a collaborative logic of "feature extraction - parameter optimization - accurate adaptation - verification optimization," breaking through the limitations of traditional fixed protocol parameters and large adaptation deviations, ensuring that protocol parameters accurately meet the communication needs of different scenarios. Finally, an adaptation verification model is constructed, combining historical adaptation data and communication quality feedback to quantify the protocol adaptation accuracy, dynamically optimize algorithm parameters (RNN iteration count, PSO particle count), output the adapted protocol parameters, and feed them back to the data transmission intelligent optimization module.

[0010] (ii) Intelligent data transmission optimization module The core of this module is to achieve highly reliable and low-latency data transmission, construct an intelligent optimization model for data transmission, solve the problem of low data transmission reliability, and realize a closed loop of "protocol adaptation result input - link status acquisition - path planning - error suppression - data transmission - transmission verification". It provides data transmission status support for real-time anomaly management and control, and its core highlights are algorithm innovation and modeling and solution principles.

[0011] Modeling Approach: Abandoning the traditional approach of "fixed transmission path, no error suppression," this approach constructs an integrated modeling logic encompassing "protocol adaptation result input - link status acquisition - path planning - data transmission - error suppression - transmission verification - optimization iteration." Combining protocol adaptation results, network topology, link status data (delay, packet loss rate, interference intensity), data transmission requirements (reliability, delay), and historical transmission data, it establishes link status acquisition, path planning, data transmission, error suppression, and transmission verification models. Dynamic planning algorithms for data transmission paths and adaptive error suppression algorithms are designed. Through algorithmic innovation, dynamic optimization of transmission paths is achieved; through modeling optimization, high reliability of data transmission is realized, highlighting the principles of algorithm efficiency enhancement and modeling innovation.

[0012] Solution Process: First, obtain the adapted protocol parameters output by the multi-scenario adaptive adaptation module to clarify the communication protocol requirements and data transmission needs of different scenarios. Simultaneously collect network topology data and link status data, including the number of transmission links, link latency, packet loss rate, interference intensity, bandwidth utilization, etc., to establish a link status dataset. Preprocess the link status dataset: Use anomaly detection algorithms to remove abnormal link status data (such as sudden high latency or high packet loss); use normalization to unify the dimensions of link status parameters and establish a standardized link status dataset. Then, a dynamic programming algorithm for data transmission paths is designed, a data transmission path system is established, and protocol adaptation results, standardized link state datasets, and network topology are integrated. An improved Dijkstra algorithm is used to construct a dynamic programming model for data transmission paths. The objective function is to minimize transmission latency and packet loss rate. Link stability weights are introduced to select the optimal transmission path in real time. At the same time, the dynamic changes in link state are monitored. When the link state deteriorates (such as a sudden increase in latency or excessive packet loss rate), the transmission path is dynamically adjusted to ensure low latency and high reliability of data transmission. The principle of algorithm efficiency enhancement is that, through the dynamic programming capability of the improved Dijkstra algorithm, it breaks through the limitations of traditional fixed transmission paths and the inability to adapt to changes in link state. It can adapt to changes in link state in real time, which greatly improves the stability and low latency of data transmission compared with the fixed path transmission mode of existing technologies. Simultaneously, an adaptive transmission error suppression algorithm is designed to establish a transmission error suppression system. Based on data transmission status (error rate, packet loss rate) and link interference intensity, an algorithm combining improved convolutional code encoding and adaptive equalization is used to encode the transmitted data, enhancing its anti-interference capability. The adaptive equalization algorithm offsets transmission distortion caused by link interference, identifies and suppresses errors during transmission, optimizes error correction strategies, and adjusts encoding parameters and equalization coefficients in real time to improve data transmission reliability. Its innovative modeling principle lies in constructing a closed-loop logic of "path planning - data transmission - error suppression - real-time optimization," breaking through the limitations of traditional methods with no error suppression and low transmission reliability, ensuring effective suppression of errors during data transmission and improving data transmission quality. Finally, a transmission verification model is constructed to monitor data transmission delay, packet loss rate, and error rate in real time, quantify data transmission reliability, dynamically optimize algorithm parameters (Dijkstra weight coefficients, convolutional code encoding length), and output highly reliable, low-latency transmission data, which is then fed back to the real-time anomaly control module.

