A system and method for co-management of service flow adaptation and transmission quality of communication automation

Abstract

The application belongs to the technical field of communication automation, and discloses a service flow adaptation and transmission quality collaborative management and control system and method for communication automation. The application proposes six unique innovations by constructing three core modules of service flow intelligent identification and classification adaptation, transmission quality dynamic monitoring and regulation, and heterogeneous communication network collaborative management, covering the whole process of communication automation from service adaptation, quality regulation to heterogeneous collaboration. By adopting core technologies such as service flow multi-dimensional feature identification, service-transmission resource dynamic adaptation, and transmission quality multi-index collaborative regulation, the application breaks through the industry bottlenecks of traditional communication automation, such as rigid service adaptation, extensive transmission quality management and control, and insufficient heterogeneous network collaboration, and realizes accurate identification and adaptation of service flow, dynamic regulation and stable guarantee of transmission quality, efficient collaboration and resource integration of heterogeneous networks, significantly improving the service adaptation capability, transmission quality stability and heterogeneous network collaboration efficiency of communication automation, and adapting to the needs of industrial heterogeneous communication, urban broadband communication, multi-terminal collaborative communication and other scenarios, especially solving the technical problems of service flow adaptation and transmission demand mismatch, transmission quality regulation lag, and poor heterogeneous network collaboration.

Description

Technical Field

[0001] This invention belongs to the field of information technology, specifically relating to a communication automation service flow adaptation and transmission quality collaborative management system and method. Background Technology

[0002] In the current field of communication automation, with the rapid development of 5G and the Industrial Internet, communication scenarios are becoming increasingly complex, business types are constantly enriching, and heterogeneous networks (wired / wireless / IoT) are being widely deployed. However, existing technologies still face specific and unresolved practical problems in the three sub-scenarios of "service flow adaptation, transmission quality control, and heterogeneous network collaboration." These are all scenario-specific problems, not macro-level challenges, and have no overlap with the previous version of the technology direction. Specifically, they are as follows: 1. Rigid business flow adaptation, lacking multi-feature recognition and dynamic adaptation: Existing business flow adaptation mostly adopts the "fixed type matching + static resource allocation" mode, lacking multi-dimensional feature recognition of business flows, and also lacking a dynamic adaptation mechanism between business and transmission resources; resulting in inaccurate identification of business flow types (unable to distinguish between high latency-sensitive and high bandwidth-demand businesses), mismatch between adaptation strategies and actual business needs, causing stuttering in high latency-sensitive businesses and insufficient bandwidth in high bandwidth-demand businesses, resulting in a poor business transmission experience.

[0003] 2. Inadequate transmission quality control, lacking multi-indicator coordinated regulation and self-healing: Existing transmission quality control mostly adopts the "single indicator monitoring + manual regulation" model, lacking multi-indicator coordinated regulation of transmission quality, as well as transmission quality anomaly early warning and self-healing mechanisms; resulting in lagging transmission quality regulation, only able to monitor a single indicator (such as packet loss rate), unable to achieve coordinated optimization of latency, packet loss rate, and bandwidth utilization, and requiring manual intervention to repair after anomalies occur, resulting in low repair efficiency and affecting normal service transmission.

[0004] 3. Insufficient heterogeneous network collaboration, lack of dynamic scheduling and performance accounting: Existing heterogeneous network management and control mostly adopts the "independent management and control + simple switching" mode, lacking dynamic scheduling of heterogeneous network resources and a heterogeneous network collaboration performance accounting mechanism; resulting in the inability to effectively integrate heterogeneous network resources, high collaboration latency, uneven resource utilization (some network resources are idle, while some network resources are overloaded), and the inability to quantify collaboration effects, blind collaboration adjustments, and inability to adapt to heterogeneous communication needs in multiple scenarios.

[0005] Existing communication automation methods lack core innovations in "intelligent service flow adaptation, dynamic transmission quality control, and heterogeneous network collaborative management," particularly in the areas of multi-feature identification of service flows, collaborative control of multiple transmission quality indicators, and modeling and solving for heterogeneous network collaborative performance evaluation. These methods fail to address the specific problems mentioned above. This invention focuses on the development needs of strategic emerging industries (industrial internet, broadband communication networks) and proposes an innovation-driven method for service flow adaptation and collaborative transmission quality management. This fills a technological gap, helps communication automation upgrade towards "precise adaptation, stable transmission, and efficient collaboration," and meets the requirements of the invention priority examination policy. Summary of the Invention

[0006] Addressing the three specific problems raised in the background art, the present invention aims to provide a communication automation service flow adaptation and transmission quality collaborative management system and method. This system achieves accurate identification and adaptation of service flows, dynamic control and stable assurance of transmission quality, and efficient collaboration and resource integration across heterogeneous networks. It solves the problems of rigid service flow adaptation, coarse transmission quality management, and insufficient heterogeneous network collaboration. The entire process emphasizes innovation and modeling solutions, without involving rules for intellectual activities. It enhances the service adaptation capability, transmission quality stability, and heterogeneous network collaboration efficiency of communication automation, further improving the communication automation technology system in complex heterogeneous communication scenarios. This aligns with the development direction of strategic emerging industries and the requirements of the invention priority examination policy.

