Hierarchical distributed computing communication system and method based on cloud side-end integration

Abstract

The invention belongs to the technical field of distributed computing and multi-level network architecture, and discloses a hierarchical distributed computing communication system and method based on cloud side-end integration. The system comprises a task grading module which is used for dividing an action calculation task into a high-level task, a middle-level task and a low-level task according to the emergency degree and complexity of the task; the node division module is used for dividing the computing nodes into three types, namely remote nodes, edge nodes and central nodes according to the geographic positions, the computing capabilities and the communication delays of the computing nodes in the network; the invention aims to improve the cooperation efficiency of remote and edge computing nodes and realize efficient real-time action data processing and action decision, and action computing tasks are divided into different levels, and coordinated processing is carried out among remote, edge and central nodes, so that the instantaneity, accuracy and reliability of action computing are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed computing and multi-level network architecture. More specifically, the present invention relates to a hierarchical distributed computing communication system and method based on cloud-edge-end integration. Background Art

[0002] With the development of science and technology, mankind has entered the era of "Internet of Everything", and the number of mobile devices and IoT devices that need to be connected has exploded. Smart homes, in-vehicle networks, health wearables, smart manufacturing and other devices need to complete complex calculations through cloud computing centers, but they cannot complete these calculations themselves. There are large data processing delays and data transmission delays between cloud computing centers and these smart devices. To solve this problem, edge servers are added between cloud computing centers and on-site smart devices. In this way, events can be processed with low latency and high efficiency. The Edge Computing Industry Alliance ECC and the Industrial Internet Industry Alliance AII jointly released the Edge Computing Reference Architecture 3.0, which has a three-layer architecture: cloud computing layer, edge computing layer and on-site device computing layer. According to IDC, global edge computing spending will reach US$176 billion in 2022, with an annual growth rate of 14.8%; China's edge computing market will reach RMB 180.37 billion in 2024;

[0003] However, existing mobile computing communication systems are not efficient in real-time mobile data processing and decision-making, and are not convenient for coordinating mobile computing tasks between remote, edge, and central nodes to ensure the real-time, accurate, and reliable performance of mobile computing.

[0004] In view of this, the present invention proposes a hierarchical distributed computing and communication system and method based on cloud-edge-end integration to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions: a hierarchical distributed computing and communication system and method based on cloud-edge-end integration, comprising:

[0006] A task classification module is used to classify mobile computing tasks into high-level tasks, medium-level tasks, and low-level tasks according to the urgency and complexity of the tasks;

[0007] A node partitioning module, which is used to classify computing nodes in the network into three categories: remote nodes, edge nodes, and central nodes based on their geographical location, computing power, and communication latency;

[0008] The task allocation and collaborative computing module includes an initial task allocation unit and a task scheduling and collaboration unit. The initial task allocation unit is used to allocate computing nodes according to the level of the task, and the task scheduling and collaboration unit is used to dynamically adjust the task allocation by monitoring the computing load of each node and the urgency of the task;

[0009] Data synchronization and consistency maintenance module, which includes a local data processing unit, an asynchronous data synchronization unit and a consistency maintenance unit;

[0010] An adaptive scheduling and fault-tolerance mechanism module, comprising an adaptive scheduling unit and a fault-tolerance mechanism unit. The adaptive scheduling unit is used to autonomously schedule tasks based on changes in the operational environment, task priority, and node load. The fault-tolerance mechanism unit is used to automatically reallocate tasks when some nodes fail.

[0011] The data transmission and communication module is used to transmit the collected data to the edge device in a predetermined format, and then use the cloud computing center to analyze and process the data and transmit it to the end user.

[0012] Furthermore, in the task grading module:

[0013] Action computing tasks classified as high-level tasks are quickly calculated at the edge nodes, action computing tasks classified as medium-level tasks are jointly processed by the central node and the edge nodes, and action computing tasks classified as low-level tasks are assigned to remote nodes for processing.

[0014] Furthermore, in the node division module:

[0015] The remote nodes are used for low real-time tasks such as storing historical data, data mining, and strategy research;

[0016] The edge nodes are used to process high real-time tasks;

[0017] The central node is located between the edge nodes and the remote nodes and serves as a central coordination system, allocating tasks between various parts of the system and being responsible for the processing of some mid-level tasks.

[0018] Furthermore, in the task allocation and collaborative computing module:

[0019] The initial task allocation unit allocates high-level tasks to edge nodes first, middle-level tasks between central nodes and edge nodes, and low-level tasks to remote nodes according to the levels of the tasks.

[0020] The task scheduling and coordination unit dynamically adjusts task allocation by monitoring the computing load and task urgency of each node. If the computing power of the edge node reaches a bottleneck, some high-level tasks will be transferred to the central node. If the central node is overloaded, low-level tasks will be preferentially delegated to remote nodes.

[0021] Furthermore, the data synchronization and consistency maintenance module:

[0022] The local data processing unit is used to pre-process and simplify calculations on edge nodes using data provided by local sensors and monitoring equipment;

[0023] The asynchronous data synchronization unit is used to asynchronously transmit part of the calculation results to the central and remote nodes after the edge node completes the calculation;

[0024] The consistency maintenance unit is used to ensure data consistency among nodes through a distributed database and a consistency algorithm.

[0025] Furthermore, in the adaptive scheduling unit:

[0026] The changes in the operational environment include technological advances of both sides, environmental factors, strategy and tactics, international relations, social culture, economic factors, health and biology, and space operations;

[0027] These changes in task priorities include goal adjustments, resource changes, external factors, risk assessments, stakeholder feedback, schedule updates, and technology changes;

[0028] The node load changes include task allocation changes, data traffic fluctuations, dynamic resource adjustments, hardware performance differences, network status changes, and failures.

[0029] Furthermore, the fault-tolerant mechanism unit includes multiple copy storage, hot backup and node failure detection mechanisms;

[0030] The multiple copy storage is used to store multiple copies of data in multiple locations or devices;

[0031] The hot backup is divided into online backup and dynamic backup. The hot backup refers to the backup performed when the database is operating normally and is accessible to users;

[0032] The node fault detection mechanism includes heartbeat detection, timeout retransmission and confirmation mechanism, log and monitoring information analysis, fault injection test and distributed consistency protocol detection.

