Digital intelligence scene enabling canal heritage land utilization decision-making method and system

Abstract

The invention relates to the technical field of land resource management, in particular to a digital intelligence scene enabling canal heritage land utilization decision-making method and system. The method comprises the following steps: acquiring environment information, policy information, culture information and economic information of a target cultural heritage area, and constructing multi-source cultural heritage information; policy semantic analysis and spatialization are carried out on the policy information to obtain policy semantic information and spatial information, and a policy rule engine is constructed based on the policy semantic information and the spatial information; analyzing the multi-source cultural heritage information to obtain spatial value distribution data of the target cultural heritage region; generating a land utilization optimization decision set based on the spatialization value distribution data and a policy rule engine; and carrying out screening analysis on the land utilization optimization decision set, and outputting a land utilization optimization report. According to the method, the balance of cultural heritage protection intensity, ecological connectivity improvement and economic activity excitation is guaranteed, and the common value game problem in a linear heritage region is effectively solved.

Description

Technical Field

[0001] This application relates to the field of land resource management technology, and in particular to a digitally-enabled, scenario-based land use decision-making method and system for canal heritage sites. Background Technology

[0002] In existing land use decision-making practices, the methods used for linear cultural heritage (such as the Grand Canal) are mainly based on traditional spatial planning techniques, resulting in several technical characteristics. First, the acquisition of cultural value typically employs point-based identification, spatially locating only tangible heritage sites such as cultural relics, lacking quantitative means to assess the dynamic range and intensity of living cultural elements (including folk activities and traditional production and lifestyles). Second, ecological assessments often rely on general ecological value assessment models (such as the equivalent factor method). These models treat the ecosystem as a homogeneous unit, failing to reflect the canal's functional transmission, directionality, and the unique value of key ecological nodes as a linear ecological corridor. Third, policy constraints are usually treated as ex-post checks in the current process, failing to achieve semantic analysis and spatial mapping of policy texts during the planning stage. This leads to potential conflicts with heritage protection policies only being discovered after the plan is generated, thus affecting the feasibility of the plan. These technical characteristics collectively manifest as insufficient quantification of cultural value, homogenization of ecological assessments, and the post-event nature of policy conflicts, limiting the realization of accurate and forward-looking land use decisions based on the specific characteristics of linear cultural heritage. Summary of the Invention

[0003] This application provides a digitally-enabled, scenario-based land use decision-making method and system for canal heritage sites to address the aforementioned issues.

[0004] Firstly, this application provides a digitally-enabled method for land use decision-making in canal heritage sites. The method includes: acquiring environmental, policy, cultural, and economic information of the target cultural heritage area to construct multi-source cultural heritage information; performing policy semantic analysis and spatialization on the policy information to obtain policy semantic and spatial information, and constructing a policy rule engine based on the policy semantic and spatial information; performing multi-dimensional dynamic value analysis on the multi-source cultural heritage information to obtain spatialized value distribution data of the target cultural heritage area; performing multi-objective collaborative optimization and conflict diagnosis based on the spatialized value distribution data and the policy rule engine to generate a land use optimization decision set; and filtering and analyzing the land use optimization decision set to output a land use optimization report.

[0005] Through the aforementioned technical solutions, the unified spatialization of multi-source information enables the simultaneous quantification and visualization of cultural, ecological, and economic values, significantly improving the spatial accuracy and dynamic response capabilities of decision-making. The pre-construction of the policy rule engine and the conflict diagnosis mechanism embed compliance checks into the optimization process, reducing the cost of later rectification and implementation risks. The multi-objective collaborative optimization algorithm, while strictly adhering to policy constraints, ensures a balance between the intensity of cultural heritage protection, the improvement of ecological connectivity, and the stimulation of economic vitality, effectively solving the value game problem commonly encountered in linear heritage areas. The replicability and modular design of the overall framework support adaptive applications in canal heritage areas at different scales, providing a scientific basis for sustainable land governance.

