Business data sharing and fusion system and method based on trusted data space

Abstract

The present application provides a business data sharing and fusion system and method based on a trusted data space, which relates to the field of data sharing technology. The method realizes the sharing and fusion of business data by constructing a trusted data space infrastructure. The present invention first establishes a node path planning model for priority evaluation and data matching; then forms a model collaborative deployment plan to assign tasks to edge nodes; then performs perception scoring and resource scheduling on tasks, and generates a multi-task concurrent transmission plan; then constructs a multi-domain network service level agreement evaluation model for service decomposition and business collaborative management; finally, heterogeneous processing and data fusion of business data. The present application solves the problems of information islands between regional institutions, multi-source heterogeneous data fusion and cross-domain business collaboration, and improves system performance and user experience.

Description

Technical Field

[0001] The present application relates to the field of data sharing technology, and in particular to a business data sharing and fusion system and method based on a trusted data space. Background Art

[0002] With the rapid development of the digital economy, data, as a key production factor, needs to be fully exploited to break down information silos and achieve cross-departmental and cross-domain data interoperability and integration. Data sharing and business collaboration between organizations are becoming increasingly important.

[0003] Currently, there are two main technical solutions for data sharing. One is a centralized architecture, which establishes a unified data center to aggregate and manage data from various parties; the other is a point-to-point data exchange channel, where different institutions establish separate data sharing interfaces. While these traditional approaches can achieve basic data sharing functions, their limitations gradually become apparent as the scale and complexity of data increase.

[0004] In recent years, newer solutions have begun to use distributed technologies like consortium blockchains to build data-sharing platforms. These platforms manage data access rights through smart contracts, enabling controlled data sharing. These solutions leverage blockchain technology to ensure data trustworthiness, improving the security and reliability of data sharing.

[0005] However, existing technologies still face the following challenges: a lack of dynamic, adaptive data matching and fusion mechanisms, making it difficult to meet the needs of time-sensitive business scenarios; inefficient edge computing resource utilization, resulting in high deployment costs for large models; inflexible allocation of communication resources in multi-tasking scenarios; and a need to improve the quality of service (QoS) assurance mechanism for cross-domain business collaboration. These issues severely hinder the improvement of business collaboration efficiency. Summary of the Invention

[0006] In view of this, the present application provides a business data sharing and fusion system and method based on a trusted data space, which solves the problem of limited improvement in business collaboration efficiency in the existing technology, realizes a dynamic and adaptive data matching and fusion mechanism, can effectively improve the utilization efficiency of edge computing resources, realize flexible allocation of communication resources in multi-task concurrent scenarios, and realize the improvement of service quality assurance mechanism in cross-domain business collaboration.

[0007] The embodiment of the present application provides a business data sharing and fusion method based on a trusted data space, comprising: obtaining business data of at least one task, wherein the business data includes task requirement data; constructing a trusted data space infrastructure, wherein the trusted data space infrastructure is used to indicate the deployment of node devices, wherein the node devices include a data access gateway and a node security communication component; establishing a node path planning model based on the trusted data space infrastructure and the task requirement data, and performing priority evaluation and data matching on the business data based on the node path planning model to generate a data matching solution; forming a model collaborative deployment solution based on the data matching solution and the business data, wherein the model collaborative deployment solution is used to indicate the allocation of the tasks to each edge node; and According to the model collaborative deployment scheme, each task is perceived and scored, and resources are scheduled for the tasks in combination with the perception scoring results to generate a multi-task concurrent transmission scheme; based on the multi-task concurrent transmission scheme and the business data, a multi-domain network service level agreement evaluation model is constructed, and service decomposition and business collaborative management are performed based on the multi-domain network service level agreement evaluation model to generate a service quality assurance scheme; the business data is heterogeneously processed, and data fusion is performed on the business data based on the heterogeneous processing results to generate a data fusion scheme; under the synergistic effect of the data matching scheme, the model collaborative deployment scheme, the multi-task concurrent transmission scheme, the service quality assurance scheme and the data fusion scheme, the business data is fused and shared.

[0008] The method of establishing a node path planning model based on the trusted data space infrastructure and the task requirement data, and performing priority evaluation and data matching on the business data based on the node path planning model to generate a data matching solution includes: analyzing node status data of a mobile node based on the trusted data space infrastructure and in combination with a preset spatiotemporal graph, wherein the mobile node is used to characterize a node device related to the task, and the node status data includes node position changes and network connection status; performing path search based on the node status data and the business data, constructing a node path planning model that meets preset timeliness requirements, and evaluating the connection reliability between the mobile nodes to obtain a reliability evaluation result; performing priority evaluation on the business data based on the node path planning model and the reliability evaluation result, and determining a computing task weight related to the task priority evaluation result; performing data matching on the business data based on the trusted data space infrastructure and the computing task weight to form a matching solution; combining the node path planning model, the computing task weight, and the matching solution into a data matching solution, and updating the data matching solution based on network status changes, task urgency, and a preset performance indicator system.

[0009] The data matching of the business data based on the trusted data space infrastructure and the computing task weight to form a matching scheme includes: constructing a data source feature vector and a task requirement vector based on the trusted data space infrastructure, wherein the data source feature vector includes the data type, update frequency and quality score, and the task requirement vector includes the data specification, timeliness requirement and accuracy requirement; based on the business data, calculating the similarity between the data source feature vector and the task requirement vector, and based on the similarity, establishing a mapping relationship between the data source of the business data and the task requirement; based on the mapping relationship, forming a matching scheme, and updating the matching scheme according to changes in task priority and network status adjustments.

[0010] The model collaborative deployment scheme is formed based on the data matching scheme and the business data, including: based on the data matching scheme, collecting edge node resource monitoring data through the deployed lightweight resource monitoring agent, the edge node resource monitoring data including CPU utilization, memory usage, GPU computing load and network bandwidth data; based on the edge node resource monitoring data, constructing a multi-dimensional resource portrait including computing power, storage capacity and network performance, and generating edge node performance evaluation results; based on the edge node performance evaluation results, establishing a load prediction model; based on the load prediction model, calculating resource usage trends.

[0011] The method of forming a model collaborative deployment scheme based on the data matching scheme and the business data also includes: dividing the task into multiple computing tasks based on the model layer dependencies indicated by the business data, and forming a model task allocation scheme acting on the node device or between the node devices based on the resource usage trend, and the model task allocation scheme is used to indicate that the computing task is allocated to the edge node; according to the model task allocation scheme, the model parameters of the computing model related to the task are INT8 quantized and compressed, and frequently co-occurring token sequence fusion is performed to construct an optimized model component; based on the optimized model component, the computing model is distributedly deployed to each node device and / or edge node using a preset edge node load balancing strategy to generate a model collaborative deployment scheme.

[0012] According to the model collaborative deployment scheme, each task is perceived and scored, and resources are scheduled for the task in combination with the perception scoring results to generate a multi-task concurrent transmission scheme, including: based on the model collaborative deployment scheme, extracting the task type, data scale and time attribute characteristics of the task from the business data to construct task characteristics; based on the task characteristics, performing task understanding on the business data to obtain business context analysis results; based on the business context analysis results, evaluating the business value and execution priority of the task to form an importance evaluation result of the task; based on the importance evaluation result and preset task performance, calculating the task score of the task, and outputting a multi-task priority sorting result based on the task score, wherein the task performance includes data timeliness, business relevance and resource consumption.

[0013] The collaborative deployment scheme of the model is used to perform a perception score on each task, and resources are scheduled for the tasks based on the perception score results to generate a multi-task concurrent transmission scheme, including: based on the multi-task priority sorting results, collecting channel status data through distributed detection nodes deployed on the edge nodes, the channel status data including bandwidth utilization, link delay and packet loss rate data; based on the channel status data, using a preset timing analysis model to predict the channel quality change trend, and constructing a channel availability evaluation index, and determining a channel resource allocation strategy based on the channel quality change trend and the channel availability evaluation index; and determining a multi-task concurrent transmission scheme for the task based on the channel resource allocation strategy and the multi-task priority sorting results.

[0014] The method of constructing a multi-domain network service level agreement evaluation model based on the multi-task concurrent transmission scheme and the business data, performing service decomposition and business collaborative management based on the multi-domain network service level agreement evaluation model, and generating a service quality assurance plan includes: establishing a service quality indicator system based on the multi-task concurrent transmission scheme, wherein the service quality indicator system includes latency, availability, and throughput; evaluating risk data of service risk events related to the tasks based on the service quality indicator system, performing hierarchical early warning analysis based on the risk data, and forming a risk assessment plan, wherein the risk data includes probability of occurrence and scope of impact; and generating a multi-domain network service level agreement evaluation model based on the risk assessment plan and in combination with the service quality requirements of a specified business scenario.