[0013] (III) Real-time Anomaly Control Module This module is designed to identify, warn, and control anomalies throughout the entire communication protocol operation process. It constructs a real-time anomaly control model to address the problem of insufficient real-time anomaly control and achieves a closed loop of "transmission status acquisition - protocol operation data acquisition - anomaly identification - early warning and control - strategy optimization". This improves the stability and security of the communication protocol software system, with a focus on algorithm innovation and modeling and solution principles.

[0014] Modeling Approach: Abandoning the traditional approach of "passive anomaly response, lack of precise identification and strategy optimization," this approach constructs an integrated modeling logic encompassing "transmission status acquisition - protocol operation data acquisition - data preprocessing - anomaly identification - early warning and control - effect calculation - dynamic optimization." It combines transmission status data, protocol operation data (parameter deviation, transmission delay, packet loss rate), anomaly type data (parameter anomaly, link anomaly, data anomaly), and historical anomaly handling data output from the intelligent data transmission optimization module. This establishes data acquisition, preprocessing, anomaly identification, early warning and control, and effect optimization models. Intelligent anomaly feature identification algorithms and dynamic optimization algorithms for anomaly control strategies are designed. Through algorithmic innovation, precise anomaly identification and real-time early warning are achieved; through modeling optimization, dynamic adjustment of control strategies is realized, highlighting the principles of algorithm efficiency enhancement and modeling innovation.

[0015] Solution Process: First, acquire the transmission status data (latency, packet loss rate, error rate) output by the intelligent data transmission optimization module. Simultaneously collect protocol operation data, including protocol parameter deviations, data frame format anomalies, link connection status, etc., to establish an original dataset for anomaly identification. Preprocess the collected dataset: remove invalid and abnormal interference data, quantify transmission status characteristics and protocol operation characteristics, establish a standardized anomaly identification dataset, and label different types of anomalies with feature tags (parameter anomalies, link anomalies, data anomalies). Then, an intelligent anomaly feature recognition algorithm was designed, an anomaly feature system was established, and standardized anomaly recognition datasets and anomaly feature labels were integrated. An improved Support Vector Machine (SVM) algorithm was used to construct an intelligent anomaly feature recognition model. Through the classification capability of the SVM algorithm, the features of various anomalies were accurately identified, achieving accurate anomaly classification and recognition. Simultaneously, a real-time monitoring mechanism was introduced to achieve real-time anomaly capture, avoiding missed or false positives. The algorithm's efficiency enhancement principle lies in overcoming the limitations of traditional anomaly recognition—low accuracy and high missed / false positive rates—through the accurate classification capability of the improved SVM algorithm. It can accurately identify subtle features of various anomalies, significantly improving the accuracy and real-time performance of anomaly recognition compared to the simple anomaly detection mode of existing technologies. Furthermore, a dynamic optimization algorithm for anomaly control strategies was designed, establishing an anomaly control optimization system and integrating a dedicated anomaly control effect calculation formula. This study employs an improved random forest algorithm, taking into account anomaly identification results, historical anomaly handling data, and scenario requirements. It accurately calculates the control effectiveness coefficients for various anomalies, analyzes shortcomings in the anomaly control process (such as untimely warnings and unreasonable control strategies), and dynamically optimizes anomaly control strategies (warning thresholds, processing procedures, and response priorities) and weighting coefficients. This system enables dynamic adjustment of anomaly control strategies, improving the real-time performance and effectiveness of anomaly control. Its innovative modeling principle lies in constructing a closed-loop logic of "anomaly identification - early warning control - effect calculation - dynamic optimization," breaking through the limitations of traditional passive anomaly response and lack of strategy optimization. This ensures that the anomaly control strategy can continuously adapt to anomaly types and scenario requirements, achieving real-time anomaly control throughout the entire process. Finally, an anomaly control verification model is built to quantify anomaly identification accuracy, early warning lead time, and control response speed. Algorithm parameters (SVM kernel function parameters, random forest decision tree depth) are dynamically optimized, outputting anomaly early warning information and control solutions, executing control operations in real time, and ensuring the stable operation of the communication protocol software system. Attached Figure Description

