Rule-driven land consolidation post-supply space analysis method and system

Abstract

The application discloses a land consolidation after the supply space analysis method and system based on rule driving, relates to the intelligent analysis technical field of land planning, and comprises the following steps: acquiring basic space data of a land consolidation area, and constructing a to-be-supplied space object set; calling a land supply related rule library to analyze a rule feature vector of each land supply related rule; generating a rule dependency chain network; establishing a space state transition model of each to-be-supplied space object in the to-be-supplied space object set; and analyzing the to-be-supplied space object set to acquire a supply management decision result. The application solves the technical problems that the existing technology relies on manual judgment of plot maturity, lacks quantitative deduction means, and leads to strong subjectivity and insufficient precision of land supply timing planning and land supply decision, and achieves the technical effects of realizing automatic deduction of the space state of land consolidation plots and quantitative measurement of supply priority, and improving the precision of land supply timing planning and land supply decision.

Description

Technical Field

[0001] This invention relates to the field of intelligent analysis technology for land planning, specifically to a rule-driven method and system for analyzing the space to be supplied after land preparation. Background Technology

[0002] In the management of existing land consolidation and land supply, current technologies mostly rely on the overlay of static GIS layers combined with manual experience to assess land parcels to be supplied. This can only display basic spatial information of land parcels and cannot perform structured analysis and correlation modeling of various land supply control rules. It lacks quantifiable rule-dependent transmission logic and is difficult to automatically deduce the dynamic changes in the spatial status of land parcels under the sequential action of multiple rules, such as consolidation, supporting facilities, industrial introduction, and supply availability. The determination of land parcel maturity and the arrangement of land supply sequence are highly dependent on the subjective qualitative judgment of staff. There is no unified quantitative gain calculation standard, which easily leads to problems such as mismatch of supply sequence, insufficient exploration of land parcel value, and insufficient accuracy of land supply decisions. It cannot adapt to the actual business needs of intelligent analysis and refined supply coordination of batches of land parcels in large-scale land consolidation areas.

[0003] Existing technologies rely on manual assessment of land maturity and lack quantitative projection methods, resulting in strong subjectivity and insufficient accuracy in land supply timing planning and land supply decisions. Summary of the Invention

[0004] This application provides a rule-driven method and system for analyzing the space to be supplied after land preparation, which addresses the technical problems of existing technologies that rely on manual judgment of land maturity and lack quantitative extrapolation methods, resulting in strong subjectivity and insufficient accuracy in land supply timing planning and land supply decisions.

[0005] In view of the above problems, this application provides a rule-driven method and system for analyzing the supply space after land preparation.

[0006] The first aspect of this application provides a rule-driven method for analyzing post-land preparation and unsupplied space, the method comprising: Acquire basic spatial data of the land preparation area, and construct a set of spatial objects to be supplied based on the basic spatial data; call the land supply-related rule base to parse the rule feature vector of each land supply-related rule, the rule feature vector including at least trigger condition features, constraint condition features, affected object features, and execution action features; generate a rule dependency chain network according to the rule feature vector of each land supply-related rule; establish a spatial state transition model for each spatial object to be supplied in the set of spatial objects to be supplied, the spatial state transition model obtains the rule-driven-state transition mapping relationship by performing rule propagation on the rule dependency chain network; obtain rule-driven gain data according to the rule-driven-state transition mapping relationship, analyze the set of spatial objects to be supplied based on the rule-driven gain data, and obtain supply management decision results.

[0007] A second aspect of this application provides a rule-driven post-land preparation supply space analysis system, the system comprising: The system comprises the following modules: a set of spatial objects to be supplied, a rule feature vector invocation module ...

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: This process involves acquiring basic spatial data of land preparation areas; analyzing the rule feature vectors of each land supply-related rule using a land supply-related rule library; generating a rule dependency chain network based on the rule feature vectors of each land supply-related rule; establishing a spatial state transition model for each spatial object in the set of spatial objects to be supplied; acquiring rule-driven gain data; analyzing the set of spatial objects to be supplied based on the rule-driven gain data; and obtaining supply management decision results. This achieves the technical effect of automating the spatial state deduction and quantitative calculation of supply priorities for land preparation plots, thereby improving the accuracy of land supply timing planning and land supply decisions. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A schematic diagram of the rule-driven land preparation and supply space analysis method provided in this application embodiment; Figure 2 A schematic diagram of the structure of a rule-driven land preparation and supply space analysis system provided in this application embodiment.

[0011] Figure labeling: Module 10 for constructing the set of spatial objects to be supplied, Module 20 for calling rule feature vectors, Module 30 for generating rule dependency chain network, Module 40 for obtaining mapping relationship, and Module 50 for obtaining decision result. Detailed Implementation

[0012] This application provides a rule-driven method and system for analyzing the space to be supplied after land preparation, which addresses the technical problems of existing technologies that rely on manual judgment of land maturity and lack quantitative extrapolation methods, resulting in strong subjectivity and insufficient accuracy in land supply timing planning and land supply decisions.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] Example 1, as Figure 1 As shown, this application provides a rule-driven method for analyzing the supply space after land preparation, the method comprising: Step S100: Obtain basic spatial data of the land preparation area, and construct a set of spatial objects to be supplied based on the basic spatial data.

