Automatic control system and method for approval of integrated construction land

Abstract

The invention relates to the technical field of geographic information management, in particular to an automatic control system and method for approval of an integrated construction land. The method comprises the following steps: obtaining construction land state index data, and taking state indexes in the construction land state index data as nodes and taking a conversion relation between states as edges, thereby obtaining a state conversion map; state tracking based on a time sequence is carried out on pre-obtained land state historical data, and state conversion path mapping is carried out according to the state conversion map to obtain state conversion path data; performing evolution trend prediction on the state conversion path data to obtain state evolution prediction data; and initializing the semantic network by using the node and edge relationship in the state transition map to obtain the land state semantic network. According to the method, the consistency and the traceability of the approval process are ensured through automatic state consistency rule check.

Description

Technical Field

[0001] The present invention relates to the technical field of geographic information management, and in particular to an integrated construction land approval automation control system and method. Background Art

[0002] The integrated construction land approval automation control method usually refers to the use of modern information technology, such as cloud computing, big data, artificial intelligence, etc., to optimize and automate the land approval process, improve approval efficiency and accuracy, reduce human intervention, and achieve transparency and standardization of the approval process.

[0003] The traditional construction land approval process is complex and time-consuming. This process is prone to information asymmetry, poor communication, and duplicate approvals, resulting in overall inefficiency. Furthermore, construction land management and approval often lack efficient data management and analysis tools. Land status data is scattered across disparate systems, making unified data integration and analysis difficult, leading to a lack of data support in the decision-making process. The status of construction land is dynamic, including its planned use, usage, and approval progress. Traditional methods struggle to track and manage these dynamic changes in real time, impacting the accuracy and timeliness of approvals. Summary of the Invention

[0004] Based on this, it is necessary for the present invention to provide an integrated construction land approval automation control method and system to solve at least one of the above technical problems.

[0005] To achieve the above objectives, an integrated construction land approval automation control method includes the following steps:

[0006] Step S1: Acquire construction land status indicator data, and use the status indicators in the construction land status indicator data as nodes and the conversion relationships between states as edges, thereby obtaining a state transition graph;

[0007] Step S2: performing state tracking based on a time series on the pre-acquired land state historical data, and mapping the state transition path according to the state transition map to obtain state transition path data; performing evolution trend prediction on the state transition path data to obtain state evolution prediction data;

[0008] Step S3: Initialize the semantic network using the node and edge relationships in the state transition graph to obtain the land state semantic network; dynamically adjust the association strength in the land state semantic network according to the state evolution prediction data to obtain the state semantic association matrix;

[0009] Step S4: Design an initial workflow template based on the state transition path data, and set rules for the workflow decision points in the initial workflow template based on the state evolution prediction data to obtain the initial workflow template data; use the state semantic association matrix to optimize task allocation and parallelize the initial workflow template data to obtain the configuration template data of the dynamic workflow;

[0010] Step S5: Determine the state set that needs to be consistent based on the state semantic association matrix, and obtain the consistent state range data; determine the legal path set for state change through the configuration template data; integrate the consistent state range data and the legal path set into a global state consistent hash;

[0011] Step S6: Project the state relationship in the state semantic association matrix into the actual geographical environment through augmented reality technology, and verify the legitimacy of user operations based on the global state consistency hash to obtain the spatial state interaction log.

[0012] By collecting and organizing construction land status indicator data, the present invention can understand the current state of land and the transition relationships between different states. Constructing a state transition map can visually display the transition paths between different states, helping decision makers better understand the evolution of land states. Time series analysis of pre-acquired historical land state data can track changing trends in land states. Mapping state transition paths using the state transition map can predict the evolution of land states. This predicted data helps planners and decision makers make accurate decisions regarding future land management and planning. By constructing a land state semantic network using the state transition map, semantic associations between different states can be established. Dynamically adjusting the association strengths within the land state semantic network based on the state evolution prediction data can more accurately reflect the degree of association between land states. This facilitates a deeper understanding of subtle changes in land states and their mutual influence, providing more accurate information for subsequent decision-making. Designing an initial workflow template based on the state transition path data can define different tasks and processes for land management and planning. Setting rules for decision points within the workflow template based on the state evolution prediction data allows for flexible workflow adjustments based on varying state evolution scenarios. Optimizing task allocation and parallel processing can improve work efficiency and ensure tasks are completed at the appropriate time. By using the state semantic association matrix to identify the set of states that require consistency, it is possible to define related states that must maintain consistency during land state changes. By configuring template data to determine the set of legal state change paths, it is possible to specify the legal methods and sequence for land state changes. This helps ensure consistency and legality between various states during land management and planning. Using augmented reality technology, the state relationships in the state semantic association matrix are projected onto the actual geographic environment, visually presenting the relationships and changes between land states. Using global state consistent hashing to verify the legality of user operations ensures that users adhere to predefined consistency and legality requirements when performing land management and planning operations. This improves decision makers and planners' understanding of land states and the accuracy of their operations. In summary, the above steps provide a better understanding of land state evolution, accurately predict land state change trends, establish semantic associations between land states, optimize task allocation and workflows, ensure the consistency and legality of land state changes, and provide intuitive visualization and user operation verification through augmented reality. These effects can help improve decision-making quality and efficiency in land management and planning, reduce errors and conflicts, and support sustainable land use.

[0013] The present invention also provides an integrated construction land approval automation control system for executing the above-mentioned integrated construction land approval automation control method. The integrated construction land approval automation control system includes:

[0014] A state graph construction module is used to obtain construction land state indicator data, and use the state indicators in the construction land state indicator data as nodes and the conversion relationships between states as edges to obtain a state transition graph;

[0015] The time series prediction and analysis module is used to track the state of pre-acquired historical land state data based on the time series, and map the state transition path according to the state transition map to obtain state transition path data; and predict the evolution trend of the state transition path data to obtain state evolution prediction data;

[0016] The semantic network optimization module is used to initialize the semantic network using the node and edge relationships in the state transition graph to obtain the land state semantic network; dynamically adjust the association strength in the land state semantic network based on the state evolution prediction data to obtain the state semantic association matrix;

[0017] The workflow intelligent configuration module is used to design the initial workflow template based on the state transition path data, and set rules for the workflow decision points in the initial workflow template based on the state evolution prediction data to obtain the initial workflow template data; the module uses the state semantic association matrix to optimize the task allocation and parallelize the initial workflow template data to obtain the configuration template data of the dynamic workflow;

[0018] The global consistency maintenance module is used to determine the state set that needs to be consistent based on the state semantic association matrix and obtain the consistency state range data; determine the legal path set for state change through configuration template data; and integrate the consistency state range data and legal path set into a global state consistency hash;

[0019] The spatial interaction verification module is used to project the state relationship in the state semantic association matrix into the actual geographical environment through augmented reality technology, and verify the legitimacy of user operations based on the global state consistency hash, thereby obtaining the spatial state interaction log.

[0020] The present invention constructs a state transition graph by acquiring construction land status indicator data, using the status indicators as nodes and the transition relationships between states as edges. The state transition graph clearly displays the transition relationships between construction land states, helping users understand the patterns and trends of state changes. The state graph can serve as input data for subsequent modules, providing a foundation for time series prediction analysis, semantic network optimization, and intelligent workflow configuration. The time series prediction analysis module uses pre-acquired historical land status data to track states based on time series and map state transition paths according to the state transition graph. Through time series prediction analysis, future land state evolution trends can be predicted and their development can be forecasted. This helps decision makers more accurately predict land state changes when making plans and decisions, allowing them to take appropriate measures in advance. The semantic network optimization module uses the node and edge relationships in the state transition graph to initialize a semantic network, generating a land state semantic network. This semantic network can better represent the semantic associations and interactions between land states. Based on the state evolution prediction data, the association strengths in the land state semantic network are dynamically adjusted to generate a state semantic association matrix. This helps improve the accuracy and reliability of state associations, providing more precise state semantic association information for subsequent intelligent workflow configuration. The intelligent workflow configuration module designs the initial workflow template based on state transition path data and sets rules for workflow decision points based on state evolution prediction data, generating the initial workflow template data. Using the state semantic association matrix, the initial workflow template data is optimized for task allocation and parallel processing, generating configuration template data for dynamic workflows. This facilitates intelligent workflow configuration and optimization, improving workflow execution efficiency and accuracy. The global consistency maintenance module determines the set of states that must maintain consistency based on the state semantic association matrix, generating consistent state range data. The configuration template data determines the set of legal state change paths and integrates the consistent state range data and the legal path set into a global state consistency hash. The global state consistency hash serves as a marker for workflow state consistency verification and can be used to verify whether user operations meet state consistency requirements, improving workflow reliability and correctness. The spatial interaction verification module uses augmented reality technology to project the state relationships in the state semantic association matrix into the actual geographic environment and verifies the legitimacy of user operations based on the global state consistency hash, generating a spatial state interaction log. Spatial interaction verification ensures that users adhere to state relationship requirements and maintain state consistency during interaction. Spatial state interaction logs record user interaction behaviors, providing a basis for workflow improvement and analysis.In summary, the effects of the above steps include: the state graph construction module converts construction land state indicator data into a state transition graph, helping users intuitively understand the transition relationships and patterns between construction land states; the time series prediction analysis module provides future land state evolution trend forecasts through time series-based state tracking and state transition path mapping, helping decision makers more accurately predict land state changes when making plans and decisions; the semantic network optimization module uses the state transition graph and evolution prediction data to initialize the land state semantic network and dynamically adjust the association strength between states, improving the accuracy and reliability of state associations; the workflow intelligent configuration module designs the initial workflow template based on state transition path data and sets rules for workflow decision points based on state evolution prediction data, improving workflow execution efficiency and accuracy through task allocation optimization and parallel processing; the global consistency maintenance module maintains workflow state consistency by determining consistent state range data and legal path sets, improving workflow reliability and correctness; and the spatial interaction verification module uses augmented reality technology to project state relationships into the actual geographic environment and verify the legitimacy of user operations based on the global state consistency hash, ensuring that users comply with state relationship requirements and improving workflow reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0022] Figure 1 This is a schematic diagram of the steps of the integrated construction land approval automation control method of the present invention;