[0033] Furthermore, the data transmission communication module includes: a data acquisition and transmission unit, a communication architecture and model building unit, an edge device communication and intent recognition unit, and a data processing and matching unit;

[0034] The data acquisition and transmission unit is used to complete data acquisition through sensors, and transmit the data to edge devices in a predetermined format by wireless transmission or other means, and then use the cloud computing center to perform necessary analysis and processing on the data and transmit the processed data to the end user;

[0035] The communication architecture and model building unit builds a model by adopting a distributed data transmission framework, wherein the communication architecture is used to realize communication between cloud computing, edge devices and mobile terminals;

[0036] The edge device communication and intent recognition unit is used to analyze the communication behavior between edge devices to infer intent.

[0037] Furthermore, the data processing and matching unit is used to process the collected data, and use the cloud computing center to control multiple edge devices to distribute massive data collection work to different devices. When the data is filtered for the second time, the data that meets the requirements is screened out according to specific rules or conditions.

[0038] The hierarchical distributed computing and communication method based on cloud-edge-end integration includes the following steps:

[0039] S1. Based on the urgency and complexity of the tasks, action computing tasks are divided into high-level tasks, medium-level tasks, and low-level tasks.

[0040] S2. Computing nodes in the network are divided into three categories based on their geographical location, computing power, and communication latency: remote nodes, edge nodes, and central nodes.

[0041] S3. Performing task allocation and collaborative computing, which includes an initial task allocation unit and a task scheduling and collaboration unit. The initial task allocation unit is used to allocate computing nodes according to the level of the task, and the task scheduling and collaboration unit is used to dynamically adjust task allocation by monitoring the computing load of each node and the urgency of the task;

[0042] S4, performing data synchronization and consistency maintenance, which includes a local data processing unit, an asynchronous data synchronization unit, and a consistency maintenance unit;

[0043] S5. Performing adaptive scheduling and fault tolerance, which includes an adaptive scheduling unit and a fault tolerance mechanism unit. The adaptive scheduling unit is used to autonomously schedule tasks according to changes in the action environment, task priority, and node load. The fault tolerance mechanism unit is used to automatically reallocate tasks when some nodes fail.

[0044] S6. The collected data is transmitted to the edge device in a predetermined format, and then the cloud computing center analyzes and processes the data and transmits it to the end user.

[0045] The technical effects and advantages of the present invention are based on a hierarchical distributed computing and communication system and method based on cloud-edge-end integration:

[0046] 1. This invention ensures data consistency during task processing through distributed data synchronization and consistency. The fault-tolerant mechanism ensures that tasks can continue to execute even if some nodes fail. The system supports multi-level node deployment, is suitable for mobile networks of different sizes, and can flexibly expand the number of nodes and task complexity according to operational needs.

[0047] 2. The present invention aims to improve the collaboration efficiency of remote and edge computing nodes and realize efficient real-time action data processing and action decision-making. Specifically, by dividing action computing tasks into different levels and coordinating processing between remote, edge and central nodes, the real-time, accuracy and reliability of action computing can be ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a schematic diagram of the structure of the hierarchical distributed computing and communication system based on cloud-edge-end integration of the present invention;

[0049] Figure 2 This is the overall architecture diagram of the hierarchical distributed computing and communication system based on cloud-edge-end integration of the present invention;

[0050] Figure 3 This is a schematic diagram of the task classification distribution in the task classification module of the present invention;

[0051] Figure 4 This is a flow chart of the hierarchical distributed computing and communication method based on cloud-edge-end integration of the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0053] Example 1

[0054] See also Figures 1 to 3 As shown, the hierarchical distributed computing and communication system based on cloud-edge-end integration described in this embodiment includes:

[0055] The task classification module is used to divide action computing tasks into high-level tasks, medium-level tasks and low-level tasks according to the urgency and complexity of the tasks. It should be noted that the urgency is determined by people based on time sensitivity, impact and urgency of resource requirements. Time sensitivity includes whether the task has a clear time limit, whether it needs to be started immediately or processed continuously, whether the time is time-sensitive, etc. The impact includes how serious the direct consequences will be if it is not handled in time, whether the problem will quickly fluctuate to other areas, and the urgency of resource requirements includes whether special resources need to be deployed immediately, whether there are backup plans to alleviate the emergency, etc. There are several indicators for determining the complexity of tasks: structural complexity, dynamic change rate and predictability. Structural complexity refers to how many interrelated subsystems are involved in the event, dynamic change rate refers to whether the nature of the problem changes rapidly and the rate at which the scope of influence expands, and predictability refers to whether there are historical cases for reference and the influence of unobservable variables on the results. The above parameters can be set with corresponding weights by relevant personnel, and the corresponding urgency and complexity can be calculated according to the corresponding weights.

[0056] The node classification module is used to classify computing nodes in the network into three categories based on their geographic location, computing power, and communication delay: remote nodes, edge nodes, and central nodes. It should be noted that geographic location, computing power, and communication delay are each weighted. The distance of the geographic location is usually positively correlated with the strength of the communication delay, so the weights assigned to each can be relatively low. The formula is calculated: distance * 0.3 + communication delay * 0.2 + computing power * 0.5. The resulting values ​​are arranged from small to large. Relatively small values ​​are designated as edge nodes, intermediate values ​​as remote nodes, and large values ​​as central nodes.

[0057] The task allocation and collaborative computing module includes an initial task allocation unit and a task scheduling and collaboration unit. The initial task allocation unit is used to allocate computing nodes according to the level of the task, and the task scheduling and collaboration unit is used to dynamically adjust the task allocation by monitoring the computing load of each node and the urgency of the task;

[0058] Data synchronization and consistency maintenance module, which includes a local data processing unit, an asynchronous data synchronization unit and a consistency maintenance unit;

[0059] An adaptive scheduling and fault-tolerance mechanism module, comprising an adaptive scheduling unit and a fault-tolerance mechanism unit. The adaptive scheduling unit is used to autonomously schedule tasks based on changes in the operational environment, task priority, and node load. The fault-tolerance mechanism unit is used to automatically reallocate tasks when some nodes fail.

[0060] The data transmission and communication module is used to transmit the collected data to the edge device in a predetermined format, and then use the cloud computing center to analyze and process the data and transmit it to the end user.

