A digital control method and system for a smart park

Abstract

The present invention discloses a digital control method and system for a smart park, which relates to the field of digital management. The method includes: parsing the basic information of the park, establishing hardware interface information and business information; configuring a multi-node cluster, and establishing a park Internet of Things platform; obtaining the park task flow, establishing node dynamic constraints, and obtaining the node backtracking window data of each node in the multi-node cluster; inputting into the master-slave node authentication network, generating the master-slave node authentication result; establishing the master-slave correlation mapping, and completing the architecture configuration of the park Internet of Things platform; receiving real-time tasks, performing balanced authentication of the node data flow, and generating a digital control scheme according to the balanced authentication result. The method solves the technical problem of the lack of intelligent decision-making ability in the existing digital control of smart parks, which leads to low utilization of park resources, and achieves the technical effect of optimizing the configuration and efficient utilization of park resources through intelligent management and scheduling.

Description

Technical Field

[0001] The present application relates to fields related to digital management, and in particular to a digital control method and system for a smart park. Background Art

[0002] With the rapid development of information technology and the acceleration of urbanization, the concept of smart parks has emerged, aiming to achieve intelligent management of park infrastructure, efficient allocation of resources and personalized provision of services by integrating advanced technologies such as the Internet of Things, big data, and cloud computing. As an important part of urban development, the operational efficiency and management level of smart parks are directly related to the sustainable development of the regional economy and the improvement of residents' quality of life. In the field of digital control of smart parks, existing methods mainly rely on fixed rules and algorithms, which makes it difficult to dynamically adjust resource allocation according to the actual operation of the park, resulting in low resource utilization.

[0003] Among the current relevant technologies, the digital control of smart parks lacks intelligent decision-making capabilities, resulting in technical problems such as low utilization of park resources. Summary of the invention

[0004] The present application provides a digital control method and system for a smart park, which adopts technical means such as reading basic information of the park, establishing hardware interface information and business information, configuring a multi-node cluster, establishing a park Internet of Things platform, establishing dynamic constraints on nodes according to the park task flow, and obtaining the backtracking window data of each node. The master-slave node authentication network is used to perform intelligent evaluation and role assignment on the nodes, realize balanced authentication of node data flow, and generate a digital control plan according to the balanced authentication results. The technical effect of achieving optimal allocation and efficient utilization of park resources through intelligent management and scheduling is achieved.

[0005] The present application provides a digital control method for a smart park, including:

[0006] Read the park basic information of the target park, parse the park basic information, establish hardware interface information and business information; perform multi-node cluster configuration according to the business information and hardware interface information, and establish a park Internet of Things platform; obtain the park task flow of the target park, establish node dynamic constraints according to the park task flow, and obtain the node backtracking window data of each node in the multi-node cluster; input the node backtracking window data and node dynamic constraints into the master-slave node authentication network to generate a master-slave node authentication result; establish a master-slave correlation mapping of the park Internet of Things platform according to the master-slave node authentication result, and complete the architecture configuration of the park Internet of Things platform; receive real-time tasks through the park Internet of Things platform that has been completed through the architecture configuration, perform balanced authentication of node data flows through the real-time tasks and master-slave correlation mapping, and generate a digital control plan according to the balanced authentication result.

[0007] In a possible implementation, the node backtracking window data and the node dynamic constraint are input into the master-slave node authentication network, a master-slave node authentication result is generated, and the following processing is performed:

[0008] A scoring subnetwork is established. The scoring subnetwork is a processing subnetwork of the master-slave node authentication network. The scoring subnetwork is as follows:

[0009] ;

[0010] in, represents the score of the i-th node, Characterizes the CPU usage of the i-th node, Characterizes the periodic change of CPU usage of the i-th node, Characterizes the memory usage of the i-th node, Characterizes the sharp change in memory usage of the i-th node, Represents the heartbeat signal of the i-th node, represents the load of the i-th node, Characterizes the periodic change of the load of the i-th node, Indicates the number of processing tasks of the i-th node, Characterizes the logarithmic change in the number of processing tasks of the i-th node, Characterizes the response time of the i-th node, Characterizes the sharp change in the response time of the i-th node, Characterizes the time node weight of the i-th node, , , , , , , are adjustment parameters of the corresponding features respectively; when the node backtracking window data and the node dynamic constraints are input into the master-slave node authentication network, the node backtracking window data is scored through the scoring sub-network, and the master-slave node authentication result is generated according to the scoring result and the node dynamic constraints.

[0011] In a possible implementation, the master-slave node authentication result is generated according to the scoring result and the node dynamic constraint, and the following processing is performed:

[0012] Analyze the node dynamic constraints, establish proportion constraints and threshold constraints; reconstruct the discriminant subnetwork through proportion constraints and threshold constraints, and the discriminant subnetwork is the processing subnetwork of the master-slave node authentication network; perform collaborative discriminant authentication of the scoring results according to the reconstructed discriminant subnetwork to generate the master-slave node authentication results.

[0013] In a possible implementation, the real-time task and the master-slave correlation mapping are used to perform balanced authentication of the node data flow, and a digital control scheme is generated according to the balanced authentication result, and the following processing is performed:

[0014] Establish node congestion perception of each node through node data flow; perform balanced coordination evaluation based on the master-slave correlation mapping and node congestion perception, establish a balanced authentication result, generate a coordination plan through the balanced authentication result, and use the coordination plan as a digital control plan.

