A lightweight cross-protocol compatible communication protocol software system and optimization method
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING XINJIACHUN TECHNOLOGY CO LTD
- Filing Date
- 2026-04-07
- Publication Date
- 2026-06-19
Smart Images
Figure CN122248077A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of information technology, specifically relating to a lightweight, cross-protocol compatible communication protocol software system and its optimization method. Background Technology
[0002] While communication protocol software systems are increasingly widely used in lightweight terminals and multi-protocol convergence scenarios, the proliferation of lightweight devices such as portable smart terminals and IoT edge devices, coupled with the increasing demand for multi-protocol convergence communication, still presents prominent challenges: insufficient lightweight adaptation, difficulties in cross-protocol compatibility, and poor energy consumption and performance synergy. Traditional systems often employ generalized protocol design, single-protocol adaptation, and fixed energy consumption control modes, lacking targeted adaptation capabilities for lightweight scenarios, intelligent multi-protocol compatibility, and synergistic optimization of energy consumption and performance. They are no longer adequate for the communication needs of low computing power, low power consumption, and multi-protocol convergence. In particular, in the three core areas of lightweight protocol adaptation, cross-protocol compatibility, and energy consumption and performance synergy, there are three specific and unresolved practical problems, all of which are specific pain points in the manufacturing process. These problems do not overlap with existing or previous communication protocol-related technologies (including previous multi-scenario adaptation solutions and general communication protocols), as follows: 1. Insufficient lightweight adaptation and lack of dedicated lightweight feature extraction and load pruning algorithms: Existing communication protocol software systems mostly adopt general protocol designs and have not been specifically adapted to the resource limitations of lightweight terminals (low computing power, low storage, low power consumption); there is no protocol lightweight feature extraction algorithm, which cannot accurately extract the core requirements (computing power, storage, power consumption) of lightweight scenarios, resulting in a mismatch between the protocol and the resources of lightweight terminals; there is no protocol load dynamic pruning algorithm, which cannot dynamically prune redundant protocol loads (redundant fields, non-core functions), resulting in excessive resource consumption by the protocol and inability to run stably on lightweight terminals.
[0003] 2. Difficulty in cross-protocol compatibility, lack of dedicated cross-protocol feature mapping and data conversion algorithms: Existing communication protocol software systems mostly focus on single protocol optimization and lack intelligent compatibility with multiple types of protocols; the lack of cross-protocol feature mapping algorithms makes it impossible to achieve accurate mapping and alignment of features of different protocols (such as TCP / IP and LoRa), resulting in irreconcilable differences in protocol features; the lack of cross-protocol adaptive data conversion algorithms makes it impossible to achieve real-time and accurate conversion of data from different protocols, resulting in data incompatibility and poor compatibility in multi-protocol scenarios.
[0004] 3. Poor coordination between energy consumption and performance, lack of dedicated collaborative modeling and dynamic control algorithms: Existing communication protocol software systems mostly adopt a single control mode of "emphasizing performance over energy consumption" or "emphasizing energy consumption over performance," lacking the ability to coordinate and optimize energy consumption and performance; there is no energy consumption and performance collaborative modeling algorithm, making it impossible to quantify the synergistic relationship between energy consumption and performance, resulting in an inability to dynamically balance energy consumption and performance; there is no energy consumption dynamic control algorithm, making it impossible to dynamically adjust energy consumption strategies according to terminal resources and communication needs, resulting in either excessive energy consumption affecting terminal battery life or insufficient performance affecting communication quality.
[0005] Existing communication protocol technologies largely focus on general-scenario protocol optimization, single-protocol adaptation, and fixed energy consumption control. They lack core algorithmic innovation in areas such as lightweight adaptive adaptation of communication protocol software systems, intelligent cross-protocol compatibility, and coordinated energy consumption and performance optimization. Significant technological gaps exist, particularly in lightweight protocol feature extraction, cross-protocol feature mapping, and coordinated energy consumption and performance modeling, failing to address the aforementioned specific problems and offering no overlap with existing or previous technologies in terms of technical direction and innovation. There is an urgent need for a lightweight, cross-protocol compatible communication protocol software system and optimization method centered on algorithmic innovation. This method should focus on three entirely new technical perspectives: protocol lightweighting, cross-protocol compatibility, and coordinated energy consumption and performance. It should emphasize algorithmic innovation and modeling principles throughout the process to achieve lightweight adaptation, multi-protocol compatibility, and coordinated energy consumption and performance in 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] Addressing the three specific problems raised in the background technology, the present invention aims to provide a lightweight, cross-protocol compatible communication protocol software system and optimization method. This system achieves precise adaptation to lightweight scenarios and communication protocols, intelligent multi-protocol compatibility and data interoperability, and dynamic coordination of energy consumption and performance. It solves the problems of insufficient lightweight adaptation, difficulties in cross-protocol compatibility, and poor coordination between energy consumption and performance. The entire process emphasizes algorithm innovation and modeling solution, without involving rules of intellectual activity. This improves the lightweight nature, cross-protocol compatibility, and energy economy of the communication protocol software system, promoting the deep application of communication protocol software in lightweight terminals and multi-protocol fusion scenarios. It 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: (a) Lightweight Adaptive Protocol Module The core of this module is to achieve precise adaptation between lightweight scenarios and communication protocols, construct a lightweight adaptive adaptation model for protocols, solve the problem of insufficient lightweight adaptation, and realize a closed loop of "lightweight terminal data acquisition - protocol load acquisition - feature extraction - load trimming - adaptation verification". It provides lightweight protocol support for cross-protocol intelligent compatibility, and its core highlights algorithm innovation and modeling and solution principles.