[0061] Furthermore, in the task grading module:

[0062] Action computing tasks classified as high-level tasks are quickly calculated on edge nodes, action computing tasks classified as medium-level tasks are processed jointly by central nodes and edge nodes, and action computing tasks classified as low-level tasks are assigned to remote nodes for processing;

[0063] Specifically, high-level tasks such as firepower allocation and target locking require rapid calculations at edge nodes; mid-level tasks such as threat assessment and intelligence analysis are jointly processed by central nodes and edge nodes; low-level tasks such as post-action data analysis and historical data storage are assigned to remote nodes for processing.

[0064] Furthermore, in the node division module:

[0065] The remote node is located in the command center or rear base, and has powerful data storage and analysis capabilities. It is mainly used for low real-time tasks such as storing historical data, data mining, and strategy research.

[0066] The edge nodes are deployed at the front lines of operations or in areas close to operations. They have strong real-time computing capabilities and are primarily responsible for processing high-real-time tasks such as firepower strike calculations, target tracking, and threat prediction.

[0067] The central node is located between the edge nodes and the remote nodes, and serves as a central coordination system, allocating tasks among various parts of the system and being responsible for processing some mid-level tasks.

[0068] Furthermore, in the task allocation and collaborative computing module:

[0069] The initial task allocation unit allocates high-level tasks to edge nodes first according to the levels of the tasks, allocates medium-level tasks between the central node and the edge nodes, and allocates low-level tasks to remote nodes.

[0070] The task scheduling and coordination unit: In actual operation, the system dynamically adjusts task allocation by monitoring the computing load and task urgency of each node. If the computing power of the edge node reaches a bottleneck, the system will transfer some high-level tasks to the central node. If the central node is overloaded, the system will give priority to delegating low-level tasks to remote nodes.

[0071] Furthermore, in the data synchronization and consistency maintenance module:

[0072] Used to pre-process and simplify calculations on edge nodes using data provided by local sensors and monitoring devices to reduce the amount of data transmitted;

[0073] The asynchronous data synchronization unit is used to asynchronously transmit part of the calculation results to the central and remote nodes after the edge node completes the action calculation for further data analysis and decision support;

[0074] The consistency maintenance unit is used to ensure data consistency between nodes through a distributed database and a consistency algorithm (such as Paxos, Raft, etc.) to avoid erroneous decisions caused by data asynchrony;

[0075] Specifically, preprocessing includes: data cleaning, data conversion and data dimensionality reduction; data cleaning mainly includes: filling missing data by deletion, interpolation or prediction, and then using statistical methods or machine learning algorithms to identify and process outliers, and then deleting duplicate records to ensure data uniqueness; data conversion includes: scaling data to a uniform range (such as 0-1), converting categorical data into numerical form (such as one-hot encoding, label encoding); creating new features or selecting important features to improve model performance; data dimensionality reduction includes: reducing the number of features through linear transformation and retaining the main information; visualizing high-dimensional data, retaining local structure, and performing nonlinear dimensionality reduction through neural networks; simplifying calculations includes: using GPUs, TPUs and other accelerated calculations, processing large-scale data through frameworks such as Hadoop and Spark, and reducing model complexity through techniques such as branching, quantization, and knowledge distillation.

[0076] Furthermore, in the adaptive scheduling and fault tolerance mechanism module:

[0077] The adaptive scheduling unit is used to autonomously schedule tasks according to changes in the action environment, task priority, and node load to ensure that the most important action computing tasks are completed first;

[0078] Among them, changes in the operational environment include technological progress of both sides, environmental factors, strategies and tactics, international relations, social culture, economic factors, health and biology, and space operations; specifically, a. Technological progress mainly refers to the increase in drones, unmanned vehicles and unmanned ships, which will reduce casualties and improve operational flexibility; artificial intelligence is used for intelligence analysis, target identification and autonomous decision-making to improve operational efficiency and accuracy; cyber attacks and defenses involve the network security of critical infrastructure and military systems; directed energy weapons such as laser weapons and microwave weapons have changed the traditional firepower confrontation mode; b. Environmental factors include climate change such as extreme weather and sea level rise that may affect the operational environment and logistics support, urbanization operations involving street fighting and underground missions, electromagnetic interference and spectrum contention operations that affect communication and navigation systems; c. Strategies and tactics include multi-domain coordinated operations such as land, sea, air, space, and network; small, dispersed action units coordinate operations through the network; asymmetric actions adopted by non-state actors and small countries; d. International relations mainly involve joint exercises and intelligence sharing between alliances and partners between countries affecting the operational environment; regional conflicts trigger intervention by major powers; international law and rules of war Changes affect operational behavior and the legitimacy of warfare; e. Social culture includes influencing public opinion and psychological warfare through social media and online platforms; the use of civilian technology and resources for military purposes; the use of autonomous weapons and artificial intelligence raises ethical and moral controversies; f. Economic factors include the competition for strategic resources such as energy and water; g. Health and biology, mainly biological weapons, may become new threats; operational medical support and epidemic prevention measures become more important in the context of this new threat; h. Space operations refer to satellite attacks and anti-satellite weapons and the competition for space resources; it should be noted that after obtaining information on changes in the operational environment through satellites, drones, ground reconnaissance, signals intelligence or human intelligence, the collected intelligence is organized, classified and verified to determine the opponent's intentions, capabilities and possible actions, analyze the severity and urgency of the enemy threat, assess the impact of terrain and weather on mission operations, integrate intelligence, threats and environment into a comprehensive operational situation, and update the situation in real time to reflect the latest changes; provide action recommendations based on the results of the assessment, and verify the effectiveness of different action plans through war games; evaluate the accuracy of the assessment process based on the results of the action, and optimize the assessment process based on feedback. Compile assessment results into reports to ensure commanders and troops at all levels have timely access to information; continuously track changes in the operational environment, and promptly identify and report significant changes;

[0079] Mission priority changes include goal adjustments, resource changes, external factors, risk assessments, stakeholder feedback, progress updates, and technological changes. Specifically, mission priority changes correspond to the mission classification module. Goal adjustments refer to changes in mission direction or objectives that may cause certain tasks to increase or decrease in priority. Resource changes refer to increases or decreases in manpower, funds, and equipment that may affect mission priorities. External factors refer to priority adjustments caused by operational requirements, form changes, or adversary actions. Risk assessments refer to the identification of new risks or the reassessment of existing risks that may affect mission priorities. Stakeholder feedback refers to the opinions of management or team members that may affect mission priorities. Progress updates refer to the advancement or postponement of certain tasks. Technological changes refer to the emergence of new technologies that may make certain tasks more urgent or no longer necessary. The specific ranking of priorities is usually determined based on the urgency of the mission, the severity of the threat, and the availability of resources. The specific framework for prioritization includes: immediate threats, critical mission objectives, intelligence gaps, logistical support, environmental factors, long-term strategic goals, training and preparation, psychology and morale, public relations and information warfare, and legal and ethical considerations.