[0016] Appendix Figure 1 : Workflow diagram of the protocol multi-scenario adaptive adaptation module Beneficial effects Specifically as follows: 1. Adaptive feature extraction algorithm for protocol scenarios: The algorithm innovatively adopts an improved RNN combined with an attention mechanism. The principle of algorithm efficiency enhancement is that it can accurately extract the core requirement features of different communication scenarios, strengthen the differentiated features of scenarios, suppress interference, and improve the accuracy and relevance of scenario feature recognition. The modeling innovation lies in constructing the logic of "scenario acquisition-feature extraction-verification optimization", which breaks through the limitations of inaccurate traditional scenario feature extraction.

[0017] 2. Dynamic Protocol Parameter Adaptation Algorithm: The innovative PSO algorithm is adopted. The algorithm's efficiency improvement principle lies in its ability to dynamically adjust protocol parameters through iterative optimization, quantify the matching degree between the scenario and the parameters, accurately select the optimal adaptation scheme, and improve the accuracy and flexibility of protocol adaptation. The modeling innovation lies in constructing a collaborative logic of "feature association - parameter optimization - accurate matching", which breaks through the limitations of traditional fixed protocol parameters and large adaptation deviations.

[0018] 3. Dynamic planning algorithm for data transmission path: The improved Dijkstra algorithm is innovatively adopted. The algorithm's efficiency is enhanced by its ability to adapt to changes in link status in real time, select the optimal transmission path, and improve the stability and low latency of data transmission. The modeling innovation lies in constructing the logic of "link acquisition - path planning - dynamic adjustment", which breaks through the limitations of traditional fixed transmission paths and their inability to adapt to changes in links.

[0019] 4. Adaptive transmission error suppression algorithm: The algorithm innovatively adopts an improved convolutional code encoding combined with adaptive equalization. The principle of algorithm efficiency enhancement is that it can effectively identify and suppress transmission errors, enhance the data anti-interference ability, and improve the reliability of data transmission. The modeling innovation lies in constructing a closed loop of "data transmission - error identification - suppression optimization", which breaks through the limitations of traditional error suppression and low transmission reliability.

[0020] 5. Intelligent anomaly feature recognition algorithm: The innovative algorithm adopts an improved SVM algorithm. The algorithm's efficiency enhancement principle lies in its ability to accurately identify the subtle features of various anomalies, avoid missed or false judgments, and improve the accuracy and real-time performance of anomaly recognition. The modeling innovation lies in constructing the logic of "data acquisition-feature extraction-anomaly classification", which breaks through the limitation of low accuracy in traditional anomaly recognition.

[0021] 6. Dynamic Optimization Algorithm for Anomaly Control Strategies: This innovative algorithm combines a proprietary calculation formula with an improved random forest algorithm. The principle behind its enhanced efficiency lies in its ability to accurately calculate control effectiveness, dynamically optimize control strategies and weights, and achieve proactive prediction and dynamic optimization of anomaly control. The innovative modeling approach constructs a closed loop of "anomaly identification - effectiveness calculation - dynamic optimization," breaking through the limitations of traditional passive anomaly responses.

[0022] Example The following four embodiments further illustrate the implementation of the present invention. Embodiment 1 includes a formula, while embodiments 2-4 do not. Each embodiment has specific steps, focusing on the principle of algorithm efficiency enhancement and the principle of modeling innovation. The efficiency enhancement effect is qualitatively explained, and the shortcomings of the prior art are compared. No data support is involved.

[0023] Example 1 Step 1: Input of status and operation data. In the industrial communication scenario, obtain the transmission status data (transmission delay, packet loss rate, error rate) output by the data transmission intelligent optimization module, and synchronously collect protocol operation data (baud rate deviation, data frame format, link connection status). Select three types of typical anomalies (parameter anomalies, link anomalies, data anomalies), establish an original dataset for anomaly identification, and label the feature tags of each type of anomaly.

[0024] Step 2: Data preprocessing and feature labeling. The collected anomaly identification raw dataset is preprocessed: invalid data and abnormal interference data are removed, and standardized processing is used to quantify transmission status characteristics and protocol operation characteristics. A standardized anomaly identification dataset is established to clarify the core characteristics of various anomalies (such as baud rate deviation of parameter anomalies and high latency of link anomalies) and complete the accurate labeling of anomaly feature labels.