[0007] The present invention is implemented through the following specific technical solution: (I) Intelligent Identification and Classification Adaptation Module for Business Flow The core of this module is to accurately identify, classify, and dynamically adapt transmission resources for service flows. It constructs an intelligent identification and adaptation modeling system for service flows, solves the problems of rigid service flow adaptation and inaccurate identification, improves the adaptability and user experience of service transmission, and provides a basic guarantee for high-quality automated transmission of communications.

[0008] Modeling Approach: Abandoning the traditional extensive modeling approach of "fixed type matching and static resource allocation," we construct an integrated modeling logic of "business flow data collection - feature extraction modeling - identification and classification modeling - dynamic adaptation modeling - adaptation verification modeling." Combining business flow characteristics (rate / latency / data packet size), terminal demand characteristics (business priority / transmission requirements), and transmission resource characteristics (bandwidth / latency / stability), we establish a business flow feature library, identification and classification model, and dynamic adaptation model. We design multi-dimensional feature recognition of business flows and dynamic adaptation of business and transmission resources to achieve accurate adaptation between business flows and transmission resources.

[0009] First, deploy multi-source data acquisition components to collect service flow data (data transmission rate / latency requirements / data packet size / service type identifier), terminal requirement data (terminal type / service priority / transmission quality requirements), and transmission resource data (available bandwidth / transmission latency / resource load) from the communication network, constructing a service flow adaptation data resource pool. Then, design a multi-dimensional feature recognition model for service flows, extracting multi-dimensional core features of the service flows, constructing a service flow feature recognition model, and using improved K-means clustering to perform cluster analysis on the service flow features. Combined with feature matching calculations, this achieves accurate identification and type classification of service flows (high latency). (Sensitive, high-bandwidth-demand, and ordinary data types); Design dynamic adaptation of services and transmission resources. Based on service flow type, terminal requirements, and transmission resource status, construct an adaptation matching model to quantify the matching degree between service flow requirements and transmission resources. With the goal of "highest matching degree and optimal service experience," dynamically adjust resource allocation strategies (such as allocating low-latency resources to high-latency sensitive services and sufficient bandwidth to high-bandwidth-demand services) to achieve accurate adaptation of service flows and transmission resources. Construct an adaptation verification model to quantify service adaptation accuracy and transmission experience compliance rate, dynamically optimize parameters, and ensure the effectiveness of intelligent identification and dynamic adaptation of service flows.

[0010] 1: Multi-dimensional feature recognition of business flow To address the issues of "single business flow identification and inaccurate classification" in existing technologies, an integrated model for multi-dimensional feature extraction, cluster analysis, and matching calculation of business flows is constructed. This model enables accurate identification and type classification of business flows, solves the problems of large identification errors and one-sided classification, and fills the technological gap in multi-dimensional feature identification of business flows in communication automation.

[0011] 2: Dynamic adaptation of service and transmission resources To address the issues of "rigid service adaptation and resource mismatch" in existing technologies, an integrated model for dynamic matching modeling and parameter optimization of service flow requirements and transmission resource status is constructed. This model enables precise adaptation of service flow and transmission resources, solves the problems of fixed adaptation strategies and poor service experience, and fills the technological gap in dynamic adaptation of communication automation services and transmission resources.

[0012] (II) Transmission Quality Dynamic Monitoring and Control Module The core of this module enables dynamic monitoring, anomaly warning, precise control, and autonomous self-healing of transmission quality. It constructs a dynamic control modeling system for transmission quality, solves the problems of crude transmission quality management and lagging control, improves transmission quality stability, and ensures normal service transmission.

[0013] Modeling Approach: Abandoning the traditional extensive modeling approach of "monitoring a single indicator and manually adjusting", we construct an integrated modeling logic of "quality indicator collection - coupled correlation modeling - collaborative control modeling - anomaly early warning modeling - self-healing repair modeling". Combining multiple transmission quality indicators (latency / packet loss rate / bandwidth utilization / signal strength), service requirement thresholds, and transmission parameter characteristics, we establish a quality indicator coupling model, a collaborative control model, and anomaly early warning model. We design collaborative control of multiple transmission quality indicators, transmission quality anomaly early warning and self-healing, to achieve dynamic control and stable guarantee of transmission quality.

[0014] First, a real-time monitoring component is deployed to collect multi-dimensional transmission quality indicator data (latency / packet loss rate / bandwidth utilization / signal strength), service transmission anomaly data (stuttering / interruption records), and transmission parameter data (modulation / demodulation parameters / bandwidth allocation parameters), constructing a transmission quality control data resource pool. Then, a multi-indicator collaborative control model for transmission quality is designed, establishing a multi-indicator coupling and correlation model to clarify the interaction relationships between indicators (e.g., excessive bandwidth utilization leads to increased latency and packet loss rate). An improved PID control is adopted, aiming for "multi-indicator collaborative achievement and stable transmission quality." The system dynamically adjusts transmission parameters (bandwidth allocation ratio, modulation and demodulation methods) to achieve coordinated optimization of latency, packet loss rate, and bandwidth utilization. It designs a transmission quality anomaly early warning and self-healing mechanism, sets anomaly thresholds for each indicator, monitors indicator fluctuations in real time, and issues early warning signals when indicators approach or exceed thresholds, automatically triggering self-healing strategies (such as adjusting transmission paths and supplementing bandwidth resources) to achieve autonomous repair of transmission quality anomalies and reduce manual intervention costs. A quality verification model is constructed to quantify the transmission quality compliance rate, anomaly early warning accuracy, and self-healing success rate, dynamically optimizing parameters to ensure effective dynamic control of transmission quality.