[0008] Modeling Approach: Abandoning the traditional approach of "generalized protocol design without lightweight adaptation," this approach constructs an integrated modeling logic encompassing "lightweight terminal data acquisition - protocol load acquisition - data preprocessing - feature extraction - load pruning - adaptation verification - optimization iteration." It combines lightweight terminal resource data (computing power, storage, bandwidth, power consumption), protocol runtime load data (redundant fields, non-core functions, data transmission volume), and historical adaptation data to establish terminal data acquisition models, protocol load acquisition models, preprocessing models, feature extraction models, load pruning models, and verification optimization models. Lightweight feature extraction algorithms and dynamic protocol load pruning algorithms are designed. Through algorithmic innovation, accurate extraction of lightweight features is achieved; through modeling optimization, dynamic pruning of protocol load is realized, highlighting the principles of algorithm efficiency enhancement and modeling innovation.
[0009] Solution Process: First, deploy lightweight data acquisition terminals to simultaneously collect resource data from various lightweight terminals, including computing resources, storage capacity, communication bandwidth, power consumption limits, and battery life requirements of different types of terminals such as portable smart terminals and IoT edge devices. Simultaneously, collect runtime load data for various communication protocols, including protocol frame structure, redundant fields, non-core functional modules, and data transmission volume, to establish a raw lightweight terminal-protocol load dataset. Preprocess the collected data: Use data cleaning algorithms to remove missing, abnormal, and invalid data (such as abnormal terminal computing power data); standardize the data to unify data dimensions and eliminate the influence of unit of measurement; and correlate and map terminal resource data with protocol load data to clarify the correspondence between terminal resource limitations and protocol load, establishing a standardized terminal-protocol load dataset. Then, a lightweight feature extraction algorithm for the protocol was designed, and a lightweight feature system for the protocol was established. The algorithm integrates the computing power features, storage features, power consumption features, and bandwidth features of standardized terminal resource data. An improved lightweight convolutional neural network (CNN) algorithm is adopted to simplify the network structure, reduce the number of parameters, adapt to the computing power requirements of lightweight terminals, and adaptively extract the core features of the protocol lightweighting. The priority (power consumption priority, computing power adaptation priority) and representation rules of lightweight features are clarified. The principle of algorithm efficiency improvement is that by using the improved lightweight CNN algorithm, the limitations of traditional feature extraction algorithms, such as high computing power consumption and unsuitability for lightweight scenarios, are overcome. It can achieve accurate extraction of lightweight features on low computing power terminals. Compared with the generalized feature extraction mode of existing technologies, it greatly improves the targeting and efficiency of lightweight scenario adaptation. Simultaneously, a dynamic protocol load pruning algorithm was designed, establishing a protocol load pruning system. This system integrates protocol lightweighting features with protocol runtime load data, employing an improved greedy algorithm combined with adaptive threshold adjustment to construct a dynamic protocol load pruning model. Using the matching degree between protocol load and lightweight terminal resources as the objective function, the greedy algorithm filters and prunes redundant protocol loads (redundant fields, non-core functions), while adaptive threshold adjustment dynamically optimizes the pruning degree, quantifying the matching degree between protocol load and terminal resources. This achieves dynamic pruning of redundant protocol loads. The innovative modeling principle lies in constructing a collaborative logic of "feature extraction - load analysis - dynamic pruning - verification and optimization," overcoming the limitations of traditional fixed protocol loads that cannot adapt to lightweight terminals. This ensures that the pruned protocol can run stably on lightweight terminals while retaining core communication functions. Finally, an adaptation verification model is constructed, combining terminal runtime feedback (resource utilization, operational stability) to quantify the protocol lightweighting adaptation success rate, dynamically optimize algorithm parameters (lightweight CNN network parameters, pruning threshold), and output the lightweight adapted protocol, feeding it back to the cross-protocol intelligent compatibility module.
[0010] (ii) Cross-protocol intelligent compatibility module The core of this module is to achieve intelligent compatibility and data interoperability of multiple communication protocols, build a cross-protocol intelligent compatibility model, solve the problem of cross-protocol compatibility difficulties, and realize a closed loop of "lightweight protocol input - multi-protocol data acquisition - feature mapping - data conversion - compatibility verification". It provides multi-protocol communication support for energy consumption and performance synergistic optimization, and the core highlights algorithm innovation and modeling and solution principles.
[0011] Modeling Approach: Abandoning the traditional approach of "single protocol adaptation with no cross-protocol compatibility," this approach constructs an integrated modeling logic encompassing "lightweight protocol input - multi-protocol data acquisition - data preprocessing - feature mapping - data conversion - compatibility verification - optimization iteration." Combining the lightweight adapted protocol, multi-type communication protocol data (frame structure, data format, communication rules), cross-protocol conversion requirements (real-time performance, integrity), and historical conversion data, this approach establishes a protocol input model, a multi-protocol data acquisition model, a preprocessing model, a feature mapping model, a data conversion model, and a compatibility verification model. It designs cross-protocol feature mapping algorithms and cross-protocol data adaptive conversion algorithms. Through algorithmic innovation, it achieves accurate mapping of cross-protocol features; through modeling optimization, it achieves real-time conversion of cross-protocol data, highlighting the principles of algorithm efficiency enhancement and modeling innovation.