[0080] It should be noted that immediate threats refer to factors that pose a direct threat to the safety of troops or the completion of missions, such as sudden enemy attacks, nuclear, biological and chemical threats, and the destruction of key facilities. We should immediately take defensive or counterattack measures; key mission objectives refer to objectives that are crucial to the success of the mission, such as occupying strategic locations, destroying enemy command centers, and protecting important logistics lines. We should prioritize the allocation of resources to ensure that the objectives are achieved; intelligence gaps refer to the lack of key intelligence that affects decision-making, such as the unknown location of the enemy's main force and the emergence of new offensive and defensive systems. We should strengthen intelligence collection and fill the gaps; logistics support refers to the materials and support needed to maintain operational capabilities, such as fuel supply, medical support, and communication support. We should ensure that the logistics chain is unobstructed and provide support in a timely manner; environmental factors refer to natural and man-made environmental factors that affect mission operations, such as bad weather, terrain changes, and electromagnetic interference. We should adjust tactics and equipment to adapt to environmental changes; long-term strategic goals refer to long-term goals that are crucial to the success of the overall strategy, such as establishing lasting peace, To weaken the enemy's war potential, we should formulate and implement long-term strategic plans; training and preparation refer to training activities that enhance the mobility and readiness of the troops, such as simulation exercises, tactical training, and psychological preparation. We should conduct training regularly to ensure that the troops are ready to deal with various situations at any time; psychology and morale refer to factors that affect the morale and psychological state of the troops, such as fatigue, psychological pressure, and low morale. We should provide psychological support and incentives to maintain high morale; public relations and information warfare refer to factors that influence public opinion and information warfare, such as media propaganda, public opinion guidance, and information warfare strategies. We should formulate and implement information warfare strategies to win public support; legal and ethical considerations refer to factors involving international law and ethical norms, such as compliance with the laws of war, protection of civilians, and avoidance of unnecessary destruction. We should ensure that actions comply with legal and ethical standards; furthermore, through this prioritization, the team can allocate resources and attention more effectively, ensure that key tasks and threats are dealt with in a timely manner, and thus improve the efficiency and success rate of operations;

[0081] It should be further explained that when conducting a risk assessment of the operational environment, attention should be paid to risk identification, that is, determining potential risks that may affect the mission or the safety of the troops. Specifically, by analyzing intelligence data, reviewing historical data and lessons learned from similar missions, and listing possible risk sources through brainstorming, expert consultation, etc.; assessing the probability and potential impact of each risk, assessing the possibility and severity of the risk based on experience and expert judgment, or using mathematical models or statistical tools to calculate the specific probability and impact of the risk; determining which risks need to be prioritized, sorting them according to risk levels, focusing on high-risk items, and assessing risk tolerance in combination with mission objectives and resource constraints; formulating measures to mitigate, transfer, or accept risks, adjusting plans to completely avoid risks (such as changing routes of travel), taking measures to reduce the probability or impact of risks (such as strengthening reconnaissance, increasing protection), and transferring risks to other parties (such as sharing of tasks through allies), choose not to take action on low-probability or low-impact risks; continuously track changes in risks to ensure the effectiveness of response measures, monitor the operational environment and risk indicators in real time, regularly evaluate risk status and the effectiveness of response measures, adjust risk assessments based on new intelligence or environmental changes, and update risk assessment reports and adjusted response plans; ensure that all relevant personnel understand the risks and their responses, communicate risk assessment results through briefings, reports or command chains, ensure that commanders and team members at all levels are clear about their responsibilities and response strategies, and establish clear risk communication records; record the risk assessment process and results to provide reference for future missions, archive risk assessment reports, response plans and monitoring results, summarize experiences and lessons, and optimize the risk assessment process; and further, through a systematic risk assessment process, the military can effectively identify and manage potential threats, reduce uncertainty, improve mission success rates and reduce losses.

[0082] The node load changes include task allocation changes, data traffic fluctuations, dynamic resource adjustments, hardware performance differences, network status changes, failures or anomalies; specifically, task allocation changes refer to the fact that the task allocation on the cloud, edge, and device sides may be dynamically adjusted according to demand, resulting in an increase or decrease in the load on some nodes. For example, the edge computing node may increase its load due to processing more local data, while the cloud load may decrease accordingly; data traffic fluctuations refer to fluctuations in data generation and transmission (such as peak periods or bursts of traffic) that cause node load changes. For example, IoT devices generate a large amount of data during a specific period, and the load on the edge node will increase significantly; dynamic resource adjustment refers to resource adjustment strategies (such as load balancing and task migration) that may cause the load to be redistributed among nodes; hardware performance differences refer to the hardware performance of different nodes (such as computing power and storage capacity) that may lead to uneven load distribution; network status changes refer to network delays, bandwidth limitations, or interruptions that may cause tasks to be unable to be allocated to the cloud in a timely manner, resulting in an increase in the load on the edge node; failures or anomalies refer to the failure of a node that may cause other nodes to take over its tasks, resulting in an increase in load.

[0083] The fault-tolerant mechanism unit is used to ensure high availability and reliability of the system by automatically reallocating tasks when some nodes fail through multiple copy storage, hot backup and node failure detection mechanisms;

[0084] Specifically, it is a data storage strategy used to save multiple copies of data in multiple locations or devices to improve data reliability and availability. The purpose is to prevent data loss caused by single point failures and ensure that data is still accessible even if some storage nodes fail. Read requests are distributed across multiple copies to improve system performance. The implementation method is synchronous replication or asynchronous replication. Synchronous replication is when data is written, all copies are updated at the same time to ensure consistency, which may increase latency. Asynchronous replication is when data is written, the copies are updated later, reducing latency, but may cause temporary inconsistencies.

[0085] Hot backups are classified as either online or dynamic. They are performed while the database is operating normally and accessible to users. Specifically, this backup method does not require stopping the database service; it performs real-time backups while the system is running. Even when data is being edited or read, the backup does not generate new data, providing continuous data protection. Hot backups require the database to be in archivelog mode to ensure data consistency. Users can still access the database throughout the backup process, facilitating workflow in multi-user systems.