[0015] Specifically, firstly, comprehensive basic spatial data of the target land consolidation area is collected through multiple channels, including the national land spatial information platform, natural resources database, and land consolidation project ledger. The data types cover a wide range of core information, such as regional administrative boundary vector data, plot outline vector data, land use data, ownership information data, planning and control data, infrastructure distribution data, public service supporting data, and current plot attribute data. Then, the collected raw data is preprocessed using a GIS spatial processing platform, sequentially performing operations such as data format unification, coordinate system unification, redundant information removal, topological error correction, missing field completion, and multi-source data layer fusion. After eliminating data conflicts and discrepancies, a standardized spatial data layer group is formed. Then, according to the natural boundaries of the land parcels, administrative boundaries, and land consolidation unit division standards, the merged spatial layers are divided into patches and units. Each independent land parcel that has completed consolidation and has supply potential is designated as a single basic spatial object, and a unique object number is assigned to each spatial object. Finally, all attribute fields such as land use type, area, ownership, planning indicators, supporting facilities status, and consolidation completion progress are associated with each spatial object. All standardized spatial objects are structured, classified, grouped, and stored in an orderly manner according to a unified data architecture, ultimately completing the construction of the set of spatial objects to be supplied.

[0016] Step S200: Call the land supply-related rule base to parse the rule feature vector of each land supply-related rule. The rule feature vector includes at least trigger condition features, constraint condition features, affected object features, and execution action features.

[0017] Specifically, the system interface connects with a pre-built land supply-related rule library, retrieving all original texts, rule entries, and supplementary explanatory information of land supply rules stored in the library one by one according to the traversal logic. Then, structured parsing is performed on each rule, extracting corresponding content from the rule text and configuration information: identifying the pre-judgment conditions required for the rule to take effect as trigger condition features, sorting out the control requirements and scope to be followed during the rule execution as constraint condition features, identifying the target carriers such as the plots, areas, and land use types affected by the rule as impact object features, and determining the corresponding disposal, allocation, and priority determination operations after the rule is implemented as execution action features. Subsequently, the four types of features are quantified, coded, and standardized, unifying the feature data dimensions and data format. The coded trigger condition features, constraint condition features, impact object features, and execution action features are combined in a preset order to form a complete rule feature vector corresponding to a single rule. After traversing all rules for parsing and vector construction, the full set of rule feature vectors is obtained.

[0018] Step S300: Generate a rule dependency chain network according to the rule feature vector of each land supply-related rule.

[0019] Specifically, based on the rule feature vectors corresponding to each rule, four types of relationships between each pair of land supply rules are calculated: the preceding triggering relationship is determined by comparing the matching degree of the result features of the preceding rule with the triggering condition features of the subsequent rule; the constraint inclusion degree is calculated based on the overlap ratio of the constraint condition features of different rules to determine the condition inheritance relationship; the object overlap degree is calculated by combining the overlapping range of the influence object features of each rule to determine the constraint transmission relationship; and the spatial state consistency before and after the execution of adjacent rules is compared to determine the result dependency relationship. Then, the four indicators of result matching degree, constraint inclusion degree, object overlap degree, and state consistency are weighted to obtain the dependency strength between each pair of rules. Subsequently, each land supply-related rule is set as an independent node in the network, and dependency edges are built between the corresponding nodes according to the four types of dependency relationships determined. The calculated dependency strength is set as the weight of the corresponding dependency edge. The layout of all rule nodes, dependency edges, and edge weights is completed in sequence, and finally a complete rule dependency chain network is constructed.

[0020] Step S400: Establish a spatial state transition model for each spatial object in the set of spatial objects to be supplied. The spatial state transition model obtains the rule-driven-state transition mapping relationship by performing rule propagation on the rule dependency chain network.

[0021] Specifically, the first step is to build the overall architecture of the spatial state migration model. This model uses a rule dependency chain network as the driving layer, the spatial objects to be supplied as the carriers, and five spatial states—completion, infrastructure improvement, public service provision, industry introduction, and supply availability—as state nodes, forming the overall structure through state migration paths as logical links. Then, relying on the node dependencies, directed edge propagation logic, and edge weights of the rule dependency chain network, the entire domain rule propagation is completed layer by layer from the network's starting node. An ordered rule propagation sequence is generated according to the dependency order between rules. Combining the characteristics of the objects affected by each rule node, each rule in the propagation sequence is bound to the corresponding target spatial object to be supplied, and the current spatial state of the spatial object is collected, extracting the corresponding state feature vector as the initial input to the model. Next, the execution logic of each rule node in the rule propagation sequence is analyzed. The output results deduce the target spatial state of the spatial object after the rule is applied. The state feature vectors of the current state and the target state and the state difference between the two are calculated respectively. When the difference is greater than the preset migration threshold, the state is determined to have undergone effective migration and the complete state migration path is recorded in the model. After completing the full rule propagation, state comparison and path recording, each rule node and the corresponding state migration path are structurally bound to form a one-to-one corresponding related entry. In this way, a complete rule-driven-state migration mapping relationship is constructed, and the parameters of the spatial state migration model are solidified and the structure is finalized simultaneously. In the model deployment stage, only the initial spatial state of the spatial object to be supplied and the rule sequence to be executed need to be input. The model can automatically match the corresponding state migration path according to the established mapping relationship and output the state change results of the spatial object after rule driving in real time, realizing the fully automated state inference process.

[0022] Step S500: Obtain rule-driven gain data according to the rule-driven-state transition mapping relationship, analyze the set of space objects to be supplied based on the rule-driven gain data, and obtain supply management decision results.

[0023] Specifically, based on the rule-driven state transition mapping relationship, the pre-migration state efficiency value and post-migration state efficiency value corresponding to each state transition path are extracted one by one. The state transition gain value corresponding to a single rule node is obtained through difference calculation. Then, according to the order of the rule propagation sequence, the state transition gain values ​​are accumulated sequentially to obtain the cumulative gain value of the rule chain. At the same time, the cumulative gain value of the rule chain is weighted and corrected by combining the strength of the dependency relationship between each node in the rule dependency chain network, and finally the complete rule-driven gain data is output. Subsequently, based on the gain data, the supply priority of each space object to be supplied is quantitatively calculated to form a supply priority set. All space objects to be supplied are sorted and divided into stages according to their priority, generating an ordered supply priority sequence. Finally, based on this sequence, information such as the supply time sequence, batch, and control requirements of the land parcels are integrated to output the final supply management decision result.