[0015] In a possible implementation, the balanced coordination evaluation is performed based on the master-slave correlation mapping and node congestion perception, and the following processing is performed:

[0016] A basic collaborative association value between nodes is established according to the master-slave correlation mapping; an increased load evaluation of each node is performed through the node congestion perception, and an increased penalty coefficient is established; and a balanced coordination evaluation is completed according to the basic collaborative association value and the increased penalty coefficient.

[0017] In a possible implementation, the following processing is performed:

[0018] Establish disaster preparedness awareness for the campus Internet of Things platform; configure off-site backup constraints through the disaster preparedness awareness, and perform periodic backup of storage data in the campus Internet of Things platform through the off-site backup constraints.

[0019] In a possible implementation, the following processing is performed:

[0020] The control effect of the digital control of the target park is authenticated and a certification mark is established; common feedback extraction of the certification mark is performed, and the control optimization of the park Internet of Things platform is performed based on the common feedback extraction results.

[0021] The present application also provides a digital control system for a smart park, including:

[0022] A park basic information parsing module, the park basic information parsing module is used to read the park basic information of the target park, parse the park basic information, and establish hardware interface information and business information; a multi-node cluster configuration module, the multi-node cluster configuration module is used to perform multi-node cluster configuration according to the business information and hardware interface information, and establish a park Internet of Things platform; a node dynamic constraint establishment module, the node dynamic constraint establishment module is used to obtain the park task flow of the target park, establish node dynamic constraints according to the park task flow, and obtain the node backtracking window data of each node in the multi-node cluster; a master-slave node authentication module, the master-slave node authentication module is used to input the node backtracking window data and node dynamic constraints into the master-slave node authentication network, and generate a master-slave node authentication result; an architecture configuration module, the architecture configuration module is used to establish a master-slave correlation mapping of the park Internet of Things platform according to the master-slave node authentication result, and complete the architecture configuration of the park Internet of Things platform; a digital control scheme generation module, the digital control scheme generation module is used to receive real-time tasks on the park Internet of Things platform completed through the architecture configuration, perform balanced authentication of node data flows through the real-time tasks and master-slave correlation mapping, and generate a digital control scheme according to the balanced authentication result.

[0023] A digital control method and system for a smart park proposed in this application first reads the park basic information of the target park, analyzes the park basic information, establishes hardware interface information and business information, then configures a multi-node cluster according to the business information and hardware interface information, establishes a park Internet of Things platform, and then obtains the park task flow of the target park, establishes node dynamic constraints according to the park task flow, and obtains the node backtracking window data of each node in the multi-node cluster, and then inputs the node backtracking window data and node dynamic constraints into the master-slave node authentication network, generates a master-slave node authentication result, and then establishes a master-slave correlation mapping of the park Internet of Things platform according to the master-slave node authentication result, completes the architecture configuration of the park Internet of Things platform, and finally receives real-time tasks through the park Internet of Things platform with completed architecture configuration, performs balanced authentication of node data flow through real-time tasks and master-slave correlation mapping, and generates a digital control scheme according to the balanced authentication result. The beneficial effect of the present invention is that the optimal configuration and efficient utilization of park resources are achieved through intelligent management and scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0025] Figure 1 A flowchart of a digital control method for a smart park provided in an embodiment of the present application;

[0026] Figure 2 A structural diagram of a digital control system for a smart park provided in an embodiment of the present application;

[0027] Explanation of the accompanying drawings: campus basic information analysis module 10, multi-node cluster configuration module 20, node dynamic constraint establishment module 30, master-slave node authentication module 40, architecture configuration module 50, digital control plan generation module 60. DETAILED DESCRIPTION

[0028] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0030] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0031] The present application embodiment provides a digital control method for a smart park, such as Figure 1 As shown, the method includes:

[0032] Step S100, read the park basic information of the target park, parse the park basic information, and establish hardware interface information and business information. Specifically, determine the source of the park basic information (the basic data of all hardware equipment and business logic in the target park, which is the basis for establishing the smart park Internet of Things platform), including the park management system database, design drawings, equipment manuals, network topology diagrams and other data sources, and obtain the park basic information from the above data sources through API interface calls, file imports, manual entry, etc. Clean the collected data, remove duplicate, erroneous or irrelevant information, and organize the cleaned data into a structured format, such as JSON, XML or database tables, for subsequent processing.

[0033] Hardware interface information refers to the technical parameters and specifications required for communication between hardware devices and systems or other devices, and is the key to achieving device interconnection; business information is information that describes the data, processes, rules, etc. required for the operation of each business department in the target park, and is the basis for the business logic design of the Internet of Things platform. Classify structured data according to hardware devices and business logic. According to the classification results, identify all hardware devices in the target park, such as sensors, cameras, access control systems, lighting equipment, etc. For each hardware device, extract its communication interface information, including interface type (such as RS-485, Ethernet, Wi-Fi, etc.), communication protocol (such as Modbus, MQTT, HTTP, etc.), IP address, port number, etc., and prepare detailed interface documents for each hardware device, including interface description, data format, calling method, etc. According to the operational needs and business needs of the target park, sort out various business processes, such as project application process, approval process, problem feedback process, etc., define corresponding business rules for each business process, including input conditions, processing logic, output results, etc., build a business data model based on business processes and business rules, and define the required data tables, fields and their relationships.