[0086] Node fault detection mechanisms include heartbeat detection, timeout retransmission and confirmation mechanism, log and monitoring information analysis, fault injection test, and distributed consistency protocol detection. Specifically, heartbeat detection is that the node regularly sends heartbeat signals to other nodes or central servers to indicate that it is operating normally. If the receiver does not receive the heartbeat signal within the specified time, it may be considered that the sender node is faulty. The timeout retransmission and confirmation mechanism is that after the node sends data or a request, it starts a timer to wait for the receiver's confirmation response. If no confirmation is received within the set time, the data or request is retransmitted. Multiple retransmission failures may indicate that the node is faulty. Log and monitoring information analysis is that the node records detailed logs, including operations, errors, and more. The monitoring system collects these logs and node performance indicators, such as CPU and memory usage, and by analyzing the log and indicator data, it can find abnormal patterns or error information and determine whether the node is faulty; fault injection testing is to artificially inject faults into the node while the system is running, such as simulating network interruption, CPU overload, etc., and observe the system response and the detection capabilities of other nodes to verify the effectiveness of the fault detection mechanism; distributed consistency protocol detection is in a distributed system, where nodes maintain data consistency through distributed consistency protocols such as Paxos and Raft. If the node fails to reach consensus for a long time or has frequent conflicts during the execution of the protocol, it may indicate that the node is faulty.

[0087] Furthermore, the data transmission communication module includes: a data acquisition and transmission unit, a communication architecture and model building unit, an edge device communication and intent recognition unit, and a data processing and matching unit;

[0088] The data acquisition and transmission unit is used to complete data acquisition through sensors, and at the same time transmit the data to the edge device by wireless transmission or other means in accordance with a predetermined format (text format such as CSV, JSON, XML; binary format such as BIN, Avro, Parquet; database format such as SQLite, MySQL, PostgreSQL, MongoDB; image format such as JPEG, PNG, GIF; audio format such as MP3, WAV, AAC; video format MP4, AVI, MKV; compression format such as ZIP, RAR, 7z; other formats such as PDF, HTML), and then use the cloud computing center to perform necessary analysis and processing on the data, and transmit the processed data to the end user. Furthermore, the present invention can ensure the security and integrity of the data, and will not cause the problem of too long delay when transmitting massive data in real time; wherein, the data acquisition and transmission unit transmits by means of sensors, edge devices, etc., which includes: preprocessing the data collected by the action, classifying it using a unified device and performing model training;

[0089] It should be noted that the communication architecture of the present invention needs to be designed according to the basic principles of reliability, scalability, maintainability, and one-to-many communication to achieve communication between cloud computing, edge devices, mobile terminals, etc. For communication between cloud computing and edge, in order to ensure that data from mobile terminals and commands from the cloud computing center can be transmitted to edge devices in a timely manner, a standard network communication interface can be adopted, based on TCP / IP, with the help of the Client / Socket model and the Socket system in the client and server programs to achieve point-to-point data transmission. For communication between edge devices and mobile terminals, the basic requirement of one-to-many must be met when performing data collection, fully considering various types of network transmission methods, and pre-setting corresponding interfaces to make the mobile data processing system more complete.

[0090] The model building unit builds the model by adopting a distributed data transmission framework. Specifically, the process of building the model includes: 1) demand analysis, determining the specific requirements of the model, such as data transmission volume, delay requirements, fault tolerance, etc., and clarifying the source and destination of the data; 2) architecture design, selecting a distributed framework, such as Apache Kafka, Apache Flink, Apache Spark, etc., and designing the system architecture, including data flow, node roles, communication protocols, etc.; 3) environment construction, preparing servers, network equipment, etc., and deploying the selected distributed framework and related tools; 4) data partitioning and distribution, dividing the data into multiple parts, distributing them to different nodes, and selecting appropriate distribution strategies, such as hash partitioning, range partitioning, etc.; 5) data transmission, selecting transmission protocols such as TCP / IP and HTTP, and writing code to implement data transmission and conversion; 6) data processing, performing necessary cleaning and conversion during data transmission, and using the parallel capabilities of distributed systems to accelerate processing; 7 ) Fault tolerance and recovery: implement fault tolerance mechanisms, such as data backup and replication mechanisms, and design automatic or manual fault recovery processes; 8) Performance optimization: ensure load balancing among nodes, optimize network communications, reduce latency, and improve throughput; 9) Testing and verification: conduct unit testing to verify the functionality of each module, conduct integration testing to verify the coordination of the entire system, and conduct performance testing to verify the performance of the system under high load; 10) Deployment and monitoring: deploy the model to the production environment, monitor the system's operating status, and promptly identify and resolve problems; 11) Maintenance and upgrade: ensure the long-term stable operation of the system and expand functions or optimize performance as needed;

[0091] It should be noted that in actual operation, data is pre-processed according to the preset data format and actual application conditions (the same as the data processing method of the data synchronization and consistency maintenance module) to form a wireless or wired data transmission method. Currently, the most widely used data acquisition methods are serial port connected spread spectrum chips, module reserved Bluetooth, etc. Different data acquisition methods have different characteristics. Spread spectrum chips have a longer transmission distance (1 to 20 km), lower energy consumption, and lower price, but a lower transmission rate (0.018 kbit / s to 37.5 kbit / s); Bluetooth has a shorter transmission distance (80 to 100 m), higher energy consumption, but a faster transmission rate (1 Mbit / s), and relatively simple hardware; in actual applications, the Bluetooth transmission used for sensors and edge devices can be set up using a multi-threaded method;

[0092] It should be further explained that in order to ensure the effectiveness of data transmission between edge devices and cloud computing centers, it is necessary to make certain modifications to the content monitored by edge devices; in order to ensure that edge devices can accurately transmit information, it is necessary to configure each edge device with an accurately identifiable identifier, such as: "year→month→day→serial number"; after the edge device is connected to the cloud, it can save its own unique ID locally and send the access application and device number to the cloud computing center; after confirming that the application number is correct, the cloud computing center can establish a connection and divide the data into different categories (cloud computing center model correction training data, local device storage data, etc.); on this basis, the server can open the response port, starting with the child thread, and through a series of corresponding operations (edge ​​device communication intention identification, edge device communication needs and number transmission, edge device and cloud computing center completion of connection, cloud computing center acquisition of data and feedback, etc.), to achieve two-way communication between the server and the client, thereby effectively reducing latency;