[0024] In one possible implementation, step S300 further includes: Step S310: Calculate the dependency relationship between any two land supply-related rules based on the rule feature vector of each land supply-related rule. The dependency relationship includes the preceding trigger relationship, the condition inheritance relationship, the constraint transitive relationship, and the result dependency relationship.

[0025] Step S320: Calculate the dependency strength between any two land supply-related rules based on the dependency relationship.

[0026] Step S330: Using each land supply-related rule as a node, establish dependency edges based on the dependency relationships, and generate a rule dependency chain network using the strength of the dependency relationships as the dependency edge weights.

[0027] Specifically, iterate through all the paired land supply rules, and denote them as the first rule. Rule 2 The process involves calculating and determining four types of dependencies in sequence: first, calculating the preceding triggering relationships and extracting... The resulting feature vector after execution and Triggering condition feature vector Using the cosine similarity formula Calculation result matching degree In the formula This represents the feature vector output after the first rule is executed. This represents the feature vector that triggers the second rule. Let be the dot product of two vectors. , Let these be the magnitudes of the two eigenvectors, respectively. When the calculated... Greater than the preset matching threshold At that time, the judgment and There are two aspects: first, there is a pre-triggered relationship; second, there is a calculation condition inheritance relationship, which is extracted. Constraint feature set , Constraint feature set According to the formula Calculate constraint coverage In the formula Represents the intersection of two constraint sets. A function to count the total number of elements in a set, if Greater than the preset coverage threshold If the conditional inheritance relationship exists between the two, then the constraint transitivity relationship is calculated and extracted. Affected object collection , Affected object collection Through formula Calculate object overlap In the formula The intersection of two sets of affected objects. For the union of two sets of affected objects, when Greater than the preset overlap threshold When determining whether there is a constraint transitive relationship between the two, and fourthly, when determining the dependency relationship of the calculation results, extract... Pre-execution state feature vector , Post-execution state feature vector Using the Euclidean distance normalization formula Computational state consistency In the formula Let Euclidean distance be the feature vector of two states. To find the maximum value function, , Let be the magnitudes of the two state feature vectors, if Greater than the preset consistency threshold If the result is determined, it is determined that there is a result dependency relationship between the two rules, and finally the calculation and identification of the four types of dependencies between all pairs of rules are completed.

[0028] Matching degree of results corresponding to the prior triggering relationship The degree of constraint inclusion corresponding to conditional inheritance relationship The degree of overlap of objects corresponding to transitive constraints State consistency corresponding to outcome dependencies As the basic calculation factors, the weight coefficients corresponding to the four factors are set as follows: , , , And satisfy Using the weighted summation formula Calculate the dependency strength W between the two land supply rules; in the formula, For the matching degree of results between rules, To define the inclusion degree of constraints between rules. For the overlap between objects in the rules, To ensure consistency of state among rules. , , , These are the preset weight coefficients corresponding to the four types of correlation indicators, and W is the final value of the dependency strength obtained. The larger the value, the stronger the correlation between the two rules. By performing the above calculation on all pairs of rules in sequence, the dependency strength corresponding to each pair of rules can be obtained.

[0029] Each independent land supply-related rule in the land supply rule base is defined as an independent node in the network, and each node is configured with a unique identifier, rule name, and rule attribute information to complete the initial construction of all network nodes. Then, all pairwise rule combinations are traversed. For rule pairs that have been determined to have any one or more types of dependency relationships, such as pre-triggered, conditional inheritance, constraint transitivity, and result dependency, directed dependency edges are built between the corresponding two network nodes. The direction of the edge is strictly set according to the logical execution order and dependency direction between the rules. Then, the corresponding dependency strength calculated above is assigned as the weight parameter of the dependency edge to quantify the degree of association between nodes. In the above manner, dependency edges are deployed and weights are configured for all rule nodes with dependency relationships one by one to complete the full matching and topological combination of nodes, directed edges, and edge weights, and finally form a rule dependency chain network with complete structure and attributes.

[0030] In one possible implementation, step S310 further includes: Step S311: Obtain the rule result features of the first land supply-related rules based on the trigger condition features.

[0031] Step S312: Calculate the matching degree between the rule result features and the rule triggering condition features of the second land supply related rules. If the matching degree is greater than the preset matching degree threshold, it is determined to be a pre-trigger relationship.

[0032] Specifically, the complete rule feature vector of the first land supply-related rules is retrieved, the trigger condition features recorded in the vector are extracted, the condition verification is completed according to the rule preset logic and business judgment standards, and the complete execution process of the rule after the corresponding trigger conditions are met is simulated. After the rule is executed, the various output information such as the control conclusion, status change, and supporting disposal requirements output by the rule are sorted out, the above output information is decomposed in a structured manner, standardized and encoded, the data format and dimensions are unified, and finally the rule result features corresponding to the rule are obtained.

[0033] Extract the feature vector of the rule result corresponding to the first land supply-related rule. The trigger condition feature vector corresponding to the second land supply-related rules Using the cosine similarity formula Perform calculations to determine the matching degree of the results. In the formula This represents the inner product of two eigenvectors. , Let the magnitudes of the two feature vectors be the values ​​of the matching degree calculated from the results. Matching degree threshold with the system preset When a comparison is performed, The value is greater than In this case, it can be determined that there is a prior triggering relationship between the first land supply-related rule and the second land supply-related rule.

[0034] In one possible implementation, step S310 further includes: Step S313: Calculate the constraint inclusion degree of the first land supply related rule and the second land supply related rule based on the constraint condition characteristics. If the constraint inclusion degree is greater than the preset inclusion degree threshold, it is determined to be a condition inheritance relationship.