[0015] 3: Coordinated control of multiple transmission quality indicators To address the problem of "single and uncoordinated transmission quality control" in existing technologies, an integrated model of multi-index coupled correlation modeling and multi-objective coordinated regulation of transmission quality is constructed. This model achieves multi-index coordinated optimization and stable transmission quality, solves the quality imbalance problem caused by single index control, and fills the technical gap in multi-index coordinated regulation of transmission quality in communication automation.

[0016] 4: Early warning and self-healing for transmission quality anomalies To address the issues of "lagging quality anomaly early warning and lack of autonomous self-healing" in existing technologies, an integrated model of anomaly threshold modeling, real-time early warning, and autonomous self-healing is constructed. This model enables early warning and rapid repair of transmission quality anomalies, solving the problems of low anomaly repair efficiency and impact on service transmission, and filling the technological gap in communication automation transmission quality anomaly early warning and self-healing.

[0017] (III) Heterogeneous Communication Network Collaborative Management and Control Module This module is designed to integrate resources, dynamically schedule and collaboratively manage multiple types of heterogeneous networks, build a modeling system for collaborative management of heterogeneous networks, solve the problems of insufficient collaboration and low resource utilization in heterogeneous networks, improve the efficiency of heterogeneous network collaboration, and adapt to heterogeneous communication needs in multiple scenarios.

[0018] Modeling Approach: Abandoning the traditional extensive modeling approach of "independent control and simple switching," we construct an integrated modeling logic of "heterogeneous network data acquisition - resource status modeling - dynamic scheduling modeling - performance accounting modeling - collaborative verification modeling." Combining the characteristics of heterogeneous networks (resource capacity / transmission rate / latency of wired / wireless / IoT), service adaptation requirements, and transmission quality requirements, we establish heterogeneous network resource models, dynamic scheduling models, and collaborative performance accounting models. We design heterogeneous network resource dynamic scheduling and heterogeneous network collaborative performance accounting to achieve efficient collaboration and resource integration of heterogeneous networks.

[0019] First, integrate heterogeneous network data of various types (resource capacity / available resources / transmission rate / cooperative latency of each network), service adaptation data (service flow type / adaptation requirements), and transmission quality data (quality indicator compliance status of each network) to construct a heterogeneous network collaborative data resource pool. Then, design a dynamic scheduling mechanism for heterogeneous network resources, establish a heterogeneous network resource status model, quantify the resource load and adaptation capabilities of each network, and dynamically allocate heterogeneous network resources based on service adaptation requirements and transmission quality requirements (e.g., allocating high-bandwidth demand services to wired networks and mobile terminal services to wireless networks) to achieve efficient resource integration and load balancing. Next, design a heterogeneous network collaborative performance calculation mechanism. Through the formula, quantify the rationality and efficiency of heterogeneous network collaboration (balancing quality compliance, resource utilization, and collaborative latency). If the performance value is lower than a set threshold, iteratively optimize the collaborative scheduling parameters (adjusting resource allocation ratios and optimizing collaborative transmission paths) to improve heterogeneous network collaborative efficiency. Finally, construct a collaborative verification model to quantify heterogeneous network resource utilization, collaborative performance value, and service transmission compliance rate, dynamically optimize parameters, and ensure efficient collaborative management and control of heterogeneous networks.

[0020] 5: Dynamic scheduling of heterogeneous network resources To address the issues of insufficient heterogeneous network collaboration and unbalanced resource allocation in existing technologies, an integrated model for heterogeneous network resource status modeling and dynamic scheduling adaptation is constructed. This model enables efficient integration and load balancing of heterogeneous network resources, solves the problem of resource idleness and overload coexisting, and fills the technological gap in dynamic scheduling of heterogeneous network resources in communication automation.

[0021] 6: Performance Calculation of Heterogeneous Network Collaboration To address the problems of "ineffective performance accounting and blind adjustment in heterogeneous network collaboration" in existing technologies, an integrated model of performance accounting formula quantification and parameter optimization is constructed to achieve scientific evaluation of the collaborative effect of heterogeneous networks, solve the problem of directionless collaborative adjustment, and fill the technical gap in performance accounting of heterogeneous network collaboration in communication automation.