[0093] The communication intention identification unit is used to infer the intention (or purpose) behind the communication behavior between edge devices by analyzing the communication behavior between them; specifically, first, it is necessary to collect the communication data of the edge devices, which include: communication protocol, message content sent and received by the device, timestamp and device ID participating in the communication; secondly, the collected data is preprocessed for subsequent analysis, and the preprocessing process includes: data cleaning, that is, removing noise and irrelevant data; extracting useful features from the original data, such as type, frequency, size, etc.; if there is a need for supervised learning, the data needs to be labeled to indicate the intention of each communication; thirdly, using machine learning or deep learning technology to identify the behavior pattern of device communication, related technologies include: cluster analysis, that is, clustering similar communication behaviors through unsupervised learning methods to find typical patterns; time series analysis, analyzing the time series of communication data to identify periodic or sudden behaviors; anomaly detection, identifying abnormal communications that do not conform to normal behavior patterns; fourthly, based on the identified behavior patterns, inferring the communication intention of the device and inferring The methods of diagnosis include: rule engine, that is, matching communication behavior and intention through predefined rules, for example, if device A sends a specific message to device B, it is inferred as "requesting data"; machine learning model, training classification model, mapping communication behavior to specific intent recognition, commonly used models include decision tree, random forest, support vector machine, etc.; deep learning model, for complex communication behavior, deep learning models such as LSTM and Transformer can be used for intent recognition; fifth, deploying the trained model to edge nodes or terminal devices for real-time inference. During deployment, the model can be lightweight processed, that is, compressing the complex model into a lightweight model suitable for edge device operation. Model inference at the edge node can reduce dependence on the cloud and reduce latency; finally, integrating the intent recognition module into the existing IoT system and optimizing it. It is necessary to monitor the communication intention of the device in real time, detect anomalies in time, and continuously optimize the intent recognition model through user feedback or automatic evaluation to ensure the security and privacy of communication data and prevent data leakage;

[0094] The communication demand process of edge device communication needs and number transmission includes: 1) local data processing and demand triggering, edge devices collect and preliminarily process data locally, such as smart cameras analyzing video streams to detect abnormal events, triggering the communication demand of sending alarm information to the cloud or other edge devices; 2) communication strategy determination, based on the urgency, type and system resource status of the data, the edge device determines the communication strategy, such as using a low-latency 5G network for data with high real-time requirements, and transmitting non-critical data when the network is idle; 3) protocol adaptation, edge devices need to adapt to different communication protocols between the cloud and the edge, and convert data into a format that the cloud platform or other edge devices can understand, such as converting local sensor data from a custom format to the MQTT protocol format; 4) communication with edge nodes, edge devices first communicate with nearby edge nodes and transmit data to edge servers or edge gateways, possibly through short-range wireless communication technologies such as WIFI and Bluetooth; 5) edge to cloud transmission, after the edge node aggregates and processes data from multiple edge devices, it transmits the data to the cloud through a high-speed network, such as using a dedicated line or the Internet to send data to a cloud data center; 6) cloud feedback and interaction, the cloud processes the data After analysis, instructions or feedback information may be sent to the edge device, which is then transmitted back to the edge device via the network to achieve closed-loop interaction between the cloud and the edge. Number transmission process: 1) Number allocation and registration: The edge device is assigned a unique identification number, such as device ID, MAC address, etc., during production or deployment, and then registered in the edge management system or cloud platform to associate the number with the device's location, function and other information; 2) Number mapping and synchronization: The cloud-edge system establishes a number mapping table to map the edge device number with the cloud's logical identifier, user identifier, etc., and synchronizes between the cloud and the edge to ensure that each part can correctly identify and Positioning device; 3) Number portability in communication: When an edge device initiates communication, it carries its own number and the target device number in the data packet header or specific field for identification and routing by nodes and devices in the network; 4) Number verification and authorization: After receiving the data, the receiver verifies the sender's identity and authority based on the number, and checks the local or cloud authorization list to confirm whether the device is allowed to communicate and access the corresponding resources; 5) Number update and maintenance: If the number of the edge device needs to be changed due to equipment replacement, upgrade, etc., the system will update the number information in various parts of the cloud and edge to ensure the continuity and accuracy of communication;

[0095] The steps to complete the connection between edge devices and cloud computing centers: First, the preparation of edge devices, 1) hardware inspection, to ensure that the hardware of edge devices is working properly, including processors, memory, storage, network interfaces, etc., without hardware failures and damage; 2) software configuration, install necessary operating systems, drivers and communication software, configure the network parameters of the device, such as IP address, subnet mask, network management, DNS server, etc., so that it can access the network; 3) security settings, set the security authentication information of the device, such as user name, password, digital certificate, etc., for subsequent secure connection with the cloud computing center; secondly, the configuration of the cloud computing center, 1) resource preparation, allocate computing, storage, network and other resources to edge devices in the cloud computing center, create corresponding virtual hosts, storage volumes and network ports, etc.; 2) service configuration, configure services related to communication with edge devices, such as message queues, data storage services, etc., set communication protocols, data formats and interface specifications, etc.; 3) security policy settings, set security policies in the cloud computing center, such as access control lists (ACLs), allow specific The edge device IP address or MAC address is accessed, firewall rules are configured, and corresponding communication ports are opened; finally, the connection between the edge device and the cloud computing center is established, 1) Initiate a connection request, the edge device initiates a connection request to the cloud computing center through the network according to the configured cloud computing center address and port information, and the request contains the device's identity authentication information; 2) Identity authentication, after the cloud computing center receives the request, it authenticates the edge device according to the pre-configured authentication information, and continues the connection process if the authentication is passed, otherwise the connection is rejected; 3) Handshake and negotiation, after passing the identity authentication, the edge device and the cloud computing center shake hands and negotiate to determine the communication parameters, such as the protocol version used, data encryption method, etc.; 4) Establish a connection, after completing the handshake and negotiation, the edge device establishes a connection with the cloud computing center, and data transmission and interaction can begin; 5) Connection monitoring and maintenance, after the connection is established, both parties continuously monitor the connection status, the edge device and the cloud computing center periodically send heartbeat packets to detect whether the connection is normal, and reconnect or troubleshoot in time when problems occur;