[0006] Optionally, the step of performing policy semantic parsing and spatialization on the policy information to obtain policy semantic information and spatial information, and constructing a policy rule engine based on the policy semantic information and spatial information, includes: performing natural language parsing on the policy information, extracting control intensity terms and spatial range descriptions from the policy information, establishing a multi-level classification system including prohibition rules, restriction rules, and encouragement rules to obtain the policy semantic information; based on the spatial range description, transforming the abstract policy information into specific machine-executable spatial constraint rules, the spatial constraint rules being used to define the spatial scope of action, constraint strength parameters, and priority relationships of various policies; and based on the policy semantic information, associating the spatial constraint rules with the geographical coordinates corresponding to each rule under the multi-level classification system in the policy semantic information through a spatial matching algorithm to obtain the policy spatial information.

[0007] Optionally, the step of performing multidimensional dynamic value analysis on the multi-source cultural heritage information to obtain spatial value distribution data of the target cultural heritage area includes: identifying the spatial distribution characteristics of cultural heritage elements based on the cultural information, and constructing a cultural influence dissemination model based on distance attenuation and spatial accessibility; calculating the spatial influence radiation range and intensity attenuation law of each cultural source through the cultural influence dissemination model, and constructing continuously distributed cultural value intensity distribution data; analyzing the ecological background characteristics and structural connectivity of the canal corridor based on the environmental information, and constructing a corridor service flow model based on ecological process simulation; and through the corridor service... The service flow model identifies key locations of ecological pinch points and ecological hubs, assesses the importance of each region in maintaining the overall ecological function of the corridor, and constructs ecological flow map data to characterize the strength of ecological function connectivity. Based on the environmental and economic information, it integrates multi-source economic vitality index data and constructs a value density estimation model based on spatial statistics and economic geography principles. Through the value density estimation model, it analyzes the impact of industrial agglomeration effects and market size factors, and constructs economic value density distribution data. Based on the cultural value intensity distribution data, the ecological flow map data, and the economic value density distribution data, it constructs the spatialized value distribution data.

[0008] Optionally, the process of constructing the cultural value intensity distribution data includes: identifying the spatial distribution characteristics of various cultural heritage elements based on the cultural information, and unifying tangible cultural heritage sites, intangible cultural heritage activity sites, historical and cultural routes, and traditional production and living areas as sources of cultural influence; constructing a cultural value dissemination model based on field strength theory and the sources of cultural influence; comprehensively considering the effects of distance attenuation, differences in accessibility, and social activity through the cultural value dissemination model, and introducing a nonlinear attenuation function to describe the dissemination characteristics of cultural value, considering the superposition effect and mutual reinforcement mechanism of influence in areas with dense cultural heritage, and quantifying the spatial diffusion law of cultural influence; integrating multi-source cultural data, including cultural activity trajectories recorded in historical documents, cultural practice popularity reflected on social media, and cultural space usage intensity obtained from on-site surveys; and, based on the spatial diffusion law, transforming the discrete cultural activity trajectories, cultural practice popularity, and cultural space usage intensity into continuously distributed cultural value intensity surface data through spatial interpolation and field strength superposition methods to obtain the cultural value intensity distribution data.

[0009] Optionally, the process of constructing the ecological circulation map data includes: analyzing the ecological status within the target cultural heritage area based on the environmental information, extracting the ecological baseline conditions of the target cultural heritage area, including hydrological information, vegetation information, and biological information; using the hydrological information, vegetation information, and biological information as node information, constructing an ecological service flow simulation model based on a directed graph, and introducing resistance factors affecting key ecological processes into the ecological service flow simulation model to simulate the circulation and change information of the three key ecological processes—species migration, water conservation, and nutrient cycling—in the corridor; the resistance factors include land use barriers, transportation facility barriers, and topographic limitations; and performing visualization map processing on the circulation and change information to construct the ecological circulation map data reflecting the ecological value of different regions.

[0010] Optionally, the process of constructing the economic value density distribution data includes: analyzing the economic vitality of the target cultural heritage area under the dual verification of environment and economy based on the environmental information and the economic information, and constructing multi-source economic vitality observation data, including nighttime light intensity, commercial facility density, traffic flow statistics, land transaction prices, and industrial input-output data; constructing a value density estimation model based on geographically weighted regression and spatial econometrics based on the multi-source economic vitality observation data, and introducing the influence of spatial heterogeneity and spatial dependence; deeply analyzing the spatial agglomeration patterns of economic activities, and identifying the distribution characteristics of industrial cluster areas, commercial center areas, and innovation activity areas; using spatial interpolation methods to transform point-like and area-like economic observation data into continuously distributed economic value density surfaces; and spatially registering the economic value density data with land use grid units to construct the economic value density distribution data.