[0012] Solution Process: First, obtain the lightweight protocol output from the lightweight adaptive adaptation module to clarify the communication protocol requirements and cross-protocol compatibility needs in the lightweight scenario. Simultaneously collect data from multiple communication protocols, including frame structures, data formats, communication rules, and data encoding methods of mainstream protocols such as TCP / IP, UDP, Modbus, and LoRa, to establish a multi-protocol raw dataset. Preprocess the multi-protocol raw dataset: use a data standardization algorithm to unify the data formats and encoding methods of different protocols; use a feature alignment algorithm to correct feature deviations between different protocols; remove invalid protocol data and abnormal interference data to establish a standardized multi-protocol dataset. Then, a cross-protocol feature mapping algorithm is designed to establish a cross-protocol feature system. This system integrates frame structure features, data format features, and communication rule features from standardized multi-protocol datasets. An algorithm combining an improved attention mechanism and feature embedding is adopted. The attention mechanism strengthens the core features of different protocols (such as the reliability features of TCP / IP and the low power consumption features of LoRa). Feature embedding achieves accurate mapping and alignment of features from different protocols, clarifying the correspondence between features of different protocols. The algorithm's efficiency enhancement principle lies in the fact that by combining the improved attention mechanism and feature embedding, it overcomes the limitations of traditional cross-protocol features, which cannot be accurately mapped and have poor compatibility. It can effectively reconcile the feature differences between different protocols and significantly improve the accuracy and compatibility of cross-protocol feature mapping compared to the simple protocol conversion mode of existing technologies. Simultaneously, a cross-protocol data adaptive conversion algorithm is designed to establish a cross-protocol data conversion system. This system integrates cross-protocol feature mapping results and data transmission requirements (real-time performance and integrity). An algorithm combining an improved recurrent neural network (RNN) and adaptive encoding is employed to construct a cross-protocol data adaptive conversion model. The RNN captures the temporal characteristics of the data, and adaptive encoding achieves real-time and accurate conversion of data from different protocols, automatically adapting to different protocol data formats and encoding methods. This ensures the integrity and consistency of cross-protocol data interoperability. The innovative modeling principle lies in constructing a closed-loop logic of "feature mapping - data conversion - real-time adaptation - verification and optimization," overcoming the limitations of inaccurate and poor real-time performance in traditional cross-protocol data conversion, and achieving seamless interoperability of multi-protocol data. Finally, a compatibility verification model is constructed to monitor the accuracy and real-time performance of cross-protocol data conversion in real time, quantify the cross-protocol compatibility effect, dynamically optimize algorithm parameters (attention weights, RNN iteration count), output cross-protocol compatible communication data, and feed it back to the energy consumption and performance co-optimization module.
[0013] (III) Energy Consumption and Performance Co-optimization Module The core of this module is to achieve dynamic coordination of energy consumption and performance during the operation of communication protocols, construct an energy consumption and performance coordination optimization model, solve the problem of poor coordination between energy consumption and performance, and realize a closed loop of "multi-protocol communication data input - energy consumption and performance data acquisition - collaborative modeling - dynamic control - effect verification", thereby improving the energy economy and operational stability of the communication protocol software system. The core highlights are algorithm innovation and modeling and solution principles.
[0014] Modeling Approach: Abandoning the traditional approach of "single energy consumption control or single performance optimization," this approach constructs an integrated modeling logic encompassing "multi-protocol communication data input - energy consumption performance data acquisition - data preprocessing - collaborative modeling - dynamic control - effect verification - optimization iteration." It combines communication data output from cross-protocol intelligent compatibility modules, protocol operation energy consumption data (power consumption, battery life), performance data (transmission rate, response time, stability), and lightweight terminal power consumption limitations. This establishes energy consumption performance data acquisition models, preprocessing models, collaborative modeling models, dynamic control models, and effect verification models. Furthermore, it designs collaborative modeling algorithms for energy consumption performance and dynamic control algorithms for energy consumption. Through algorithmic innovation, it achieves precise coordination between energy consumption and performance; through modeling optimization, it achieves dynamic control of energy consumption, highlighting the principles of algorithm efficiency enhancement and modeling innovation.