[0096] The process of cloud computing centers acquiring data from edge devices and terminal devices is as follows: first, data collection is performed. Edge devices (such as sensors, cameras, smart terminals, etc.) are responsible for collecting raw data (such as temperature, humidity, images, videos, etc.), and the raw data is preliminarily processed at the edge nodes (such as filtering, compression, feature extraction, etc.) to reduce the amount of data transmitted to the cloud; then data transmission is performed. Efficient communication protocols (such as MQTT, CoAP, HTTP / 2, etc.) are used to transmit data from edge devices to the cloud computing center. High-speed network technologies such as 5G and WIFI 6 ensure low latency and high reliability of data transmission. When the network is unstable, the edge nodes can cache data and upload it to the cloud after the network is restored; finally, data storage is performed. The cloud computing center uses distributed storage systems (such as HDFS, object storage, etc.) to store massive data. According to the type and purpose of the data, the data is stored in different databases (such as relational databases, time series databases, NoSQL databases, etc.);

[0097] It should be noted that after data collection is completed, the data is preprocessed through edge devices, mobile terminals, and cloud computing centers. Specifically, on this basis, the cloud computing center is used to control multiple edge devices, distributing the massive data collection work to different devices, reducing the pressure on the cloud computing center and improving the efficiency of data collection and processing. At the same time, edge devices are used as data collection terminals, and web crawler technology and related algorithms are used for data collection. After all data collection work is completed, the goal is to set up terminals to obtain unified resource positioning of the system. After completing the necessary data collection, the goal is to reduce the scale of data processing and analysis. A distance-based method is used to accurately identify data with sufficient reference related elements (data with inaccurate format and content, data with incorrect logical relationships, data with deleted or supplemented defects, useless data, etc.). It should be noted that the principle of the distance-based method is as follows: for a dataset, once the set distance is exceeded, the object can be identified as abnormal data based on the dataset and distance. After the abnormal data is judged and identified, the preprocessing solution can be edited in Python, that is, the Beautiful Soup database is used to obtain the data type to be analyzed. The necessary post-processing of the data is completed using appropriate tools (such as XPath).

[0098] The data processing and matching unit includes: obtaining data related to system adjustment through data matching and other means, obtaining corresponding identification parameters, and recording the parameters when necessary to accurately calibrate the tracking function, so as to prevent the corresponding factors from affecting the operation of the data acquisition channel; after the initial data is fully and accurately collected, the massive data is filtered twice according to the matching principle, abnormal data is removed in time, the integrity and relevance of the data are judged, and whether it meets the inspection standards; if it does not meet the standard requirements, the data needs to be filtered again, and a series of operations such as multi-source data fusion, feature comparison, feature association detection, and feature information system conversion are completed using data feature functions and related sensors; in actual operation, the sensor signal needs to be converted according to the operating function to obtain a unified data information signal, and necessary noise and stain filtering is performed after the signal source is clear, so as to obtain more effective data; at the same time, appropriate algorithms should be used to strengthen the data processing system, enhance the data monitoring effect, and ensure the effective fusion of the extracted signal features and the data set;

[0099] It should be noted that the matching principle refers to the process of filtering out data that meets the requirements based on specific rules or conditions during secondary filtering of data. Specifically, different matching principles need to be used for different scenarios and different content. For scenarios requiring high precision, the exact matching principle can be used, and the data must be completely consistent with the preset conditions; for text search and keyword matching scenarios, the fuzzy matching principle can be used, and the data only needs to be partially consistent with the conditions; for filtering data in a specific time period or numerical range, the range matching principle can be used, and the data must fall within the preset numerical value or time range; for complex text matching, the regular expression matching principle can be used, and complex rules can be defined through regular expressions to filter data that meets the pattern; for multi-condition combination filtering, the logical matching principle can be used, and multiple conditions can be combined through logical operators (AND, OR, NOT) for filtering; for similarity matching of text, images, etc., the similarity matching principle can be used, and the similarity between the data and the conditions can be calculated to filter data with a similarity higher than the threshold; for structured data, such as filtering data with specific field values, the field matching principle can be used to filter according to the value of the data field; for complex data analysis scenarios, the multi-dimensional matching principle can be used to filter based on conditions in multiple dimensions; for real-time data processing, the dynamic matching principle can be used to dynamically filter data based on real-time changing conditions.

[0100] In this embodiment, the present invention can ensure the data consistency of the system in task processing through distributed data synchronization and consistency. The fault-tolerant mechanism unit ensures that even if some nodes fail, the task can still continue to be executed; the system supports multi-level node deployment, is suitable for mobile networks of different sizes, and can flexibly expand the number of nodes and task complexity according to action requirements.

[0101] Example 2

[0102] See also Figure 4 As shown, the hierarchical distributed computing and communication method based on cloud-edge-end integration described in this embodiment includes the following steps:

[0103] S1. Based on the urgency and complexity of the tasks, action computing tasks are divided into high-level tasks, medium-level tasks, and low-level tasks.

[0104] S2. Computing nodes in the network are divided into three categories based on their geographical location, computing power, and communication latency: remote nodes, edge nodes, and central nodes.

[0105] S3. Performing task allocation and collaborative computing, which includes an initial task allocation unit and a task scheduling and collaboration unit. The initial task allocation unit is used to allocate computing nodes according to the level of the task, and the task scheduling and collaboration unit is used to dynamically adjust task allocation by monitoring the computing load of each node and the urgency of the task;

[0106] S4, performing data synchronization and consistency maintenance, which includes a local data processing unit, an asynchronous data synchronization unit, and a consistency maintenance unit;

[0107] S5. Performing adaptive scheduling and fault tolerance, which includes an adaptive scheduling unit and a fault tolerance mechanism unit. The adaptive scheduling unit is used to autonomously schedule tasks according to changes in the action environment, task priority, and node load. The fault tolerance mechanism unit is used to automatically reallocate tasks when some nodes fail.

[0108] S6. The collected data is transmitted to the edge device in a predetermined format, and then the cloud computing center analyzes and processes the data and transmits it to the end user.

[0109] In this embodiment, the present invention reduces the computing pressure of the central node through hierarchical distributed computing, and the edge nodes can process key action tasks in real time, reduce latency, and improve decision-making speed; the system dynamically allocates tasks according to the complexity of the tasks and the computing power of the nodes, avoiding single-point overload and improving the overall performance of the system.