[0011] Optionally, the step of generating a land use optimization decision set by performing multi-objective collaborative optimization and conflict diagnosis based on the spatialized value distribution data and the policy rule engine includes: based on the policy rule engine, analyzing the spatial regions corresponding to the prohibited, restricted, and encouraged rules according to the spatialized value distribution data; using the spatial constraint rules of the policy rule engine as hard constraints in the multi-objective optimization process; taking the maximization of cultural value intensity, corridor ecological function flow, and economic value density as the core optimization objectives; and introducing structural rationality and spatial coordination of land use as secondary optimization objectives to construct a multi-objective optimization model; based on the multi-objective optimization model, using a targeted multi-objective evolutionary strategy for optimization solution; and constructing the land use optimization decision set through adaptive parameter adjustment and non-dominated ranking mechanisms; and during the multi-objective optimization process, monitoring the compliance with policy constraints in real time and accurately recording the policy compliance degree and constraint violation location of each potential scheme.

[0012] Optionally, the targeted multi-objective evolutionary strategy includes: constructing a chromosome coding scheme for land use spatial configuration, wherein each chromosome represents a complete land use scheme, chromosome gene loci correspond to planning grid units, and gene values ​​characterize the land use types allocated within that unit; designing a multi-objective fitness function, and using a weighted summation mechanism to evaluate the fitness of the cultural value intensity distribution data, corridor ecological function circulation data, and economic value density distribution data, quantifying the cultural value intensity distribution data, corridor ecological function circulation data, and economic value density distribution data into corresponding fitness values ​​to evaluate the merits of each chromosome; setting the operating parameters and operations of the genetic algorithm, and using the genetic algorithm to initially... A random population is initialized; simulated binary crossover is used to exchange gene segments between parent chromosomes in the random population to generate new individuals; polynomial mutation is implemented to randomly change some gene loci of the new individuals, introducing a small probability of random perturbation to maintain population diversity; an iterative optimization process is executed, in each generation, the population is non-dominated and sorted according to the fitness function, the non-dominated sorting result is obtained, and the crowding degree of individuals in the same frontier layer is calculated. Based on the non-dominated sorting result and the crowding degree, a tournament selection method is used to select superior individuals to enter the next generation; a convergence condition is set and a solution set is output. When the number of iterations reaches a preset maximum value, the algorithm is terminated, and all non-dominated solutions in the final population are output as the land use optimization decision set.

[0013] Optionally, the step of screening and analyzing the land use optimization decision set and outputting a land use optimization report includes: establishing a scheme screening mechanism based on multi-attribute utility theory; calculating the standardized utility values ​​of each scheme in the economic, ecological, and cultural dimensions for each scheme in the land use optimization decision set; ranking and initially selecting all schemes through weighted comprehensive scoring to obtain a preliminary scheme set; performing spatial overlay and change detection analysis on different preliminary schemes based on the preliminary scheme set; spatially overlaying the land use layout maps of different preliminary schemes with the current land use map; identifying the areas where land use types have changed through raster algorithms; and statistically analyzing their spatial distribution, area, and direction of change to obtain the land use scheme set corresponding to the preliminary scheme set; and analyzing the... The land use scheme set is described, and the land use scheme corresponding to each preliminary selection is compared with the current situation in terms of cultural, ecological and economic value. The percentage increase in cultural, ecological and economic value compared with the current situation is quantified, and the policy rule engine is used to perform a second compliance verification to ensure that the preliminary selection schemes do not contain any land use configurations that violate mandatory policy constraints, thus obtaining the optimal scheme set. The optimal scheme set is analyzed, and the land spatial configuration parameters of each scheme are decoded and visualized to generate a planning map of the land use spatial layout corresponding to each optimal scheme, a land use structure configuration table of land use area and spatial location of each land type, and an analysis report including comprehensive benefit comparison, policy compliance conclusions and potential implementation risks. The land use optimization report is constructed and output.