[0035] Step S314: Calculate the object overlap between the first land supply related rule and the second land supply related rule based on the characteristics of the affected object. If the object overlap is greater than a preset overlap threshold, it is determined to be a constraint transitive relationship.

[0036] Step S315: Calculate the consistency between the state before the execution of the first land supply-related rule and the state after the execution of the second land supply-related rule. If the consistency is greater than a preset consistency threshold, it is determined to be a result dependency relationship.

[0037] Specifically, do not extract the constraint feature set of the first land supply-related rules. The set of constraint characteristics of rules related to the second land supply According to the formula Calculate constraint coverage In the formula This represents the intersection of two sets of constraint feature sets. The function that counts the number of elements in a set will calculate the constraint coverage. Compared with the system's preset inclusion threshold To make a comparison, when Greater than When determining that there is a conditional inheritance relationship between the first land supply-related rules and the second land supply-related rules.

[0038] Extract the feature set of the objects affected by the first land supply-related rules respectively. The set of characteristics of objects affected by rules related to the second land supply According to the formula Calculate object overlap In the formula Represents the intersection of two sets of features affecting objects. Represents the union of two sets of features affecting objects. The function that counts the number of elements in a set calculates the object overlap. overlap threshold with system preset When a comparison is performed, Greater than When determining that there is a constraint transmission relationship between the first land supply-related rules and the second land supply-related rules.

[0039] Extract the state feature vectors of the first land supply-related rules before their execution. The state feature vector after the implementation of the second land supply-related rules The Euclidean distance normalization formula is adopted. Computational state consistency In the formula Let Euclidean distance be the feature vector of two states. , These are the magnitudes of the two state feature vectors, respectively. To find the function with the maximum value, the calculated state consistency is... Consistency threshold with system preset When a comparison is performed, Greater than When determining that there is an outcome dependency between the first land supply-related rule and the second land supply-related rule.

[0040] In one possible implementation, step S320 further includes: The dependency strength between any two land supply-related rules is calculated based on the dependency relationship. The dependency strength is obtained by weighting the result matching degree, constraint inclusion degree, object overlap degree, and state consistency.

[0041] Specifically, extract the calculated result matching degree. Constraint inclusion degree Object overlap and state consistency Four indicators, each with its own pre-assigned weight coefficient. , , The sum of the values ​​of each weight coefficient satisfies Based on the weighted summation formula Calculate the dependency strength W between two land supply-related rules, where... , , , These are the preset weight coefficients for result matching degree, constraint inclusion degree, object overlap degree, and state consistency, respectively. For the matching degree of results between rules, To define the inclusion degree of constraints between rules. For the overlap between objects in the rules, To ensure consistency of state among rules, and with W representing the final dependency strength, the dependency strength of each pair of rules can be obtained by iterating through all the land supply-related rules.

[0042] In one possible implementation, step S400 further includes: Step S410: The spatial state transition model obtains the rule propagation sequence by performing rule propagation on the rule dependency chain network.

[0043] Step S420: Identify the target space object to be supplied corresponding to each rule node and the current space status corresponding to each target space object to be supplied according to the rule propagation sequence. The space status includes the preparation completion status, infrastructure improvement status, public service support status, industry introduction status, and supply status.

[0044] Step S430: Analyze the rule execution result corresponding to each rule node in the rule propagation sequence to obtain the target space state.

[0045] Step S440: Determine the state transition path based on the current spatial state and the target spatial state.

[0046] Step S450: Obtain the rule-driven state transition mapping relationship based on the mapping relationship between each rule node and the corresponding state transition path.

[0047] Specifically, the process involves traversing all nodes in the rule dependency chain network, selecting rule nodes without preceding dependency edges as the starting nodes for rule propagation, and determining the order of rule execution based on the pointing relationships of directed dependency edges and the strength of dependency relationships between nodes. Starting from the starting node, the process propagates the rule across the entire domain by passing it layer by layer according to the directed dependency edges. During propagation, adjacent nodes with higher dependency strength are prioritized as the next execution nodes. At the same time, different topologies such as single dependency and multiple dependency are distinguished. For nodes with multiple preceding dependency edges, execution is triggered only after all preceding rule nodes have completed propagation. The process continues to traverse all rule nodes sequentially along the network topology, fully recording the execution order, associated dependency edges, and corresponding weights of rule nodes in each round of propagation. Finally, all rule nodes are arranged in order according to the propagation sequence to generate a rule propagation sequence with a logical order.

[0048] The system iterates through each rule node in the rule propagation sequence, retrieves the rule feature vector corresponding to that node, extracts the features of the affected objects, and compares these features with the attribute features of each spatial object in the set of spatial objects to be supplied. This accurately locates all target spatial objects to be supplied affected by the current rule node. Then, for the identified target spatial objects to be supplied, the system retrieves their real-time status data from the spatial object attribute database. It then compares these data with the judgment criteria and feature indicators of five standard spatial states: preparation completion status, infrastructure improvement status, public service support status, industry introduction status, and supply availability status. This process classifies and identifies the status, clearly records the current spatial state of each target spatial object to be supplied, and sequentially completes the association identification and information collection of all rule nodes, corresponding target spatial objects, and the current spatial states of the objects in the rule propagation sequence.