[0023] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0024] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION

[0025] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0027] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 The present invention provides an integrated construction land approval automation control method, which includes the following steps:

[0029] Step S1: Acquire construction land status indicator data, and use the status indicators in the construction land status indicator data as nodes and the conversion relationships between states as edges, thereby obtaining a state transition graph;

[0030] Step S2: performing state tracking based on a time series on the pre-acquired land state historical data, and mapping the state transition path according to the state transition map to obtain state transition path data; performing evolution trend prediction on the state transition path data to obtain state evolution prediction data;

[0031] Step S3: Initialize the semantic network using the node and edge relationships in the state transition graph to obtain the land state semantic network; dynamically adjust the association strength in the land state semantic network according to the state evolution prediction data to obtain the state semantic association matrix;

[0032] Step S4: Design an initial workflow template based on the state transition path data, and set rules for the workflow decision points in the initial workflow template based on the state evolution prediction data to obtain the initial workflow template data; use the state semantic association matrix to optimize task allocation and parallelize the initial workflow template data to obtain the configuration template data of the dynamic workflow;

[0033] Step S5: Determine the state set that needs to be consistent based on the state semantic association matrix, and obtain the consistent state range data; determine the legal path set for state change through the configuration template data; integrate the consistent state range data and the legal path set into a global state consistent hash;

[0034] Step S6: Project the state relationship in the state semantic association matrix into the actual geographical environment through augmented reality technology, and verify the legitimacy of user operations based on the global state consistency hash to obtain the spatial state interaction log.

[0035] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of the integrated construction land approval automation control method of the present invention. In this example, the integrated construction land approval automation control method includes the following steps:

[0036] Step S1: Acquire construction land status indicator data, and use the status indicators in the construction land status indicator data as nodes and the conversion relationships between states as edges, thereby obtaining a state transition graph;

[0037] This embodiment of the present invention collects construction land status indicator data, which can be obtained through surveys, monitoring, sensors, and other methods. The status indicators are then used as nodes in a graph, and the transition relationships between states are used as edges. Transition rules between states can be defined based on domain knowledge and expert experience. Finally, a graph construction tool (such as the network graph library Neo4j or a graph database) is used to create a state transition graph.

[0038] Step S2: performing state tracking based on a time series on the pre-acquired land state historical data, and mapping the state transition path according to the state transition map to obtain state transition path data; performing evolution trend prediction on the state transition path data to obtain state evolution prediction data;

[0039] This embodiment of the present invention uses time series analysis methods, such as ARIMA models and exponential smoothing, to track the state of pre-acquired historical land state data. The state tracking results are then mapped into state transition path data based on a state transition map. Evolutionary trend prediction of this state transition path data can be performed using time series prediction methods (such as ARIMA and exponential smoothing) or machine learning methods (such as regression and neural networks).

[0040] Step S3: Initialize the semantic network using the node and edge relationships in the state transition graph to obtain the land state semantic network; dynamically adjust the association strength in the land state semantic network according to the state evolution prediction data to obtain the state semantic association matrix;

[0041] In this embodiment, a semantic network is initialized using the node and edge relationships in the state transition graph. Graph analysis tools (such as NetworkX and Gephi) can be used to construct and visualize the semantic network. Based on the state evolution prediction data, the strength of the associations between states in the semantic network can be adjusted based on the prediction results, for example, by increasing or decreasing edge weights.

[0042] Step S4: Design an initial workflow template based on the state transition path data, and set rules for the workflow decision points in the initial workflow template based on the state evolution prediction data to obtain the initial workflow template data; use the state semantic association matrix to optimize task allocation and parallelize the initial workflow template data to obtain the configuration template data of the dynamic workflow;

[0043] In this embodiment of the present invention, an initial workflow template is designed based on state transition path data. Process modeling tools (such as BPMN tools) can be used for visual design. Based on the state evolution prediction data, rules are set for decision points in the workflow template. For example, rules can be configured using a rule engine (such as Drools or Jess). Task allocation and parallel processing can be optimized for the workflow template. Workflow management systems (such as Activiti or Camunda) can be used for task allocation and process optimization.

[0044] Step S5: Determine the state set that needs to be consistent based on the state semantic association matrix, and obtain the consistent state range data; determine the legal path set for state change through the configuration template data; integrate the consistent state range data and the legal path set into a global state consistent hash;

[0045] In an embodiment of the present invention, the set of states that need to be consistent is determined based on the state semantic association matrix, and the consistency state set can be defined using rules. The set of legal paths for state changes is determined by configuring template data, and the state change path can be defined using methods such as state machines and decision trees. The consistency state range data and the legal path set are integrated into a global state consistency hash, and a hash algorithm (such as SHA-256) can be used to calculate the global state consistency hash value.

[0046] Step S6: Project the state relationship in the state semantic association matrix into the actual geographical environment through augmented reality technology, and verify the legitimacy of user operations based on the global state consistency hash to obtain the spatial state interaction log.

[0047] Embodiments of the present invention use augmented reality technology to project the state relationships in the state semantic association matrix into the actual geographic environment. This projection and visualization can be performed using augmented reality frameworks (such as ARKit and ARCore). User operations are validated based on a global state consistent hash. A verification module can be embedded in the user interface to verify the legitimacy of user operations by comparing them with the global state consistent hash value. The verification module can be implemented using programming languages and frameworks, such as JavaScript and web development frameworks (such as React and Angular) to build the user interface and verification logic. When a user performs an operation, the verification module obtains state information related to the user operation and calculates the corresponding local state consistent hash value. The calculated local state consistent hash value is then compared with the global state consistent hash value. If the two values match, the user operation is valid; if they do not match, the user operation is invalid, and a corresponding prompt can be given or the user can be prevented from continuing. The verification module can also log the user's spatial state interactions. Logging can be performed using a logging library or framework, such as a Python logging library (such as logging) or other logging tools, to record user operations and verification results in a log file or database.

[0048] By collecting and organizing construction land status indicator data, the present invention can understand the current state of land and the transition relationships between different states. Constructing a state transition map can visually display the transition paths between different states, helping decision makers better understand the evolution of land states. Time series analysis of pre-acquired historical land state data can track changing trends in land states. Mapping state transition paths using the state transition map can predict the evolution of land states. This predicted data helps planners and decision makers make accurate decisions regarding future land management and planning. By constructing a land state semantic network using the state transition map, semantic associations between different states can be established. Dynamically adjusting the association strengths within the land state semantic network based on the state evolution prediction data can more accurately reflect the degree of association between land states. This facilitates a deeper understanding of subtle changes in land states and their mutual influence, providing more accurate information for subsequent decision-making. Designing an initial workflow template based on the state transition path data can define different tasks and processes for land management and planning. Setting rules for decision points within the workflow template based on the state evolution prediction data allows for flexible workflow adjustments based on varying state evolution scenarios. Optimizing task allocation and parallel processing can improve work efficiency and ensure tasks are completed at the appropriate time. By using the state semantic association matrix to identify the set of states that require consistency, it is possible to define related states that must maintain consistency during land state changes. By configuring template data to determine the set of legal state change paths, it is possible to specify the legal methods and sequence for land state changes. This helps ensure consistency and legality between various states during land management and planning. Using augmented reality technology, the state relationships in the state semantic association matrix are projected onto the actual geographic environment, visually presenting the relationships and changes between land states. Using global state consistent hashing to verify the legality of user operations ensures that users adhere to predefined consistency and legality requirements when performing land management and planning operations. This improves decision makers and planners' understanding of land states and the accuracy of their operations. In summary, the above steps provide a better understanding of land state evolution, accurately predict land state change trends, establish semantic associations between land states, optimize task allocation and workflows, ensure the consistency and legality of land state changes, and provide intuitive visualization and user operation verification through augmented reality. These effects can help improve decision-making quality and efficiency in land management and planning, reduce errors and conflicts, and support sustainable land use.