[0034] Step S200, configure a multi-node cluster according to the business information and hardware interface information to establish a park IoT platform. Specifically, based on the hardware interface information and business information established in step S100, analyze the functions and performance requirements that the park IoT platform needs to support, analyze the specific needs of user roles such as enterprise users, department managers, and platform administrators in the target park, and ensure that the park IoT platform can meet the daily work and management needs of users.

[0035] Based on the multi-node cluster architecture, the park IoT platform is built. The multi-node cluster refers to a computing cluster composed of multiple computing nodes (such as servers, hardware devices, etc.), which improves the overall computing power and data processing capabilities through parallel processing and data sharing; the IoT platform refers to a platform that provides connection, management, data analysis and application services for IoT devices, and supports interconnection and data exchange between devices. Specifically, according to the scale and business needs of the target park, select appropriate hardware devices and servers as nodes of the IoT platform, plan the distribution and connection methods of the nodes, and ensure the reliability and efficiency of data transmission. Design the architecture of the multi-node cluster, including the configuration and deployment of components such as master nodes, slave nodes, load balancers, and database servers, and determine the communication protocols and data exchange mechanisms between nodes, such as using IoT communication protocols such as MQTT and CoAP. According to the hardware interface information, write the adaptation layer code for each hardware device to realize the connection between the device and the system; convert the business information into a data model that can be recognized by the system, and integrate it with the data of the hardware device to ensure the correct execution of the business logic.

[0036] Deploy the IoT platform software on the selected server, perform preliminary configuration and debugging, and conduct system integration testing to ensure that the communication between nodes is normal, data exchange is accurate, and business needs are met. Based on the test results, optimize the performance of the cluster architecture, such as adjusting the load balancing strategy and optimizing database queries.

[0037] Step S300, obtain the park task flow of the target park, establish node dynamic constraints based on the park task flow, and obtain the node backtracking window data of each node in the multi-node cluster. Specifically, determine the process of each task (such as project approval, equipment maintenance, environmental monitoring, etc.) in the target park, including the starting point, end point and key nodes in the middle of the task. Obtain the task flow data of the current park in real time or regularly through the park management system, workflow engine or task information submitted by users.

[0038] Based on the task flow data, the dependencies between tasks are analyzed to determine which tasks need to be executed in sequence and which tasks can be processed in parallel. According to the task dependencies, dynamic constraints are set for each node, that is, when executing the park task flow, constraints on the execution order, time, resources, etc. of each node (task) are set to ensure that the tasks can be executed smoothly according to the predetermined rules and processes, such as the completion status of the previous tasks, time windows, resource restrictions, etc. The constraints are converted into rules that the system can recognize for dynamic verification and adjustment during the task execution process.

[0039] According to business needs and system performance, set an appropriate backtracking window size for each node, that is, how much historical data (operation records, performance indicators, etc.) is retained for backtracking analysis of the node's execution status in order to discover potential problems, optimize task execution processes, or predict future trends. Collect the operation data of each node in a multi-node cluster in real time or regularly, including task execution status, resource usage, performance indicators, etc. Store the collected data in the database and create an index to quickly retrieve and query the data in the backtracking window.

[0040] Step S400, input the node backtracking window data and node dynamic constraints into the master-slave node authentication network to generate a master-slave node authentication result. Specifically, the node backtracking window data of each node in the multi-node cluster is obtained from step S300, and these data contain information such as the node's historical operating status, performance indicators, and resource usage. At the same time, the node dynamic constraints established according to the campus task flow are obtained. These constraints define the limitations and requirements of the nodes when performing tasks.

[0041] Clean and format the node backtracking window data, including removing outliers, filling missing values, and normalizing data to ensure data consistency and accuracy. Convert node dynamic constraints into a format recognizable by the master-slave node authentication network, such as feature vectors or labels.

[0042] The preprocessed node backtracking window data and node dynamic constraints are used as input and passed to the master-slave node authentication network. The master-slave node authentication network is a neural network or machine learning model specifically used to evaluate the capabilities, stability, and reliability of each node in the park's Internet of Things platform. By analyzing the node's historical data and dynamic constraints, it generates node authentication results to provide a basis for subsequent architecture configuration and task allocation. Within the master-slave node authentication network, the model performs calculations and reasoning based on the input data, including feature extraction, pattern recognition, relational reasoning and other steps to evaluate the capabilities, stability, and reliability of each node when performing tasks. At the same time, combined with node dynamic constraints, it ensures that the authentication results meet the business needs and process regulations of the target park.

[0043] After network calculation and reasoning, the master-slave node authentication network outputs the authentication results of each node, including node priority ranking, role allocation (master node, slave node), task allocation recommendations, etc.

[0044] In a possible implementation, the node backtracking window data and the node dynamic constraint are input into the master-slave node authentication network to generate the master-slave node authentication result. Step S400 further includes step S410, establishing a scoring subnetwork, the scoring subnetwork being a processing subnetwork of the master-slave node authentication network, and the scoring subnetwork is as follows:

[0045] ;