[0049] Following the order of the rule propagation sequence, each rule node is processed sequentially. First, the complete rule feature vector of the current rule node is retrieved, and the execution action features are extracted. Combined with the pre-set business logic, control requirements, and disposal standards of the rule, the complete execution process of the rule in the current spatial state is simulated, and standardized and quantitative rule execution results are output. For the five spatial states of preparation completion, infrastructure improvement, public service support, industry introduction, and supply availability, corresponding state indicator systems and judgment threshold ranges are pre-constructed. The rule execution results are decomposed into sub-quantitative indicators that correspond one-to-one with the five states. Then, the decomposed indicator data are compared with the indicator thresholds, judgment conditions, and feature ranges of each spatial state. Accurate matching is achieved through item-by-item comparison and comprehensive scoring. The form formed by the spatial object after the rule is determined based on the category with the highest matching degree. Finally, the corresponding target spatial state is locked and output.

[0050] The system retrieves the current spatial state of the target space object to be supplied and the target spatial state obtained through rule execution parsing. Complete quantitative feature vectors are extracted for both states, covering five core dimensions: preparation completion, infrastructure completeness, public service support completeness, industry introduction maturity, and land availability. Then, each dimension of the two states is aligned and compared, calculating the state difference of each dimension and the overall state difference. The overall state difference is compared to a preset effective state transition threshold. If the overall difference is less than or equal to the preset threshold, the space object is determined not to have undergone effective state transition and has no corresponding transition path. If the overall difference is greater than the preset threshold, effective state transition is determined. Further analysis is performed by combining the execution order of the rule propagation sequence, the initial category of the current spatial state, and the target spatial state. The final classification of spatial states involves tracing the complete hierarchical change process of spatial states from the initial five states—namely, completed preparation state, improved infrastructure state, public service support state, industrial introduction state, and available state (single or combined forms)—to the target state under the current rule-driven conditions. Key parameters such as the dimension of state change, the magnitude of indicator change, the source of the rule-driven mechanism, and the sequence of migrations are recorded during the migration process. Continuous state change nodes are linked together in chronological and logical order to form a complete and orderly link encompassing the initial state, intermediate change states, and the final target state. Ultimately, a standardized spatial state migration path uniquely matching this rule-driven scenario is generated and determined. This path is then bound and archived with the current rule node and the corresponding available spatial object, providing accurate path data support for subsequently constructing a rule-driven state migration mapping relationship.

[0051] The algorithm iterates through all rule nodes that have completed execution and parsing in the rule propagation sequence, matching each rule node with its unique pending spatial object, initial current spatial state, target spatial state after rule execution, and established standardized state transition path. Using rule nodes in the rule dependency chain network as the core mapping entity, it establishes a one-to-one basic association entry: "single rule node - corresponding spatial object - initial state - target state - state transition path." Based on this, it integrates the dependency levels, execution order, rule-driven gains, and corresponding state transition dimensions, amplitudes, and validity characteristics of all rule nodes. It then performs concatenation, aggregation, and deduplication calibration on duplicate spatial objects and multi-level state transition paths driven by continuous rules, eliminating invalid or non-triggered empty mapping entries and retaining all valid complete state transition links driven by rules. Finally, it structures and standardizes all association entries, unifying the mapping data format and dimensions, and solidifying the corresponding association logic of rule node parameters, rule dependency strength, spatial state parameters, and transition path characteristics. This forms a comprehensive, structured rule-driven-state transition mapping relationship covering all pending spatial objects, all land supply rules, and complete state transition links.

[0052] In one possible implementation, step S440 further includes: Step S441: Calculate the state difference degree between the current state feature vector of the current spatial state and the target state feature vector of the target spatial state.

[0053] Step S442: When the state difference is greater than the preset migration threshold, it is determined that the current spatial state has migrated to the target spatial state, and the state migration path is recorded.

[0054] Specifically, extract the current state feature vector corresponding to the current spatial state respectively. Target state feature vector corresponding to the target space state The vector dimension uniformly corresponds to five quantitative indicators: preparation completion, infrastructure completeness, public service support completeness, industry introduction maturity, and land supply availability, and adopts a normalized Euclidean distance formula. Calculate the state difference degree D, where This represents the value of the i-th dimension of the current state feature vector. The i-th dimension of the target state feature vector represents the index value. The summation term is the square root of the sum of the squared differences of the two vectors in each dimension, yielding the original Euclidean distance. , These are the magnitudes of the current state feature vector and the target state feature vector, respectively. To obtain the maximum value function, the distance normalization process is completed through the modulus to obtain the state difference degree D with a value range of 0 to 1. The larger the value of D, the more significant the difference between the current spatial state and the target spatial state in various indicators, thereby quantifying the overall deviation between the two types of spatial states.

[0055] The calculated state difference degree D is compared with the system's pre-configured migration threshold. Perform numerical comparison, if If the supplied spatial object undergoes a valid state transition driven by the current rule node, then the current spatial state category, original indicator values ​​for each dimension, target spatial state category, changed indicator values ​​for each dimension, current rule node number, rule dependency strength, and rule execution sequence information corresponding to the object are extracted and arranged in an orderly manner according to a fixed data structure of initial state - changed dimension - rule driving source - final target state, generating a complete and traceable state transition path and storing it in the model's internal path database; if If no valid state transition occurs, no corresponding transition path is generated or recorded. Instead, the rule is marked as having no effect on the current spatial object's state change. The difference comparison and path recording operations for all rule nodes in the rule propagation sequence are then completed sequentially.

[0056] In one possible implementation, step S500 further includes: Step S510: Based on the rule-driven state transition mapping relationship, obtain the pre-migration state performance value and post-migration state performance value for each state transition path.

[0057] Step S520: Calculate the state migration gain value of the corresponding rule node based on the state performance value before migration and the state performance value after migration.

[0058] Step S530: Calculate the cumulative gain value of the state transition according to the rule propagation sequence to obtain the cumulative gain value of the rule chain.

[0059] Step S540: By identifying the strength of the dependency relationship between each rule node in the rule propagation sequence, the cumulative gain value of the rule chain is weighted and corrected using the strength of the dependency relationship, and rule-driven gain data is output.