[0049] Preferably, step S1 includes the following steps:

[0050] Step S11: collecting original construction land status indicator data through the land management system, land planning database and environmental monitoring system;

[0051] Step S12: classifying the construction land status indicator data and assigning a unique code to each type of status indicator, thereby obtaining a status indicator classification code table;

[0052] Step S13: defining each state indicator as a node according to the state indicator classification code table to obtain a state node set; analyzing the state change sequence in the pre-acquired historical data and identifying the state transition relationship, thereby defining transition conditions and constraints to obtain a state transition relationship set;

[0053] Step S14: importing the state node set into a preset graph database, and importing the state transition relationship set into the graph database as edges, thereby obtaining an initial state transition graph;

[0054] Step S15: Identify isolated nodes and subgraphs on the initial state transition graph, and optimize the connectivity of the graph to obtain a state transition graph.

[0055] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in the embodiment of the present invention, step S1 includes the following steps:

[0056] Step S11: collecting original construction land status indicator data through the land management system, land planning database and environmental monitoring system;

[0057] The present invention collects raw construction land status indicator data by interacting with or extracting data from land management systems, land planning databases, and environmental monitoring systems. These systems and databases may have different data interfaces and formats, so it is necessary to select appropriate data extraction methods and tools based on the specific situation, such as using database query languages (such as SQL) or API calls.

[0058] Step S12: classifying the construction land status indicator data and assigning a unique code to each type of status indicator, thereby obtaining a status indicator classification code table;

[0059] The present invention classifies construction land status indicators according to their characteristics and meanings, and assigns a unique code to each type of status indicator. Data classification and coding operations can be performed using data processing tools and programming languages, such as a data processing library (such as pandas) in the Python programming language, or using specialized data processing tools (such as Excel).

[0060] Step S13: defining each state indicator as a node according to the state indicator classification code table to obtain a state node set; analyzing the state change sequence in the pre-acquired historical data and identifying the state transition relationship, thereby defining transition conditions and constraints to obtain a state transition relationship set;

[0061] In this embodiment, each state indicator is defined as a node in a graph based on a classification code table for state indicators, and a state node set is constructed. Based on the state change sequence in pre-acquired historical data, the transition relationships between states are analyzed. Based on the analysis results, transition conditions and constraints are defined to construct a state transition relationship set. This can be achieved through data analysis and modeling methods, such as using the Python programming language for data analysis and pattern recognition, or using graph analysis tools (such as NetworkX) for graph construction and state transition relationship identification.

[0062] Step S14: importing the state node set into a preset graph database, and importing the state transition relationship set into the graph database as edges, thereby obtaining an initial state transition graph;

[0063] In this embodiment, based on a pre-defined graph database interface and data import method, a set of state nodes is imported into the graph database, and a set of state transition relationships is imported as edges into the graph database. This can be accomplished using the import tools, APIs, or programming interfaces provided by the graph database, such as using the Cypher query language of the Neo4j graph database to perform data import operations.

[0064] Step S15: Identify isolated nodes and subgraphs on the initial state transition graph, and optimize the connectivity of the graph to obtain a state transition graph.

[0065] This embodiment of the present invention identifies isolated nodes and subgraphs in the initial state transition graph, finds isolated nodes without incoming or outgoing edges, and removes them from the graph. Then, graph algorithms and connectivity analysis methods are used to optimize the graph's connectivity, ensuring that all nodes are connected by paths. This can be achieved using graph analysis tools and algorithms, such as the NetworkX library, for isolated node and connectivity analysis.

[0066] The present invention collects raw construction land status indicator data through a land management system, a land planning database, and an environmental monitoring system, obtaining information on land use type, land quality, and land use intensity. This data is fundamental to land management and planning, helping to understand the current state of land and potential issues. Classifying construction land status indicator data allows similar indicators to be grouped together, facilitating subsequent data processing and analysis. Assigning a unique code to each status indicator ensures accurate identification and recognition of each status indicator in subsequent state transition relationship definition and data processing. According to the status indicator classification code table, each status indicator is defined as a node, forming a state node set. By analyzing the state change sequence in pre-acquired historical data, the transition relationships between different states, including transition conditions and constraints, can be identified. This helps establish correlations between states and provides a basis for land state transitions. Importing the state node set and transition relationship set into a pre-set graph database allows the state indicators and transition relationships to be stored and managed in a graph format. The graph database offers efficient graph query and analysis capabilities, facilitating query and manipulation of state nodes and transition relationships. The initial state transition graph provides the foundation for subsequent graph analysis and optimization. By identifying isolated nodes and subgraphs in the initial state transition graph, we can identify isolated nodes that are not connected to other nodes, allowing us to analyze and process these nodes. By optimizing the graph's connectivity, we ensure that the state transition graph is a complete, connected structure, with every node connected to every other node. This helps improve the reliability and accuracy of subsequent state transition graphs.

[0067] Preferably, step S15 includes the following steps:

[0068] Step S151: traverse the initial state transition graph and check the in-degree and out-degree of each node. If both the in-degree and out-degree of a node are 0, mark it as an isolated node to obtain an isolated node set.

[0069] This embodiment of the present invention traverses the initial state transition graph and checks the in-degree and out-degree of each node. If both the in-degree and out-degree of a node are 0, the node is marked as an isolated node and added to the isolated node set. This can be achieved using graph analysis tools and graph algorithms, such as the NetworkX library for graph traversal and node degree analysis.

[0070] Step S152: traverse the initial state transition graph based on the connectivity of the graph, and identify all maximal connected subgraphs to obtain a subgraph set;

[0071] This embodiment of the present invention traverses the initial state transition graph based on graph connectivity and identifies all maximal connected subgraphs. A maximal connected subgraph is one in which a path exists between any two nodes in the subgraph, and no additional nodes can be added to maintain connectivity. The identified maximal connected subgraphs are considered part of the subgraph set. This can be achieved using graph analysis tools and graph algorithms, such as the NetworkX library for graph connectivity analysis and subgraph identification.

[0072] Step S153: Perform cause analysis on the isolated node set and subgraph set to obtain disconnection cause data, wherein the cause analysis includes checking the corresponding data source to confirm whether there is an error in the data collection or processing process, confirming whether it is a legal but rare state or transition path, and checking whether the state or transition path is no longer applicable due to changes in regulations;

[0073] An embodiment of the present invention performs a cause analysis on isolated node sets and subgraph sets to identify the causes of disconnection. Cause analysis includes the following aspects: confirming whether there are errors in the data collection or processing process, such as missing data or incorrect data format; confirming whether the state or transition path is legal but rare, which may be caused by special circumstances or abnormal conditions; and checking whether the state or transition path is no longer applicable due to changes in regulations, which may require reference to the latest regulations and provisions. Based on the results of the cause analysis, disconnection cause data is obtained, that is, the specific reasons that lead to the disconnection of isolated nodes or subgraphs.

[0074] Step S154: Nodes are deleted for isolated node sets or subgraph sets whose disconnection causes data to be errors during data collection or processing; connection paths are designed for isolated node sets or subgraph sets whose disconnection causes data to be legal but rare states or transition paths; and "historical state" tags are added for isolated node sets or subgraph sets whose disconnection causes data to be states or transition paths that are no longer applicable due to changes in regulations, thereby obtaining a state transition map.

[0075] The embodiment of the present invention adopts corresponding processing methods according to the specific circumstances of the data causing the disconnection: for isolated nodes or subgraphs caused by errors in the data collection or processing process, you can choose to delete them or perform data correction. Deletion can be achieved by deleting the corresponding nodes and edges in the graph database, and data correction requires corresponding data processing operations based on the specific circumstances. For isolated nodes or subgraphs caused by legal but rare states or transition paths, new connection paths can be designed to connect them with other nodes or subgraphs to maintain connectivity. For isolated nodes or subgraphs whose states or transition paths are no longer applicable due to changes in regulations, a "historical state" mark can be added to indicate that it was a valid state or transition path in the past, but is no longer applicable in the current situation. Depending on the processing method, graph database operations, data processing tools, or programming languages can be used to implement the corresponding operations.