[0015] Solution Process: First, acquire cross-protocol communication data output by the cross-protocol intelligent compatibility module to clarify performance requirements in multi-protocol communication scenarios. Simultaneously collect energy consumption and performance data of protocol operation, including protocol power consumption, terminal battery life, data transmission rate, response time, and operational stability coefficient, to establish a raw energy consumption performance dataset. Preprocess the collected dataset: remove invalid and abnormal interference data, quantify energy consumption and performance characteristics, establish a standardized energy consumption performance dataset, and clarify the correlation between energy consumption and performance. Then, design an energy consumption performance collaborative modeling algorithm to establish an energy consumption performance collaborative system, integrating the standardized energy consumption performance dataset, lightweight terminal power consumption limitations, and communication performance requirements, combined with a dedicated energy consumption performance collaborative calculation formula. An improved Bayesian network algorithm is used to construct an energy consumption and performance collaborative modeling model. By leveraging the probabilistic reasoning capabilities of Bayesian networks, the collaborative relationship between energy consumption and performance is quantified, and the optimal balance range between energy consumption and performance under different communication scenarios is identified. The algorithm's efficiency enhancement principle lies in the combination of the improved Bayesian network algorithm and a dedicated accounting formula, which overcomes the limitations of traditional methods that cannot accurately coordinate energy consumption and performance and are difficult to balance. It can accurately quantify the collaborative relationship between energy consumption and performance, and significantly improve the scientificity and rationality of energy consumption and performance coordination compared to the single control mode of existing technologies. Simultaneously, a dynamic energy consumption control algorithm is designed, establishing a dynamic energy consumption control system. This system integrates energy consumption performance collaborative modeling results, lightweight terminal power consumption limitations, and communication requirements. An improved reinforcement learning algorithm is employed, aiming to maximize the energy consumption performance synergy coefficient. It dynamically adjusts protocol operating parameters (transmission frequency, data frame size, sleep strategy) to reduce protocol operating energy consumption while ensuring communication performance (meeting transmission rate and response time requirements), achieving dynamic energy consumption control. Its innovative modeling principle lies in constructing a closed-loop logic of "collaborative modeling - dynamic control - effect feedback - iterative optimization," breaking through the limitations of traditional fixed energy consumption control that cannot adapt to dynamic scenarios, ensuring that energy consumption and performance are always in an optimal balance. Finally, an effect verification model is constructed to monitor the energy consumption performance synergy coefficient, energy consumption reduction rate, and performance compliance rate in real time. The algorithm parameters (Bayesian network parameters, reinforcement learning reward function) are dynamically optimized, outputting the protocol operating parameters after energy consumption performance synergy optimization. This ensures that the communication protocol software system achieves low-energy, high-performance operation on lightweight terminals. Attached Figure Description
[0016] Appendix Figure 1 : Workflow diagram of the lightweight adaptive adaptation module for the protocol Beneficial effects The core benefits of this invention lie in the innovation of six undisclosed algorithms and the optimization of modeling logic. It emphasizes the principles of algorithm efficiency enhancement and modeling innovation throughout, and has no overlap with existing or previous technologies. Specifically: 1. Lightweight Feature Extraction Algorithm: The algorithm innovatively adopts an improved lightweight CNN algorithm. The principle of algorithm efficiency improvement lies in simplifying the network structure and reducing computing power consumption. It can achieve accurate extraction of lightweight features on lightweight terminals with low computing power, and improve the targeting and efficiency of lightweight scenario adaptation. The modeling innovation lies in constructing the logic of "terminal acquisition-feature extraction-verification optimization", which breaks through the limitations of traditional feature extraction, which has high computing power consumption and is not suitable for lightweight scenarios.
[0017] 2. Protocol Load Dynamic Trimming Algorithm: This innovative algorithm combines an improved greedy algorithm with adaptive threshold adjustment. The algorithm's efficiency is enhanced by its ability to accurately filter and trim redundant protocol loads, dynamically optimize the trimming degree, and improve the matching degree between protocol loads and lightweight terminal resources. The modeling innovation lies in constructing a collaborative logic of "feature association - load trimming - precise adaptation," breaking through the limitations of traditional fixed protocol loads that cannot adapt to lightweight terminals.
[0018] 3. Cross-protocol feature mapping algorithm: The algorithm innovatively adopts an improved attention mechanism combined with feature embedding. The principle of algorithm efficiency enhancement is that it can accurately reconcile the feature differences of different protocols, realize the accurate mapping and alignment of features, and improve the accuracy of cross-protocol compatibility. The modeling innovation lies in constructing the logic of "multi-protocol preprocessing-feature mapping-feature alignment", which breaks through the limitations of traditional cross-protocol features that cannot be accurately mapped and have poor compatibility.
[0019] 4. Cross-protocol data adaptive conversion algorithm: The algorithm innovatively adopts an improved RNN combined with adaptive coding. The principle of algorithm efficiency enhancement is that it can realize real-time and accurate conversion of data from different protocols, automatically adapt to protocol differences, and improve the integrity and real-time performance of cross-protocol data interoperability. The modeling innovation lies in constructing a closed loop of "feature mapping-data conversion-real-time adaptation", which breaks through the limitations of traditional cross-protocol data conversion that is inaccurate and has poor real-time performance.
[0020] 5. Energy Consumption and Performance Collaborative Modeling Algorithm: This innovative algorithm combines a proprietary calculation formula with an improved Bayesian network algorithm. The principle behind its enhanced efficiency lies in its ability to accurately quantify the collaborative relationship between energy consumption and performance, clarify the optimal balance range, and improve the scientific nature of energy consumption and performance collaboration. The modeling innovation lies in constructing a logic of "energy consumption and performance acquisition - collaborative modeling - balance analysis," breaking through the limitations of traditional methods that cannot accurately coordinate energy consumption and performance.
[0021] 6. Dynamic Energy Consumption Control Algorithm: The innovative algorithm adopts an improved reinforcement learning algorithm. The principle of algorithm efficiency enhancement lies in its ability to dynamically adapt to the needs of the scenario and adjust the protocol operation parameters to achieve precise energy consumption control and improve energy economy and performance stability. The modeling innovation lies in building a closed loop of "collaborative modeling-dynamic control-effect feedback", which breaks through the limitations of traditional energy consumption control that is fixed and cannot adapt to dynamic scenarios.
[0022] Example The following four examples further illustrate the implementation of the present invention.
[0023] Example 1 Step 1: Input communication and energy consumption performance data. In the IoT edge device scenario, acquire cross-protocol communication data (TCP / IP and LoRa protocol data) output by the cross-protocol intelligent compatibility module, clarify the communication performance requirements (transmission rate, response time) of the scenario, and synchronously collect energy consumption data (power consumption, battery life) and performance data (transmission rate, response time, stability coefficient) of the protocol operation, establish a raw energy consumption performance dataset, and label the energy consumption and performance characteristics under different operating states.