[0060] Specifically, it iterates through all valid state transition paths in the rule-driven state transition mapping relationship. First, it extracts the current state feature vector before migration and the target state feature vector after migration from each individual path. These vectors contain five dimensions: preparation completion, infrastructure completeness, public service support completeness, industry introduction maturity, and land availability. Then, it pre-configures the efficiency weight coefficients corresponding to the five spatial state dimensions. , , , , ,satisfy The efficiency-weighted calculation formula is adopted. Solve for the performance values ​​separately, where Let the i-th dimension of the state feature vector be the index value, and substitute it into the formula to calculate the state efficiency value before the transition. The efficiency value of the post-transition state is calculated by substituting the feature vector of the target state after the transition into the formula. Match the corresponding migration path. and Binding storage is performed to complete the batch calculation and aggregation of two-stage performance values ​​for all state transition paths.

[0061] Retrieve the pre-migration state performance value bound to a single state transition path Performance value after migration The difference calculation formula is used. Solve for the state transition base gain G, where This represents the overall state performance value of the space object to be supplied before the rules are executed. G represents the overall state performance value of the object after the state transition driven by the current rule node, where G represents the original performance improvement under a single path. The strength of the dependency relationship W between the rule node and the corresponding spatial object is then introduced as a correction coefficient, and the correction formula is used to further refine the performance. The final state transition gain value corresponding to the rule node is calculated. In the formula, W represents the strength of the dependency relationship between rules calculated using the weighted average of the four types of correlation indicators mentioned earlier, which is used to quantify the effectiveness of the rule's effect. The higher the value, the stronger the optimization and improvement effect of the rule on the supply conditions of the corresponding spatial object. Traverse all state transition paths and substitute them into the formula one by one to complete the calculation and storage of the state transition gain value of all rule nodes.

[0062] The execution order of the rule propagation sequence is used as the timing basis for cumulative calculation, and the temporary variable of cumulative gain is initialized. Iterate through each rule node in the sequence from beginning to end, and retrieve the final state transition gain value matched by the current rule node. Add the gain value to the temporary variable. In the process, single-step gain accumulation is completed; if the same space object to be supplied has multiple consecutive rule nodes in the sequence that trigger multi-level state transitions in sequence, then the corresponding rules of each level are continuously superimposed in sequence. Without skipping any intermediate rule gains, the process continues until all rule nodes associated with the propagation sequence of that rule have been traversed. After the traversal is complete, a temporary variable is used. The final value is the cumulative gain value of the rule chain for the corresponding space object to be supplied. This cumulative gain value is used to characterize the overall improvement of the comprehensive efficiency of land supply after the action of the entire set of continuous rules. Each rule propagation sequence is bound to its calculated cumulative gain value and stored for later use.

[0063] First, extract the dependency strength W between each pair of adjacent rule nodes in the rule propagation sequence, and then calculate the average value of the dependency strengths of all adjacent nodes in the entire rule propagation sequence. Using the modified calculation formula Complete the gain weighting correction, where To obtain the cumulative gain value of the rule chain, The average dependency strength among rules within the sequence. This is the corrected rule-driven gain data. The correction logic is used to calibrate the overall gain level by combining the tightness of the correlation between rules, weaken the inflated gain deviation caused by weakly correlated rule chains, strengthen the gain weight of strongly correlated rule combinations, and after completing the weighted correction operation of all rule propagation sequences, the corresponding spatial object identifier to be supplied, rule propagation sequence number, original cumulative gain value, average dependency strength, and corrected rule-driven gain data of each sequence are uniformly structured and encapsulated to obtain a complete and standardized rule-driven gain dataset and output it, providing a quantitative basis for subsequent land supply priority assessment.

[0064] In one possible implementation, step S500 further includes: Step S550: Calculate the supply priority set of the set of spatial objects to be supplied according to the rule-driven gain data.

[0065] Step S560: Divide the set of spatial objects to be supplied into time sequences according to the supply priority set, obtain the supply priority sequence, and generate supply management decision results based on the supply priority sequence.

[0066] Specifically, extract the rule-driven gain data corresponding to each space object to be supplied within the set. Filter all gain data to obtain the global maximum value. and minimum value Through the extreme value normalization formula Solve for the supply priority score of the i-th spatial object The score ranges from 0 to 1, with higher gain resulting in higher priority score. The unique identifier, rule-driven gain, and priority score of each space object to be supplied are linked together. The associated data of all objects are collected and organized into a standardized structured dataset, forming a supply priority set covering all space objects to be supplied and outputting it.

[0067] Extract the priority score corresponding to each spatial object to be supplied within the supply priority set, sort all spatial objects to be supplied in descending order of score, divide them into different supply time batches according to the score gradient, match the earlier supply time period with the higher priority objects, and match the later supply time period with the lower priority objects, and form a complete supply priority sequence after orderly arrangement; then combine the cumulative gain of the rule chain corresponding to each spatial object, complete information of spatial status, supporting indicators of the plot, and other auxiliary data, and determine the order of land supply, development start time and supporting construction synchronization requirements of each spatial object to be supplied based on the sorted supply priority sequence, integrate all time arrangement and control requirements, and output standardized land supply management decision results.

[0068] This embodiment takes 10 land parcels in an industrial park as the analysis object. Based on the rule-driven gain data calculated above, the priority score of each spatial object to be supplied is solved by extreme value normalization. The priority ranking, supply batch and time sequence are completed by combining the scores. The specific calculation results are shown in Table 1: Table 1. Gains, Priorities, and Supply Arrangements for Space Objects to be Supplied

[0069] Example 2, based on the same inventive concept as the rule-driven land preparation post-supply space analysis method in the foregoing examples, such as... Figure 2 As shown, this application provides a rule-driven system for analyzing the supply space after land preparation. The system and method embodiments in this application are based on the same inventive concept. The system includes: The module 10 for constructing a set of spatial objects to be supplied is used to acquire basic spatial data of the land preparation area and construct a set of spatial objects to be supplied based on the basic spatial data.