[0076] The present invention traverses the initial state transition graph and checks the in-degree and out-degree of each node. When both the in-degree and out-degree of a node are 0, it indicates that the node has no edges connecting to other nodes and is therefore an isolated node. These isolated nodes are marked and collected to form an isolated node set. This helps identify nodes without state transition relationships, allowing for further analysis and processing of these nodes. Based on the connectivity of the graph, the initial state transition graph is traversed to identify all maximal connected subgraphs. A maximal connected subgraph is a maximal connected subgraph in which a path exists between any two nodes. By identifying maximal connected subgraphs, the state transition graph can be segmented into multiple interconnected subgraphs, each representing a set of related states and transition relationships. This facilitates analysis and understanding of complex state transition graphs. Cause analysis is performed on the isolated node set and subgraph set to determine the cause of their disconnection. Cause analysis includes checking the corresponding data source to confirm whether there are errors in data collection or processing, confirming whether there are legal but rare states or transition paths, and checking whether the states or transition paths are no longer applicable due to regulatory changes. Cause analysis can identify disconnected data, providing a basis and guidance for subsequent processing. Based on the results of the cause analysis, nodes in isolated node sets or subgraph sets caused by data collection or processing errors are deleted. For disconnected data related to legal but rare states or transition paths, appropriate connection paths are designed to establish connections with other nodes or subgraphs. For disconnected data related to states or transition paths that are no longer applicable due to regulatory changes, a "historical state" tag is added to distinguish outdated states and transition paths. By processing disconnected data, the structure and connectivity of the state transition map can be revised, making it more accurate and complete.

[0077] Preferably, step S2 includes the following steps:

[0078] Step S21: Acquire historical land status data, cleanse the historical land status data, and sort the data based on time, thereby obtaining land status time series data;

[0079] Step S22: decomposing the land status time series data into trend, seasonality and residual components to obtain time series component data;

[0080] Step S23: constructing a state tracking model based on a hidden Markov model according to the time series component data and the state transition graph;

[0081] Step S24: Mapping the land state time series data to the path on the state transition map using the state tracking model, thereby obtaining state transition path data;

[0082] Step S25: extracting recurring state transition sequences from the state transition path data using a sequence pattern mining algorithm, thereby obtaining a set of time series patterns;

[0083] Step S26: performing evolution trend prediction on the time series pattern set to obtain state evolution prediction data.

[0084] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S2 in the embodiment of the present invention, step S2 includes the following steps:

[0085] Step S21: Acquire historical land status data, cleanse the historical land status data, and sort the data based on time, thereby obtaining land status time series data;

[0086] The present invention acquires historical land status data through various data sources, database queries, or data collection tools. The acquired data is cleaned, including addressing missing values, outliers, and duplicates. The data is then sorted based on time to ensure temporal order. This can be accomplished using data processing tools and programming languages, such as the pandas library in Python, for data cleaning and sorting.

[0087] Step S22: decomposing the land status time series data into trend, seasonality and residual components to obtain time series component data;

[0088] This embodiment of the present invention decomposes land status time series data using decomposition methods used in time series analysis, such as seasonal decomposition, trend decomposition, and residual decomposition. Common decomposition methods include STL decomposition and Holt-Winters decomposition. Through decomposition, time series data can be separated into trend, seasonal, and residual components, thereby generating time series component data. This can be achieved using time series analysis tools and libraries, such as the seasonal_decompose function in the statsmodels library.

[0089] Step S23: constructing a state tracking model based on a hidden Markov model according to the time series component data and the state transition graph;

[0090] Embodiments of the present invention utilize time series component data and a constructed state transition map to construct a state tracking model using a Hidden Markov Model (HMM). An HMM is a statistical model used to model random processes with hidden states. Based on the time series component data, parameters such as transition probabilities, observation probabilities, and initial state probabilities in the HMM can be estimated. This can be achieved using machine learning and statistical modeling tools, such as the HMM class in the HMMlearn library.

[0091] Step S24: Mapping the land state time series data to the path on the state transition map using the state tracking model, thereby obtaining state transition path data;

[0092] This embodiment of the present invention utilizes a constructed state tracking model to map land state time series data to paths on a state transition map. By performing state prediction and transition path inference on the time series data, state transition path data can be obtained. This can be achieved using an inference algorithm within the state tracking model, such as the Viterbi algorithm. The Viterbi algorithm finds the most likely state sequence corresponding to the path of the land state time series data on the state transition map.

[0093] Step S25: extracting recurring state transition sequences from the state transition path data using a sequence pattern mining algorithm, thereby obtaining a set of time series patterns;

[0094] The present invention utilizes a sequential pattern mining algorithm to analyze state transition path data and extract recurring state transition sequences, thereby obtaining a set of temporal patterns. Sequential pattern mining algorithms can discover frequently occurring patterns or sequences in sequence data. Commonly used sequential pattern mining algorithms include the Apriori algorithm, the Generalized Sequential Pattern (GSP) algorithm, and the PrefixSpan algorithm. These algorithms can extract frequently occurring state transition sequences based on the repetitive nature of sequences in state transition path data.

[0095] Step S26: performing evolution trend prediction on the time series pattern set to obtain state evolution prediction data.

[0096] The present invention utilizes a set of time series patterns to predict evolutionary trends. Time series analysis and forecasting methods, such as the ARIMA model (Autoregressive Integrated Moving Average), exponential smoothing, and regression analysis, can be used. These methods can predict future state evolution based on the extracted set of time series patterns. The appropriate method can be selected based on the specific situation and implemented using appropriate forecasting tools and libraries, such as the ARIMA model in the statsmodels library.

[0097] By acquiring historical data on land conditions, the present invention can obtain a series of time series data on land conditions. Cleaning this data can remove noise, address missing values, and outliers, making the data more reliable and accurate. Time-based sorting ensures that the data is arranged in chronological order, providing the correct time sequence for subsequent time series analysis. Decomposing the land condition time series data can be decomposed into three components: trend, seasonality, and residual. The trend component reflects the long-term trend of land conditions, the seasonal component reflects cyclical seasonal changes, and the residual component represents random fluctuations that cannot be explained by trend and seasonality. By decomposing time series data, the changing patterns and trends of land conditions can be better understood, providing a foundation for subsequent state tracking and predictive modeling. Based on the time series component data and the previously constructed state transition map, a state tracking model based on the hidden Markov model can be constructed. The hidden Markov model is a commonly used sequence modeling method that can use the state transition map and observed data (time series component data) to infer hidden state sequences. Using the state tracking model, time series data can be mapped to paths on the state transition map, enabling tracking and analysis of land conditions. Using a state tracking model, land state time series data can be mapped to paths on a state transition graph. This yields state transition path data describing land state changes, i.e., state transition sequences within the state transition graph. This helps better understand the evolution of land states, identifies key state transitions and transition paths, and provides a foundation for subsequent time series pattern mining and evolution trend prediction. Sequential pattern mining algorithms can be used to analyze state transition path data and extract recurring state transition sequences. These recurring state transition sequences represent common patterns and regularities in land state evolution. By extracting a collection of time series patterns, important patterns in land state transitions can be identified, providing insights for land management and planning, supporting decision-making and planning. Based on this collection of extracted time series patterns, state evolution trends can be predicted. By analyzing the evolutionary trends of these time series patterns, future directions and trends in land state development can be predicted. This helps predict changes in land state, proactively develop adaptive strategies and planning measures, and support the implementation of sustainable land management and planning. In summary, the above steps result in the acquisition, cleaning, and sorting of historical land status data; decomposition of time series data to identify trend, seasonal, and residual components; construction of a state tracking model based on a hidden Markov model; mapping land status time series data to state transition paths; extraction of recurring state transition sequences to obtain a collection of temporal patterns; and trend prediction of state evolution. These steps provide accurate land status data, understanding the changing patterns and trends of land status, enabling tracking and analysis of land status, identifying key patterns and regularities, supporting decision-making and planning, and predicting future development directions and trends of land status.These effects help improve the efficiency and accuracy of land management and planning, and provide important reference and guidance for decision makers and planners.