[0024] Step 2: Data preprocessing and feature quantification. The collected raw energy consumption performance dataset is preprocessed: invalid data and abnormal interference data (such as sudden high energy consumption and abnormal performance data) are removed; energy consumption characteristics (power consumption, battery life) and performance characteristics (transmission rate, response time, stability coefficient) are quantified using standardized processing to establish a standardized energy consumption performance dataset, clarify the correlation between energy consumption and performance, and mark the goals of energy consumption performance co-optimization (low energy consumption, high performance).
[0025] Step 3: Collaborative modeling of energy consumption performance. Using the collaborative modeling algorithm for energy consumption performance designed in this invention, a collaborative energy consumption performance system is established, and global weight coefficients are set. Clearly define the values of each parameter ( Transmission rate compliance coefficient, response time compliance coefficient; Power consumption at the current and previous time points; Protocol load factor; (Operational stability coefficient), substituted into the dedicated energy consumption performance collaborative calculation formula. An improved Bayesian network algorithm is used to construct an energy consumption and performance collaborative model, quantify the collaborative relationship between energy consumption and performance, and clarify the optimal balance range between energy consumption and performance in this scenario.
[0026] Step 4: Dynamic Energy Consumption Control. Using the dynamic energy consumption control algorithm designed in this invention, a dynamic energy consumption control system is established. The input includes the energy consumption performance collaborative modeling results, the power consumption limits of IoT edge devices, and communication performance requirements. An improved reinforcement learning algorithm is used to dynamically adjust the protocol operating parameters with the goal of maximizing the energy consumption performance collaboration coefficient: reducing the transmission frequency of non-real-time data, optimizing the data frame size, and setting a reasonable protocol sleep strategy. Under the premise of ensuring that the transmission rate and response time meet the standards, the energy consumption of the protocol operation is reduced.
[0027] Step 5: Validation and optimization of synergistic effects. Construct an effect validation model, monitor the energy consumption performance synergy coefficient, energy consumption reduction rate, and performance compliance rate in real time, analyze shortcomings in synergistic optimization (e.g., energy consumption reduced but performance not meeting standards, performance meeting standards but energy consumption too high), and dynamically optimize algorithm parameters (Bayesian network parameters, reinforcement learning reward function, weight coefficients). The energy consumption control strategy is iteratively optimized to ensure that the protocol always operates at the optimal balance between energy consumption and performance.
[0028] Efficiency Enhancement Principles (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the energy consumption and performance collaborative modeling algorithm combines an improved Bayesian network with a dedicated accounting formula. This allows for precise quantification of the synergistic relationship between energy consumption and performance, clearly defining the optimal balance range. Compared to existing technologies that rely solely on single energy consumption control or performance optimization, this significantly improves the scientific rigor of energy consumption and performance coordination. The energy consumption dynamic control algorithm employs an improved reinforcement learning algorithm, enabling dynamic adaptation to scenario requirements and adjustment of operating parameters to achieve precise energy consumption control. Compared to existing technologies that rely on fixed energy consumption strategies, this significantly improves energy economy and performance stability. At the modeling level, an integrated modeling logic of "data acquisition - collaborative modeling - dynamic control - effect verification - iterative optimization" is constructed, deeply binding energy consumption and performance. The modeling innovation lies in achieving dynamic coordination and precise control of energy consumption and performance, breaking through the limitations of traditional energy consumption and performance imbalances, and ensuring low-energy, high-performance operation of the protocol on lightweight terminals. Compared with existing technologies, which adopt a single control mode, either excessive energy consumption affects the terminal's battery life or insufficient performance affects communication quality, this embodiment achieves dynamic coordination between energy consumption and performance through algorithm and modeling innovation, significantly improving the energy economy and operational stability of the communication protocol software system.
[0029] Example 2 Step 1: Terminal and Protocol Data Acquisition. Select two typical lightweight terminals: portable smart terminals and IoT edge devices. Deploy lightweight data acquisition terminals to collect detailed resource data for each type of terminal: portable smart terminal (computing power: 256M, storage: 32M, bandwidth: 10Mbps, power consumption limit: 5W); IoT edge device (computing power: 128M, storage: 16M, bandwidth: 5Mbps, power consumption limit: 3W). Simultaneously, collect the runtime load data of various communication protocols (frame structure, redundant fields, non-core functions, and data transmission volume of TCP / IP and LoRa protocols) to establish a raw dataset of lightweight terminal-protocol load.
[0030] Step 2: Data preprocessing. The collected lightweight terminal-protocol load raw dataset is preprocessed as follows: Data cleaning algorithms are used to remove missing data, abnormal deviations, and invalid data (such as abnormal terminal computing power data and invalid protocol load data); standardization processing is used to unify data dimensions and eliminate the influence of units; terminal resource data and protocol load data are correlated and mapped to clarify the correspondence between terminal resource limitations and protocol load (such as low computing power terminals corresponding to low load protocols), and a standardized terminal-protocol load dataset is established.
[0031] Step 3: Lightweight Feature Adaptive Extraction. Using the lightweight feature extraction algorithm designed in this invention, a lightweight feature system for the protocol is established. This system integrates the computing power, storage, power consumption, and bandwidth features of standardized terminal resource data. An improved lightweight CNN algorithm is used to simplify the network structure, reduce the number of parameters, and adapt to the computing power requirements of lightweight terminals. The core features of the lightweight protocol are adaptively extracted, and the priority of lightweight features is clarified (power consumption and computing power are prioritized for IoT edge devices, and storage and bandwidth are prioritized for portable smart terminals). The representation rules and weights of each feature are also clarified.