[0025] Step 3: Intelligent identification of abnormal features. Using the intelligent identification algorithm of abnormal features designed in this invention, an abnormal feature system is established. An improved SVM algorithm is used to construct an intelligent identification model of abnormal features. The standardized abnormal identification dataset and feature labels are input. Through classification training of the SVM algorithm, the features of various abnormalities are accurately identified, realizing accurate classification and real-time identification of parameter abnormalities, link abnormalities, and data abnormalities, avoiding missed judgments and false judgments.

[0026] Step 4: Dynamic optimization of anomaly control strategy. Using the dynamic optimization algorithm for anomaly control strategy designed in this invention, an anomaly control optimization system is established, and global weight coefficients are set. Clearly define the values ​​of each parameter ( Parameter anomaly 0.95, link anomaly 0.92, data anomaly 0.96; Parameter anomaly 0.85, link anomaly 0.8, data anomaly 0.88; Parameter anomalies: 0.9, 0.88; Link anomalies: 0.88, 0.85; Data anomalies: 0.92, 0.9. (Parameter anomaly 0.86, link anomaly 0.82, data anomaly 0.89), substitute into the dedicated anomaly control effectiveness calculation formula. An improved random forest algorithm is used to accurately calculate the control effect coefficients of various anomalies and analyze the shortcomings of control (such as untimely link anomaly warnings and unreasonable parameter anomaly control strategies).

[0027] Step 5: Anomaly Warning and Control Optimization. Based on the anomaly identification results and control effectiveness coefficient, output anomaly warning information in real time (clearly specifying the anomaly type, location, and severity), and execute corresponding control operations (parameter adjustment, link switching, and data retransmission). Based on the analysis of control deficiencies, dynamically optimize the anomaly control strategy (adjust warning thresholds, increase link anomaly response priority), adjust weight coefficients, collect anomaly processing data in real time, and continuously iterate and optimize the control model to improve the real-time performance and effectiveness of anomaly control.

[0028] Efficiency Enhancement Principles (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the intelligent anomaly feature recognition algorithm adopts an improved SVM algorithm, which can accurately identify subtle features of various anomalies, avoiding missed and false judgments. Compared with the simple anomaly detection mode of existing technologies, it significantly improves the accuracy and real-time performance of anomaly recognition. The dynamic optimization algorithm for anomaly control strategies combines a dedicated calculation formula with an improved random forest algorithm, which can accurately calculate the control effect and dynamically optimize the control strategy and weights. Compared with the passive anomaly response mode of existing technologies, it realizes proactive prediction and dynamic optimization of anomaly control. At the modeling level, an integrated modeling logic of "data collection - anomaly recognition - early warning control - effect calculation - dynamic optimization" is constructed, which deeply binds anomaly features with control effects. The modeling innovation lies in realizing accurate anomaly recognition and dynamic optimization of control strategies, breaking through the limitations of traditional passive anomaly response and lack of strategy optimization, ensuring that anomalies can be identified in real time, given timely early warnings, and effectively controlled, thereby improving the stability of the communication protocol software system. Compared with existing technologies, which adopt a passive anomaly response mode, the accuracy of anomaly identification is low and the response is slow, making it impossible to achieve real-time control of the entire process. In contrast, this embodiment achieves real-time anomaly identification and dynamic control through algorithm and modeling innovation, significantly improving the stability and security of the communication protocol software system.

[0029] Example 2 (without formulas, corresponding to the adaptive feature extraction algorithm for the protocol scenario) Step 1: Scene and Protocol Data Acquisition. Select three typical communication scenarios: industrial communication, IoT, and smart terminals. Deploy multi-source data acquisition terminals to collect detailed data for each scenario: Industrial communication scenario (communication rate requirement: high speed, transmission distance: medium to long distance, interference intensity: medium to high, data type: real-time control data); IoT scenario (communication rate requirement: medium to low speed, transmission distance: long distance, interference intensity: medium to low, data type: sensor data); Smart terminal scenario (communication rate requirement: high speed, transmission distance: short distance, interference intensity: low, data type: multimedia data). Simultaneously, collect the corresponding protocol operating parameters (baud rate, parity bit, protocol type) for each scenario to establish the original scenario and protocol dataset.