[0022] Beneficial effects 1. Multi-dimensional feature recognition of business flow: Abandoning the crude approach of single feature recognition, a modeling system of multi-feature extraction, clustering and matching is constructed, which significantly improves the accuracy of business flow recognition and classification precision, completely solving the problems of large recognition errors and one-sided classification. It focuses on the innovation of accurate business flow recognition, which meets the development needs of strategic emerging industries in the industrial Internet. 2. Dynamic Adaptation of Service and Transmission Resources: Construct a dynamic matching modeling system for service requirements and resource status, significantly improving the accuracy of service adaptation and the pass rate of transmission experience, completely solving the problems of rigid adaptation and resource mismatch, and filling the technical gap in dynamic adaptation of service and transmission resources. 3. Multi-indicator coordinated control of transmission quality: Construct a modeling system for the coupling and coordinated control of multiple indicators, which significantly improves the stability of transmission quality, achieves coordinated compliance of multiple indicators, completely solves the quality imbalance problem caused by single indicator control, and focuses on innovation in coordinated control of transmission quality; 4. Transmission quality anomaly early warning and self-healing: Construct an integrated modeling system for early warning and self-healing, significantly improving the accuracy of anomaly early warning and the success rate of self-healing, greatly shortening the anomaly repair time, reducing the cost of manual intervention, and filling the technical gap in transmission quality anomaly early warning and self-healing; 5. Dynamic scheduling of heterogeneous network resources: Construct a modeling system for the integration and dynamic scheduling of heterogeneous network resources, significantly improve resource utilization and collaborative efficiency, achieve load balancing, and completely solve the problem of resource idleness and overload coexisting, focusing on collaborative innovation in heterogeneous networks; 6. Performance Accounting of Heterogeneous Network Collaboration: A modeling system for performance accounting and parameter optimization is constructed, which significantly improves the rationality and efficiency of heterogeneous network collaboration and greatly enhances the accuracy of collaborative adjustment. This fills the technical gap in performance accounting of heterogeneous network collaboration and meets the requirements of the invention priority examination policy.

[0023] Figure 1 Detailed Implementation of the Workflow Intelligent Recognition and Classification Adaptation Module The following four specific embodiments illustrate the implementation steps of the present invention in detail.

[0024] Example 1: Industrial Heterogeneous Communication Collaborative Management and Control Scenario Implementation steps Step 1: Data Acquisition and Parameter Setting: Collect data from industrial heterogeneous communication networks (resource capacity, available resources, transmission rate, and collaborative latency of wired / wireless / IoT networks), service adaptation data (industrial control services - high latency sensitive type, data acquisition services - general data type), and transmission quality data (latency and packet loss rate compliance status of each network). Set the qualified threshold for industrial heterogeneous communication collaborative performance. .

[0025] Step 2: Heterogeneous network resource status modeling: Using dynamic scheduling of heterogeneous network resources, establish an industrial heterogeneous network resource status model to quantify the resource load and adaptability of each network (e.g., wired networks have sufficient bandwidth and low latency, adapting to industrial control services; IoT resources are flexible and have wide coverage, adapting to data acquisition services).

[0026] Step 3: Dynamic Resource Scheduling and Performance Calculation: Based on service adaptation requirements and transmission quality requirements, dynamically allocate heterogeneous network resources (allocating industrial control services to wired networks and data acquisition services to IoT and wireless networks); employ heterogeneous network collaborative performance calculation, using performance calculation formulas... Quantify the collaborative performance of heterogeneous networks and calculate the transmission quality compliance rate of each network. Resource utilization rate Cooperative delay With resource consumption costs .

[0027] Step 4: Collaborative Optimization and Effect Verification: If the performance value Iterative optimization of collaborative scheduling parameters (adjusting the allocation ratio of network resources, reducing collaborative latency, and improving resource utilization); verification of heterogeneous network resource utilization (no idle, no overload), collaborative efficiency value (≥0.88), and service transmission compliance rate (no lag in industrial control services, no loss in data acquisition services).

[0028] Step 5: Continuous optimization: Collect network operation data and service feedback from heterogeneous industrial communications, dynamically adjust collaborative efficiency thresholds and scheduling parameters, and improve the adaptability to sudden business traffic surges and network status fluctuations in industrial production scenarios.

[0029] Modeling Innovation Principles Abandoning the traditional crude modeling approach of "independent management and simple switching of heterogeneous networks," this paper constructs an integrated closed-loop model of "data acquisition - resource modeling - dynamic scheduling - performance accounting," which addresses the high-reliability collaborative requirements of industrial heterogeneous communication. Using business adaptation characteristics and network resource characteristics as core inputs, this approach overcomes the limitations of insufficient heterogeneous network collaboration and unbalanced resource allocation. Heterogeneous network resource status modeling achieves accurate characterization of each network resource, dynamic scheduling modeling achieves efficient resource integration and load balancing, performance accounting formula modeling achieves quantitative evaluation of collaborative effects, and parameter optimization modeling achieves continuous improvement in collaborative efficiency, filling the gap in collaborative management and control modeling for industrial heterogeneous communication networks. The modeling process focuses on the high reliability and low latency requirements of industrial scenarios, completely differing from the independent management and non-accounting modeling approaches and technical directions of existing technologies. It also has no overlap with the previous modeling logic, representing a completely new modeling direction that aligns with the development needs of the strategic emerging industries of the industrial internet and the requirements of the invention priority examination policy.