[0046] in, represents the score of the i-th node, Characterizes the CPU usage of the i-th node, Characterizes the periodic change of CPU usage of the i-th node, Characterizes the memory usage of the i-th node, Characterizes the sharp change in memory usage of the i-th node, Represents the heartbeat signal of the i-th node, represents the load of the i-th node, Characterizes the periodic change of the load of the i-th node, Indicates the number of processing tasks of the i-th node, Characterizes the logarithmic change in the number of processing tasks of the i-th node, Characterizes the response time of the i-th node, Characterizes the sharp change in the response time of the i-th node, Characterizes the time node weight of the i-th node, , , , , , , They are adjustment parameters for corresponding features respectively. Specifically, the scoring subnetwork is used to score nodes according to the node backtracking window data and evaluate the comprehensive performance of the nodes. In the scoring subnetwork, a scoring formula is defined, in which the CPU usage rate represents the occupancy of the node CPU and reflects the computing power of the node; the memory usage rate represents the occupancy of the node memory and reflects the storage capacity of the node; the heartbeat signal is a signal sent regularly by the node to detect the online status and health of the node; the load represents the amount of tasks or workload currently undertaken by the node; the number of tasks processed is the number of tasks processed by the node within a period of time; the response time represents the response speed of the node to the task request; the adjustment parameters are used to adjust the weights of different features in the scoring formula. Step S420, when the node backtracking window data and the node dynamic constraints are input into the master-slave node authentication network, the node backtracking window data is scored and processed through the scoring subnetwork, and the master-slave node authentication result is generated according to the scoring result and the node dynamic constraint. Specifically, the node backtracking window data and node dynamic constraints are input into the master-slave node authentication network, and the node backtracking window data is scored through the scoring sub-network. The comprehensive score of each node is calculated according to the scoring formula and adjustment parameters. The master-slave node authentication result is generated according to the scoring result and the node dynamic constraints. The authentication result includes which nodes are selected as master nodes, which nodes are selected as slave nodes, and the master-slave relationship between the master node and the slave node. This implementation method establishes a scoring sub-network to perform comprehensive scoring processing on the node backtracking window data, accurately evaluates the performance status, load capacity, response speed and other factors of each node, and achieves a technical effect that helps to reasonably allocate node roles and tasks.

[0047] In a possible implementation, the master-slave node authentication result is generated according to the scoring result and the node dynamic constraint, and step S420 further includes step S421, parsing the node dynamic constraint, establishing a ratio constraint and a threshold constraint. Specifically, the node dynamic constraint is a constraint condition that needs to be considered in the node authentication process and changes with time or conditions, including time constraints (within a specific time period), performance constraints (CPU usage, memory usage upper limit), task constraints (ability to handle specific types of tasks), etc. Parse these constraints, convert them into quantifiable indicators or parameters, and establish ratio constraints and threshold constraints. Among them, the ratio constraint is a relative ratio relationship of a certain attribute or capability between nodes determined according to business requirements and system design. For example, the CPU usage of the master node should be lower than a certain proportion of the slave node, or the number of tasks processed by the master node should account for a certain proportion of the number of tasks of all nodes. Threshold constraints refer to absolute restrictions on node attributes or capabilities. For example, the CPU usage of the node must not exceed a certain threshold, or the response time of the node must be less than a certain threshold. Step S422, reconstruct the discriminant subnetwork through the proportion constraint and the threshold constraint, and the discriminant subnetwork is the processing subnetwork of the master-slave node authentication network. Specifically, the proportion constraint and threshold constraint obtained by parsing are integrated into the discriminant subnetwork, and the discriminant subnetwork is a processing subnetwork in the master-slave node authentication network for discriminating according to the scoring results and the node dynamic constraints. According to the specific requirements of the constraint conditions, adjust the structure and parameters of the discriminant subnetwork. For example, add additional neurons or layers to process the logical operation of the proportion constraint, or modify the activation function to meet the nonlinear characteristics of the threshold constraint. Step S423, perform collaborative discriminant authentication of the scoring results according to the reconstructed discriminant subnetwork, and generate the master-slave node authentication result. Specifically, the scoring result obtained by the scoring subnetwork in step S420 is input into the reconstructed discriminant subnetwork, and the discriminant subnetwork combines the scoring results and the node dynamic constraints (proportional constraints and threshold constraints) to comprehensively discriminate the nodes, and calculate the probability or score of each node meeting the master-slave node conditions through the forward propagation and reverse propagation of the network. According to the output of the discriminant subnetwork, the master-slave node authentication result is generated. This implementation method achieves the coordinated judgment of scoring results and constraint conditions by analyzing node dynamic constraints and establishing proportion constraints and threshold constraints, achieving the technical effect of improving the accuracy and reliability of master-slave node authentication.

[0048] Step S500, establish the master-slave correlation mapping of the park Internet of Things platform according to the master-slave node authentication result, and complete the architecture configuration of the park Internet of Things platform. Specifically, from the obtained master-slave node authentication result, parse out the role of each node (master node or slave node) and the potential relationship between the roles. Analyze the priority sorting, task allocation suggestions and other information in the master-slave node authentication result to prepare for the master-slave correlation mapping. According to the parsed master-slave node authentication result, use the graph theory method to construct the master-slave relationship diagram between the nodes in the park Internet of Things platform. In the master-slave relationship diagram, the master node has a higher priority and more resource allocation rights, and has the ability to manage and control the slave node. The slave node executes the task according to the instruction of the master node. The master-slave relationship diagram represents the hierarchy and dependency relationship between the nodes. Based on the constructed master-slave relationship diagram, a group of slave nodes are assigned to each master node to form a master-slave pair or a master-slave group. This mapping relationship is used to ensure that the master node can effectively manage and schedule its slave nodes to achieve efficient execution of tasks. According to the established master-slave correlation mapping, the architecture of the campus IoT platform is configured, including setting the node communication protocol, data exchange format, task scheduling strategy, etc., to ensure that the platform architecture can support real-time communication and data sharing between master and slave nodes, as well as dynamic allocation and scheduling of tasks.