[0030] Step 2: Data preprocessing. The collected scenario and protocol raw datasets are preprocessed as follows: Data cleaning algorithms are used to remove missing data, abnormal deviations, and invalid data (such as rate data caused by abnormal interference); standardization is used to unify data dimensions and eliminate the influence of units; scenario data and protocol parameters are correlated and mapped to clarify the correspondence between scenario requirements and protocol parameters, and a standardized scenario-protocol dataset is established.

[0031] Step 3: Adaptive Extraction of Scene Features. Using the adaptive extraction algorithm for protocol scene features designed in this invention, a communication scene feature system is established. The system integrates the rate features, distance features, interference features, and data type features of standardized scene data. An improved RNN combined with an attention mechanism is used to construct a scene feature extraction model. The RNN extracts the temporal features of the scene (such as the dynamic changes in the interference intensity of industrial communication). The attention mechanism strengthens the core requirement features of various scenarios (industrial communication strengthens the "high reliability and high speed" features, the Internet of Things strengthens the "low power consumption and long distance" features, and smart terminals strengthen the "high speed and low latency" features), suppresses irrelevant interference features, and adaptively extracts the core features of the three types of scenarios, clarifying the type, weight, and representation rules of each scene feature.

[0032] Step 4: Feature extraction verification. Based on the actual communication needs and industry standards of various communication scenarios, verify the accuracy and relevance of scenario feature extraction, analyze feature extraction biases (such as confusing the core features of IoT and smart terminals), dynamically optimize algorithm parameters (RNN iteration count, attention weight), adjust feature extraction strategies, and improve the accuracy and relevance of feature extraction.

[0033] Step 5: Feature Output. Organize the core features of various scenarios, establish a scenario feature library, clarify the feature differences and core communication requirements of different scenarios, output the core feature data of the scenarios, and feed it back to the dynamic adaptation of protocol parameters to provide support for the dynamic adaptation of protocol parameters.

[0034] Efficiency Enhancement Principle (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the adaptive feature extraction algorithm for protocol scenarios combines an improved RNN with an attention mechanism. This enables precise extraction of core requirement features for different scenarios, strengthens scenario-differentiated features, and suppresses interference. Compared to existing technologies with fixed feature extraction and a lack of specificity, this significantly improves the accuracy and specificity of scenario feature recognition, accurately distinguishing the core requirements of different types of communication scenarios. At the modeling level, an integrated modeling logic of "scenario acquisition - preprocessing - feature extraction - verification and optimization" is constructed. This integrates the differentiated requirements of different types of communication scenarios into the modeling process. The modeling innovation lies in achieving adaptive extraction and differentiated representation of scenario features, breaking through the limitations of inaccurate and non-specific traditional scenario feature extraction. This ensures that scenario features accurately reflect the core communication requirements of the scenario, laying a solid foundation for subsequent protocol parameter adaptation. Compared to existing technologies, which cannot accurately extract the core features of different communication scenarios, resulting in large protocol adaptation deviations and failing to meet the needs of multi-scenario communication, this embodiment achieves accurate and adaptive extraction of scenario features through algorithmic and modeling innovation, significantly improving the accuracy of protocol adaptation.

[0035] Example 3 (without formulas, corresponding to the dynamic adaptation algorithm for protocol parameters) Step 1: Input feature and protocol data. Obtain the core feature data of the three types of communication scenarios (industrial communication, Internet of Things, and smart terminal) output in Example 2. Simultaneously collect the communication protocol operation parameters (baud rate, parity bit, and protocol type) corresponding to each type of scenario. Establish a scenario feature and protocol parameter dataset and clarify the correspondence between the core requirements of different scenarios and the protocol parameters (e.g., the high reliability requirement of industrial communication corresponds to high baud rate and odd parity).

[0036] Step 2: Data association preprocessing. The scenario feature and protocol parameter datasets are associated and preprocessed: the weights of scenario features and protocol parameters are quantified, a feature-parameter association matrix is ​​established, and the adaptation relationship between the core scenario features and protocol parameters is clarified; irrelevant association relationships are eliminated, feature-parameter association deviations are corrected, and a standardized scenario-protocol parameter association dataset is established.