[0015] The method further comprises: constructing a multi-domain network service level agreement evaluation model based on the multi-task concurrent transmission scheme and the business data, and performing service decomposition and business collaborative management based on the multi-domain network service level agreement evaluation model to generate a service quality assurance scheme, and further comprises: constructing a business process dependency graph of the task based on the multi-domain network service level agreement evaluation model, and constructing an output service topology structure based on the business process dependency graph, wherein the service topology structure is used to indicate the calling relationship and resource dependency between each service component in the task; determining a search strategy based on the service topology structure, wherein the search strategy is used to indicate iteratively optimizing the service decomposition scheme, and evaluating the scheme indicators of the service decomposition scheme, and outputting a service decomposition result when the scheme indicators reach a preset convergence condition, wherein the scheme indicators include the feasibility and optimization space of the service decomposition scheme, and the service decomposition scheme is used to indicate adjustment of the service component configuration; and performing cross-domain collaborative management based on the service decomposition result. Generate a service quality assurance plan; then perform heterogeneous processing on the business data, and perform data fusion on the business data based on the heterogeneous processing results to generate a data fusion plan, including: using a preset semantic knowledge graph to extract the semantic features of different data sources indicated by the business data; using preset quality assessment indicators to perform data quality assessment on the business data, and clean the business data based on the data quality assessment results to obtain cleaned business data, wherein the quality assessment indicators include the integrity, accuracy, consistency and timeliness of the business data; based on the semantic features, establish a data feature model, and use the data feature model to analyze the data feature portrait, wherein the data feature portrait includes the structural features of the data source and the data distribution law; based on the data feature portrait and the cleaned business data, generate a data fusion plan, wherein the data fusion plan is used to indicate the fusion of multi-source heterogeneous data in the business data.

[0016] The embodiment of the present application also provides a business data sharing and fusion system based on a trusted data space, comprising: an acquisition module for acquiring business data of at least one task, wherein the business data includes task requirement data; a construction module for constructing a trusted data space infrastructure, wherein the trusted data space infrastructure is used to indicate the deployment of node devices, wherein the node devices include a data access gateway and a node security communication component; a data matching module for establishing a node path planning model based on the trusted data space infrastructure and the task requirement data, and performing priority evaluation and data matching on the business data based on the node path planning model to generate a data matching solution; a deployment module for forming a model collaborative deployment solution based on the data matching solution and the business data, wherein the model collaborative deployment solution is used to indicate the allocation of the task to each edge node; a perception evaluation module for generating a data matching solution based on the trusted data space infrastructure and the task requirement data; a data matching ... The sub-module is used to perform perception scoring on each task according to the model collaborative deployment scheme, and perform resource scheduling on the task in combination with the perception scoring results to generate a multi-task concurrent transmission scheme; the collaborative management module is used to construct a multi-domain network service level agreement evaluation model according to the multi-task concurrent transmission scheme and the business data, and perform service decomposition and business collaborative management based on the multi-domain network service level agreement evaluation model to generate a service quality assurance scheme; the data fusion module is used to perform heterogeneous processing on the business data, and perform data fusion on the business data based on the heterogeneous processing results to generate a data fusion scheme; the sharing module is used to fuse and share the business data under the synergistic effect of the data matching scheme, the model collaborative deployment scheme, the multi-task concurrent transmission scheme, the service quality assurance scheme and the data fusion scheme.

[0017] An embodiment of the present application also provides a computer device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above-mentioned business data sharing and fusion method based on trusted data space.

[0018] An embodiment of the present application also provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the above-mentioned business data sharing and integration method based on the trusted data space.

[0019] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the above-mentioned business data sharing and fusion method based on trusted data space.

[0020] This application has the following technical effects:

[0021] By building a trusted data space infrastructure, data interconnection and interoperability between multiple regional institutions is achieved, effectively solving the problem of information islands between regional institutions; based on the priority evaluation and data matching mechanism of the node path planning model, dynamic and adaptive data matching is achieved to meet the needs of business scenarios with high timeliness requirements; the edge LLM collaboration framework is adopted to improve the efficiency of edge computing resource utilization and reduce the cost of large model deployment through model segmentation, collaborative deployment and compression optimization; the multi-task communication mechanism realizes flexible communication resource allocation and improves system performance in multi-task concurrent scenarios; the risk-aware SLA decomposition and business management mechanism improves the service quality assurance system for cross-domain business collaboration and ensures the stable operation of the business. Therefore, this application solves the problem of limited improvement in business collaboration efficiency in the existing technology, realizes a dynamic and adaptive data matching and fusion mechanism, can effectively improve the efficiency of edge computing resource utilization, realize flexible allocation of communication resources in multi-task concurrent scenarios, and realize the improvement of service quality assurance mechanism in cross-domain business collaboration. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0023] Figure 1 This is a flow chart of a business data sharing and integration method based on a trusted data space in an embodiment of the present application;

[0024] Figure 2 This is a flow chart of the node path planning model establishment and data matching method in the embodiment of the present application;

[0025] Figure 3 This is a flow chart of a method for forming a model collaborative deployment solution in an embodiment of the present application;

[0026] Figure 4 This is a flow chart of the task perception scoring and resource scheduling method in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0028] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0029] The term "and / or" herein simply describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. In addition, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0030] like Figure 1 As shown, the embodiment of the present application provides a business data sharing and fusion method based on a trusted data space, including steps S1 to S8, namely, obtaining business data, building a trusted data space infrastructure, establishing a node path planning model, forming a model collaborative deployment plan, performing task perception scoring and resource scheduling, building a service level agreement evaluation model, performing heterogeneous data processing and fusion, and realizing integrated sharing of business data. These steps are described in detail below.

[0031] S1: Acquire business data of at least one task, where the business data includes task requirement data.

[0032] It should be noted that this business data may come from business systems across different departments and domains, and includes various types of information, including task requirements, business process data, and resource status data. By acquiring this business data, we can understand the specific content and priority of business requirements, providing a foundation for subsequent data processing and task allocation.

[0033] In this step S1, various business data related to the task are collected through multiple channels. These data come from different business systems and departments and may have various formats and structures. This application requires preliminary processing of these data to ensure the integrity and availability of the data. Obtaining business data is the starting point of the entire method and provides basic material for subsequent data processing and analysis. By comprehensively and accurately acquiring business data, we can have a clearer understanding of task requirements and lay a solid foundation for subsequent data sharing and integration work.

[0034] S2: Build a trusted data space infrastructure, where the trusted data space infrastructure is used to instruct the deployment of node devices, including a data access gateway and a node security communication component.

[0035] In this application, the trusted data space provides a safe and reliable environment for data sharing among different departments and fields. During the construction process, this application needs to deploy data access gateways and node security communication components, establish unified data standards and exchange specifications, and realize trusted access and management of data resources. The trusted data space avoids the single point failure risk of the traditional centralized model through distributed architecture design, and improves the reliability and scalability of the system. At the same time, by establishing unified data classification and grading standards, metadata specifications and data quality standards, the standardization and consistency of data in the circulation process are ensured. The deployment of data security management and control components ensures the security of data during the sharing process and prevents the leakage and abuse of sensitive data.

[0036] A trusted data space refers to a data circulation and utilization infrastructure that connects multiple parties based on consensus rules to achieve data resource sharing and utilization. It is an application ecosystem for the co-creation of data element value, and is also an important carrier for supporting the construction of a national integrated data market. The trusted data space has three core capabilities: data trust management and control, resource interaction, and value co-creation. Among them, data trust management and control capabilities ensure the security and compliance of data during circulation and use; resource interaction capabilities support data exchange and service calls between multiple parties; and value co-creation capabilities promote the deep integration of data resources and value mining. Through the organic combination of these three core capabilities, the trusted data space provides a reliable basic support for cross-departmental and cross-domain data sharing and business collaboration. It should be noted that in this application, the three terms trusted data space, data space, and space have the same meaning and all refer to the data circulation and utilization infrastructure defined above.

[0037] Furthermore, the trusted data space infrastructure includes components such as a unified data standards system, a distributed node network, data resource catalog management, and data security management. Specifically, the unified data standards system includes data classification and grading standards, metadata specifications, and data quality standards. The distributed node network utilizes data access gateways to enable secure inter-node communication. The data resource catalog management establishes a unified resource registration, discovery, and access mechanism. The data security management component implements data desensitization, access control, and audit traceability. Through the collaborative work of these components, the trusted data space infrastructure provides a secure and reliable environment for business data sharing and integration.

[0038] S3: Based on the trusted data space infrastructure and the task requirement data, a node path planning model is established, and priority evaluation and data matching are performed on the business data based on the node path planning model to generate a data matching solution.

[0039] In this step, a node path planning model is established and data matching is performed. That is, the node status data is analyzed in combination with the spatiotemporal graph to construct a path planning model that meets the timeliness requirements, and the business data is prioritized and matched. The node path planning model takes into account the mobility and network connection status of the node, and can provide reliable path selection for data transmission. The priority evaluation mechanism assigns reasonable priorities to different business data based on factors such as the urgency and importance of the task, ensuring that key businesses are given priority. The data matching process analyzes the characteristics of the data source and the task requirements, establishes a mapping relationship between them, and achieves accurate matching of data and tasks. This dynamic and adaptive data matching mechanism can effectively cope with complex and changing business environments and meet the needs of high-timeliness business scenarios.