[0098] Preferably, step S26 includes the following steps:

[0099] Step S261: constructing an ARIMA-based evolution trend prediction model based on the state transition path data and the time series pattern set;

[0100] In this embodiment of the present invention, an evolutionary trend prediction model based on the time series pattern set extracted in step S25 and the state transition path data obtained in step S24 can be constructed. The ARIMA model is a commonly used time series prediction model that can capture characteristics such as trends and seasonality in time series data. Based on the time series pattern set and state transition path data, an appropriate ARIMA model order can be selected, and model parameters can be estimated and fitted using historical data. This can be achieved using time series analysis tools and libraries, such as the ARIMA model in the statsmodels library.

[0101] Step S262: performing state evolution simulation under different scenario parameters according to the evolution trend prediction model, thereby obtaining multi-scenario state evolution prediction data;

[0102] Based on the evolution trend prediction model constructed in step S261, embodiments of the present invention can simulate state evolution under different scenario parameters. This can be accomplished by adjusting the model's input conditions or parameter values based on different scenario parameter settings, and then running the prediction model to simulate the state evolution process. Through multiple simulations, state evolution prediction data under different scenarios can be obtained. The specific scenario parameters can be determined based on needs and research objectives.

[0103] Step S263: Calculate the confidence interval and possibility distribution of the prediction results for the multi-scenario state evolution prediction data, thereby obtaining state evolution prediction data including uncertainty indicators.

[0104] Embodiments of the present invention can calculate confidence intervals and probability distributions for multi-scenario state evolution prediction data to reflect the uncertainty of the prediction results. This can be achieved using statistical methods and techniques such as Monte Carlo simulation. By performing statistical analysis on multiple simulation results, confidence intervals, probability distributions, or probability distributions can be calculated to express the reliability and uncertainty of the prediction results. This can be achieved using statistical analysis tools and corresponding functions and libraries in programming languages, such as the numpy and scipy libraries in Python.

[0105] The present invention constructs an evolution trend prediction model based on the ARIMA (Autoregressive Moving Average) model based on state transition path data and a set of time series patterns. The ARIMA model is a commonly used time series analysis method that can identify trends, seasonality, and residuals in a sequence and use this information to predict future values. By constructing an evolution trend prediction model, future changes in land conditions can be predicted, providing quantitative information about land evolution trends. Based on the constructed evolution trend prediction model, state evolution simulations under different scenario parameters can be performed. Scenario parameters are external environmental conditions that reflect different development assumptions and forecasting conditions. By simulating state evolution under different scenario parameters, multiple prediction results can be obtained, understanding the possible changes in land conditions under different conditions and providing decision-makers with decision support under different scenarios. Confidence intervals and probability distributions are calculated for multi-scenario state evolution prediction data to provide state evolution prediction data containing uncertainty indicators. The confidence interval reflects the uncertainty range of the prediction results and can measure the reliability of the prediction results. The probability distribution indicates the likelihood of different state evolution scenarios occurring, helping to assess the probability of different state changes. By considering uncertainty indicators, more comprehensive and reliable state evolution forecasts can be provided, supporting decision makers in assessing and making decisions about future land conditions. In summary, the above steps result in the construction of an ARIMA-based evolution trend forecast model, simulation of state evolution under different scenario parameters, and calculation of confidence intervals and probability distributions for the forecast results. These results help provide quantitative evolution trend forecast information, support decision makers in understanding and predicting future changes in land conditions, provide decision support under different scenarios, and provide more comprehensive and reliable forecast results by considering uncertainty indicators. This information can help planners and decision makers develop adaptive strategies and formulate planning measures to achieve the goals of sustainable land management and planning.

[0106] Preferably, step S3 includes the following steps:

[0107] Step S31: constructing an initial semantic network model based on the node set and edge set in the state transition graph;

[0108] Embodiments of the present invention can construct an initial semantic network model based on the node and edge sets in the state transition graph. A semantic network is a graph structure in which nodes represent concepts or entities and edges represent the relationships between them. Based on the state transition graph, each state node can be treated as a node in the semantic network, and the relationships between nodes can be defined using edge sets. This can be achieved using graph algorithms and network analysis tools, such as the NetworkX library.

[0109] Step S32: evaluating the association strength between every two nodes based on the transition frequency and probability between nodes in different states in the state evolution prediction data, thereby obtaining a node association strength matrix;

[0110] Embodiments of the present invention can evaluate the strength of the association between each pair of nodes based on the frequency and probability of transitions between nodes in different states in the state evolution prediction data. This can be achieved by calculating the correlation, similarity, or other relevant metrics between the nodes to measure the association between the nodes. Based on the evaluation results, a node association strength matrix can be constructed, where each element of the matrix represents the strength of the association between a pair of nodes. This can be achieved using statistical analysis methods and similarity calculation methods, such as the Pearson correlation coefficient and cosine similarity.

[0111] Step S33: applying the node association strength matrix to the semantic network model to adjust the weights of the edges between nodes in the network, thereby obtaining a land status semantic network;

[0112] Embodiments of the present invention apply a node association strength matrix to a semantic network model to adjust the weights of edges between nodes in the network. Based on the values in the node association strength matrix, the weights of edges in the semantic network can be updated to reflect the strength of the associations between nodes. This can be achieved by traversing the edge set of the semantic network and adjusting the weights based on the corresponding elements in the node association strength matrix. This can be achieved using the APIs and functions provided by graph databases or graph analysis tools, such as Neo4j's Cypher query language.

[0113] Step S34: extracting node-pair association strength from the land state semantic network, thereby generating a state semantic association matrix.

[0114] This embodiment of the present invention extracts node-pair association strengths from a land state semantic network to generate a state semantic association matrix. This matrix is constructed by traversing node pairs in the semantic network and extracting the association strengths between them. This can be achieved using the APIs and functions provided by graph databases or graph analysis tools, such as Neo4j's Cypher query language.

[0115] The present invention constructs an initial semantic network model based on the node and edge sets in the state transition graph. A semantic network model is a graph structure that represents the relationships between concepts, where nodes represent concepts and edges represent the associations between concepts. By constructing a semantic network model, the various concepts of land status and their relationships can be visualized and formalized, helping people understand and analyze the structure and interactions of land status. Based on the transition frequency and probability between nodes in different states in the state evolution prediction data, the strength of the association between each two nodes can be evaluated. The association strength reflects the degree of association between nodes and measures the degree of information transmission and mutual influence between nodes. By evaluating the association strength between nodes, the correlation between different nodes can be quantified, providing a basis for subsequent network adjustment and analysis. Applying the node association strength matrix to the semantic network model allows for adjusting the weights of edges between nodes, thereby generating a land status semantic network. By adjusting the edge weights, the strength of the association between nodes can be reflected, highlighting important nodes and relationships and reducing the influence of irrelevant nodes and relationships. The resulting land status semantic network more accurately represents the structure and associations of land status, providing a more reliable basis for subsequent state analysis and decision-making. Extracting node-pair association strengths from the land state semantic network generates a state semantic association matrix. This is a two-dimensional matrix whose elements represent the strength of associations between different pairs of nodes. This matrix provides an intuitive understanding of the degree of association between different node pairs, identifies important node pairs and relationships, and provides a basis for further network analysis, pattern recognition, and decision support. In summary, the above steps result in constructing an initial semantic network model, assessing the strength of associations between nodes, adjusting edge weights between nodes in the semantic network, and generating the state semantic association matrix. These results help provide an understanding and analysis of the structure and relationships of land state, quantify the degree of association between nodes, highlight important nodes and relationships, and provide a more reliable basis for state analysis and decision-making. This information can help planners and decision makers identify key factors and relationships in land state, guiding decision-making and optimizing land management strategies.

[0116] Preferably, step S4 includes the following steps:

[0117] Step S41: extracting task nodes, conditional branch nodes, and workflow elements of the path from the state transition path data, thereby constructing a workflow element library;

[0118] Based on state transition path data, embodiments of the present invention can extract task nodes, conditional branch nodes, and paths as workflow elements. Task nodes represent nodes that execute a task, while conditional branch nodes represent nodes that select different paths based on different conditions. By parsing the state transition path data, task nodes, conditional branch nodes, and paths can be extracted and constructed into a workflow element library. This can be achieved using methods such as text processing and pattern matching, such as regular expressions or natural language processing techniques.

[0119] Step S42: Design a workflow template according to the approval process, and assemble and embed the elements in the workflow element library into the workflow template to obtain an initial workflow template;

[0120] According to the design of the approval process, embodiments of the present invention can create a workflow template. Task nodes, conditional branch nodes, and path elements in the workflow element library are assembled and embedded according to the design requirements to construct an initial workflow template. This can be achieved using process modeling tools or process control statements in programming languages, such as BPMN tools, business process management systems (BPMS), or process frameworks in Python.