[0037] Step 3: Dynamic Protocol Parameter Adaptation. Using the dynamic protocol parameter adaptation algorithm designed in this invention, a protocol parameter adaptation system is established. An improved PSO algorithm is employed to construct a dynamic protocol parameter adaptation model. A standardized scenario-protocol parameter association dataset is input. Using the matching degree between scenario requirements and protocol parameters as the objective function, iterative optimization through particle swarm optimization dynamically adjusts the protocol parameters (industrial communication: high baud rate, odd parity, TCP / IP protocol; IoT: medium-low baud rate, even parity, UDP protocol; smart terminals: high-speed baud rate, no parity, TCP / IP protocol). This quantifies the matching degree between scenario requirements and protocol parameters, and selects the protocol parameter adaptation scheme with the highest matching degree.

[0038] Step 4: Verify the adaptation effect. Based on the communication quality feedback (transmission stability, adaptation accuracy) of various scenarios, verify the accuracy and effectiveness of protocol parameter adaptation, analyze adaptation deviations (such as excessive transmission delay after protocol parameter adaptation in IoT scenarios), dynamically optimize algorithm parameters (PSO particle count, iteration count), adjust parameter adaptation strategies, and improve the accuracy and flexibility of adaptation.

[0039] Step 5: Output adaptation results, organize the dynamic adaptation results of protocol parameters, identify the optimal protocol parameters for different scenarios, output a protocol parameter adaptation report, and feed it back to the data transmission intelligent optimization module to guide data transmission path planning and error suppression.

[0040] Efficiency Enhancement Principle (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the dynamic protocol parameter adaptation algorithm adopts an improved PSO algorithm, which can dynamically adjust protocol parameters through iterative optimization, quantify the matching degree between the scenario and the parameters, and accurately select the optimal adaptation scheme. Compared with the existing technology with fixed protocol parameters and large adaptation deviations, this significantly improves the accuracy and flexibility of protocol adaptation, ensuring that the protocol parameters can meet the communication needs of different scenarios. At the modeling level, an integrated modeling logic of "feature input - association preprocessing - parameter optimization - accurate adaptation - verification optimization" is constructed, which deeply integrates scenario features and protocol parameters. The modeling innovation lies in realizing the dynamic adaptation and quantitative matching of protocol parameters, breaking through the limitations of traditional fixed protocol parameters and arbitrary adaptation, and ensuring the scientific and targeted nature of the protocol parameter adaptation results. Compared with existing technologies, which use fixed protocol parameters and cannot be dynamically adjusted according to scenario needs, resulting in a disconnect between protocol and scenario adaptation and poor communication quality, this embodiment achieves dynamic adaptation of protocol parameters through algorithm and modeling innovation, significantly improving the multi-scenario adaptability of the communication protocol software system.

[0041] Example 4 (without formulas, corresponding to dynamic programming of data transmission path and adaptive suppression algorithm for transmission errors) Step 1: Protocol adaptation results and link data input. Obtain the protocol parameter adaptation results output by Example 3 (industrial communication: TCP / IP protocol, high baud rate; Internet of Things: UDP protocol, medium and low baud rate). Synchronously collect network topology data and link status data, including the number of transmission links, link delay, packet loss rate, interference intensity, and bandwidth utilization rate, and establish a link status dataset.

[0042] Step 2: Link data preprocessing. The link status dataset is preprocessed as follows: anomaly detection algorithms are used to remove abnormal link status data (such as bursts of high latency and high packet loss); normalization is used to unify the dimensions of link status parameters and eliminate the influence of units; the link status is graded and labeled (high quality, good, poor) to establish a standardized link status dataset.

[0043] Step 3: Dynamic planning of data transmission paths. Using the dynamic planning algorithm for data transmission paths designed in this invention, a data transmission path system is established. An improved Dijkstra algorithm is used to construct a dynamic planning model for data transmission paths. The inputs are protocol adaptation results, standardized link state dataset, and network topology. The objective function is to minimize transmission delay and packet loss rate. Link stability weights are introduced to select the optimal transmission path in real time: low-latency, high-reliability links are selected for industrial communication scenarios, and long-distance, low-power links are selected for IoT scenarios. At the same time, the link state changes are monitored in real time, and the transmission path is dynamically adjusted when the link state deteriorates.