[0040] In some embodiments, as Figure 2 As shown, step S3 includes the following sub-steps S3.1 to S3.5.

[0041] S3.1: Based on the trusted data space infrastructure, combined with the preset spatiotemporal graph, the node status data of the mobile node is analyzed. The mobile node is used to characterize the node device related to the task. The node status data includes node position changes and network connection status.

[0042] In this step, we first identify the mobile node devices related to the task. These devices may be mobile terminals, edge servers, or other dynamic nodes connected to the network. Then, we analyze the status data of these nodes using spatiotemporal graph technology, including changes in node location and network connection status. It should be noted that a spatiotemporal graph is a data model that describes the changing patterns of nodes in time and space. It can capture the movement trajectory of nodes and the dynamic characteristics of network connections. By analyzing this status data, we can predict the future location and connection status of the nodes, providing an important basis for path planning. Especially in scenarios where nodes move frequently, this spatiotemporal graph-based analysis method can effectively improve the accuracy and reliability of path planning.

[0043] S3.2: Perform path search based on the node status data and the service data, construct a node path planning model that meets the preset timeliness requirements, and evaluate the connection reliability between the mobile nodes to obtain a reliability evaluation result.

[0044] In this step, an improved A algorithm can be used for path search, which takes into account node mobility and task time constraints. It should be noted that the improved A algorithm introduces a time window constraint on the basis of the traditional A* algorithm to ensure that the planning results meet the timeliness requirements of task execution. For example, for a data acquisition task that needs to be completed within 15 minutes, priority is given to node paths with stable connections within this time window. Then, through path search, a node path planning model is constructed, which describes the optimal path and time schedule for data transmission. At the same time, the connection reliability between mobile nodes is evaluated, and a reliability evaluation result is generated, which provides an important reference for subsequent task priority evaluation. This path planning method that takes into account node mobility and network reliability can effectively cope with the challenges of data transmission in a dynamic network environment.

[0045] In addition, the application of the improved A algorithm in node path planning is mainly reflected in its consideration of time factors. The traditional A algorithm mainly focuses on the shortest path of spatial distance, while this embodiment introduces a time window constraint so that path planning can meet specific timeliness requirements. For example, take a specific scenario as an example: suppose in an inter-departmental collaborative case handling system, the relevant departments need to obtain on-site investigation data of a case within 15 minutes, and these data are distributed on multiple mobile law enforcement terminals. The system needs to plan a path from the data request initiation point to each mobile terminal, and then to the data integration point to ensure that all data collection is completed within 15 minutes.

[0046] Specifically, the improved A algorithm is used for path search. First, a spatiotemporal graph is constructed, where nodes represent different mobile terminals and edges represent connections between nodes. Each edge has two weights: transmission time and connection reliability. During the search process, the algorithm considers not only the spatial distance of the path (the focus of traditional A), but also the reachability and connection stability of each node within a specific time window.

[0047] In terms of specific operations, a time dimension attribute is added to each node to record the estimated time to reach the node. During the search process, the algorithm will check whether the target node can be reached within the time window (here is 15 minutes). If the estimated arrival time exceeds the time window, the path will be pruned and no further exploration will be carried out. In addition, nodes with stable connections within the estimated time window will be given priority. For example, if there are two paths that can be completed within 15 minutes, but the nodes on one path are more stably connected during this time period (perhaps because these law enforcement officers work in a fixed location rather than on the move), the more stable path will be given priority.

[0048] In actual operation, when the relevant department initiates a data request, path planning is immediately executed. Assuming that there are five mobile terminals holding relevant data, an optimal path is calculated, indicating that data should be obtained from node A (which may be the nearest terminal with the most stable connection) first, followed by nodes B, C, D, and E, and finally all the data is integrated and sent to the relevant department. The entire process is planned to be completed within 14 minutes, meeting the 15-minute timeliness requirement. If during the execution process, it is found that a node (such as node C) suddenly moves to a weak signal area and the connection becomes unstable, the path is replanned in real time, which may be adjusted to the order of A→B→E→D→C. Or, if the connection of C is too unstable and it is not critical data, C may even be temporarily skipped to complete the collection of other data first. Therefore, this embodiment can effectively address the path planning challenges in dynamic network environments and ensure that data transmission meets the timeliness requirements, which is of great significance for time-sensitive tasks.

[0049] S3.3: Based on the node path planning model and the reliability evaluation result, the business data is prioritized and a computing task weight related to the task priority evaluation result is determined.

[0050] In this step, a distributed computing architecture is employed, with evaluation agents deployed locally on each node to perform multi-dimensional priority assessments on business data. This assessment process considers various factors, including task urgency (e.g., emergency response takes the highest priority), data timeliness requirements (e.g., real-time data stream processing), and business criticality (e.g., core business processes). Task weights are then dynamically calculated using a weighted scoring model, and priority information is synchronized across the distributed network through a consensus mechanism. The assessment results are output as standardized scores, representing the weight of the computational tasks associated with the business data. This distributed task priority assessment mechanism allows for rapid response to local needs while taking into account the global situation, improving the overall efficiency and responsiveness of the system.

[0051] S3.4: Based on the trusted data space infrastructure and the computing task weights, perform data matching on the business data to form a matching solution.

[0052] In this step, we first construct a data source feature vector and a task requirement vector. The data source feature vector includes dimensions such as data type, update frequency, and quality score, describing the basic characteristics and quality status of the data source. The task requirement vector includes dimensions such as data specifications, timeliness requirements, and accuracy requirements, describing the specific data requirements of the task. Next, we calculate the similarity between these two types of vectors, and quantify the degree of match between the data source and the task requirements using cosine similarity or other similarity calculation methods. Then, based on the similarity calculation results, we establish a mapping relationship between the data source of the business data and the task requirements, forming an initial matching solution. This data matching method based on vector similarity can evaluate the compatibility of the data source and task requirements from multiple dimensions, improving the accuracy and effectiveness of the matching.

[0053] In an optional embodiment, in step S3.4, the specific implementation of data matching includes:

[0054] Based on the trusted data space infrastructure, construct a data source feature vector and a task requirement vector, wherein the data source feature vector includes data type, update frequency and quality score, and the task requirement vector includes data specifications, timeliness requirements and accuracy requirements;

[0055] Based on the business data, calculating the similarity between the data source feature vector and the task requirement vector, and establishing a mapping relationship between the data source of the business data and the task requirement based on the similarity;

[0056] Based on the mapping relationship, a matching solution is formed, and the matching solution is updated according to the change of task priority and the adjustment of network status.

[0057] Specifically, implementing data matching first involves constructing a data source feature vector and a task requirement vector. The data source feature vector is a multi-dimensional description of the data source's characteristics, including key attributes such as data type, update frequency, and quality score. For example, for a real-time video stream data source, its feature vector might include attributes such as data type "video stream", update frequency "30 frames per second", and quality score "high definition". The task requirement vector describes the task's specific data requirements, including dimensions such as data specifications, timeliness requirements, and accuracy requirements. For example, for a video analysis task, its requirement vector might include attributes such as data specifications "H.264 encoded video", timeliness requirements "real-time processing", and accuracy requirements "high-definition resolution".

[0058] After constructing these two types of vectors, a similarity calculation method is used to evaluate the degree of match between them. Commonly used similarity calculation methods include cosine similarity, Euclidean distance, and weighted similarity. For example, taking cosine similarity as an example, the two vectors are normalized and the cosine value of the angle between them is calculated. The closer the cosine value is to 1, the more similar the two vectors are, that is, the higher the match between the data source and the task requirements. For example, if the similarity calculated for a high-definition video stream data source and an AI analysis task that requires high-definition video input is 0.95, and the similarity with a simple monitoring task that only requires low-resolution data is 0.6, the system will give priority to matching this data source to the AI ​​analysis task.

[0059] Based on the similarity calculation results, a mapping relationship is established between the data source and the task requirements. This process uses a bilateral matching algorithm to consider the global optimal match between multiple data sources and multiple task requirements. Specifically, an initial match is established based on the level of similarity. Then, the matching relationship is adjusted through iterative optimization until a stable state is achieved. In actual operation, a similarity threshold may be set, and a match relationship is only established when the similarity exceeds a certain threshold to ensure matching quality.

[0060] After forming an initial matching plan, it can be dynamically updated based on changes in task priority and network status. When task priorities change, such as when an urgent task is added or the priority of an existing task is increased, the system reevaluates resource allocation, potentially disrupting existing matching relationships and reallocating high-quality data sources to high-priority tasks. When network conditions change, such as when bandwidth decreases or latency increases on certain transmission paths, data source selection is adjusted accordingly, prioritizing those on paths with better transmission conditions. This dynamic adjustment mechanism ensures that the system can adapt to environmental changes and maintain high matching efficiency.

[0061] S3.5: The node path planning model, the computing task weight and the matching scheme are combined into a data matching scheme, and the data matching scheme is updated according to changes in network status, task urgency and a preset performance indicator system.