[0121] Step S43: setting rules for workflow decision points in the initial workflow template according to the predicted transition paths of different state nodes in the state evolution prediction data, to obtain initial data of the workflow template;

[0122] In embodiments of the present invention, based on the predicted transition paths of different state nodes in the state evolution prediction data, rules can be set for workflow decision points in the initial workflow template. Workflow decision points are nodes that determine the path based on conditional branching nodes. Based on the path information in the predicted data, rules for workflow decision points can be determined to specify path selection under different conditions. This can be implemented using conditional statements or a rule engine, such as if-else statements or the Drools rule engine.

[0123] Step S44: Identifying parallel executable tasks based on the state semantic association matrix, and sorting the execution priorities of the tasks based on the association strength, thereby obtaining a parallel task sequence;

[0124] Embodiments of the present invention analyze the state semantic association matrix to identify tasks that can be executed in parallel. Based on the strength of the association, the execution priority of the tasks can be determined. Based on the strength of the association between tasks, the tasks can be sorted to construct a sequence for executing the parallel tasks. This can be achieved using graph algorithms and sorting algorithms, such as topological sorting or shortest path algorithms.

[0125] Step S45: Optimizing task allocation for the initial data of the workflow template according to the parallelizable task sequence, thereby obtaining configuration template data of the dynamic workflow.

[0126] Embodiments of the present invention can optimize task allocation within the initial workflow template data based on parallelizable task sequences. Based on task characteristics and resource constraints, tasks can be assigned to different executors or execution resources to achieve optimized task allocation. This can be achieved using task scheduling and optimization algorithms, such as greedy algorithms, genetic algorithms, or linear programming.

[0127] The present invention analyzes state transition path data to extract task nodes, conditional branch nodes, and workflow elements along the path, thereby constructing a workflow element library. The workflow element library contains various types of workflow elements, such as task nodes, conditional branch nodes, and paths, for use in constructing and designing workflow templates. By constructing a workflow element library, workflow elements can be systematically managed and organized, facilitating subsequent workflow template design and construction. Based on approval process design requirements, elements from the workflow element library can be assembled and embedded into a workflow template to create an initial workflow template. A workflow template is a structured graphical representation that defines the relationships between workflows and nodes, used to standardize and control workflow execution. By embedding workflow elements into a workflow template, an initial workflow template that meets specific approval process requirements can be constructed. Based on the predicted transition paths of different state nodes in the state evolution prediction data, rules can be set for workflow decision points in the initial workflow template to obtain the initial data for the workflow template. Workflow decision points are nodes in the decision process that require judgment and selection. By setting rules, automatic decisions can be made and workflow execution can be guided based on the prediction results of the state evolution prediction data. By setting workflow decision point rules, workflow automation can be improved, reducing manual intervention and boosting efficiency. Analysis of the state semantic association matrix identifies concurrently executable tasks and prioritizes their execution based on the strength of their association. Parallel executable tasks are tasks that can be executed simultaneously within a workflow. Identifying these tasks and prioritizing their execution can improve workflow parallelism and efficiency. Prioritizing tasks allows for a more efficient execution sequence, optimizing workflow execution efficiency and resource utilization. Based on the sequence of concurrently executable tasks, task allocation can be optimized within the initial workflow template data to generate dynamic workflow configuration template data. Task allocation optimization rationally assigns tasks to appropriate executors based on task attributes, execution requirements, and resource availability, optimizing workflow execution efficiency and resource utilization. Optimizing task allocation improves workflow flexibility and adaptability, enabling dynamic adjustment and allocation of tasks based on actual conditions. In summary, the above steps include building a workflow element library, designing workflow templates and embedding workflow elements, setting workflow decision point rules, identifying and prioritizing concurrently executable tasks, and optimizing task allocation and configuring dynamic workflow template data. These results help build workflow templates that meet approval process requirements, improve workflow automation and efficiency, optimize task execution sequence and resource utilization, and achieve workflow flexibility and adaptability. This information can help organize and manage workflows, improve work efficiency, reduce manual intervention, and ensure the proper allocation and execution sequence of tasks, thereby optimizing the execution and management of the entire workflow.

[0128] Preferably, step S5 includes the following steps:

[0129] Step S51: determining state node pairs whose association strength exceeds a preset threshold in the state semantic association matrix, and taking them as the state set that needs to be kept consistent, and obtaining consistency state range data;

[0130] Based on the state semantic association matrix, embodiments of the present invention can identify state node pairs whose association strength exceeds a preset threshold. These state node pairs represent state nodes with high association within the system. These state node pairs are considered the state set for which consistency is required. This can be achieved by setting a threshold to filter out state node pairs with high association strength and recording these pairs as consistent state range data.

[0131] Step S52: extract all executable state change paths based on the configuration template data, and eliminate paths that destroy state consistency based on the consistency state range data to obtain a set of legal paths;

[0132] Based on the configuration template data, embodiments of the present invention can extract all executable state change paths. These paths represent sequences of state transition operations that can be performed in the system. Based on the consistency state range data, each path can be checked to see if it contains state node pairs that violate state consistency. If a path contains these state node pairs, the path is removed from the set. The resulting set of paths is the set of legal paths, which do not violate state consistency.

[0133] Step S53: Encode the consistency state range data and the legal path set into a unique hash fingerprint as the identification and verification basis of the global state consistency to obtain the global state consistency hash.

[0134] In an embodiment of the present invention, consistent state range data and a set of legal paths are encoded to generate a unique hash fingerprint. The consistent state range data and the set of legal paths can be converted into strings or other hashable data structures, and their hash values calculated using a hash function. This hash value serves as an identifier and verification basis for global state consistency, verifying that the system's state remains consistent. The uniqueness of the hash value ensures that changes in state consistency can be detected when the state range or path changes.

[0135] The present invention analyzes the state semantic association matrix to identify pairs of state nodes whose association strength exceeds a preset threshold and defines these as state sets that require consistency. State consistency refers to the requirement that the associations and dependencies between related states remain consistent during a workflow. By determining the consistent state set, nodes that need to be in the same state can be clearly identified, ensuring the consistency of related states during workflow execution and avoiding errors and confusion caused by state conflicts and inconsistencies. Based on the configuration template data, all executable state change paths are extracted, and paths that violate state consistency are eliminated based on the consistent state range data to obtain a set of legal paths. State change paths refer to the transition paths between state nodes during a workflow. By extracting the set of legal paths, it is possible to ensure that the workflow adheres to the consistent state range requirements during execution and prevent illegal paths that violate state consistency. This helps maintain the correctness and consistency of the workflow and reduces the occurrence of potential errors and anomalies. The consistent state range data and the set of legal paths are encoded into a unique hash fingerprint, which serves as the identification and verification basis for global state consistency, resulting in a global state consistency hash. The global state consistency hash can serve as a workflow verification mechanism to verify whether the workflow meets the expected state consistency requirements during execution. By generating a global state consistent hash, the correctness and consistency of the workflow can be effectively guaranteed, preventing the execution of illegal paths and the destruction of state consistency. In summary, the effects of the above steps include determining the set of states that need to maintain consistency, extracting the set of legal paths, and generating a global state consistent hash. These effects help ensure that the workflow adheres to the requirements of the consistent state range during execution, maintaining the correctness and consistency of the workflow, and reducing the occurrence of errors and anomalies. Through the verification mechanism of the global state consistent hash, the execution results of the workflow can be verified and monitored to ensure that the state consistency of the workflow is effectively maintained. This information can improve the reliability and stability of the workflow, enhance the manageability and traceability of the workflow, and ensure the smooth execution and effective control of the workflow.

[0136] Preferably, step S6 includes the following steps:

[0137] Step S61: Acquire the geospatial data of the construction land, associate the geospatial data with the state semantic association matrix, and construct a semantic geographic information model;

[0138] This embodiment of the present invention acquires geospatial data for construction land, which can include map data, satellite imagery, or other geographic information data sources. This geospatial data is then associated with a state semantic association matrix to create a geographic information model. This association can be based on spatial location matching or other semantic association methods, associating location elements in the geospatial data with state nodes in the state semantic association matrix.

[0139] Step S62: Rendering the state nodes and their associated relationships into the actual geographical environment based on the semantic geographic information model, thereby obtaining an augmented reality visualization scene;

[0140] Embodiments of the present invention utilize a semantic geographic information model to render state nodes and their relationships within a real-world geographic environment, creating augmented reality visualizations. This can be achieved by overlaying symbols, labels, or other visual representations of the state nodes on top of the geospatial data. The rendering can accurately position the state nodes based on geographic coordinates and use appropriate graphics or symbols to represent the nodes and their relationships.