[0049] Step S600, the campus Internet of Things platform with completed architecture configuration receives real-time tasks, performs balanced authentication of node data flow through the real-time tasks and master-slave correlation mapping, and generates a digital control plan based on the balanced authentication result. Specifically, the campus Internet of Things platform with completed architecture configuration receives real-time task requests from enterprise users, department managers or other systems. The received real-time tasks are parsed to extract key information of the tasks, such as task type, priority, required resources, etc., and the tasks are assigned to the appropriate master nodes according to the master-slave correlation mapping. The master nodes are responsible for further decomposition and scheduling of the tasks.

[0050] During the task allocation process, the node data flow is balanced and authenticated based on the current load, processing capacity, resource status, etc. of each node. Use load balancing algorithms (such as polling, minimum number of connections, IP hash, etc.) or scheduling strategies (such as prediction-based scheduling, dynamic priority adjustment, etc.) to ensure that tasks are evenly distributed to each slave node to avoid overloading some nodes while other nodes are idle.

[0051] The slave node executes the task according to the instruction of the master node. During the execution process, the master node and the platform administrator can monitor the execution status, progress and resource consumption of the task in real time. If the task execution is abnormal or the resources are insufficient, the master node can dynamically adjust the task allocation or trigger the resource scheduling mechanism to ensure the smooth execution of the task. According to the results of task execution, monitoring data and user feedback, a digital control scheme is generated, including task scheduling strategy, resource allocation optimization, fault warning and response mechanism, etc., to improve the operation efficiency of the park, reduce costs and enhance user experience. The generated digital control scheme is implemented in the park Internet of Things platform, and its implementation effect is monitored. According to the feedback results, the scheme is continuously adjusted and optimized to ensure that it adapts to the changes in the actual operation needs of the target park. The embodiment of the present application adopts the method of reading the basic information of the park, establishing hardware interface information and business information, performing multi-node cluster configuration, establishing a park Internet of Things platform, establishing node dynamic constraints according to the park task flow, and obtaining the backtracking window data of each node, using the master-slave node authentication network to intelligently evaluate and assign roles to the nodes, realize the balanced authentication of the node data flow, and generate a digital control scheme according to the balanced authentication results. Technical means such as the above have achieved the technical effect of realizing the optimal configuration and efficient utilization of park resources through intelligent management and scheduling.

[0052] In a possible implementation, the node data flow is balanced authenticated by the real-time task and the master-slave correlation mapping, and a digital control scheme is generated according to the balanced authentication result. Step S600 further includes step S610, establishing node congestion perception of each node through the node data flow. Specifically, the data flow information of each node is collected in real time, including indicators such as the sending rate, receiving rate, packet loss rate, and delay time of the data packet. Based on the collected data flow information, the congestion degree of each node is calculated by a mathematical model or algorithm, such as calculating the congestion index by weighting the packet loss rate and the delay time, or evaluating by using relevant parameters in the flow control algorithm (such as the congestion control mechanism of TCP). According to the calculated congestion index, the state of each node is divided into different congestion levels, such as "no congestion", "mild congestion", "moderate congestion" and "severe congestion".

[0053] Step S620, based on the master-slave correlation mapping and node congestion perception, a balanced coordination evaluation is performed, a balanced authentication result is established, a coordination scheme is generated through the balanced authentication result, and the coordination scheme is used as a digital control scheme. Specifically, according to the master-slave correlation mapping, the dependency and priority between the nodes are determined, and which nodes are core nodes (master nodes) and which nodes are slave nodes (slave nodes) are identified. Combined with the node congestion perception results, it is analyzed which nodes' congestion status will affect the performance or stability of the entire system. According to the analysis results, a balanced coordination strategy is formulated, aiming to reduce or eliminate congestion by adjusting data flow allocation, optimizing resource use or implementing flow control and other measures. The balanced coordination strategy is simulated or tested on a small scale to evaluate its effect, and a balanced authentication result is established based on the test results. The balanced authentication result is a verification and confirmation of the effectiveness of the strategy. According to the balanced authentication result, the balanced coordination strategy is converted into a specific digital control scheme, including specific parameter settings (such as the sending interval of the data packet, the routing selection strategy, etc.), resource allocation scheme or flow control instructions, etc. The digital control scheme is deployed to the system, and its implementation effect is monitored in real time. According to the monitoring results, the scheme is adjusted and optimized when necessary. This implementation method realizes the refined management and dynamic adjustment of network resources by real-time perception of the congestion status of node data flow and conducting balanced coordination evaluation based on the master-slave correlation between nodes, achieving the technical effect of optimizing the performance and stability of the entire system.