[0014] Secondly, this application provides a digitally-enabled, scenario-driven land use decision-making system for canal heritage sites. The system includes: an information collection module for acquiring environmental, policy, cultural, and economic information of the target cultural heritage area, constructing multi-source cultural heritage information; a policy analysis module for performing policy semantic parsing and spatialization on the policy information to obtain policy semantic and spatial information, and constructing a policy rule engine based on the policy semantic and spatial information; a value analysis module for performing multi-dimensional dynamic value analysis on the multi-source cultural heritage information to obtain spatialized value distribution data of the target cultural heritage area; a decision optimization module for performing multi-objective collaborative optimization and conflict diagnosis based on the spatialized value distribution data and the policy rule engine, generating a land use optimization decision set; and a report output module for filtering and analyzing the land use optimization decision set and outputting a land use optimization report. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram illustrating an application scenario provided in one embodiment of this application; Figure 2 A flowchart illustrating a digitally-enabled land use decision-making method for canal heritage sites, provided as an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a digitally-enabled land use decision-making system for canal heritage sites, provided as an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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 some, not all, of the embodiments of this application. 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.

[0018] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0019] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0020] In existing land use decision-making practices, the methods used for linear cultural heritage (such as the Grand Canal) are mainly based on traditional spatial planning techniques, resulting in several technical characteristics. First, the acquisition of cultural value typically employs point-based identification, spatially locating only tangible heritage sites such as cultural relics, lacking quantitative means to assess the dynamic range and intensity of living cultural elements (including folk activities and traditional production and lifestyles). Second, ecological assessments often rely on general ecological value assessment models (such as the equivalent factor method). These models treat the ecosystem as a homogeneous unit, failing to reflect the canal's functional transmission, directionality, and the unique value of key ecological nodes as a linear ecological corridor. Third, policy constraints are usually treated as ex-post checks in the current process, failing to achieve semantic analysis and spatial mapping of policy texts during the planning stage. This leads to potential conflicts with heritage protection policies only being discovered after the plan is generated, thus affecting the feasibility of the plan. These technical characteristics collectively manifest as insufficient quantification of cultural value, homogenization of ecological assessments, and the post-event nature of policy conflicts, limiting the realization of accurate and forward-looking land use decisions based on the specific characteristics of linear cultural heritage.

[0021] Based on this, this application provides a digitally-enabled land use decision-making method and system for canal heritage sites. Through the unified spatialization of multi-source information, it achieves the simultaneous quantification and visualization of cultural, ecological, and economic values, significantly improving the spatial accuracy and dynamic response capability of decision-making. The pre-construction of the policy rule engine and the conflict diagnosis mechanism embed compliance checks into the optimization process, reducing the cost of later rectification and implementation risks. The multi-objective collaborative optimization algorithm, while strictly adhering to policy constraints, ensures a balance between the intensity of cultural heritage protection, the improvement of ecological connectivity, and the stimulation of economic vitality, effectively solving the value game problem commonly found in linear heritage areas. The replicability and modular design of the overall framework support adaptive applications in canal heritage areas at different scales, providing a scientific basis for sustainable land governance.

[0022] Figure 1 This application provides an illustration of an application scenario. When planning the land use of canal heritage sites, the method provided in this application ensures a balance between the intensity of cultural heritage protection, the enhancement of ecological connectivity, and the stimulation of economic vitality, effectively solving the value game problem commonly encountered in linear heritage areas.

[0023] Specifically, the method provided in this application is applied to any server, which interacts with multi-source data collection nodes to obtain multi-source cultural heritage information provided by these nodes. Through the unified spatialization of this multi-source cultural heritage information, the synchronous quantification and visualization of cultural, ecological, and economic values ​​are achieved, significantly improving the spatial accuracy and dynamic response capability of decision-making. The pre-construction of the policy rule engine and the conflict diagnosis mechanism embed compliance checks into the optimization process, reducing the cost and implementation risk of later rectification of the plan. The multi-objective collaborative optimization algorithm, while strictly adhering to policy constraints, ensures a balance between the intensity of cultural heritage protection, the improvement of ecological connectivity, and the stimulation of economic vitality, effectively solving the value game problem commonly encountered in linear heritage areas. The replicability and modular design of the overall framework support adaptive applications in canal heritage areas at different scales, providing a scientific basis for sustainable land governance and a reliable solution reference for planners. Specific implementation methods can be found in the following embodiments.