[0070] The rule feature vector calling module 20 is used to call the land supply related rule library to parse the rule feature vector of each land supply related rule. The rule feature vector includes at least trigger condition features, constraint condition features, affected object features, and execution action features.

[0071] The rule dependency chain network generation module 30 is used to generate a rule dependency chain network according to the rule feature vector of each land supply-related rule.

[0072] The mapping relationship acquisition module 40 is used to establish a spatial state transition model for each spatial object in the set of spatial objects to be supplied. The spatial state transition model obtains the rule-driven-state transition mapping relationship by performing rule propagation on the rule dependency chain network.

[0073] The decision result acquisition module 50 is used to acquire rule-driven gain data according to the rule-driven-state transition mapping relationship, analyze the set of space objects to be supplied based on the rule-driven gain data, and obtain supply management decision results.

[0074] Furthermore, the system is also used to implement the following functions: Based on the rule feature vector of each land supply-related rule, the dependency relationship between any two land supply-related rules is calculated, wherein the dependency relationship includes the pre-trigger relationship, the condition inheritance relationship, the constraint transitive relationship, and the result dependency relationship; the dependency strength between any two land supply-related rules is calculated based on the dependency relationship; with each land supply-related rule as a node, a dependency edge is established based on the dependency relationship, and a rule dependency chain network is generated with the dependency strength as the dependency edge weight.

[0075] Furthermore, the system is also used to implement the following functions: Obtain the rule result features of the first land supply-related rule based on the trigger condition features; calculate the result matching degree between the rule result features and the rule trigger condition features of the second land supply-related rule; if the result matching degree is greater than the preset matching degree threshold, it is determined to be a pre-trigger relationship.

[0076] Furthermore, the system is also used to implement the following functions: Calculate the constraint inclusion degree between the first land supply-related rule and the second land supply-related rule based on constraint condition characteristics. If the constraint inclusion degree is greater than a preset inclusion degree threshold, it is determined to be a condition inheritance relationship. Calculate the object overlap degree between the first land supply-related rule and the second land supply-related rule based on the influence object characteristics. If the object overlap degree is greater than a preset overlap threshold, it is determined to be a constraint transitive relationship. Calculate the state consistency between the state before rule execution of the first land supply-related rule and the state after rule execution of the second land supply-related rule. If the consistency is greater than a preset consistency threshold, it is determined to be a result dependency relationship.

[0077] Furthermore, the system is also used to implement the following functions: The dependency strength between any two land supply-related rules is calculated based on the dependency relationship. The dependency strength is obtained by weighting the result matching degree, constraint inclusion degree, object overlap degree, and state consistency.

[0078] Furthermore, the system is also used to implement the following functions: The spatial state transition model obtains a rule propagation sequence by performing rule propagation on the rule dependency chain network; it identifies the target space object to be supplied corresponding to each rule node and the current spatial state corresponding to each target space object based on the rule propagation sequence, wherein the spatial state includes preparation completion state, infrastructure improvement state, public service support state, industry introduction state, and supplyable state; it analyzes the rule execution result corresponding to each rule node in the rule propagation sequence to obtain the target spatial state; it determines the state transition path based on the current spatial state and the target spatial state; and it obtains the rule-driven-state transition mapping relationship based on the mapping relationship between each rule node and the corresponding state transition path.

[0079] Furthermore, the system is also used to implement the following functions: Calculate the state difference degree between the current state feature vector of the current spatial state and the target state feature vector of the target spatial state; when the state difference degree is greater than a preset migration threshold, determine that the current spatial state has migrated to the target spatial state, and record the state migration path.

[0080] Furthermore, the system is also used to implement the following functions: Based on the rule-driven state transition mapping relationship, obtain the pre-migration state performance value and post-migration state performance value for each state transition path; calculate the state transition gain value of the corresponding rule node based on the pre-migration state performance value and post-migration state performance value; perform cumulative calculation of the state transition gain value according to the rule propagation sequence to obtain the cumulative gain value of the rule chain; by identifying the dependency strength between each rule node in the rule propagation sequence, use the dependency strength to perform weighted correction on the cumulative gain value of the rule chain, and output the rule-driven gain data.

[0081] Furthermore, the system is also used to implement the following functions: The supply priority set of the set of spatial objects to be supplied is calculated based on the rule-driven gain data; the set of spatial objects to be supplied is divided into time sequences according to the supply priority set to obtain the supply priority sequence; and the supply management decision result is generated based on the supply priority sequence.

[0082] It should be noted that the order of the embodiments described above is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. Specific embodiments of this specification have been described above. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0083] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0084] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A rule-driven method for analyzing the supply space after land preparation, characterized in that, The method includes: Acquire basic spatial data of the land preparation area, and construct a set of spatial objects to be supplied based on the basic spatial data. The basic spatial data includes at least regional administrative boundary vector data, plot outline vector data, land use data, ownership information data, planning and control data, infrastructure distribution data, public service supporting data, and current plot attribute data. The rule feature vector of each land supply-related rule is parsed by calling the land supply-related rule base. The land supply-related rules include land preparation rules, infrastructure rules, public service support rules, industry introduction rules, and supply rules related to the space to be supplied. The rule feature vector includes at least trigger condition features, constraint condition features, affected object features, and execution action features. Generate a rule dependency chain network based on the rule feature vector of each land supply-related rule; Establish a spatial state transition model for each spatial object in the set of spatial objects to be supplied. The spatial state transition model obtains the rule-driven-state transition mapping relationship by performing rule propagation on the rule dependency chain network. According to the rule-driven state transition mapping relationship, rule-driven gain data is obtained. The set of space objects to be supplied is analyzed based on the rule-driven gain data to obtain supply management decision results. The rule-driven gain data is data that characterizes the degree of state efficiency improvement generated by the rule propagation driving the space objects to be supplied to migrate from the current space state to the target space state. The supply management decision results include at least the supply priority and corresponding supply sequence of the space objects to be supplied.