[0032] Step 4: Feature extraction verification. Based on the actual resource constraints and communication requirements of the two types of lightweight terminals, verify the accuracy and relevance of lightweight feature extraction, analyze feature extraction biases (such as confusing the lightweight priority of the two types of terminals), dynamically optimize algorithm parameters (lightweight CNN network parameters, feature extraction threshold), adjust feature extraction strategies, improve the accuracy and relevance of feature extraction, and ensure that the extracted lightweight features can accurately reflect the terminal resource constraints and communication requirements.
[0033] Step 5: Feature Output. Organize the core features of the lightweight protocol for the two types of lightweight terminals, establish a lightweight feature library, clarify the feature differences and core requirements of different types of lightweight terminals, output lightweight feature data, and feed it back to the dynamic trimming of protocol load to support the dynamic trimming of protocol load.
[0034] Efficiency Enhancement Principle (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the lightweight feature extraction algorithm adopts an improved lightweight CNN algorithm, simplifying the network structure and reducing computational power consumption. It enables accurate extraction of lightweight features on low-computing-power lightweight terminals. Compared to existing general-purpose feature extraction algorithms (high computational power consumption, lack of specificity), this significantly improves the targeting and efficiency of lightweight scenario adaptation, avoiding excessive terminal resource consumption during feature extraction. At the modeling level, an integrated modeling logic of "terminal acquisition - preprocessing - feature extraction - verification and optimization" is constructed, incorporating the resource constraints and communication requirements of lightweight terminals into the modeling process. The modeling innovation lies in achieving accurate extraction and priority differentiation of lightweight features, breaking through the limitations of traditional feature extraction that is not suitable for lightweight scenarios and has high computational power consumption. This ensures that the extracted features can accurately support subsequent protocol load pruning, laying a solid foundation for lightweight adaptation. Compared to existing technologies, which cannot accurately extract lightweight features, leading to mismatches between protocols and lightweight terminal resources and unstable operation, this embodiment achieves accurate and efficient extraction of lightweight features through algorithmic and modeling innovation, significantly improving the targeting of lightweight protocol adaptation.
[0035] Example 3 Step 1: Input feature and load data. Obtain the core feature data of lightweight protocol for the two types of lightweight terminals (portable smart terminals and IoT edge devices) output in Example 2. Simultaneously collect the runtime load data (frame structure, redundant fields, non-core functions, data transmission volume) of various communication protocols (TCP / IP, LoRa). Establish a lightweight feature and protocol load dataset to clarify the resource limitations and protocol load adaptation relationship of different terminals (e.g., low-load protocols for IoT edge devices).
[0036] Step 2: Data association preprocessing. Perform association preprocessing on the lightweight feature and protocol load datasets: quantify the weights of lightweight features and protocol loads, establish a feature-load association matrix, clarify the adaptation thresholds of lightweight features and protocol loads (e.g., the upper limit of protocol load for terminals with computing power ≤ 128M); eliminate irrelevant associations, correct feature-load association deviations, identify redundant protocol loads (redundant fields, non-core functions), and establish a standardized feature-load association dataset.
[0037] Step 3: Dynamic Protocol Load Trimming. Using the dynamic protocol load trimming algorithm designed in this invention, a protocol load trimming system is established. An improved greedy algorithm combined with adaptive threshold adjustment is used to construct a dynamic protocol load trimming model. A standardized feature-load association dataset is input. Using the matching degree between protocol load and lightweight terminal resources as the objective function, the greedy algorithm filters and trims redundant protocol loads (such as redundant check fields in TCP / IP protocol and non-core control functions in LoRa protocol). The degree of trimming is dynamically optimized through adaptive threshold adjustment, quantifying the matching degree between protocol load and terminal resources, and selecting the load trimming scheme with the highest matching degree.
[0038] Step 4: Verify the trimming effect. Based on the operational feedback (resource utilization, operational stability, and communication quality) of the two types of lightweight terminals, verify the accuracy and effectiveness of protocol load trimming, analyze trimming deviations (such as excessive trimming leading to the loss of core functions, and insufficient trimming leading to excessive resource consumption), dynamically optimize algorithm parameters (number of iterations of the greedy algorithm, trimming threshold), adjust the load trimming strategy, and improve the accuracy and flexibility of trimming.
[0039] Step 5: Output the trimming results, organize the dynamic trimming results of the protocol load, identify the optimal protocol load (trimmed TCP / IP, LoRa protocol) for different types of lightweight terminals, output the lightweight adapted protocol, and feed it back to the cross-protocol intelligent compatibility module to guide cross-protocol feature mapping and data conversion.
[0040] Efficiency Enhancement Principle (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the dynamic protocol load pruning algorithm combines an improved greedy algorithm with adaptive threshold adjustment. This allows for precise screening and pruning of redundant loads, dynamically optimizing the pruning degree. Compared to existing technologies with fixed loads, no pruning, or inaccurate pruning, this significantly improves the matching degree between protocol loads and lightweight terminal resources, preventing redundant loads from consuming excessive terminal resources. At the modeling level, an integrated modeling logic of "feature input - correlation preprocessing - load pruning - verification optimization" is constructed, deeply integrating lightweight features with protocol loads. The modeling innovation lies in achieving dynamic pruning and precise adaptation of protocol loads, breaking through the limitations of traditional fixed protocol loads that cannot adapt to lightweight terminals. This ensures that the pruned protocol can run stably on lightweight terminals while retaining core communication functions. Compared to existing technologies, which lack protocol load pruning mechanisms, resulting in excessively high resource consumption and inability to run stably on lightweight terminals, this embodiment achieves dynamic pruning of protocol loads through algorithmic and modeling innovations, significantly improving the lightweight nature and adaptability of the communication protocol software system.