[0024] Figure 2 This is a flowchart illustrating a digitally-enabled land use decision-making method for canal heritage sites, provided as an embodiment of this application. The method of this embodiment can be applied to servers in the aforementioned scenarios. Figure 2 As shown, the method includes: S201. Obtain environmental, policy, cultural, and economic information about the target cultural heritage area to construct multi-source cultural heritage information; S202. Perform policy semantic parsing and spatialization on the policy information to obtain policy semantic information and spatial information, and construct a policy rule engine based on the policy semantic information and spatial information; S203. Perform multidimensional dynamic value analysis on the multi-source cultural heritage information to obtain spatial value distribution data of the target cultural heritage area; S204. Based on the spatialized value distribution data and the policy rule engine, perform multi-objective collaborative optimization and conflict diagnosis to generate a land use optimization decision set; S205. Screen and analyze the land use optimization decision set, and output a land use optimization report.

[0025] Technical Background and Working Principle: Linear cultural heritage (LCH) areas, such as the Grand Canal region, possess multiple attributes including culture, ecology, and economy. Land use decisions in these areas face complex challenges due to conflicting values ​​and policy constraints. Traditional decision-making methods often rely on single-objective optimization or static assessment, making it difficult to simultaneously integrate the spatial correlations of environmental, policy, cultural, and economic information. This results in homogenized solutions, poor compliance, and low overall benefits. This embodiment, based on the concept of digital and intelligent scenario empowerment, solves the dynamic coordination problem between multi-dimensional value quantification and policy constraints through multi-source information fusion and spatial expression. The working principle is as follows: First, four heterogeneous data categories—environmental, policy, cultural, and economic—are unified into multi-source cultural heritage information. Natural language processing technology is used to parse policy texts and transform them into machine-executable spatial constraint rules, constructing a policy rule engine. Second, through cultural influence dissemination models, ecosystem service flow models, and economic value density estimation models, spatial dynamic assessment of cultural, ecological, and economic values ​​is achieved, generating continuously distributed value data. Finally, combining the policy rule engine and spatial value data, a multi-objective evolutionary algorithm is used for collaborative optimization and conflict diagnosis, generating a set of land use schemes that balance compliance and value maximization. An optimization report is then output through screening and analysis. This process achieves end-to-end digitalization from data perception to decision output, ensuring a sustainable balance between cultural heritage preservation, ecological protection, and economic development.

[0026] Technical Solution and Component Functions: The technical solution in this embodiment includes five core steps: information collection, policy analysis, value analysis, decision optimization, and report output. The information collection module constructs a multi-source cultural heritage information database through an environmental information acquisition unit (integrating remote sensing imagery, meteorological station data, etc.), a policy information acquisition unit (accessing publicly available government texts and regulations), a cultural information acquisition unit (collecting tangible / intangible cultural heritage sites and social media activity trajectories), and an economic information acquisition unit (integrating nighttime lighting, land transaction prices, etc.). The policy analysis module consists of a natural language parsing unit (using lexical analysis and entity recognition technology to extract control vocabulary), a rule classification unit (establishing a three-tiered rule system of prohibition, restriction, and encouragement), a spatial constraint generation unit (mapping rules into geographic polygons and buffer zones), and a knowledge graph unit (supporting dynamic updates and version management), realizing policy semantic parsing and spatialization, and outputting a policy rule engine. The value analysis module comprises a cultural value dissemination model (calculating the spatial influence decay and superposition of cultural heritage sites based on field strength theory), an ecosystem service flow model (simulating the flow of processes such as species migration and water conservation through directed graphs), and an economic value density estimation model (applying geographically weighted regression analysis to analyze spatial heterogeneity). These three models are processed by a data fusion unit (using spatial interpolation and weighted superposition) to generate spatialized value distribution data. The decision optimization module, through a constraint rule mapping unit (converting policy constraints into grid feasibility markers), a multi-objective fitness calculation unit (weighted integration of cultural, ecological, and economic value objectives), and an evolutionary strategy-based solution unit (using the NSGA-II algorithm for non-dominated ranking and crowding calculation), generates a land use optimization decision set under rigid policy constraints. The report output module utilizes a multi-attribute utility calculation unit (standardizing three-dimensional values ​​and weighted ranking), a spatial overlay analysis unit (identifying land use change areas through raster operations), and a compliance verification unit (secondary verification of policy compliance) to output a land use optimization report containing planning maps, land use structure tables, and risk analysis.