[0062] In this step, the node path planning model generated in the previous steps, the calculation task weights, and the mapping relationship between the data source and the task requirements are first integrated into a complete data matching solution. In this embodiment, it describes which data sources should be matched with which task requirements, through which paths the data is transmitted, and the priority and resource allocation of each task. Then, the network status changes, task urgency changes, and performance indicator changes are monitored, and the data matching solution is dynamically updated based on these changes. For example, when the network connection status changes, the path planning can be recalculated; when a new high-priority task is inserted, the resource allocation and priority sorting are adjusted; when a certain performance indicator decreases, the relevant matching strategy is optimized. This feedback optimization mechanism enables the data matching solution to adapt to the dynamic changes of the environment and maintain the best matching effect.

[0063] S4: forming a model collaborative deployment plan based on the data matching plan and the business data, wherein the model collaborative deployment plan is used to instruct the distribution of the tasks to each edge node.

[0064] In this step, resource monitoring data from edge nodes is first collected, resource profiles are constructed, and resource usage trends are predicted. Then, based on the dependencies between model layers and resource usage trends, the task is divided into multiple computing tasks to form a model task allocation plan. To improve the computing efficiency of edge nodes, model parameters are quantized, compressed, and optimized to reduce computational complexity and storage requirements. Finally, a load balancing strategy is implemented to distribute the optimized model components across various node devices and edge nodes, forming a complete model collaborative deployment solution. This edge LLM collaborative framework fully utilizes distributed computing resources, improves the efficiency of edge computing, reduces the cost of deploying large models, and enables complex computing models to run efficiently in resource-constrained edge environments.

[0065] In some embodiments, as Figure 3 As shown, step S4 includes the following sub-steps S4.1 to S4.7.

[0066] S4.1: Based on the data matching solution, edge node resource monitoring data is collected through the deployed lightweight resource monitoring agent, where the edge node resource monitoring data includes CPU utilization, memory usage, GPU computing load, and network bandwidth data.

[0067] In step S4.1, lightweight resource monitoring agents are low-overhead software components deployed on edge nodes to collect resource usage information. These agents utilize a distributed architecture, enabling real-time collection of edge node resource status with minimal system load. Specific monitoring data includes CPU utilization (core utilization percentage, thread load distribution), memory usage (physical memory usage, virtual memory allocation, and memory fragmentation), GPU compute load (computing core utilization, video memory usage, and compute queue length), and network bandwidth data (uplink and downlink traffic, link congestion, and packet loss rate). These agents transmit collected data back through asynchronous communication, minimizing the impact of the monitoring process on business execution.

[0068] S4.2: Based on the edge node resource monitoring data, construct a multi-dimensional resource portrait including computing power, storage capacity and network performance, and generate an edge node performance evaluation result.

[0069] In step S4.2, a multidimensional resource profile is constructed based on resource monitoring data. This profile is a multidimensional vector that accurately describes the edge node's computing power (such as floating-point performance, parallel processing capabilities, and instruction set support), storage capacity (including storage space size, read / write speed, and I / O concurrency), and network performance (such as link stability, communication latency, and bandwidth fluctuation range). Standardization is used to normalize the indicators of different dimensions, and a weighted scoring mechanism is introduced to assign different weights to different resource dimensions based on task characteristics, thereby generating a comprehensive edge node performance evaluation. This multidimensional resource profile enables the system to fully understand the resource status of edge nodes, providing a precise basis for subsequent task allocation.

[0070] S4.3: Establish a load prediction model based on the edge node performance evaluation results.

[0071] In step S4.3, a load prediction model is established based on the edge node performance evaluation results. This model uses a combination of time series analysis and machine learning to integrate historical load data and current state information to predict changes in resource load at each node over a period of time. Specifically, a long short-term memory network (LSTM) is used to process historical load sequences to capture cyclical and trending load changes. At the same time, regression analysis methods are combined to consider currently known task scheduling and resource allocation to improve prediction accuracy. The model also considers mechanisms for handling emergencies and abnormal loads, and can dynamically adjust prediction results when load anomalies are detected, maintaining the model's adaptability and robustness.

[0072] S4.4: Calculate resource usage trends based on the load prediction model.

[0073] In step S4.4, resource usage trends within future time windows are calculated based on the established load forecasting model. This calculation process includes trend analysis at multiple time scales, covering short-term (minute-level), medium-term (hour-level), and long-term (day-level) resource usage forecasts. A sliding window method is used to continuously update the forecast results to ensure real-time trend calculations. The results include not only predicted values ​​for resource utilization of various types, but also resource saturation assessment, bottleneck resource identification, and resource elasticity analysis. This trend data provides a valuable reference for subsequent task allocation, enabling the early planning of resource allocation strategies to avoid resource contention and overload.

[0074] S4.5: Based on the dependencies between the model layers indicated by the business data, the task is divided into multiple computing tasks, and based on the resource usage trend, a model task allocation scheme is formed that acts within the node device or between the node devices. The model task allocation scheme is used to indicate the allocation of the computing task to the edge node.

[0075] In step S4.5, the dependencies between model layers in the business data are analyzed, and complex tasks are decomposed into multiple computing subtasks with clear dependencies. This process uses a directed acyclic graph (DAG) to represent task dependencies, identifying task groups that can be executed in parallel and task chains that must be processed serially. Combined with the resource usage trends calculated previously, the system constructs a mixed integer programming model to solve the optimal task allocation solution. This solution not only takes into account the multi-core parallel processing capabilities within the node, but also makes full use of the collaborative computing potential between nodes to form a distributed execution strategy across nodes. At the same time, a comprehensive balance is made between the real-time requirements of the task, data transmission overhead, and computational complexity to ensure the practicality and efficiency of the allocation solution.

[0076] S4.6: According to the model task allocation scheme, the model parameters of the computing model related to the task are INT8 quantized and compressed, and frequent co-occurring token sequence fusion is performed to construct an optimized model component.

[0077] In step S4.6, optimizing the computational model is a key step in improving edge computing efficiency. First, the model parameters are quantized and compressed using INT8, converting the original floating-point parameters to 8-bit integer representations. This significantly reduces parameter storage space (typically by 75%) and computational complexity, while maintaining model accuracy through calibration techniques. Furthermore, frequent co-occurrence token sequence fusion is performed to identify frequently occurring token sequence patterns in the model and combine them into a single operation unit, reducing computational redundancy. This optimization not only reduces the model's storage and computational requirements but also improves its execution efficiency in resource-constrained environments, facilitating model deployment on edge devices.

[0078] S4.7: Based on the optimized model components, the computing model is distributedly deployed to each node device and / or edge node using a preset edge node load balancing strategy to generate a model collaborative deployment plan.

[0079] In step S4.7, the computing model is distributed and deployed to each node device and edge node based on the optimized model components and the preset load balancing strategy. This load balancing strategy comprehensively considers static load balancing (based on node hardware configuration and network topology) and dynamic load adjustment (based on real-time resource status and task execution). A layered deployment architecture is adopted to allocate components at different levels of the model to appropriate computing nodes, and establish secure communication channels between components. In addition, a real-time monitoring and exception handling mechanism for task execution is implemented, which can trigger emergency processing processes when performance bottlenecks or node failures are detected, ensuring the reliable execution of the model collaborative deployment solution. This distributed deployment method fully utilizes edge computing resources and realizes the efficient operation of complex models in resource-constrained environments.

[0080] S5: Perform a perception score on each task according to the model collaborative deployment plan, and perform resource scheduling on the task based on the perception score results to generate a multi-task concurrent transmission plan.

[0081] In this step, task features are first extracted from service data to understand the tasks and assess their business value. Task scores are calculated and prioritized. Next, channel status data is collected to predict channel quality trends and determine the channel resource allocation strategy. Finally, a multi-task concurrent transmission plan is generated based on the resource allocation strategy and task priorities. This LLM-based multi-task perception and scoring mechanism, combined with channel adaptation technology, enables flexible allocation of communication resources, ensuring the communication needs of critical services in multi-task concurrent scenarios and improving overall performance. Especially in situations where network resources are limited or fluctuating, resource allocation strategies can be dynamically adjusted to ensure the execution quality of important tasks.

[0082] In some embodiments, as Figure 4 As shown, S5 includes the following sub-steps S5.1 to S5.7.

[0083] S5.1: Based on the model collaborative deployment solution, extract the task type, data scale and time attribute characteristics of the task from the business data to construct task features.

[0084] Specifically, feature extraction algorithms are used to identify and extract task types (such as real-time monitoring, batch analysis, and interactive query), data scale (such as data volume, processing complexity, and data distribution characteristics), and temporal attributes (such as deadlines, execution cycles, and response time requirements) from structured and unstructured business data. During the extraction process, multimodal feature fusion techniques are employed to integrate diverse information, including text descriptions, structured parameters, and historical execution records, into a unified feature representation. This representation takes the form of a vector, with each dimension corresponding to a key characteristic of the task. This creates a comprehensive task feature profile, laying the foundation for subsequent task understanding and evaluation.