[0054] In a possible implementation, the balanced coordination evaluation is performed based on the master-slave correlation mapping and node congestion perception, and step S620 further includes step S621, establishing a basic collaborative association value between nodes according to the master-slave correlation mapping. Specifically, the master-slave correlation mapping is parsed to determine the master-slave relationship between each node, that is, which nodes are master nodes (control or dependent centers) and which nodes are slave nodes (controlled or dependent objects). Based on the master-slave relationship, the collaborative association between each node is evaluated based on the frequency of data transmission between nodes, the complexity of data exchange, the closeness of mutual dependence, etc., and the evaluated collaborative association is quantified into a specific value, that is, the basic collaborative association value, which reflects the closeness of collaborative work between nodes under normal or ideal conditions. Step S622, the increase load evaluation of each node is performed through the node congestion perception, and an increase penalty coefficient is established. Specifically, according to the result of node congestion perception, the current congestion state of each node is analyzed, including congestion level, congestion duration, etc. It is evaluated that if the load continues to be added to a certain node (such as increasing the amount of data transmission, increasing the frequency of processing requests, etc.), the node will face additional pressure. Based on the evaluation result of the increased load, an increased penalty coefficient is calculated, and the increased penalty coefficient reflects the degree of negative impact such as system performance degradation and increased stability risk caused by continuing to increase the load on the node. Step S623, the balanced coordination evaluation is completed according to the basic collaborative association value and the increased penalty coefficient. Specifically, the basic collaborative association value and the increased penalty coefficient are comprehensively evaluated to analyze the degree of coordination between nodes and the negative impact caused by the increased load. Based on the results of the comprehensive evaluation, the balanced coordination state of each node is evaluated, including determining which nodes need to reduce the load to alleviate congestion, and which nodes need to strengthen coordination to improve overall efficiency. According to the results of the balanced coordination evaluation, corresponding optimization suggestions or adjustment plans are generated, including adjusting the data transmission path, optimizing resource allocation, implementing flow control, etc. This implementation method quantifies the degree of coordination between nodes under normal conditions by establishing a basic collaborative association value, and evaluates the negative impact that may be caused by increasing the load by establishing an increased penalty coefficient. The two are combined for balanced coordination evaluation, achieving the technical effect of accurately identifying bottlenecks and potential risks in the system, thereby generating more scientific and reasonable optimization suggestions and adjustment plans.

[0055] In a possible implementation, step S600 further includes step S630, establishing disaster preparedness awareness of the park IoT platform. Specifically, a comprehensive risk assessment is conducted on the park IoT platform to identify potential natural disasters (such as earthquakes, floods), technical failures (such as hardware failures, network interruptions), human errors or malicious attacks, and other risk factors that may lead to data loss or system paralysis. Based on the risk assessment results, monitoring equipment or systems are deployed at key locations of the park IoT platform, such as environmental sensors (monitoring temperature, humidity, vibration, etc.), network monitoring tools (monitoring network traffic, delay, packet loss rate, etc.) and security audit systems (monitoring abnormal logins, data tampering, etc.). Data generated by the monitoring equipment or system is collected, and data analysis techniques (such as machine learning, statistical analysis) are used to process and analyze the data to identify potential disaster preparedness risks. Once an abnormality is found or a preset threshold is reached, an early warning mechanism is immediately triggered to execute emergency response measures. Step S640, off-site backup constraints are configured through the disaster preparedness awareness, and periodic backup of storage data in the park IoT platform is performed through the off-site backup constraints. Specifically, based on the results of disaster preparedness perception, formulate off-site backup strategies, including determining the scope of backup data (which data needs to be backed up), the frequency of backup (daily, weekly, monthly, etc.), the location of backup (select a location geographically far away from the original data center to reduce the risk of simultaneous disasters), and the method of backup (such as full backup, incremental backup, differential backup, etc.). According to the off-site backup strategy, configure the corresponding off-site backup constraints, including the security requirements for data transmission (such as encrypted transmission), the integrity verification mechanism of backup data (such as hash verification), the recovery drill cycle of backup data, etc. According to the configured off-site backup constraints, automatically or manually perform periodic data backup tasks. During the backup process, record the detailed information of the backup, such as the backup time, the amount of backup data, the backup status, etc., and regularly verify the backup data to ensure the availability and integrity of the backup data. At the same time, according to the verification results and the development and changes of the campus IoT platform, continuously optimize the off-site backup strategy and constraints to adapt to new backup needs and risk changes. This implementation method establishes disaster preparedness awareness and configures off-site backup constraints on the campus IoT platform. When a serious failure or catastrophic event occurs in the original data center, the system can be quickly restored through off-site backup data, reducing losses and impacts, thereby achieving the technical effect of improving data security and system reliability.

[0056] In a possible implementation, step S600 further includes step S650, certifying the control effect of digital control of the target park and establishing a certification mark. Specifically, according to the characteristics of the target park and the goals of digital control, a set of evaluation index systems are formulated, including production efficiency improvement rate, energy consumption reduction rate, operating cost reduction rate, customer satisfaction improvement, etc. Through means such as the Internet of Things platform and big data analysis tools, relevant data of the target park before and after digital control are collected, and these data are compared and analyzed to evaluate the actual effect of digital control. Based on the data analysis results, the effect of digital control is certified. If it reaches or exceeds the preset evaluation index, it is considered that digital control has achieved significant results, and a certification mark is established for the certified digital control project. Step S660, perform common feedback extraction of the certification mark, and optimize the control of the park Internet of Things platform based on the common feedback extraction results. Specifically, collect and analyze user feedback, expert evaluation and other information of the digital control project of the park that has obtained the certification mark, extract common problems and improvement suggestions therein, and the common feedback may include technical implementation, user experience, cost control and other aspects. Based on the results of common feedback extraction, the control and optimization needs of the park's IoT platform are analyzed to determine the specific links, goals, and challenges that need to be optimized. According to the results of the control and optimization needs analysis, an optimization plan is formulated, including optimization goals, specific measures, implementation steps, time plans, etc. According to the requirements of the optimization plan, the park's IoT platform is regulated and optimized. This implementation method can timely discover and solve the problems and deficiencies in the digital construction of the target park through the certification of digital control effects and the extraction of common feedback, achieving the technical effect of continuously optimizing and improving the park's IoT platform.