[0110] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0111] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0112] The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0113] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A hierarchical distributed computing and communication system based on cloud-edge-end integration, characterized by: include: A task classification module is used to classify mobile computing tasks into high-level tasks, medium-level tasks, and low-level tasks according to the urgency and complexity of the tasks; A node partitioning module, which is used to classify computing nodes in the network into three categories: remote nodes, edge nodes, and central nodes based on their geographical location, computing power, and communication latency; The task allocation and collaborative computing module includes an initial task allocation unit and a task scheduling and collaboration unit. The initial task allocation unit is used to allocate computing nodes according to the level of the task, and the task scheduling and collaboration unit is used to dynamically adjust the task allocation by monitoring the computing load of each node and the urgency of the task; Data synchronization and consistency maintenance module, which includes a local data processing unit, an asynchronous data synchronization unit and a consistency maintenance unit; An adaptive scheduling and fault-tolerance mechanism module, comprising an adaptive scheduling unit and a fault-tolerance mechanism unit. The adaptive scheduling unit is used to autonomously schedule tasks based on changes in the operational environment, task priority, and node load. The fault-tolerance mechanism unit is used to automatically reallocate tasks when some nodes fail. The data transmission and communication module is used to transmit the collected data to the edge device in a predetermined format, and then use the cloud computing center to analyze and process the data and transmit it to the end user.

2. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 1 is characterized in that: In the task classification module: Action computing tasks classified as high-level tasks are quickly calculated at the edge nodes, action computing tasks classified as medium-level tasks are jointly processed by the central node and the edge nodes, and action computing tasks classified as low-level tasks are assigned to remote nodes for processing.

3. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 1 is characterized in that: In the node partition module: The remote nodes are used for low real-time tasks such as storing historical data, data mining, and strategy research; The edge nodes are used to process high real-time tasks; The central node is located between the edge nodes and the remote nodes and serves as a central coordination system, allocating tasks between various parts of the system and being responsible for the processing of some mid-level tasks.

4. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 1 is characterized in that: In the task allocation and collaborative computing module: The initial task allocation unit allocates high-level tasks to edge nodes first, middle-level tasks to central nodes and edge nodes, and low-level tasks to remote nodes according to the task levels. The task scheduling and coordination unit dynamically adjusts task allocation by monitoring the computing load and task urgency of each node. If the computing power of the edge node reaches a bottleneck, some high-level tasks will be transferred to the central node. If the central node is overloaded, low-level tasks will be preferentially delegated to remote nodes.

5. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 1 is characterized in that: In the data synchronization and consistency maintenance module: The local data processing unit is used to pre-process and simplify calculations on edge nodes using data provided by local sensors and monitoring equipment; The asynchronous data synchronization unit is used to asynchronously transmit part of the calculation results to the central and remote nodes after the edge node completes the calculation; The consistency maintenance unit is used to ensure data consistency among nodes through a distributed database and a consistency algorithm.

6. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 1 is characterized in that: In the adaptive scheduling unit: The changes in the operational environment include technological advances of both sides, environmental factors, strategy and tactics, international relations, social culture, economic factors, health and biology, and space operations; These changes in task priorities include goal adjustments, resource changes, external factors, risk assessments, stakeholder feedback, schedule updates, and technology changes; The node load changes include task allocation changes, data traffic fluctuations, dynamic resource adjustments, hardware performance differences, network status changes, and failures.

7. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 1 is characterized in that: The fault-tolerant mechanism unit includes multiple copy storage, hot backup and node failure detection mechanisms; The multiple copy storage is used to store multiple copies of data in multiple locations or devices; The hot backup is divided into online backup and dynamic backup. The hot backup refers to the backup performed when the database is operating normally and is accessible to users; The node fault detection mechanism includes heartbeat detection, timeout retransmission and confirmation mechanism, log and monitoring information analysis, fault injection test and distributed consistency protocol detection.

8. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 1 is characterized in that: The data transmission communication module includes: a data acquisition and transmission unit, a communication architecture and model building unit, an edge device communication and intention recognition unit, and a data processing and matching unit; The data acquisition and transmission unit is used to complete data acquisition through sensors, and transmit the data to the edge device by wireless transmission in a predetermined format, and then use the cloud computing center to analyze and process the data and transmit the processed data to the end user; The communication architecture and model building unit builds a model by adopting a distributed data transmission framework, wherein the communication architecture is used to realize communication between cloud computing, edge devices and mobile terminals; The edge device communication and intent recognition unit is used to analyze the communication behavior between edge devices to infer intent.

9. The hierarchical distributed computing and communication system based on cloud-edge-end integration according to claim 8 is characterized in that: The data processing and matching unit is used to process the collected data and use the cloud computing center to control multiple edge devices to distribute massive data collection work to different devices. When the data is filtered for the second time, the data that meets the requirements is screened out according to rules or conditions.

10. A hierarchical distributed computing and communication method based on cloud-edge-end integration, characterized in that: A method for implementing the cloud-edge-end integrated hierarchical distributed computing and communication system according to any one of claims 1 to 9, characterized in that it comprises the following steps: S1. Based on the urgency and complexity of the tasks, action computing tasks are divided into high-level tasks, medium-level tasks, and low-level tasks. S2. Computing nodes in the network are divided into three categories based on their geographical location, computing power, and communication latency: remote nodes, edge nodes, and central nodes. S3, performing task allocation and collaborative computing, which includes an initial task allocation unit and a task scheduling and collaboration unit, wherein the initial task allocation unit is used to allocate computing nodes according to the level of the task, and the task scheduling and collaboration unit is used to dynamically adjust the task allocation by monitoring the computing load of each node and the urgency of the task; S4, performing data synchronization and consistency maintenance, which includes a local data processing unit, an asynchronous data synchronization unit, and a consistency maintenance unit; S5. Performing adaptive scheduling and fault tolerance, which includes an adaptive scheduling unit and a fault tolerance mechanism unit. The adaptive scheduling unit is used to autonomously schedule tasks according to changes in the action environment, task priority, and node load. The fault tolerance mechanism unit is used to automatically reallocate tasks when some nodes fail. S6. The collected data is transmitted to the edge device in a predetermined format, and then the cloud computing center analyzes and processes the data and transmits it to the end user.

Images