[0085] S5.2: Based on the task characteristics, perform task understanding on the business data to obtain business context analysis results.

[0086] In this step, semantic analysis technology, combined with pre-trained domain knowledge models, is used to understand the role and significance of the task within the business process. Through a comprehensive analysis of the task description, relevant business rules, and historical execution, the task's business objectives, prerequisite dependencies, and subsequent impact are identified. Based on this foundation, a business context map is constructed, depicting the relationships between the task and other business activities, including direct dependencies and indirect impacts. This deep understanding of tasks enables the system to assess the importance of tasks from a holistic business perspective, rather than simply focusing on technical parameters, resulting in a more comprehensive and accurate business context analysis.

[0087] S5.3: Based on the business context analysis result, the business value and execution priority of the task are evaluated to form an importance evaluation result of the task.

[0088] In this step, based on the results of the business context analysis, a multi-dimensional assessment of the task's business value and execution priority is conducted. Business value assessment involves both quantitative and qualitative aspects. The quantitative assessment includes quantifying the task's direct economic benefits, risk mitigation value, and compliance assurance value; the qualitative assessment considers the task's impact on business continuity, user experience, and organizational reputation. The execution priority assessment comprehensively considers the task's urgency (e.g., whether it has strict time constraints), importance (e.g., whether it relates to core business), and relevance (e.g., the scope of its impact on other tasks). Using the Analytic Hierarchy Process (AHP) and fuzzy comprehensive evaluation methods, these factors are integrated into a comprehensive score to form a task importance assessment. This assessment not only reflects the absolute importance of the task but also considers its relative value within the overall business ecosystem, providing a scientific basis for subsequent resource allocation.

[0089] S5.4: Based on the importance assessment result and the preset task performance, calculate the task score of the task, and output the multi-task priority sorting result according to the task score, wherein the task performance includes data timeliness, business relevance and resource consumption.

[0090] In this step, the comprehensive score of the task is calculated based on the importance assessment results and combined with the preset task performance indicators. Task performance indicators mainly include three aspects: data timeliness (real-time requirements and validity period of data), business relevance (closeness to core business processes), and resource consumption (computing, storage, and network resources required to complete the task). A weighted summation model is used to assign different weights to these indicators according to the characteristics of different business scenarios to calculate the comprehensive score of the task. In the case of multiple concurrent tasks, based on these scoring results, an improved priority queue algorithm is used to generate the multi-task priority sorting results. This sorting takes into account the dependencies and resource competition between tasks, ensuring that high-priority tasks can obtain sufficient resources while avoiding long-term starvation of low-priority tasks, thereby achieving fairness and efficiency in task scheduling.

[0091] S5.5: Based on the multi-task priority sorting result, channel status data is collected through the distributed detection nodes deployed at the edge nodes, where the channel status data includes bandwidth utilization, link delay and packet loss rate data.

[0092] In this step, channel status data is collected through a distributed network of probe nodes based on the results of multi-task prioritization. These probe nodes are strategically deployed at key locations across the network, forming a network-wide monitoring network that collects real-time status information on each communication channel. Specific data collected includes bandwidth utilization (the ratio of the channel's current transmission volume to its maximum capacity), link latency (the time it takes for a packet to travel from source to destination), and packet loss rate (the proportion of packets lost during transmission). The collection process utilizes a combination of low-overhead active probing and passive monitoring to ensure that the monitoring itself does not significantly impact network performance. These probe nodes utilize a hierarchical reporting mechanism, transmitting the collected raw data to a central analysis system after preliminary processing, providing comprehensive and accurate baseline data for subsequent channel quality predictions.

[0093] S5.6: Based on the channel status data, a preset time series analysis model is used to predict the channel quality change trend, and a channel availability evaluation index is constructed. Based on the channel quality change trend and the channel availability evaluation index, a channel resource allocation strategy is determined.

[0094] In step S5.6, a pre-set time series analysis model is used to predict channel quality trends based on the collected channel status data. This model combines the Autoregressive Integrated Moving Average (ARIMA) method with deep learning techniques to capture the regularity and uncertainty of channel quality changes over time. Prediction results include short-term (seconds to minutes) and medium-term (hourly) trends in bandwidth variation, latency fluctuation, and packet loss rate. Based on these predictions, a comprehensive channel availability evaluation metric system is constructed, including a stability index (which measures the degree of channel quality fluctuation), a reliability score (which measures the channel's ability to meet service quality requirements), and an adaptability index (which measures the channel's ability to cope with traffic bursts). Based on these quality trends and evaluation metrics, a multi-objective optimization algorithm is used to determine a channel resource allocation strategy. This strategy considers both the rigid constraints of meeting high-priority tasks and improving overall network resource utilization efficiency.

[0095] S5.7: Determine a multi-task concurrent transmission scheme for the task based on the channel resource allocation strategy and the multi-task priority sorting result.

[0096] In step S5.7, the multi-task concurrent transmission plan is determined based on the channel resource allocation strategy and the multi-task priority ranking results. This plan is a detailed scheduling plan that assigns specific transmission time windows, channel selection, and resource quotas to each task. When formulating the plan, the system uses a heuristic scheduling algorithm that comprehensively considers task priorities, data dependencies, channel quality predictions, and overall system load. For high-priority tasks, sufficient channel resources are reserved and quality of service guarantees are provided. For average-priority tasks, resource allocation is dynamically adjusted based on current network conditions. For low-priority tasks, an opportunistic scheduling strategy is adopted, allowing transmission to take advantage of network idle periods. Furthermore, the plan includes an emergency response mechanism that can rapidly adjust the transmission strategy upon detecting a sudden deterioration in channel quality, ensuring the normal execution of critical tasks. This multi-layered, adaptive transmission solution effectively improves network resource utilization while ensuring the reliability and timeliness of task execution.

[0097] During the multi-task perception scoring and resource scheduling process, task features are first extracted from business data. Based on these features, task understanding is performed to obtain business context analysis results. Next, the business value and execution priority of the tasks are evaluated to form an importance assessment result. Task scores are calculated based on task performance (such as data timeliness, business relevance, and resource consumption), and a multi-task priority ranking result is output. Based on this, channel status data is collected through distributed detection nodes to predict channel quality trends, construct channel availability evaluation indicators, and determine the channel resource allocation strategy. Finally, based on the channel resource allocation strategy and the multi-task priority ranking results, a multi-task concurrent transmission plan is determined. This design prioritizes the communication needs of important tasks even when resources are limited, improving overall efficiency.

[0098] S6: Construct a multi-domain network service level agreement evaluation model based on the multi-task concurrent transmission scheme and the business data, perform service decomposition and business collaborative management based on the multi-domain network service level agreement evaluation model, and generate a service quality assurance plan.

[0099] In this step, a service quality indicator system is first established, service risks are assessed, a risk assessment plan is developed, and a multi-domain network SLA assessment model is generated. The system then constructs a business process dependency graph and service topology, determines a search strategy, and iteratively optimizes the service decomposition plan. Finally, cross-domain collaborative management is implemented to generate a service quality assurance plan. This risk-aware SLA decomposition and business management mechanism innovatively addresses the issue of service quality assurance in multi-domain networks and improves the service quality assurance system for cross-domain business collaboration. By accurately identifying and quantifying service risks and dynamically optimizing the service decomposition plan, it ensures stable business operations in complex multi-domain network environments, improving service reliability and continuity.

[0100] In some embodiments, step S6 includes the following sub-steps S6.1 to S6.6.

[0101] S6.1: Based on the multi-task concurrent transmission solution, establish a service quality indicator system, where the service quality indicator system includes latency, availability, and throughput.

[0102] In step S6.1, a service quality indicator system is established based on the multi-task concurrent transmission scheme. This serves as the foundation for constructing a multi-domain network service level agreement evaluation model. This indicator system adopts a layered design, comprising base-layer indicators and derived-layer indicators. Base-layer indicators include latency (network transmission delay, processing response time, end-to-end completion time), availability (service continuity guarantee rate, system recovery time objective, and failure recovery point objective), and throughput (service volume processed per unit time, peak processing capacity, and data transmission rate). Derived-layer indicators are derived from these base-layer indicators and include a business resilience index (which measures the system's ability to cope with load fluctuations), a service consistency score (which measures the smoothness of business process execution), and user experience indicators (which assess service quality perception from a user's perspective). This quantifiable, comparable, and traceable indicator system provides a scientific basis for service quality assessment and management, while addressing both technical and business requirements.

[0103] S6.2: Based on the service quality indicator system, evaluate the risk data of the service risk events related to the task, perform a graded warning analysis based on the risk data, and form a risk assessment plan, wherein the risk data includes the probability of occurrence and the scope of impact.