[0030] Dynamic scheduling of heterogeneous network resources, through resource status modeling and dynamic allocation, significantly improves the utilization rate of heterogeneous network resources compared to the traditional independent management and control mode, completely solving the problem of resource idleness and overload coexisting, and achieving efficient resource integration and load balancing. Heterogeneous network collaborative performance accounting, through performance accounting formula quantification and parameter optimization, significantly improves the rationality and efficiency of heterogeneous network collaboration compared to collaborative modes without performance accounting, greatly reduces collaborative latency, and significantly improves the accuracy of collaborative adjustments, avoiding blind collaboration. These two types of collaborative effects enable industrial heterogeneous communication to achieve "precise resource scheduling, efficient and rational collaboration, and stable and reliable transmission." Compared with existing technologies, the collaborative efficiency and service transmission quality of heterogeneous networks have achieved a qualitative improvement, fully meeting the high requirements of industrial heterogeneous communication and conforming to the requirement of "enhancing the core competitiveness of the industry" in the invention priority examination policy.

[0031] Existing technologies employ a "heterogeneous network independent management and control + simple switching" model, lacking dynamic scheduling and performance accounting. This results in ineffective integration of heterogeneous network resources, high latency, uneven resource utilization, and an inability to quantify collaborative effects, leading to blind adjustments and failing to meet the high reliability and low latency requirements of industrial heterogeneous communication. This embodiment, through innovation and modeling optimization, achieves dynamic scheduling and collaborative management of industrial heterogeneous communication networks, completely resolving the pain points of existing technologies. Resource utilization and collaborative performance meet industrial heterogeneous communication standards, and there is no overlap in technical direction or modeling approach with existing or previous technologies. Its innovation is prominent, its practicality is strong, and it aligns with the development needs of strategic emerging industries and the requirements of the invention priority examination policy.

[0032] Example 2: Urban Broadband Communication Service Flow Adaptation Scenario (corresponding to the intelligent identification and classification adaptation module for service flows) Implementation steps Step 1: Business Flow and Related Data Acquisition: Deploy multi-source data acquisition components to collect business flow data (video stream - high bandwidth requirement, voice call - high latency sensitivity, file transfer - ordinary data, including transmission rate, latency requirement, and data packet size), terminal requirement data (terminal type, service priority), and transmission resource data (available bandwidth, transmission latency, and resource load) in urban broadband communication.

[0033] Step 2: Multi-dimensional feature identification and classification of business flows: Multi-dimensional feature identification of business flows is adopted to extract multi-dimensional core features of business flows (video stream: high bandwidth, large data packets; voice call: low latency, small data packets), construct feature identification model, and perform cluster analysis on business flow features by improving K-means clustering. Combined with feature matching calculation, the business flow type is accurately identified and classified.

[0034] Step 3: Dynamic Adaptation of Service-Transmission Resources: Dynamic adaptation of service-transmission resources is adopted. Based on the service flow type, terminal requirements and transmission resource status, an adaptation matching model is built to quantify the matching degree between service flow requirements and transmission resources, and dynamically adjust the resource allocation strategy (allocate sufficient bandwidth for video streams, allocate low-latency resources for voice calls, and allocate normal resources for file transfers).

[0035] Step 4: Adaptation effect verification and optimization: Verify the accuracy of business flow recognition (no recognition error), the degree of adaptation matching (meets the standard), and the business transmission experience (no video stuttering, no voice delay); collect business feedback data, optimize feature weights and adaptation parameters, and improve adaptation accuracy.

[0036] Step 5: Continuous optimization: Collect service flow change data and resource status data of urban broadband communication, dynamically update the service flow feature library, optimize clustering parameters, and improve the ability to identify and adapt to new service flows (such as VR / AR services).

[0037] Modeling Innovation Principles Abandoning the traditional extensive modeling approach of "fixed type matching and static resource allocation," this paper constructs an integrated closed-loop model of "data collection, feature modeling, identification and classification, and dynamic adaptation." It uses the diverse service needs, terminal characteristics, and resource status of urban broadband communications as core inputs, overcoming the limitations of rigid service flow adaptation and inaccurate identification. Multi-dimensional feature modeling of service flows achieves a comprehensive characterization, clustering identification modeling achieves accurate classification, and dynamic adaptation modeling achieves precise matching of service needs and resources, filling the gap in intelligent adaptation modeling of urban broadband communication service flows. The modeling process focuses on the diverse service needs of urban broadband, completely different from the single identification and static adaptation modeling approaches and technical directions of existing technologies. It also has no overlap with the modeling logic of the previous version, representing a completely new modeling direction that aligns with the development needs of the strategic emerging industries of broadband communication networks.

[0038] Multi-dimensional feature recognition of service flows, through multi-dimensional feature extraction, clustering, and matching calculation, significantly improves the accuracy of service flow recognition and classification precision compared to traditional single-feature recognition modes, completely solving the problems of large recognition errors and one-sided classification, and achieving accurate differentiation of various service flows; Dynamic adaptation of service and transmission resources, through dynamic matching modeling and parameter optimization, significantly improves the accuracy of service adaptation and the pass rate of transmission experience compared to traditional static adaptation modes, completely solving the problems of rigid adaptation and resource mismatch, and avoiding insufficient bandwidth for high-bandwidth services and excessive latency for high-latency services; The synergistic effect of these two types enables urban broadband communication to achieve "accurate service identification, accurate resource adaptation, and stable and high-quality experience." Compared with existing technologies, the service adaptation capability and transmission experience have achieved a qualitative improvement, fully meeting the diverse service needs of urban broadband.