2. The method as described in claim 1, characterized in that, The method for generating a rule dependency chain network based on the rule feature vector of each land supply-related rule includes: Based on the rule feature vector of each land supply-related rule, calculate the dependency relationship between any two land supply-related rules, wherein the dependency relationship includes the preceding trigger relationship, the condition inheritance relationship, the constraint transitive relationship, and the result dependency relationship; Calculate the dependency strength between any two land supply-related rules based on the aforementioned dependencies; Each land supply-related rule is used as a node, and dependency edges are established based on the aforementioned dependency relationships. The strength of the dependency relationships is used as the weight of the dependency edges to generate a rule dependency chain network.

3. The method as described in claim 2, characterized in that, Methods for calculating the dependency between any two land supply-related rules include: Obtain the rule result characteristics of the first land supply-related rules based on the trigger condition characteristics; Calculate the matching degree between the rule result features and the rule triggering condition features of the second land supply related rules. If the matching degree is greater than a preset matching degree threshold, it is determined to be a pre-trigger relationship.

4. The method as described in claim 2, characterized in that, Methods for calculating the dependency between any two land supply-related rules include: Calculate the constraint inclusion degree of the first land supply-related rule and the second land supply-related rule based on the constraint condition characteristics. If the constraint inclusion degree is greater than a preset inclusion degree threshold, it is determined to be a condition inheritance relationship. Calculate the overlap between the first land supply-related rule and the second land supply-related rule based on the characteristics of the affected objects. If the overlap is greater than a preset overlap threshold, it is determined to be a constraint transitive relationship. Calculate the consistency between the state before the execution of the first land supply-related rule and the state after the execution of the second land supply-related rule. If the consistency is greater than a preset consistency threshold, it is determined to be a result dependency relationship.

5. The method as described in claim 2, characterized in that, The dependency strength between any two land supply-related rules is calculated based on the dependency relationship. The dependency strength is obtained by weighting the result matching degree, constraint inclusion degree, object overlap degree, and state consistency.

6. The method as described in claim 1, characterized in that, The spatial state transition model obtains the rule-driven-state transition mapping relationship by performing rule propagation on the rule dependency chain network, and the method includes: The spatial state transition model obtains the rule propagation sequence by performing rule propagation on the rule dependency chain network; The target space object to be supplied corresponding to each rule node is identified according to the rule propagation sequence, and the current space status corresponding to each target space object to be supplied is identified. The space status includes preparation completion status, infrastructure improvement status, public service support status, industry introduction status, and supply status. Analyze the rule execution result corresponding to each rule node in the rule propagation sequence to obtain the target space state; Determine the state transition path based on the current spatial state and the target spatial state; Based on the mapping relationship between each rule node and its corresponding state transition path, obtain the rule-driven state transition mapping relationship.

7. The method as described in claim 6, characterized in that, The method for determining a state transition path based on the current spatial state and the target spatial state includes: Calculate the state difference degree between the current state feature vector of the current spatial state and the target state feature vector of the target spatial state; When the state difference is greater than a preset migration threshold, it is determined that the current spatial state has migrated to the target spatial state, and the state migration path is recorded.

8. The method as described in claim 6, characterized in that, The method for obtaining rule-driven gain data according to the aforementioned rule-driven-state transition mapping relationship includes: Based on the rule-driven state transition mapping relationship, obtain the state performance value before and after the transition for each state transition path; Calculate the state migration gain value of the corresponding rule node based on the state performance value before migration and the state performance value after migration; The cumulative gain value of the rule chain is obtained by calculating the cumulative gain value of the state transition value according to the propagation sequence of the rule. By identifying the strength of the dependency relationships between each rule node in the rule propagation sequence, the cumulative gain value of the rule chain is weighted and corrected using the strength of the dependency relationships, and rule-driven gain data is output.

9. The method as described in claim 1, characterized in that, The method involves analyzing the set of space objects to be supplied based on the rule-driven gain data to obtain supply management decision results, including: The supply priority set of the set of spatial objects to be supplied is calculated based on the rule-driven gain data. The set of spatial objects to be supplied is divided into time sequences according to the supply priority set to obtain the supply priority sequence, and the supply management decision result is generated based on the supply priority sequence.

10. A rule-driven land preparation post-supply space analysis system, characterized in that, The system is used to implement the rule-driven land preparation post-supply space analysis method according to any one of claims 1-9, the system comprising: The module for constructing a set of spatial objects to be supplied is used to acquire basic spatial data of the land preparation area and construct a set of spatial objects to be supplied based on the basic spatial data. The rule feature vector invocation module is used to invoke the land supply-related rule library to parse the rule feature vector of each land supply-related rule. The rule feature vector includes at least trigger condition features, constraint condition features, affected object features, and execution action features. The rule dependency chain network generation module is used to generate a rule dependency chain network according to the rule feature vector of each land supply-related rule; The mapping relationship acquisition module is used to establish a spatial state transition model for each spatial object to be supplied in the set of spatial objects to be supplied. The spatial state transition model obtains the rule-driven-state transition mapping relationship by performing rule propagation on the rule dependency chain network. The decision result acquisition module is used to acquire rule-driven gain data according to the rule-driven-state transition mapping relationship, analyze the set of space objects to be supplied based on the rule-driven gain data, and obtain supply management decision results.

Images