[0104] In step S6.2, a comprehensive assessment of task-related service risk events is conducted based on the service quality indicator system. This risk data assessment utilizes a structured approach, quantitatively analyzing each potential risk event based on two dimensions: probability of occurrence and scope of impact. The probability of occurrence assessment is based on historical data statistics and expert knowledge models, taking into account multiple factors such as the current state, environmental factors, and known threats. The scope of impact assessment analyzes factors such as the scope of business processes that may be affected by the risk event, the size of the user base, and potential economic losses. Based on this, a graded early warning analysis is performed, classifying risk events into different severity levels (e.g., critical, high, medium, and low), with corresponding handling strategies and resource reservation plans developed for each level. This risk-aware analysis approach enables early identification of potential service quality threats and targeted risk prevention and control, resulting in a comprehensive and detailed risk assessment plan.

[0105] S6.3: Generate a multi-domain network service level agreement assessment model based on the risk assessment plan and the service quality requirements of the specified business scenario.

[0106] In step S6.3, based on the risk assessment plan and the service quality requirements of the specified business scenario, a multi-domain network service level agreement assessment model is generated. This model adopts a hierarchical design, including two dimensions: business-layer SLA and technical-layer SLA. The business-layer SLA defines the user's expectations for service quality, such as business processing time limit, service availability window, and business success rate; the technical-layer SLA breaks down these business requirements into specific technical indicators, such as network response time, throughput capacity, and data processing accuracy. By establishing a mapping relationship between business indicators and technical indicators, the model achieves two-way traceability from business requirements to technical implementation. In addition, the model takes into account the particularities of multi-domain network environments, introduces inter-domain collaboration indicators and boundary responsibility definitions, clarifies the service quality responsibilities and coordination mechanisms between different network domains, and ensures the consistency and coherence of service quality for cross-domain services.

[0107] S6.4: Based on the multi-domain network service level agreement evaluation model, construct a business process dependency graph for the task, and construct an output service topology structure based on the business process dependency graph. The service topology structure is used to indicate the calling relationship and resource dependency between each service component in the task.

[0108] In step S6.4, a business process dependency graph for the task is constructed based on the multi-domain network service level agreement assessment model. This dependency graph uses a directed graph structure, with nodes representing business activities or service components and edges representing the dependencies and interactions between them. During the construction process, the system analyzes business process documents, historical execution logs, and service call relationships to identify key business nodes and dependency paths. The dependency graph not only describes explicit call relationships but also considers implicit data and state dependencies, fully reflecting the complex interactions in actual business operations. Based on this dependency graph, a service topology is further constructed. This structure describes the call relationships and resource dependencies between the service components in the task from a technical implementation perspective. The service topology includes detailed information such as the deployment location, interface definitions, communication methods, and resource requirements of the service components, providing a technical foundation for subsequent service decomposition. This mapping from business processes to service topology seamlessly connects the business and technical perspectives, helping to ensure consistency between technical implementation and business requirements.

[0109] S6.5: Based on the service topology structure, determine a search strategy, which is used to indicate the iterative optimization of the service decomposition scheme and evaluate the scheme indicators of the service decomposition scheme. When the scheme indicators reach the preset convergence conditions, output the service decomposition results. The scheme indicators include the feasibility and optimization space of the service decomposition scheme. The service decomposition scheme is used to indicate the adjustment of the service component configuration.

[0110] In step S6.5, a search strategy for service decomposition optimization is determined based on the service topology. This strategy employs an iterative optimization approach, searching for the optimal service decomposition solution through multiple rounds of search. Specifically, an initial set of decomposition solutions is generated based on the service topology. Then, candidate solutions within this set are evaluated and improved in each iteration. The search process utilizes a modified genetic algorithm to continuously optimize the solution space through crossover, mutation, and selection operations. In each evaluation round, solution metrics are calculated, including the solution's feasibility (whether it meets all technical constraints and business requirements) and the optimization space (the solution's resource efficiency and performance improvement potential). When the solution metrics reach the preset convergence criteria, the iteration is terminated and the final service decomposition results are output. During this iterative optimization process, the configuration parameters, deployment locations, and interaction methods of service components are continuously adjusted to find the optimal decomposition solution that both meets business requirements and maximizes resource utilization efficiency.

[0111] S6.6: Based on the service decomposition result, perform cross-domain collaborative management and generate a service quality assurance plan.

[0112] In step S6.6, based on the service decomposition results, cross-domain collaborative management is implemented to generate a final service quality assurance plan. Cross-domain collaborative management is a key step in ensuring consistent service quality in multi-domain network environments. First, an inter-domain service coordination mechanism is established, defining collaboration rules, data exchange standards, and service interoperability protocols between different network domains. Then, based on a pre-defined multi-domain network SLA assessment model, distributed service monitoring is implemented to collect real-time service status within each domain and identify potential service quality issues through collaborative analysis. When service quality anomalies are detected, a pre-defined collaborative process is triggered to coordinate resource scheduling and service adjustments within the relevant domains to ensure end-to-end service quality. The resulting service quality assurance plan includes a service quality maintenance strategy during normal operation, an emergency response mechanism for abnormal situations, and a methodology for continuous service quality optimization, forming a complete service quality lifecycle management system. This risk-aware cross-domain collaborative management mechanism effectively addresses the challenges of service quality assurance in multi-domain network environments and provides reliable guarantees for the stable operation of cross-domain services.

[0113] During the service level agreement assessment and business collaborative management process, a service quality indicator system is first established to assess risk data for service risk events, develop a risk assessment plan, and generate a multi-domain network service level agreement assessment model. Next, a business process dependency graph and service topology are constructed, a search strategy is determined, and the service decomposition plan is iteratively optimized. When the plan's metrics reach convergence, the service decomposition results are output. Finally, based on the service decomposition results, cross-domain collaborative management is implemented to generate a service quality assurance plan. This design enables the system to guarantee the service quality of various services in complex multi-domain network environments, improving system reliability and stability.

[0114] S7: Perform heterogeneous processing on the business data, and perform data fusion on the business data based on the heterogeneous processing results to generate a data fusion solution.

[0115] In this step, the semantic knowledge graph is used to extract semantic features from data sources, perform data quality assessment and cleansing, establish a data feature model, analyze data feature profiles, and ultimately generate a data fusion solution. This fusion and sharing mechanism, tailored to the multi-source, heterogeneous nature of business data, solves the integration challenges of data from different sources and formats, improving the efficiency and value of data utilization. Semantic understanding and mapping ensure semantic consistency across different data sources; data quality assessment and cleansing improve data availability and reliability; and data feature analysis and fusion enable deeper insights and value to be extracted from multi-source data, supporting more complex business needs and decision-making analysis.

[0116] In some embodiments, step S7 includes the following sub-steps S7.1 to S7.4.

[0117] S7.1: Using a preset semantic knowledge graph, extract semantic features of different data sources indicated by the business data.

[0118] In step S7.1, the preset semantic knowledge graph is used to extract the semantic features of different data sources in the business data. The semantic knowledge graph is a multi-level knowledge representation structure, which includes three levels: domain concepts, attribute relationships, and entity instances. During the extraction process, the key entities and concepts in the business data are first identified and mapped to the corresponding nodes of the knowledge graph; then the relationships between the entities are analyzed to identify the implicit semantic connections in the data; finally, the structural features and content features of the data source are extracted to form a complete semantic feature representation. Specifically, deep semantic analysis technology is used, combined with natural language processing and ontology reasoning methods, to extract a unified semantic representation from structured data, semi-structured data, and unstructured data. This semantic feature extraction can not only understand the surface meaning of the data, but also deeply explore the contextual associations and implicit information of the data, providing a semantic level foundation for subsequent data fusion, and ensuring the semantic consistency and compatibility of data from different sources.

[0119] S7.2: Use preset quality assessment indicators to perform data quality assessment on the business data, and clean the business data based on the data quality assessment results to obtain cleansed business data, wherein the quality assessment indicators include the completeness, accuracy, consistency and timeliness of the business data.

[0120] In step S7.2, a comprehensive quality assessment and cleansing of business data is performed using pre-defined quality assessment indicators. This quality assessment indicator system covers four core dimensions of data quality: completeness (missing data records and fields), accuracy (the degree to which data values ​​correspond to reality), consistency (the degree to which data are consistent across systems and time points), and timeliness (data update frequency and expiration date). Using a combination of a rule engine and statistical models, a multi-dimensional quality score is assigned to each data record, generating a detailed quality assessment report. Based on the assessment results, a data cleansing process is implemented, including missing value handling (such as interpolation, deletion, or tagging), outlier detection and correction (based on statistical models and domain rules), redundant data removal (using similarity calculations and entity matching), and format standardization (unifying data formats and unit systems). The cleansing process adopts an incremental design, retaining the original data while generating cleansed versions of the data. All cleansing operations are recorded to ensure traceability and reversibility of data processing. This step significantly improves the quality and reliability of subsequent data fusion, laying a solid foundation for fully realizing the value of the data.

[0121] S7.3: Based on the semantic features, establish a data feature model, and use the data feature model to analyze the data feature portrait, wherein the data feature portrait includes the structural features of the data source and the data distribution pattern.