[0041] Example 4 Step 1: Lightweight Protocol and Multi-Protocol Data Input. Obtain the lightweight adapted protocols (tailored TCP / IP and LoRa protocols) output from Example 3, clarify the multi-protocol compatibility requirements (TCP / IP and LoRa protocol data interoperability), synchronously collect detailed data (frame structure, data format, communication rules, and data encoding methods) of TCP / IP and LoRa protocols, and establish a multi-protocol raw dataset.
[0042] Step 2: Multi-protocol data preprocessing. The original multi-protocol dataset is preprocessed as follows: a data standardization algorithm is used to unify the data format and encoding method of TCP / IP and LoRa protocols to eliminate format differences; a feature alignment algorithm is used to correct the feature deviations of the two types of protocols and clarify the feature correspondence between the two types of protocols; invalid protocol data and abnormal interference data are removed to establish a standardized multi-protocol dataset.
[0043] Step 3: Cross-protocol feature mapping. Using the cross-protocol feature mapping algorithm designed in this invention, a cross-protocol feature system is established. The frame structure features, data format features, and communication rule features of the standardized multi-protocol dataset are integrated. An algorithm combining an improved attention mechanism and feature embedding is used to construct a cross-protocol feature mapping model. The attention mechanism enhances the reliability features of the TCP / IP protocol and the low power consumption features of the LoRa protocol. Feature embedding achieves accurate mapping and alignment of the two types of protocol features, clarifying the correspondence between the two types of protocol features (such as the feature mapping relationship between TCP / IP data frames and LoRa data frames).
[0044] Step 4: Cross-protocol data adaptive conversion. Using the cross-protocol data adaptive conversion algorithm designed in this invention, a cross-protocol data conversion system is established. It integrates cross-protocol feature mapping results and data transmission requirements (real-time performance and integrity). An algorithm combining an improved RNN and adaptive coding is used to construct a cross-protocol data adaptive conversion model. A standardized multi-protocol dataset is input, and the RNN captures the temporal characteristics of the data. Adaptive coding is used to achieve real-time and accurate conversion between TCP / IP and LoRa protocol data, automatically adapting the data format and encoding method of the two protocols to ensure the integrity and consistency of data interoperability.
[0045] Step 5: Compatibility effect verification and optimization. Construct a compatibility verification model, monitor the accuracy and real-time performance of cross-protocol data conversion in real time, analyze compatibility deficiencies (such as incomplete data conversion and poor real-time performance), dynamically optimize algorithm parameters (attention weights, RNN iteration count, and encoding parameters), iteratively optimize feature mapping and data conversion strategies, output cross-protocol compatible communication data, and feed it back to the energy consumption and performance collaborative optimization module.
[0046] Efficiency Enhancement Principles (Algorithm Enhancement + Modeling Innovation): At the algorithm level, the cross-protocol feature mapping algorithm combines an improved attention mechanism with feature embedding, accurately reconciling feature differences between different protocols to achieve precise feature mapping and alignment. Compared to existing technologies that rely on simple protocol conversion and feature misalignment, this significantly improves the accuracy of cross-protocol compatibility. The cross-protocol data adaptive conversion algorithm combines an improved RNN with adaptive encoding, enabling real-time and accurate conversion of data from different protocols and automatically adapting to protocol differences. Compared to existing technologies with fixed conversion rules and poor compatibility, this significantly improves the completeness and real-time performance of cross-protocol data interoperability. At the modeling level, an integrated modeling logic of "protocol input - data preprocessing - feature mapping - data conversion - verification and optimization" is constructed, deeply binding lightweight protocols with multi-protocol compatibility requirements. The modeling innovation lies in achieving accurate cross-protocol feature mapping and adaptive data conversion, overcoming the limitations of traditional cross-protocol compatibility difficulties and data interoperability, and ensuring seamless communication in multi-protocol scenarios. Compared with existing technologies, which cannot achieve precise compatibility and data interoperability between different protocols, communication is hindered in multi-protocol scenarios. However, this embodiment achieves intelligent compatibility and data interoperability between multiple protocols through algorithm and modeling innovation, significantly improving the cross-protocol compatibility of communication protocol software systems.
[0047] In summary, this invention, through six core algorithmic innovations and integrated modeling logic optimization, solves the specific problems of insufficient lightweight adaptation, difficulty in cross-protocol compatibility, and poor energy consumption and performance synergy in existing technologies. It achieves lightweight adaptation, multi-protocol compatibility, and energy consumption and performance synergy in communication protocol software systems, significantly improving the lightweightness, cross-protocol compatibility, and energy economy of communication protocol software systems. This promotes the deep application of communication protocol software in lightweight terminals and multi-protocol integration scenarios, fills a technological gap in this field, and has no duplication with existing or previous related technologies.