[0044] Step 4: Adaptive suppression of transmission errors. Using the adaptive suppression algorithm for transmission errors designed in this invention, a transmission error suppression system is established. An algorithm combining improved convolutional code encoding and adaptive equalization is used to encode the transmitted data, enhancing the data's anti-interference capability. The adaptive equalization algorithm is used to offset transmission distortion caused by link interference, and the error rate and packet loss rate of data transmission are monitored in real time. Errors in the transmission process are identified and suppressed, the error correction strategy is optimized, and the encoding parameters and equalization coefficients are adjusted to improve the reliability of data transmission.

[0045] Step 5: Transmission Verification and Optimization. Construct a transmission verification model, monitor data transmission latency, packet loss rate, and error rate in real time, quantify data transmission reliability, analyze transmission deficiencies (such as high transmission latency in industrial communication scenarios and high packet loss rate in IoT scenarios), dynamically optimize algorithm parameters (Dijkstra weight coefficients, convolutional code encoding length), iteratively optimize path planning and error suppression strategies, output highly reliable and low-latency transmission data, and feed it back to the real-time anomaly control module.

[0046] Efficiency Enhancement Principles (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the dynamic planning algorithm for data transmission paths adopts an improved Dijkstra algorithm, which can adapt to changes in link status in real time and select the optimal transmission path. Compared with the fixed-path transmission mode of existing technologies, it significantly improves the stability and low latency of data transmission. The adaptive transmission error suppression algorithm adopts a combination of improved convolutional code encoding and adaptive equalization, which can effectively identify and suppress transmission errors. Compared with the error suppression mode of existing technologies, it significantly improves the reliability of data transmission. At the modeling level, an integrated modeling logic of "link acquisition - path planning - data transmission - error suppression - verification and optimization" is constructed, which deeply binds protocol adaptation, link status and data transmission. The modeling innovation lies in realizing the synergistic advancement of dynamic planning of transmission paths and error suppression, breaking through the limitations of traditional fixed paths and no error suppression, and ensuring high reliability and low latency of data transmission. Compared with existing technologies, which use fixed transmission paths and lack effective error suppression mechanisms, resulting in high data transmission latency, high packet loss rate and low reliability, this embodiment achieves intelligent optimization of data transmission through algorithm and modeling innovation, significantly improving the quality of data transmission.

[0047] In summary, this invention solves the specific problems of poor adaptability to multiple scenarios, low data transmission reliability, and insufficient real-time anomaly control in the prior art. It realizes multi-scenario adaptability, high-reliability transmission, and real-time anomaly control of communication protocol software systems, significantly improves the adaptability, reliability, and stability of communication protocol software systems, promotes the deep integration of communication protocol software with multi-scenario applications, fills the technical gap in this field, and has no duplication with existing or previous related technologies.

Claims

1. A communication protocol software system and optimization method adaptable to multiple scenarios, characterized in that, Includes the following steps: S1: Multi-scenario adaptive adaptation processing of protocols. Collect communication requirement data and protocol operation parameters in multiple scenarios. Through protocol scenario feature adaptive extraction algorithm and protocol parameter dynamic adaptation algorithm, construct a multi-scenario adaptive adaptation model of protocols to achieve accurate adaptation of multiple scenarios and communication protocols. S2: Intelligent data transmission optimization processing. Based on protocol adaptation results and data transmission requirements, it constructs an intelligent data transmission optimization model through data transmission path dynamic planning algorithm and transmission error adaptive suppression algorithm to achieve highly reliable and low-latency data transmission. S3: Real-time anomaly control and processing. Based on data transmission status and protocol operation data, an anomaly control model is constructed through intelligent anomaly feature identification algorithm and dynamic anomaly control strategy optimization algorithm to realize anomaly identification, early warning and control throughout the entire communication protocol operation process. The dynamic optimization algorithm for anomaly control strategy in step S3 includes an anomaly control effect calculation formula: The constraints are and , Let be the control effectiveness coefficient for the j-th type of anomaly at time t. Let be the anomaly detection accuracy at time t. This represents the lead time for an anomaly warning at time t. These are the control effectiveness coefficients for this type of anomaly at times t-1 and t-2, respectively. The abnormal control response speed at time t. These are the weighting coefficients for identification accuracy, early warning lead time, effect change rate, and response speed, respectively.