[0122] In step S7.3, a feature model for multi-source data is established based on the extracted semantic features. This model is represented using a graph structure, with nodes representing data entities or attributes and edges representing semantic relationships or data dependencies between them. During model construction, machine learning methods are used to learn correlations and evolution patterns from historical data. Domain expert knowledge is then incorporated to supplement explicit semantic constraints, resulting in a hybrid feature model that is both data-driven and knowledge-driven. This feature model is used to conduct in-depth analysis of the data sources and generate a data feature profile. This profile encompasses not only the structural characteristics of the data sources (such as data patterns, type distribution, and associations) and data distribution patterns (such as numerical distribution characteristics, temporal trends, and spatial distribution patterns), but also higher-level semantic and quality features. This comprehensive feature analysis enables the system to deeply understand the characteristics and value of each data source, providing a decision-making basis for intelligent data fusion strategy selection and effectively improving the accuracy and efficiency of data fusion.

[0123] S7.4: Generate a data fusion plan based on the data feature portrait and the cleaned business data, wherein the data fusion plan is used to indicate the fusion of multi-source heterogeneous data in the business data.

[0124] In this step, the solution employs a multi-level fusion architecture, comprising entity-level fusion, attribute-level fusion, and relationship-level fusion. Entity-level fusion addresses the identification and mapping of the same entity across different data sources, employing entity resolution techniques to identify and merge different records referring to the same object. Attribute-level fusion addresses conflicts and complementary relationships between entity attributes, employing a truth-finding algorithm to select the most reliable attribute values ​​from multiple sources. Relationship-level fusion integrates complex relationships between entities to construct a unified relationship network. During the fusion process, an appropriate fusion strategy is dynamically selected based on data characteristics and business needs. For example, strict matching rules may be used for data requiring high consistency, while more relaxed association strategies may be employed for exploratory analysis. A fusion quality monitoring mechanism is also established, evaluating fusion results through a series of metrics (such as fusion coverage, conflict resolution rate, and information gain), and continuously optimizing fusion strategies based on feedback. The resulting data fusion solution not only guides the technical implementation of multi-source heterogeneous data fusion but also ensures that the fusion results effectively support business needs, truly maximizing data value.

[0125] During the fusion process of multi-source heterogeneous data, a pre-set semantic knowledge graph is first used to extract semantic features from different data sources to ensure semantic consistency. Next, quality assessment metrics are used to assess and cleanse the business data to improve data usability. Next, a data feature model is established based on the semantic features, analyzing the data feature profile, including the structural characteristics and distribution patterns of the data sources. Finally, based on the data feature profile and the cleansed business data, a data fusion solution is generated to achieve effective fusion of multi-source heterogeneous data. This design enables the system to process data from different sources and formats, improving the quality and efficiency of data fusion.

[0126] S8: Under the synergistic effect of the data matching solution, the model collaborative deployment solution, the multi-task concurrent transmission solution, the service quality assurance solution and the data fusion solution, the business data is fused and shared.

[0127] In this application, this is the ultimate goal of the entire method. Through the organic combination of data matching solutions, model collaborative deployment solutions, multi-task concurrent transmission solutions, service quality assurance solutions and data fusion solutions, efficient sharing and deep integration of business data are achieved. In practical applications, this multi-scheme collaborative mechanism can effectively cope with various complex business scenarios and meet the data sharing needs of different departments and different fields. For example, in cross-departmental collaborative office, it can ensure the real-time transmission and processing of various business data and support the seamless connection of business processes; in data analysis and decision-making, it can integrate multi-source data to provide comprehensive and accurate information support; in emergency response scenarios, it can give priority to the execution of key businesses and improve response speed and efficiency. This all-round business data sharing and integration capability provides strong support for digital transformation and intelligent development.

[0128] Therefore, this application can dynamically adapt to changing network environments and task requirements, ensuring the accuracy and effectiveness of data matching. By constructing data source feature vectors and task requirement vectors, the matching degree between data sources and task requirements can be evaluated from multiple dimensions, improving the accuracy of data matching. At the same time, the matching solution can be dynamically updated based on changes in task priority and adjustments to network status, ensuring the real-time and adaptability of data matching.

[0129] In the model collaborative deployment solution, a lightweight resource monitoring agent first collects resource data from edge nodes, constructing a multi-dimensional resource profile. Based on this profile, a load prediction model is established to calculate resource usage trends. This information provides a basis for subsequent task allocation decisions. Next, tasks are divided into multiple computing tasks based on the dependencies between model layers, and a model task allocation plan is formed. To improve edge node processing efficiency, the computing model is optimized using INT8 quantization compression and token sequence fusion, significantly reducing the model's computational complexity and storage requirements. Finally, a load balancing strategy is used to distribute the optimized model components across nodes, creating a complete model collaborative deployment solution.

[0130] Furthermore, in one embodiment, step S8 integrates all of the preceding solutions to enable the fusion and sharing of business data. Specifically, a data matching solution determines the mapping relationship between data sources and task requirements, a model collaborative deployment solution efficiently deploys computing models, a multi-task concurrent transmission solution ensures data transmission efficiency and quality, a service quality assurance solution ensures the service level of each business, and a data fusion solution enables the fusion of multi-source heterogeneous data. The synergistic effect of these solutions ensures the security, reliability, and efficiency of data sharing while meeting various business requirements.

[0131] For example, in actual application scenarios, the method of the present application can be applied to cross-departmental and cross-domain business data sharing and integration. For example, in the field work of grassroots units, mobile terminals need to collect on-site data in real time and interact with the central system. Through pre-path planning, data can be transmitted reliably even in areas with unstable signals. The task priority evaluation mechanism gives priority to information with high urgency, such as information related to important cases. The adaptive matching algorithm ensures that the multimedia data collected on-site can be quickly associated and matched with the historical data in the archive system. Through resource status perception, processing tasks are reasonably allocated to each computing node. This systematic design not only ensures the efficiency of business handling, but also ensures the security and standardization of information processing.

[0132] The embodiment of the present application further provides a business data sharing and fusion system based on a trusted data space. The business data sharing and fusion system 500 based on a trusted data space includes:

[0133] An acquisition module 501 is configured to acquire business data of at least one task, wherein the business data includes task requirement data;

[0134] A construction module 502 is used to construct a trusted data space infrastructure, wherein the trusted data space infrastructure is used to instruct the deployment of node devices, wherein the node devices include a data access gateway and a node security communication component;

[0135] A data matching module 503 is configured to establish a node path planning model based on the trusted data space infrastructure and the task requirement data, and to perform priority evaluation and data matching on the business data based on the node path planning model to generate a data matching solution;

[0136] A deployment module 504 is configured to form a model collaborative deployment plan based on the data matching plan and the business data, wherein the model collaborative deployment plan is used to instruct the distribution of the task to each edge node;

[0137] A perception scoring module 505 is configured to perform a perception scoring on each task according to the model collaborative deployment scheme, and perform resource scheduling on the task based on the perception scoring results to generate a multi-task concurrent transmission scheme;

[0138] A collaborative management module 506 is configured to construct a multi-domain network service level agreement evaluation model based on the multi-task concurrent transmission scheme and the service data, perform service decomposition and service collaborative management based on the multi-domain network service level agreement evaluation model, and generate a service quality assurance plan;

[0139] The data fusion module 507 is used to perform heterogeneous processing on the business data, and perform data fusion on the business data based on the heterogeneous processing results to generate a data fusion solution;

[0140] The sharing module 508 is used to integrate and share the business data under the coordinated action of the data matching solution, the model collaborative deployment solution, the multi-task concurrent transmission solution, the service quality assurance solution and the data fusion solution.

[0141] The functions of each module correspond one-to-one to the corresponding steps of the above method, and together they realize the sharing and integration of business data. Through the above detailed description, it can be seen that the business data sharing and integration system and method based on the trusted data space provided by this application has obvious technical innovation and practical value, can effectively solve the problems existing in the existing technology, and improve the efficiency and quality of data sharing and business collaboration.

[0142] The present application also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program executes the steps of the method for sharing and integrating business data based on a trusted data space as described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0143] In addition, an embodiment of the present application also provides a computer program product, which stores a computer program. When the computer program is run by a processor, it executes the steps of the method for sharing and integrating business data based on a trusted data space provided in any of the above embodiments of the present disclosure. For details, please refer to the above method embodiments and will not be repeated here.

[0144] The computer program product may be implemented in hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is embodied as a computer storage medium, which may be a volatile or non-volatile computer-readable storage medium. In another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK).