Claims
1. A lightweight cross-protocol compatible communication protocol software optimization method, characterized in that, Includes the following steps: S1: Lightweight protocol adaptive adaptation processing: Collect lightweight terminal communication requirements and protocol operation load data, and construct a lightweight protocol adaptive adaptation model through lightweight protocol feature extraction algorithm and protocol load dynamic pruning algorithm to achieve accurate adaptation between lightweight scenarios and communication protocols. S2: Cross-protocol intelligent compatibility processing. Based on lightweight adaptation results and multi-protocol communication requirements, it constructs a cross-protocol intelligent compatibility model through cross-protocol feature mapping algorithm and cross-protocol data adaptive conversion algorithm to achieve intelligent compatibility and data interoperability of multiple types of communication protocols. S3: Energy consumption and performance co-optimization processing. Based on protocol adaptation and cross-protocol compatibility results, it constructs an energy consumption and performance co-optimization model through energy consumption and performance co-modeling algorithm and energy consumption dynamic control algorithm to achieve dynamic balance between energy consumption and performance during the operation of communication protocols. In the energy consumption performance synergy modeling algorithm in step S3, the energy consumption performance synergy calculation formula is included: , the constraint condition is and , is the energy consumption performance synergy coefficient at time t, is the protocol running performance coefficient at time t, are the protocol running energy consumptions at times t and t-1 respectively, is the protocol load coefficient at time t, is the protocol running stability coefficient at time t, are the weight coefficients of performance, energy consumption change rate, load, and stability respectively.
2. The method of claim 1, wherein, The protocol lightweight feature extraction algorithm in step S1 includes the following sub-steps: establishing a protocol lightweight feature system, integrating the computing resources, storage capacity, communication bandwidth, and power consumption limitations of lightweight terminals (portable smart terminals, IoT edge devices), adopting an improved lightweight convolutional neural network (CNN) algorithm, adaptively extracting the core features of protocol lightweighting, clarifying the priority and representation rules of lightweight features, and providing support for protocol load pruning.
3. The method of claim 1, wherein, The protocol load dynamic trimming algorithm in step S1 includes the following sub-steps: establishing a protocol load trimming system, integrating protocol lightweight features with protocol runtime load (redundant fields, non-core functions, data transmission volume), using an improved greedy algorithm combined with threshold adaptive adjustment, constructing a protocol load dynamic trimming model, quantifying the matching degree between protocol load and lightweight terminal resources, realizing dynamic trimming of protocol redundant load, and outputting the lightweight adapted protocol.
4. The method of claim 1, wherein, The cross-protocol feature mapping algorithm in step S2 includes the following sub-steps: establishing a cross-protocol feature system, integrating the frame structure, data format, and communication rules of different types of communication protocols (TCP / IP, UDP, Modbus, LoRa), using an algorithm that combines an improved attention mechanism with feature embedding, constructing a cross-protocol feature mapping model, achieving accurate mapping and alignment of features of different protocols, and providing support for cross-protocol data conversion.
5. The method according to claim 1, characterized in that, The cross-protocol data adaptive conversion algorithm in step S2 includes the following sub-steps: establishing a cross-protocol data conversion system, integrating cross-protocol feature mapping results and data transmission requirements (real-time performance and integrity), using an algorithm combining an improved recurrent neural network (RNN) and adaptive encoding, constructing a cross-protocol data adaptive conversion model, realizing real-time and accurate conversion of data from different protocols, and ensuring the integrity and consistency of cross-protocol data interoperability.
6. The method according to claim 1, characterized in that, The energy consumption performance collaborative modeling algorithm in step S3 includes the following sub-steps: establishing an energy consumption performance collaborative system, integrating protocol operation performance data (transmission rate, response time), energy consumption data (power consumption, battery life), and protocol load data, combining the energy consumption performance collaborative calculation formula, using an improved Bayesian network algorithm, constructing an energy consumption performance collaborative modeling model, quantifying the collaborative relationship between energy consumption and performance, and achieving a dynamic balance between energy consumption and performance.
7. The method according to claim 1, characterized in that, The energy consumption dynamic control algorithm in step S3 includes the following sub-steps: establishing an energy consumption dynamic control system, integrating the results of energy consumption performance collaborative modeling, the power consumption limit of lightweight terminals, and communication requirements, and adopting an improved reinforcement learning algorithm to dynamically adjust the protocol operation parameters (transmission frequency, data frame size, sleep strategy) to achieve dynamic control of protocol operation energy consumption and reduce energy consumption while ensuring performance.
8. The method according to any one of claims 1-7, characterized in that, The process parameters of the communication protocol software system are as follows: lightweight adaptation success rate ≥99.2%, cross-protocol conversion accuracy ≥99.6%, energy consumption reduction ≥30%, protocol operation response time ≤0.4ms, computing power of the adapted lightweight terminal ≤512M, storage occupation ≤64M, and compatibility with mainstream communication protocols such as TCP / IP, UDP, Modbus, and LoRa.
9. The method according to any one of claims 1-7, characterized in that, The method can be applied to portable smart terminals, IoT edge devices, multi-protocol industrial control, remote sensing and other fields. It supports intelligent management and control of the entire process, including lightweight protocol adaptation, cross-protocol compatibility, and energy consumption performance optimization. It is suitable for application scenarios with low computing power, low power consumption and multi-protocol integration.
10. A lightweight, cross-protocol compatible communication protocol software system, characterized in that, It includes a protocol lightweight adaptive adaptation module, a cross-protocol intelligent compatibility module, an energy consumption and performance collaborative optimization 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 achieve lightweight adaptation, cross-protocol compatibility, and energy consumption and performance collaborative optimization of the communication protocol software system.