[0141] Step S63: Integrate the global state consistent hash as the criterion for interaction legitimacy check, and design the interaction mode of the state relationship to obtain interaction mode configuration data;

[0142] This embodiment of the present invention integrates a global state consistent hash as a criterion for interaction legitimacy checks into the system. This ensures the legitimacy of user operations by checking whether they match the global state consistent hash during the interaction process. Furthermore, an interaction model for state relationships is designed, defining the user interaction methods and operation rules for state nodes and their associated relationships. This interaction model configuration data is recorded for subsequent use and reference.

[0143] Step S64: Track and record the user operation of selecting state nodes and associated state behaviors according to the augmented reality visualization scene and the interaction mode configuration data, thereby generating a space state interaction log.

[0144] This embodiment of the present invention tracks user actions based on augmented reality visualization scenes and interaction mode configuration data, and records the state nodes selected by the user and the associated state behaviors. This can be achieved through the design of the user interface and interactive elements. Based on the user's selections and actions, a spatial state interaction log is generated, recording the user's interactions with the state nodes in the system.

[0145] The present invention can construct a semantic geographic information model by acquiring the geographic spatial data of construction land and associating it with the state semantic association matrix. The semantic geographic information model models the association relationship between geographic spatial data and workflow status, so that the geographic spatial data has semantic expression and understanding capabilities. By constructing a semantic geographic information model, a more intuitive and easy-to-understand way of displaying geographic spatial data can be provided, providing a foundation for subsequent augmented reality visualization scenes. Based on the semantic geographic information model, the state nodes and their association relationships are rendered into the actual geographic environment to generate an augmented reality visualization scene. The augmented reality visualization scene superimposes the workflow state nodes and related information in a virtual manner on the actual geographic environment, allowing users to intuitively observe and understand the distribution and changes of the workflow status in the geographic space. Through the augmented reality visualization scene, users can perceive and understand the workflow status more intuitively, and improve their ability to understand and grasp the workflow execution status. The global state consistency hash is integrated as a criterion for interaction legitimacy checking, and the interaction mode of the state relationship is designed to obtain the interaction mode configuration data. As a marker for workflow state consistency, the global state consistent hash can be used to verify whether user interactions meet state consistency requirements, enhancing the legitimacy and reliability of workflow execution. By designing interaction mode configuration data, the user interaction method and operation rules with the augmented reality visualization scene can be defined, ensuring that users can perform operations in accordance with state relationships and maintain state consistency during interaction. Based on the augmented reality visualization scene and interaction mode configuration data, user operations are tracked, including state node selection and associated state behaviors, to generate a spatial state interaction log. The spatial state interaction log records user interactions within the augmented reality visualization scene, including selected state nodes and associated state behaviors. By generating a spatial state interaction log, user operations can be recorded and analyzed to understand user interactions with workflow states and feedback, providing a reference and basis for subsequent workflow improvements and optimization. In summary, the above steps include constructing a semantic geographic information model, generating an augmented reality visualization scene, integrating the global state consistent hash, designing interaction mode configuration data, and generating the spatial state interaction log. These results help provide an intuitive and understandable presentation of workflow states, enhancing users' perception and understanding of workflow execution. By integrating global state consistent hashing and designing interaction patterns, we can ensure the legitimacy and state consistency of user interactions. Generating spatial state interaction logs records user interactions, providing data support for workflow improvement and optimization. This information can enhance workflow visualization and interaction, and the effectiveness of augmented reality technology in workflow management.

[0146] The present invention also provides an integrated construction land approval automation control system for executing the above-mentioned integrated construction land approval automation control method. The integrated construction land approval automation control system includes:

[0147] A state graph construction module is used to obtain construction land state indicator data, and use the state indicators in the construction land state indicator data as nodes and the conversion relationships between states as edges to obtain a state transition graph;

[0148] The time series prediction and analysis module is used to track the state of pre-acquired historical land state data based on the time series, and map the state transition path according to the state transition map to obtain state transition path data; and predict the evolution trend of the state transition path data to obtain state evolution prediction data;

[0149] The semantic network optimization module is used to initialize the semantic network using the node and edge relationships in the state transition graph to obtain the land state semantic network; dynamically adjust the association strength in the land state semantic network based on the state evolution prediction data to obtain the state semantic association matrix;

[0150] The workflow intelligent configuration module is used to design the initial workflow template based on the state transition path data, and set rules for the workflow decision points in the initial workflow template based on the state evolution prediction data to obtain the initial workflow template data; the module uses the state semantic association matrix to optimize the task allocation and parallelize the initial workflow template data to obtain the configuration template data of the dynamic workflow;

[0151] The global consistency maintenance module is used to determine the state set that needs to be consistent based on the state semantic association matrix and obtain the consistency state range data; determine the legal path set for state change through configuration template data; and integrate the consistency state range data and legal path set into a global state consistency hash;

[0152] The spatial interaction verification module is used to project the state relationship in the state semantic association matrix into the actual geographical environment through augmented reality technology, and verify the legitimacy of user operations based on the global state consistency hash, thereby obtaining the spatial state interaction log.

[0153] The present invention constructs a state transition graph by acquiring construction land status indicator data, using the status indicators as nodes and the transition relationships between states as edges. The state transition graph clearly displays the transition relationships between construction land states, helping users understand the patterns and trends of state changes. The state graph can serve as input data for subsequent modules, providing a foundation for time series prediction analysis, semantic network optimization, and intelligent workflow configuration. The time series prediction analysis module uses pre-acquired historical land status data to track states based on time series and map state transition paths according to the state transition graph. Through time series prediction analysis, future land state evolution trends can be predicted and their development can be forecasted. This helps decision makers more accurately predict land state changes when making plans and decisions, allowing them to take appropriate measures in advance. The semantic network optimization module uses the node and edge relationships in the state transition graph to initialize a semantic network, generating a land state semantic network. This semantic network can better represent the semantic associations and interactions between land states. Based on the state evolution prediction data, the association strengths in the land state semantic network are dynamically adjusted to generate a state semantic association matrix. This helps improve the accuracy and reliability of state associations, providing more precise state semantic association information for subsequent intelligent workflow configuration. The intelligent workflow configuration module designs the initial workflow template based on state transition path data and sets rules for workflow decision points based on state evolution prediction data, generating the initial workflow template data. Using the state semantic association matrix, the initial workflow template data is optimized for task allocation and parallel processing, generating configuration template data for dynamic workflows. This facilitates intelligent workflow configuration and optimization, improving workflow execution efficiency and accuracy. The global consistency maintenance module determines the set of states that must maintain consistency based on the state semantic association matrix, generating consistent state range data. The configuration template data determines the set of legal state change paths and integrates the consistent state range data and the legal path set into a global state consistency hash. The global state consistency hash serves as a marker for workflow state consistency verification and can be used to verify whether user operations meet state consistency requirements, improving workflow reliability and correctness. The spatial interaction verification module uses augmented reality technology to project the state relationships in the state semantic association matrix into the actual geographic environment and verifies the legitimacy of user operations based on the global state consistency hash, generating a spatial state interaction log. Spatial interaction verification ensures that users adhere to state relationship requirements and maintain state consistency during interaction. Spatial state interaction logs record user interaction behaviors, providing a basis for workflow improvement and analysis.In summary, the effects of the above steps include: the state graph construction module converts construction land state indicator data into a state transition graph, helping users intuitively understand the transition relationships and patterns between construction land states; the time series prediction analysis module provides future land state evolution trend forecasts through time series-based state tracking and state transition path mapping, helping decision makers more accurately predict land state changes when making plans and decisions; the semantic network optimization module uses the state transition graph and evolution prediction data to initialize the land state semantic network and dynamically adjust the association strength between states, improving the accuracy and reliability of state associations; the workflow intelligent configuration module designs the initial workflow template based on state transition path data and sets rules for workflow decision points based on state evolution prediction data, improving workflow execution efficiency and accuracy through task allocation optimization and parallel processing; the global consistency maintenance module maintains workflow state consistency by determining consistent state range data and legal path sets, improving workflow reliability and correctness; and the spatial interaction verification module uses augmented reality technology to project state relationships into the actual geographic environment and verify the legitimacy of user operations based on the global state consistency hash, ensuring that users comply with state relationship requirements and improving workflow reliability.