2. The method according to claim 1, characterized in that, The protocol scenario feature adaptive extraction algorithm in step S1 includes the following sub-steps: establishing a communication scenario feature system, integrating the communication rate, data type, transmission distance, and interference intensity of multiple scenarios (industrial communication, Internet of Things, smart terminals), adopting an algorithm combining an improved recurrent neural network (RNN) and an attention mechanism, adaptively extracting the core features of the scenario, clarifying the type, weight, and representation rules of the scenario features, and providing support for protocol parameter adaptation.

3. The method according to claim 1, characterized in that, The protocol parameter dynamic adaptation algorithm in step S1 includes the following sub-steps: establishing a protocol parameter adaptation system, integrating core features of the scenario with protocol operating parameters (baud rate, parity bit, transmission protocol type), using an improved particle swarm optimization (PSO) algorithm, constructing a protocol parameter dynamic adaptation model, quantifying the matching degree between scenario requirements and protocol parameters, realizing dynamic adjustment and adaptation of protocol parameters, and outputting the adapted protocol parameters.

4. The method according to claim 1, characterized in that, The data transmission path dynamic planning algorithm in step S2 includes the following sub-steps: establishing a data transmission path system, integrating protocol adaptation results, network topology, and transmission link status, using an improved Dijkstra algorithm, constructing a data transmission path dynamic planning model, filtering the optimal transmission path in real time, realizing dynamic adjustment of the transmission path, and ensuring low latency and high reliability of data transmission.

5. The method according to claim 1, characterized in that, The adaptive transmission error suppression algorithm in step S2 includes the following sub-steps: establishing a transmission error suppression system; based on the data transmission status (error rate, packet loss rate) and link interference intensity, using an algorithm combining improved convolutional code encoding and adaptive equalization to identify and suppress transmission errors, optimize error correction strategies, and improve the reliability of data transmission.

6. The method according to claim 1, characterized in that, The intelligent identification algorithm for abnormal features in step S3 includes the following sub-steps: establishing an abnormal feature system, integrating protocol operation data (parameter deviation, transmission delay, packet loss rate) and abnormal types (parameter abnormality, link abnormality, data abnormality), and using an improved support vector machine (SVM) algorithm to construct an intelligent identification model for abnormal features, thereby achieving accurate identification and classification of various abnormalities.

7. The method according to claim 1, characterized in that, The dynamic optimization algorithm for anomaly control strategy in step S3 includes the following sub-steps: establishing an anomaly control optimization system, integrating anomaly control effect calculation formula, anomaly handling historical data, and scenario requirements, and using an improved random forest algorithm to dynamically optimize the anomaly control strategy and weight coefficients to improve the real-time performance and effectiveness of anomaly control.

8. The method according to any one of claims 1-7, characterized in that, The process parameters of the communication protocol software system are: scene adaptation accuracy ≥ 99.0%, data transmission reliability ≥ 99.5%, anomaly identification accuracy ≥ 98.8%, anomaly response time ≤ 0.5ms, transmission delay ≤ 10ms, adaptable to various communication scenarios such as industrial communication, Internet of Things, smart terminals, and vehicle communication.

9. The method according to any one of claims 1-7, characterized in that, The method can be applied to fields such as industrial automation, smart home, intelligent transportation, and telemedicine. It is compatible with various mainstream communication protocols such as TCP / IP, UDP, and Modbus, and supports intelligent management and control of the entire process, including protocol adaptation, data transmission, and anomaly control.

10. A communication protocol software system adaptable to multiple scenarios, characterized in that, It includes a protocol multi-scenario adaptive adaptation module, a data transmission intelligent optimization module, an anomaly real-time control module, and a system control center. The control center communicates bidirectionally with the three functional modules, integrates six core algorithms, and executes the method described in any one of claims 1-9 to realize multi-scenario adaptation, data transmission optimization, and anomaly real-time control of the communication protocol software system.

Images