[0057] In the above, refer to Figure 1 A digital control method for a smart park according to an embodiment of the present invention is described in detail. Figure 2 A digital control system for a smart park according to an embodiment of the present invention is described.

[0058] A digital control system for a smart park according to an embodiment of the present invention is used to solve the technical problem of the lack of intelligent decision-making ability in the existing digital control of smart parks, which leads to low utilization of park resources, and achieves the technical effect of optimizing the allocation and efficient utilization of park resources through intelligent management and scheduling. A digital control system for a smart park includes: a park basic information analysis module 10, a multi-node cluster configuration module 20, a node dynamic constraint establishment module 30, a master-slave node authentication module 40, an architecture configuration module 50, and a digital control scheme generation module 60.

[0059] The park basic information parsing module 10 is used to read the park basic information of the target park, parse the park basic information, and establish hardware interface information and business information; the multi-node cluster configuration module 20 is used to configure the multi-node cluster according to the business information and hardware interface information, and establish a park Internet of Things platform; the node dynamic constraint establishment module 30 is used to obtain the park task flow of the target park, establish node dynamic constraints according to the park task flow, and obtain the node backtracking window data of each node in the multi-node cluster; the master-slave node authentication module 40 is used to input the node backtracking window data and node dynamic constraints into the master-slave node authentication network to generate a master-slave node authentication result; the architecture configuration module 50 is used to establish the master-slave correlation mapping of the park Internet of Things platform according to the master-slave node authentication result, and complete the architecture configuration of the park Internet of Things platform; the digital control scheme generation module 60 is used to receive real-time tasks through the park Internet of Things platform with completed architecture configuration, perform balanced authentication of node data flow through the real-time tasks and master-slave correlation mapping, and generate a digital control scheme according to the balanced authentication result.

[0060] The specific configuration of the master-slave node authentication module 40 will be described in detail below. As described above, the node traceback window data and the node dynamic constraint are input into the master-slave node authentication network to generate the master-slave node authentication result. The master-slave node authentication module 40 may further include: a scoring subnetwork establishment unit for establishing a scoring subnetwork, the scoring subnetwork being a processing subnetwork of the master-slave node authentication network, and the scoring subnetwork is as follows: ;

[0061] in, represents the score of the i-th node, Characterizes the CPU usage of the i-th node, Characterizes the periodic change of CPU usage of the i-th node, Characterizes the memory usage of the i-th node, Characterizes the sharp change in memory usage of the i-th node, Represents the heartbeat signal of the i-th node, represents the load of the i-th node, Characterizes the periodic change of the load of the i-th node, Indicates the number of processing tasks of the i-th node, Characterizes the logarithmic change in the number of processing tasks of the i-th node, Characterizes the response time of the i-th node, Characterizes the sharp change in the response time of the i-th node, Characterizes the time node weight of the i-th node, , , , , , , They are adjustment parameters of the corresponding features respectively; the scoring processing unit is used to perform scoring processing on the node backtracking window data through the scoring sub-network after the node backtracking window data and the node dynamic constraints are input into the master-slave node authentication network, and generate the master-slave node authentication result according to the scoring result and the node dynamic constraints.

[0062] Among them, the master-slave node authentication result is generated according to the scoring result and the node dynamic constraint, and the scoring processing unit may further include: a node dynamic constraint parsing subunit is used to parse the node dynamic constraint, and establish a proportional constraint and a threshold constraint; a discriminant subnetwork reconstruction subunit is used to reconstruct the discriminant subnetwork through the proportional constraint and the threshold constraint, and the discriminant subnetwork is a processing subnetwork of the master-slave node authentication network; a collaborative discriminant authentication subunit is used to perform collaborative discriminant authentication of the scoring result according to the reconstructed discriminant subnetwork, and generate a master-slave node authentication result.

[0063] The specific configuration of the digital control scheme generation module 60 will be described in detail below. As described above, the node data stream is balanced authenticated through the real-time task and the master-slave correlation mapping, and the digital control scheme is generated according to the balanced authentication result. The digital control scheme generation module 60 may further include: a node congestion perception establishment unit for establishing node congestion perception of each node through the node data stream; a balanced coordination evaluation unit for performing balanced coordination evaluation based on the master-slave correlation mapping and node congestion perception, establishing a balanced authentication result, generating a coordination scheme through the balanced authentication result, and using the coordination scheme as a digital control scheme.

[0064] Among them, the balanced coordination evaluation is performed based on the master-slave correlation mapping and node congestion perception, and the balanced coordination evaluation unit may further include: a basic collaborative association value establishment subunit is used to establish a basic collaborative association value between nodes according to the master-slave correlation mapping; an increased load evaluation subunit is used to perform increased load evaluation of each node through the node congestion perception, and establish an increased penalty coefficient; the balanced coordination evaluation subunit is used to complete the balanced coordination evaluation according to the basic collaborative association value and the increased penalty coefficient.

[0065] Among them, the digital control plan generation module 60 can further include: a disaster preparedness perception establishment unit is used to establish disaster preparedness perception of the park Internet of Things platform; an off-site backup constraint configuration unit is used to configure off-site backup constraints through the disaster preparedness perception, and perform periodic backup of storage data in the park Internet of Things platform through the off-site backup constraints.