[0027] Beneficial effects: This implementation method achieves simultaneous quantification and visualization of cultural, ecological, and economic values ​​through the unified spatialization of multi-source information, significantly improving the spatial accuracy and dynamic response capability of decision-making; the pre-construction of the policy rule engine and the conflict diagnosis mechanism embed compliance checks into the optimization process, reducing the cost of later rectification and implementation risks; the multi-objective collaborative optimization algorithm, while strictly adhering to policy constraints, ensures a balance between the intensity of cultural heritage protection, the improvement of ecological connectivity, and the stimulation of economic vitality, effectively solving the value game problem commonly found in linear heritage areas; the replicability and modular design of the overall framework support the adaptive application of canal heritage areas at different scales, providing a scientific basis for sustainable land governance.

[0028] In some embodiments, natural language processing is performed on the policy information to extract control intensity terms and spatial scope descriptions, and a multi-level classification system including prohibition rules, restriction rules, and encouragement rules is established to obtain the policy semantic information. Based on the spatial scope description, the abstract policy information is transformed into specific machine-executable spatial constraint rules, which define the spatial scope of action, constraint strength parameters, and priority relationships of various policies. Based on the policy semantic information, a spatial matching algorithm is used to associate the spatial constraint rules with the geographic coordinates corresponding to each rule in the multi-level classification system of the policy semantic information to obtain the policy spatial information.

[0029] Technical Background and Working Principle: The construction of a policy rule engine is central to addressing the challenges of policy compliance in land use decisions for Linear Cultural Heritage (LCH) sites. Traditional policy texts, presented in natural language, lack machine-readable structured expressions, making it difficult to automate constraint mapping and conflict detection in spatial planning. Especially for LCH areas such as the Grand Canal, policy provisions (e.g., the core protected area control requirements in the "Grand Canal Heritage Protection Plan") often involve complex spatial descriptions and multi-level control intensities, making manual interpretation prone to ambiguity and omissions. This embodiment integrates Natural Language Processing (NLP) with spatial information technology to transform abstract policy provisions into executable spatial constraint rules. The working principle is as follows: First, NLP technology is used to parse policy texts, extracting terms related to control intensity (such as "prohibited" and "restricted") and spatial descriptions (such as "200-meter buffer zone along the river") to construct a multi-level classification system. Second, geometric modeling is used to map rules to spatial objects (such as polygons and buffer zones), and constraint strength parameters and priority relationships are defined. Then, graph theory algorithms are used to detect spatial topological conflicts between rules (such as control contradictions in overlapping areas), and consistency is achieved through a priority coordination mechanism. Finally, knowledge graphs are used to dynamically maintain rule versions and relationships, and spatial matching algorithms are used to achieve precise binding between rules and geographic coordinates. This process ensures the pre-emptive and automated compliance checks of policy requirements in land use decision-making, significantly improving the accuracy and timeliness of decision-making.