[0154] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0155] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. An integrated construction land approval automation control method, characterized in that: The following steps are involved: Step S1: Acquire construction land status indicator data, and use the status indicators in the construction land status indicator data as nodes and the conversion relationships between states as edges, thereby obtaining a state transition graph; Step S2: performing state tracking based on a time series on the pre-acquired land state historical data, and mapping the state transition path according to the state transition map to obtain state transition path data; performing evolution trend prediction on the state transition path data to obtain state evolution prediction data; Step S3: Initialize the semantic network using the node and edge relationships in the state transition graph to obtain the land state semantic network; dynamically adjust the association strength in the land state semantic network according to the state evolution prediction data to obtain the state semantic association matrix; Step S4: Design an initial workflow template based on the state transition path data, and set rules for the decision points of the workflow in the initial workflow template based on the state evolution prediction data to obtain initial data of the workflow template; The state semantic association matrix is used to optimize the task allocation and parallel process the initial data of the workflow template to obtain the configuration template data of the dynamic workflow; Step S5: Determine the state set that needs to be consistent based on the state semantic association matrix, and obtain the consistent state range data; determine the legal path set for state change through the configuration template data; integrate the consistent state range data and the legal path set into a global state consistent hash; Step S6: Project the state relationship in the state semantic association matrix into the actual geographical environment through augmented reality technology, and verify the legitimacy of user operations based on the global state consistency hash to obtain the spatial state interaction log.

2. The integrated construction land approval automation control method according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: collecting original construction land status indicator data through the land management system, land planning database and environmental monitoring system; Step S12: classifying the construction land status indicator data and assigning a unique code to each type of status indicator, thereby obtaining a status indicator classification code table; Step S13: defining each state indicator as a node according to the state indicator classification code table to obtain a state node set; analyzing the state change sequence in the pre-acquired historical data and identifying the state transition relationship, thereby defining transition conditions and constraints to obtain a state transition relationship set; Step S14: importing the state node set into a preset graph database, and importing the state transition relationship set into the graph database as edges, thereby obtaining an initial state transition graph; Step S15: Identify isolated nodes and subgraphs on the initial state transition graph, and optimize the connectivity of the graph to obtain a state transition graph.

3. The integrated construction land approval automation control method according to claim 2 is characterized in that: Step S15 includes the following steps: Step S151: traverse the initial state transition graph and check the in-degree and out-degree of each node. If both the in-degree and out-degree of a node are 0, mark it as an isolated node to obtain an isolated node set. Step S152: traverse the initial state transition graph based on the connectivity of the graph, and identify all maximal connected subgraphs to obtain a subgraph set; Step S153: Perform cause analysis on the isolated node set and subgraph set to obtain disconnection cause data, wherein the cause analysis includes checking the corresponding data source to confirm whether there is an error in the data collection or processing process, confirming whether it is a legal but rare state or transition path, and checking whether the state or transition path is no longer applicable due to changes in regulations; Step S154: Nodes are deleted for isolated node sets or subgraph sets whose disconnection causes data to be errors during data collection or processing; connection paths are designed for isolated node sets or subgraph sets whose disconnection causes data to be legal but rare states or transition paths; and "historical state" tags are added for isolated node sets or subgraph sets whose disconnection causes data to be states or transition paths that are no longer applicable due to changes in regulations, thereby obtaining a state transition map.

4. The integrated construction land approval automation control method according to claim 3 is characterized in that: Step S2 includes the following steps: Step S21: Acquire historical land status data, cleanse the historical land status data, and sort the data based on time, thereby obtaining land status time series data; Step S22: decomposing the land status time series data into trend, seasonality and residual components to obtain time series component data; Step S23: constructing a state tracking model based on a hidden Markov model according to the time series component data and the state transition graph; Step S24: Mapping the land state time series data to the path on the state transition map using the state tracking model, thereby obtaining state transition path data; Step S25: extracting recurring state transition sequences from the state transition path data using a sequence pattern mining algorithm, thereby obtaining a set of time series patterns; Step S26: performing evolution trend prediction on the time series pattern set to obtain state evolution prediction data.

5. The integrated construction land approval automation control method according to claim 4 is characterized in that: Step S26 includes the following steps: Step S261: constructing an ARIMA-based evolution trend prediction model based on the state transition path data and the time series pattern set; Step S262: performing state evolution simulation under different scenario parameters according to the evolution trend prediction model, thereby obtaining multi-scenario state evolution prediction data; Step S263: Calculate the confidence interval and possibility distribution of the prediction results for the multi-scenario state evolution prediction data, thereby obtaining state evolution prediction data including uncertainty indicators.

6. The integrated construction land approval automation control method according to claim 5 is characterized in that: Step S3 includes the following steps: Step S31: constructing an initial semantic network model based on the node set and edge set in the state transition graph; Step S32: evaluating the association strength between every two nodes based on the transition frequency and probability between nodes in different states in the state evolution prediction data, thereby obtaining a node association strength matrix; Step S33: applying the node association strength matrix to the semantic network model to adjust the weights of the edges between nodes in the network, thereby obtaining a land status semantic network; Step S34: extracting node-pair association strength from the land state semantic network, thereby generating a state semantic association matrix.

7. The integrated construction land approval automation control method according to claim 6 is characterized in that: Step S4 includes the following steps: Step S41: extracting task nodes, conditional branch nodes, and workflow elements of the path from the state transition path data, thereby constructing a workflow element library; Step S42: Design a workflow template according to the approval process, and assemble and embed the elements in the workflow element library into the workflow template to obtain an initial workflow template; Step S43: setting rules for workflow decision points in the initial workflow template according to the predicted transition paths of different state nodes in the state evolution prediction data, to obtain initial data of the workflow template; Step S44: Identifying parallel executable tasks based on the state semantic association matrix, and sorting the execution priorities of the tasks based on the association strength, thereby obtaining a parallel task sequence; Step S45: Optimizing task allocation for the initial data of the workflow template according to the parallelizable task sequence, thereby obtaining configuration template data of the dynamic workflow.

8. The integrated construction land approval automation control method according to claim 7 is characterized in that: Step S5 includes the following steps: Step S51: determining state node pairs whose association strength exceeds a preset threshold in the state semantic association matrix, and taking them as the state set that needs to be kept consistent, and obtaining consistency state range data; Step S52: extract all executable state change paths based on the configuration template data, and eliminate paths that destroy state consistency based on the consistency state range data to obtain a set of legal paths; Step S53: Encode the consistency state range data and the legal path set into a unique hash fingerprint as the identification and verification basis of the global state consistency to obtain the global state consistency hash.

9. The integrated construction land approval automation control method according to claim 8 is characterized in that: Step S6 includes the following steps: Step S61: Acquire the geographic spatial data of the construction land, and associate the geographic spatial data with the state semantic association matrix to construct a semantic geographic information model; Step S62: Rendering the state nodes and their associated relationships into the actual geographical environment based on the semantic geographic information model, thereby obtaining an augmented reality visualization scene; Step S63: Integrate the global state consistent hash as the criterion for interaction legitimacy check, and design the interaction mode of the state relationship to obtain interaction mode configuration data; Step S64: Track and record the user operation of selecting state nodes and associated state behaviors according to the augmented reality visualization scene and the interaction mode configuration data, thereby generating a space state interaction log.

10. An integrated construction land approval automation control system, characterized in that: For executing the integrated construction land approval automation control method according to claim 1, the integrated construction land approval automation control system comprises: A state graph construction module is used to obtain construction land state indicator data, and use the state indicators in the construction land state indicator data as nodes and the conversion relationships between states as edges to obtain a state transition graph; The time series prediction and analysis module is used to track the state of pre-acquired historical land state data based on the time series, and map the state transition path according to the state transition map to obtain state transition path data; and predict the evolution trend of the state transition path data to obtain state evolution prediction data; The semantic network optimization module is used to initialize the semantic network using the node and edge relationships in the state transition graph to obtain the land state semantic network; dynamically adjust the association strength in the land state semantic network based on the state evolution prediction data to obtain the state semantic association matrix; The workflow intelligent configuration module is used to design the initial workflow template based on the state transition path data, and set rules for the workflow decision points in the initial workflow template based on the state evolution prediction data to obtain the initial workflow template data; the module uses the state semantic association matrix to optimize the task allocation and parallelize the initial workflow template data to obtain the configuration template data of the dynamic workflow; The global consistency maintenance module is used to determine the state set that needs to be consistent based on the state semantic association matrix and obtain the consistency state range data; determine the legal path set for state change through configuration template data; and integrate the consistency state range data and legal path set into a global state consistency hash; The spatial interaction verification module is used to project the state relationship in the state semantic association matrix into the actual geographical environment through augmented reality technology, and verify the legitimacy of user operations based on the global state consistency hash, thereby obtaining the spatial state interaction log.

Images