[0066] Among them, the digital control scheme generation module 60 can further include: a control effect authentication unit for authenticating the control effect of the digital control of the target park and establishing a certification mark; a control optimization unit for performing common feedback extraction of the certification mark and performing control optimization of the park Internet of Things platform based on the common feedback extraction results.

[0067] A digital control system for a smart park provided by an embodiment of the present invention can execute a digital control method for a smart park provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0068] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0069] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A digital control method for a smart park, characterized in that: The method comprises: Read the park basic information of the target park, parse the park basic information, and establish hardware interface information and business information; Perform multi-node cluster configuration according to the business information and hardware interface information to establish a campus Internet of Things platform; Obtaining a park task flow of a target park, establishing node dynamic constraints according to the park task flow, and obtaining node backtracking window data of each node in a multi-node cluster; Inputting the node backtracking window data and node dynamic constraints into the master-slave node authentication network to generate a master-slave node authentication result; Establishing a master-slave correlation mapping of the campus Internet of Things platform according to the master-slave node authentication result, and completing the architecture configuration of the campus Internet of Things platform; The park IoT platform that has been configured with the architecture receives real-time tasks, performs balanced authentication of node data streams through real-time tasks and master-slave correlation mapping, and generates a digital control plan based on the balanced authentication results; The step of inputting the node backtracking window data and the node dynamic constraint into the master-slave node authentication network to generate the master-slave node authentication result includes: A scoring subnetwork is established. The scoring subnetwork is a processing subnetwork of the master-slave node authentication network. The scoring subnetwork is as follows: ； in, represents the score of the i-th node, Characterizes the CPU usage of the i-th node, Characterizes the periodic change of CPU usage of the i-th node, Characterizes the memory usage of the i-th node, Characterizes the sharp change in memory usage of the i-th node, Represents the heartbeat signal of the i-th node, represents the load of the i-th node, Characterizes the periodic change of the load of the i-th node, Indicates the number of processing tasks of the i-th node, Characterizes the logarithmic change in the number of processing tasks of the i-th node, Characterizes the response time of the i-th node, Characterizes the sharp change in the response time of the i-th node, Characterizes the time node weight of the i-th node, , , , , , , are the adjustment parameters of the corresponding features respectively; After the node backtracking window data and the node dynamic constraints are input into the master-slave node authentication network, the node backtracking window data is scored through the scoring subnetwork, and the master-slave node authentication result is generated according to the scoring result and the node dynamic constraints; The generating of the master-slave node authentication result according to the scoring result and the node dynamic constraint includes: Analyze the node dynamic constraints and establish ratio constraints and threshold constraints; Reconstructing the discriminant subnetwork through proportion constraints and threshold constraints, wherein the discriminant subnetwork is a processing subnetwork of the master-slave node authentication network; According to the reconstructed discriminant sub-network, the scoring results are collaboratively discriminated and authenticated to generate the master-slave node authentication results; The method of performing balanced authentication of node data streams through the real-time tasks and master-slave correlation mapping and generating a digital control scheme according to the balanced authentication result includes: Establish node congestion awareness of each node through node data flow; Performing a balanced coordination evaluation based on the master-slave correlation mapping and node congestion perception, establishing a balanced authentication result, generating a coordination plan through the balanced authentication result, and using the coordination plan as a digital control plan; The balanced coordination evaluation based on the master-slave correlation mapping and node congestion perception includes: Establishing a basic collaborative association value between nodes according to the master-slave correlation mapping; Performing load increase evaluation on each node through the node congestion perception and establishing an increase penalty coefficient; The balanced coordination evaluation is completed according to the basic synergistic association value and the added penalty coefficient.

2. A digital control method for a smart park as claimed in claim 1, characterized in that: The method further comprises: Establish disaster preparedness awareness for the campus IoT platform; The off-site backup constraints are configured through the disaster preparedness perception, and the storage data in the park Internet of Things platform is periodically backed up through the off-site backup constraints.

3. The digital control method of a smart park according to claim 1, characterized in that: The method further comprises: Certify the control effect of digital control on the target park and establish a certification mark; Perform common feedback extraction of authentication marks, and optimize the regulation of the park's Internet of Things platform based on the common feedback extraction results.

4. A digital control system for a smart park, characterized in that: The system is used to implement a digital control method for a smart park according to any one of claims 1 to 3, and the system comprises: A park basic information parsing module, which is used to read the park basic information of the target park, parse the park basic information, and establish hardware interface information and business information; A multi-node cluster configuration module, wherein the multi-node cluster configuration module is used to configure a multi-node cluster according to the business information and the hardware interface information to establish a campus Internet of Things platform; A node dynamic constraint establishment module, the node dynamic constraint establishment module is used to obtain a park task flow of a target park, establish node dynamic constraints according to the park task flow, and obtain node backtracking window data of each node in a multi-node cluster; A master-slave node authentication module, the master-slave node authentication module is used to input the node backtracking window data and node dynamic constraints into the master-slave node authentication network to generate a master-slave node authentication result; An architecture configuration module, the architecture configuration module is used to establish a master-slave correlation mapping of the park Internet of Things platform according to the master-slave node authentication result, and complete the architecture configuration of the park Internet of Things platform; A digital control scheme generation module is used to receive real-time tasks through the campus Internet of Things platform that has been completed through architecture configuration, perform balanced authentication of node data streams through the real-time tasks and master-slave correlation mapping, and generate a digital control scheme based on the balanced authentication results.

Images