[0039] Existing technologies employ a "fixed type matching + static resource allocation" service flow adaptation model, lacking multi-feature recognition and dynamic adaptation. This results in inaccurate service flow identification, fixed adaptation strategies, and a mismatch with actual service needs, leading to issues such as video stuttering and voice delays, and failing to meet the diverse service requirements of urban broadband. This embodiment, through innovation and modeling optimization, achieves intelligent identification and dynamic adaptation of urban broadband communication service flows, completely resolving the pain points of existing technologies. Its identification and adaptation capabilities meet urban broadband communication standards, and it does not overlap with existing technologies or previous versions in terms of technical direction or implementation scenarios. Its innovations are prominent, its practicality is strong, and it aligns with the development needs of strategic emerging industries.

[0040] Example 3: Multi-terminal collaborative communication transmission quality control scenario (corresponding to the transmission quality dynamic monitoring and control module) Implementation steps Step 1: Data collection related to transmission quality: Collect multi-dimensional data on transmission quality (latency, packet loss rate, bandwidth utilization, signal strength), abnormal data on service transmission (stuttering, interruption records), and transmission parameter data (modulation and demodulation parameters, bandwidth allocation parameters) of multi-terminal collaborative communication (mobile phones, tablets, computers, smart terminals).

[0041] Step 2: Multi-index coupling and correlation modeling of transmission quality: A multi-index coupling and correlation model of transmission quality is established by adopting coordinated control of multiple indicators of transmission quality, and the interaction relationship between each indicator is clarified (such as excessive bandwidth utilization leading to increased latency and packet loss rate, and insufficient signal strength leading to increased packet loss rate).

[0042] Step 3: Transmission quality coordinated control and anomaly handling: By improving PID control, with the goal of "multi-indicator coordinated achievement and stable transmission quality", transmission parameters (bandwidth allocation ratio, modulation and demodulation method) are dynamically adjusted; transmission quality anomaly early warning and self-healing are adopted, setting anomaly thresholds for each indicator, monitoring indicator fluctuations in real time, issuing early warnings in advance, and automatically triggering self-healing strategies (adjusting transmission path and supplementing bandwidth resources).

[0043] Step 4: Verification and optimization of control effect: Verify the transmission quality compliance rate (multi-indicator collaborative compliance), the accuracy of anomaly warning, and the self-healing success rate to ensure that multi-terminal collaborative communication is smooth and uninterrupted; collect transmission quality feedback data and optimize control parameters and anomaly thresholds.

[0044] Step 5: Continuous optimization: Collect terminal access change data and transmission quality data for multi-terminal collaborative communication, dynamically optimize the coupling correlation model parameters and control parameters, and improve the transmission quality control capability for multi-terminal concurrent access scenarios.

[0045] Modeling Innovation Principles Abandoning the traditional extensive modeling approach of "single indicator monitoring and manual control," this paper constructs an integrated closed-loop model of "data acquisition, coupled modeling, collaborative control, and early warning self-healing." It uses the transmission quality requirements, terminal access characteristics, and transmission parameter characteristics of multi-terminal collaborative communication as core inputs, overcoming the limitations of extensive and lagging transmission quality control. Multi-indicator coupled correlation modeling clearly depicts the relationships between various quality indicators; collaborative control modeling achieves synergistic optimization of multiple indicators; and early warning self-healing modeling enables early prevention and rapid repair of anomalies, filling the gap in dynamic control modeling for multi-terminal collaborative communication transmission quality. The modeling process focuses on the high stability requirements of multi-terminal collaboration, completely differing from the single-indicator and manual control modeling approaches and technical directions of existing technologies. It also has no overlap with the previous modeling logic, representing a completely new modeling direction that aligns with the development needs of multi-terminal collaborative communication in strategic emerging industries.

[0046] Multi-indicator coordinated control of transmission quality, through multi-indicator coupling and correlation modeling and improved PID control, significantly improves transmission quality stability compared to the traditional single-indicator control mode, achieving coordinated compliance of latency, packet loss rate, and bandwidth utilization, and completely solving the quality imbalance problem caused by single-indicator control. Transmission quality anomaly early warning and self-healing, through early warning modeling and self-healing strategies, significantly improves the accuracy of anomaly early warning and the success rate of self-healing compared to the traditional manual repair mode, greatly shortens anomaly repair time, reduces manual intervention costs, and avoids the impact of anomalies on multi-terminal collaborative communication. These two synergistic effects enable multi-terminal collaborative communication to achieve "stable quality, controllable anomalies, and efficient self-healing." Compared with existing technologies, the level and stability of transmission quality control have been qualitatively improved, fully meeting the high requirements of multi-terminal collaborative communication.

[0047] Existing technologies employ a "single indicator monitoring + manual adjustment" transmission quality control model, lacking multi-indicator collaborative control and self-healing capabilities. Transmission quality control is lagging, only able to monitor a single indicator, unable to achieve multi-indicator collaborative optimization, and requires manual intervention for repair after anomalies occur, resulting in low repair efficiency and impacting the multi-terminal collaborative communication experience. This embodiment, through innovation and model optimization, achieves dynamic control and autonomous self-healing of transmission quality in multi-terminal collaborative communication, completely resolving the pain points of existing technologies. Its control capabilities and stability meet multi-terminal collaborative communication standards, and it does not overlap with existing technologies or previous versions in terms of technical direction or implementation scenarios. Its innovation is prominent, its practicality is strong, and it aligns with the development needs of strategic emerging industries.