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment and devices can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0146] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0147] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0148] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0149] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-mentioned embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A business data sharing and integration method based on a trusted data space, characterized in that: include: Acquire business data of at least one task, wherein the business data includes task requirement data; Building a trusted data space infrastructure, the trusted data space infrastructure is used to instruct the deployment of node devices, the node devices including a data access gateway and a node security communication component; Based on the trusted data space infrastructure and the task requirement data, a node path planning model is established, and priority evaluation and data matching are performed on the business data based on the node path planning model to generate a data matching solution; forming a model collaborative deployment scheme according to the data matching scheme and the business data, wherein the model collaborative deployment scheme is used to instruct allocation of the tasks to the edge nodes; According to the model collaborative deployment plan, each task is perceived and scored, and resources of the task are scheduled based on the perception score results to generate a multi-task concurrent transmission plan; Constructing a multi-domain network service level agreement evaluation model based on the multi-task concurrent transmission scheme and the business data, and performing service decomposition and business collaborative management based on the multi-domain network service level agreement evaluation model to generate a service quality assurance plan; Performing heterogeneous processing on the business data, and performing data fusion on the business data based on the heterogeneous processing results to generate a data fusion solution; Under the synergistic effect of the data matching scheme, the model collaborative deployment scheme, the multi-task concurrent transmission scheme, the service quality assurance scheme and the data fusion scheme, the business data is fused and shared.

2. The method according to claim 1, characterized in that The step of establishing a node path planning model based on the trusted data space infrastructure and the task requirement data, and performing priority evaluation and data matching on the business data based on the node path planning model to generate a data matching solution includes: Analyzing node status data of a mobile node based on the trusted data space infrastructure and in combination with a preset spatiotemporal graph, wherein the mobile node is used to represent a node device related to the task, and the node status data includes a node position change and a network connection status; Performing a path search based on the node status data and the service data, constructing a node path planning model that meets preset timeliness requirements, and evaluating the connection reliability between the mobile nodes to obtain a reliability evaluation result; Performing a priority evaluation on the service data according to the node path planning model and the reliability evaluation result, and determining a computing task weight related to the task priority evaluation result; Based on the trusted data space infrastructure and the computing task weights, performing data matching on the business data to form a matching solution; The node path planning model, the calculation task weight and the matching scheme are combined into a data matching scheme, and the data matching scheme is updated according to changes in network status, task urgency and a preset performance indicator system.

3. The method according to claim 2, characterized in that The performing data matching on the business data based on the trusted data space infrastructure and the computing task weight to form a matching solution includes: Based on the trusted data space infrastructure, construct a data source feature vector and a task requirement vector, wherein the data source feature vector includes data type, update frequency and quality score, and the task requirement vector includes data specifications, timeliness requirements and accuracy requirements; Based on the business data, calculating the similarity between the data source feature vector and the task requirement vector, and establishing a mapping relationship between the data source of the business data and the task requirement based on the similarity; Based on the mapping relationship, a matching solution is formed, and the matching solution is updated according to the change of task priority and the adjustment of network status.

4. The method according to claim 3, characterized in that The forming of a model collaborative deployment scheme based on the data matching scheme and the business data includes: Based on the data matching scheme, edge node resource monitoring data is collected through the deployed lightweight resource monitoring agent, and the edge node resource monitoring data includes CPU utilization, memory usage, GPU computing load and network bandwidth data; Based on the edge node resource monitoring data, a multi-dimensional resource portrait including computing power, storage capacity, and network performance is constructed to generate an edge node performance evaluation result; Establishing a load prediction model based on the edge node performance evaluation results; Based on the load prediction model, a resource usage trend is calculated.

5. The method according to claim 4, characterized in that The forming of a model collaborative deployment solution based on the data matching solution and the business data further includes: Based on the dependencies between the model layers indicated by the business data, the task is divided into multiple computing tasks, and according to the resource usage trend, a model task allocation scheme is formed that acts within the node device or between the node devices, wherein the model task allocation scheme is used to indicate that the computing task is allocated to the edge node; According to the model task allocation scheme, the model parameters of the computing model related to the task are quantized and compressed using INT8, and frequent co-occurring token sequence fusion is performed to construct an optimized model component; Based on the optimized model components, the computing model is distributedly deployed to each node device and / or edge node using a preset edge node load balancing strategy to generate a model collaborative deployment solution.

6. The method according to claim 5, characterized in that The method of performing a perception score on each task according to the model collaborative deployment scheme, and performing resource scheduling on the task in combination with the perception score result to generate a multi-task concurrent transmission scheme includes: Based on the model collaborative deployment solution, extracting the task type, data scale and time attribute characteristics of the task from the business data to construct task features; Based on the task characteristics, the business data is subjected to task understanding to obtain business context analysis results; Based on the business context analysis result, the business value and execution priority of the task are evaluated to form an importance evaluation result of the task; Based on the importance assessment result and the preset task performance, the task score of the task is calculated, and the multi-task priority sorting result is output according to the task score, wherein the task performance includes data timeliness, business relevance and resource consumption.

7. The method according to claim 6, characterized in that The method of performing a perception score on each task according to the model collaborative deployment scheme, and performing resource scheduling on the task in combination with the perception score result to generate a multi-task concurrent transmission scheme includes: Based on the multi-task priority sorting result, collecting channel status data through distributed detection nodes deployed at the edge nodes, the channel status data including bandwidth utilization, link delay and packet loss rate data; Based on the channel status data, a preset time series analysis model is used to predict the channel quality change trend, and a channel availability evaluation index is constructed, and a channel resource allocation strategy is determined based on the channel quality change trend and the channel availability evaluation index; A multi-task concurrent transmission scheme for the task is determined according to the channel resource allocation strategy and the multi-task priority sorting result.

8. The method according to claim 1, characterized in that The method includes: constructing a multi-domain network service level agreement evaluation model based on the multi-task concurrent transmission scheme and the business data, performing service decomposition and business collaborative management based on the multi-domain network service level agreement evaluation model, and generating a service quality assurance plan, including: Establishing a service quality indicator system based on the multi-task concurrent transmission scheme, wherein the service quality indicator system includes latency, availability, and throughput; Based on the service quality indicator system, assess risk data of service risk events related to the task, perform hierarchical early warning analysis based on the risk data, and form a risk assessment plan, wherein the risk data includes probability of occurrence and scope of impact; Based on the risk assessment scheme and combined with the service quality requirements of the specified business scenario, a multi-domain network service level agreement assessment model is generated.

9. The method according to claim 1, characterized in that The method further comprises: constructing a multi-domain network service level agreement evaluation model according to the multi-task concurrent transmission scheme and the service data, performing service decomposition and service collaborative management based on the multi-domain network service level agreement evaluation model, and generating a service quality assurance scheme. Based on the multi-domain network service level agreement evaluation model, construct a business process dependency graph for the task, and construct an output service topology structure based on the business process dependency graph, wherein the service topology structure is used to indicate the call relationship and resource dependency between each service component in the task; Determining a search strategy based on the service topology, the search strategy is used to instruct iterative optimization of a service decomposition scheme, and evaluating scheme indicators of the service decomposition scheme, and outputting a service decomposition result when the scheme indicators reach a preset convergence condition, the scheme indicators including the feasibility and optimization space of the service decomposition scheme, and the service decomposition scheme is used to instruct adjustment of service component configuration; Based on the service decomposition results, perform cross-domain collaborative management and generate a service quality assurance plan; Then, performing heterogeneous processing on the business data, and performing data fusion on the business data based on the heterogeneous processing results to generate a data fusion solution includes: Using a preset semantic knowledge graph, extracting semantic features of different data sources indicated by the business data; Using preset quality assessment indicators, the business data is evaluated for data quality, and the business data is cleansed based on the data quality assessment results to obtain cleansed business data, wherein the quality assessment indicators include the completeness, accuracy, consistency and timeliness of the business data; Based on the semantic features, a data feature model is established, and the data feature model is used to analyze a data feature profile, wherein the data feature profile includes structural features of the data source and data distribution patterns; Based on the data feature portrait and the cleaned business data, a data fusion plan is generated, wherein the data fusion plan is used to instruct the fusion of multi-source heterogeneous data in the business data.

10. A business data sharing and fusion system based on a trusted data space, characterized in that: include: An acquisition module, configured to acquire business data of at least one task, wherein the business data includes task requirement data; A construction module is used to construct a trusted data space infrastructure, wherein the trusted data space infrastructure is used to instruct the deployment of node devices, wherein the node devices include a data access gateway and a node security communication component; A data matching module is used to establish a node path planning model based on the trusted data space infrastructure and the task requirement data, and to perform priority evaluation and data matching on the business data based on the node path planning model to generate a data matching solution; A deployment module, configured to form a model collaborative deployment plan based on the data matching plan and the business data, wherein the model collaborative deployment plan is used to instruct the distribution of the tasks to the edge nodes; A perception scoring module is used to perform perception scoring on each task according to the model collaborative deployment plan, and to schedule resources for the task based on the perception scoring results to generate a multi-task concurrent transmission plan; a collaborative management module, configured to construct a multi-domain network service level agreement evaluation model based on the multi-task concurrent transmission scheme and the service data, and perform service decomposition and business collaborative management based on the multi-domain network service level agreement evaluation model to generate a service quality assurance plan; A data fusion module, configured to perform heterogeneous processing on the business data, and perform data fusion on the business data based on the heterogeneous processing results to generate a data fusion solution; A sharing module is used to integrate and share the business data under the coordinated action of the data matching scheme, the model collaborative deployment scheme, the multi-task concurrent transmission scheme, the service quality assurance scheme and the data fusion scheme.

Images