[0048] Example 4: Multi-scenario converged communication platform (industrial + urban broadband + multi-terminal) collaborative optimization scenario (integration of three core modules) Implementation steps Step 1: Intelligent Business Flow Identification and Adaptation: Collect business flow data, terminal demand data, and transmission resource data from the multi-scenario fusion platform. Using two components of the intelligent business flow identification and classification adaptation module, extract multi-dimensional features of the business flow. Accurately identify the business flow type through clustering and matching calculations, dynamically adapt transmission resources, and output multi-scenario business flow adaptation solutions.

[0049] Step 2: Dynamic Management and Control of Transmission Quality: Collect multi-dimensional transmission quality indicator data and abnormal service transmission data from the platform. Utilize two components of the dynamic monitoring and control module for transmission quality to establish a coupled correlation model of quality indicators. Through multi-indicator collaborative control, dynamically adjust transmission parameters to achieve anomaly warning and autonomous self-healing, ensuring stable transmission quality in multiple scenarios.

[0050] Step 3: Heterogeneous Network Collaborative Management and Control: Collect heterogeneous network data, service adaptation data, and transmission quality data from the platform. Using two components of the heterogeneous communication network collaborative management and control module, establish a heterogeneous network resource status model, dynamically schedule resources, quantify collaborative efficiency through performance accounting formulas, iteratively optimize collaborative parameters, and achieve efficient collaboration of heterogeneous networks.

[0051] Step 4: Multi-module collaborative management and control: The three core modules realize real-time data interaction through a high-speed communication bus, integrate the results of business adaptation, quality control, and heterogeneous collaboration, and output the full-domain collaborative optimization instructions of the multi-scenario fusion platform to achieve precise collaborative communication across multiple scenarios, services, and networks, ensuring the stable and efficient operation of the platform.

[0052] Step 5: Full-process verification and optimization: Verify the platform's business flow identification accuracy, transmission quality compliance rate, and heterogeneous network collaborative performance value; collect business feedback from various scenarios; optimize the parameters of the three major modules; realize continuous optimization and scenario expansion of platform communication; and meet the needs of multi-scenario integrated applications in strategic emerging industries and the requirements of the invention priority examination policy.

[0053] Modeling Innovation Principles Abandoning the traditional, crude modeling approach of "independent modules and single-level control," this paper constructs an integrated, full-domain modeling logic encompassing "business adaptation, quality control, heterogeneous collaboration, and multi-module fusion." It uses the business diversity, transmission quality requirements, and heterogeneous network characteristics of multi-scenario converged platforms as core inputs, overcoming the limitations of traditional communication automation modules being independent and lacking in collaboration. The deep integration of the three core modules achieves a closed-loop process of business adaptation, quality control, and heterogeneous collaboration. Business flow adaptation modeling enables precise adaptation of services across multiple scenarios, transmission quality modeling ensures stable transmission, and heterogeneous collaboration modeling achieves efficient resource integration, filling the gap in full-domain collaborative management modeling for multi-scenario converged communication platforms. The modeling process focuses on the multi-scenario convergence and efficient collaboration needs of strategic emerging industries, completely differing from the single-module, single-scenario modeling approach and technical direction of existing technologies. It also has no overlap with the previous modeling logic, representing a completely new modeling direction that complies with the policy requirements for priority examination of inventions.

[0054] The six core aspects of this invention achieve synergistic efficiency in a multi-scenario converged communication platform: Two aspects of service flow adaptation enable accurate identification and dynamic adaptation of service flows across multiple scenarios. Compared to traditional single adaptation modes, this significantly improves service adaptation accuracy and transmission experience compliance, resulting in a substantial improvement in multi-scenario service transmission experience. Two aspects of transmission quality control enable collaborative regulation and autonomous self-healing of transmission quality across multiple scenarios. Compared to traditional manual control modes, this significantly improves transmission quality stability and anomaly handling efficiency, and drastically reduces platform transmission failure rates. Two aspects of heterogeneous collaboration enable efficient collaboration and resource integration across heterogeneous networks in multiple scenarios. Compared to traditional independent control modes, this significantly improves resource utilization and collaboration efficiency, and drastically reduces heterogeneous network collaboration latency. These six aspects, working in conjunction with the three main modules, achieve comprehensive optimization of the multi-scenario converged communication platform, achieving "accurate adaptation, stable transmission, and efficient collaboration." Compared to existing technologies, this represents a qualitative leap in communication automation, fully meeting the multi-scenario converged communication needs of strategic emerging industries and complying with the "promoting industrial transformation and upgrading" requirement of the invention priority examination policy.

[0055] Existing communication automation methods suffer from problems such as independent and singular modules, lack of collaborative management and control, and absence of multi-dimensional feature identification of service flows, collaborative control of multiple transmission quality indicators, dynamic scheduling and performance calculation of heterogeneous networks. They also suffer from rigid adaptation to communication services across multiple scenarios, unstable transmission quality, and poor heterogeneous network collaboration, making it difficult to meet the high requirements of multi-scenario converged communication platforms. This embodiment, through three core modules and six core integrated innovations, achieves service flow adaptation and collaborative control of transmission quality in communication automation, completely resolving the pain points of existing technologies. It significantly improves the service adaptation capability, transmission quality stability, and heterogeneous network collaboration efficiency of multi-scenario communication. Furthermore, it does not overlap with existing technologies or previous versions in terms of technical direction or implementation scenarios, highlighting its innovations and strong practicality. It can be widely applied to various communication automation scenarios such as industrial applications, urban broadband, and multi-terminal applications.

[0056] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for coordinated management and control of service flow adaptation and transmission quality in communication automation, characterized in that, Includes the following steps: S1: Intelligent identification and classification adaptation of service flows. It collects service flow data, terminal demand data and transmission resource data in the communication network. Through multi-dimensional feature identification of service flows and dynamic adaptation of service and transmission resources, it achieves accurate identification, type classification and dynamic adaptation of service flows and outputs service flow adaptation solutions. S2: Dynamic monitoring and control of transmission quality. It collects multi-dimensional data of transmission quality in real time, and achieves dynamic monitoring, early warning, precise control and autonomous self-healing of transmission quality through coordinated control of multiple transmission quality indicators, early warning of transmission quality anomalies and self-healing, so as to ensure stable transmission quality. S3: Heterogeneous communication network collaborative management and control processing, integrates multiple types of heterogeneous network data, service adaptation data and transmission quality data, and realizes resource integration, dynamic scheduling and collaborative management and control of heterogeneous networks through dynamic scheduling of heterogeneous network resources and collaborative performance calculation of heterogeneous networks, forming a closed loop of collaborative optimization of the entire communication automation process; Among them, the heterogeneous network collaborative performance calculation in step S3 includes a performance calculation formula, which is as follows: The constraints are , This represents the collaborative performance value of heterogeneous networks. The transmission quality compliance rate of the j-th type of heterogeneous network. Let be the resource utilization rate of the j-th type of heterogeneous network. For the cooperative delay of the j-th type of heterogeneous network, Let $\frac{j}{j}$ be the resource consumption cost of the j-th type of heterogeneous network. The threshold for the collaborative performance of heterogeneous networks is set according to the type of heterogeneous network and business requirements.

2. The method according to claim 1, characterized in that, The multi-dimensional feature identification of the business flow in step S1 includes the following sub-steps: extracting multi-dimensional features of the business flow (data transmission rate / latency requirements / data packet size / business type identifier), constructing a business flow feature identification model, and achieving accurate identification and type classification of the business flow through multi-feature clustering and matching calculation.

3. The method according to claim 1, characterized in that, The dynamic adaptation of service-transmission resources in step S1 dynamically adjusts the resource allocation strategy based on service flow type, terminal requirements and transmission resource status, so as to achieve accurate matching between service flow requirements and transmission resources and improve service transmission adaptability.

4. The method according to claim 1, characterized in that, The multi-indicator coordinated control of transmission quality in step S2 involves constructing a multi-indicator coupled correlation model for transmission quality, integrating indicators such as latency, packet loss rate, and bandwidth utilization, and dynamically adjusting transmission parameters to achieve multi-indicator coordinated optimization and stable transmission quality.

5. The method according to claim 1, characterized in that, The transmission quality anomaly warning and self-healing in step S2 involves setting a transmission quality anomaly threshold, monitoring index fluctuations in real time, issuing early warnings, and automatically triggering self-healing strategies to reduce the impact of transmission quality anomalies on services.

6. The method according to claim 1, characterized in that, The heterogeneous network resource dynamic scheduling in step S3 is based on the heterogeneous network resource status, service adaptation requirements and transmission quality requirements, to dynamically allocate heterogeneous network resources and achieve efficient integration and collaborative utilization of resources.

7. The method according to claim 1, characterized in that, The heterogeneous network collaboration efficiency calculation in step S3 quantifies the rationality and efficiency of heterogeneous network collaboration through the efficiency calculation formula. If the efficiency value is lower than the threshold, the collaborative scheduling parameters are iteratively optimized to improve the efficiency of heterogeneous network collaboration.

8. The method according to claim 1, characterized in that, The qualified threshold for heterogeneous network collaborative performance Flexible adjustment based on the scenario, industrial heterogeneous communication Urban broadband communication Multi-terminal collaborative communication .

9. The method according to any one of claims 1-8, characterized in that, The method can be applied to communication automation scenarios such as industrial heterogeneous communication, urban broadband communication, multi-terminal collaborative communication, and intelligent transportation communication, to achieve service flow adaptation, transmission quality control, and collaborative management of heterogeneous networks.

10. A communication automation service flow adaptation and transmission quality collaborative management system, characterized in that, include: The system comprises a service flow intelligent identification and classification adaptation module, a transmission quality dynamic monitoring and control module, a heterogeneous communication network collaborative management and control module, a multi-source data acquisition module, and a collaborative management and control engine module. The service flow adaptation module implements the claims 1-2, the transmission quality control module implements the claims 4-5, and the heterogeneous collaborative module implements the claims 6-7. Each module achieves real-time data interaction through a high-speed communication bus, thereby completing the communication automation of service flow adaptation and transmission quality collaborative management and control.

Images