[0030] Technical Solution and Component Functions: The technical solution of this embodiment includes five core steps: natural language parsing, rule classification and parameterization, conflict detection and coordination, knowledge graph construction, and spatial matching. The natural language parsing unit uses lexical analysis (such as word segmentation and entity recognition) and dependency parsing techniques to extract control intensity terms (e.g., "strictly prohibited development," "priority protection") and spatial scope descriptions (e.g., "1000-meter core area along the canal") from policy texts, and outputs structured labeled data. The rule classification unit establishes a three-level classification system based on the extraction results: prohibition rules (e.g., absolutely prohibiting the expansion of construction land), restriction rules (e.g., restricting development intensity), and encouragement rules (e.g., encouraging ecological restoration), and assigns a unique identifier and metadata to each type of rule. The spatial constraint generation unit transforms the classified rules into machine-executable spatial objects—prohibition rules are mapped to prohibited construction zone polygons, restriction rules are mapped to buffer zones with added constraint strength parameters (e.g., development density thresholds), and encouragement rules are mapped to incentive zones with set priority weights. Simultaneously, spatial topology operations (e.g., overlay analysis) are used to define... The rules cover relationships; the conflict detection unit uses a graph theory model to construct a rule interaction network, where nodes represent rule entities and edges represent spatial overlap relationships. It identifies conflict areas (such as the same location being both prohibited and encouraged) through traversal algorithms (e.g., prohibited classes take precedence over restricted classes) and generates a set of consistency constraints based on priority labels (e.g., prohibited classes take precedence over restricted classes) and reconciliation strategies (e.g., weighted average). The knowledge graph unit stores rule entities, attributes, version history, and dependencies in RDF / OWL format, providing a SPARQL query interface and a dynamic update mechanism (e.g., incremental loading during policy revisions). The spatial matching algorithm unit uses spatial indexing technology (e.g., R-Tree) to quickly match constraint rules with land use grid units (e.g., 100ha grids). Through geometric inclusion judgment and attribute mapping, it achieves a direct association between policy requirements and specific geographic coordinates, outputting a gridded feasibility marker layer.

[0031] Beneficial effects: This implementation method achieves precise implementation of policy constraints through automated policy analysis and spatialization, avoiding the subjective bias and delays of traditional manual interpretation; the multi-level classification system and parameterized design enhance the flexibility and adaptability of the rules, supporting dynamic adjustments to control needs at different granularities; the conflict detection and coordination mechanism eliminates inherent policy contradictions in the early stages of decision-making, reducing legal risks and rectification costs during the implementation process; the dynamic maintenance capability of the knowledge graph ensures the system's immediate response to policy updates, improving the sustainability of long-term decision-making; the high efficiency of the spatial matching algorithm significantly shortens compliance check time, providing technical support for large-scale land use optimization.

[0032] In some embodiments, based on the cultural information, the spatial distribution characteristics of cultural heritage elements are identified, and a cultural influence propagation model based on distance attenuation and spatial accessibility is constructed. The cultural influence propagation model is used to calculate the spatial influence radiation range and intensity attenuation law of each cultural source, constructing continuously distributed cultural value intensity distribution data. Based on the environmental information, the ecological background characteristics and structural connectivity of the canal corridor are analyzed, and a corridor service flow model based on ecological process simulation is constructed. The corridor service flow model is used to identify key locations of ecological pinch points and ecological hubs, assess the importance of each region in maintaining the overall ecological function of the corridor, and construct ecological circulation map data characterizing the strength of ecological function connectivity. Based on the environmental and economic information, multi-source economic vitality indicator data is integrated, and a value density estimation model based on spatial statistics and economic geography principles is constructed. The value density estimation model is used to analyze the impact of industrial agglomeration effects and market size factors, constructing economic value density distribution data. Based on the cultural value intensity distribution data, the ecological circulation map data, and the economic value density distribution data, the spatialized value distribution data is constructed.

[0033] Technical Background and Working Principle: Land use decisions in linear cultural heritage areas require a holistic approach, considering cultural, ecological, and economic values. Traditional assessment methods often analyze these dimensions in isolation, failing to reflect their spatial interactions and dynamic balance. LCH areas, such as the Grand Canal, possess the combined functions of living cultural heritage, ecological corridors, and economic corridors; a single value assessment can easily lead to decision-making biases. This embodiment addresses the issues of spatial continuity and timeliness in value quantification by constructing a multidimensional dynamic value analysis framework. Its core principles are: a cultural influence dissemination model based on field strength theory, transforming discrete cultural heritage elements into a continuous spatial radiation field, comprehensively considering distance attenuation, accessibility, and social activity factors; a corridor service flow model based on ecological process simulation, analyzing the flow paths and resistance of key ecological processes such as species migration and water conservation through directed graph analysis; and a value density estimation model based on spatial statistics and economic geography principles, capturing the spatial heterogeneity and agglomeration effects of economic activities. Finally, through multi-source data fusion and spatial interpolation techniques, value distribution data under a unified coordinate system is generated, providing accurate quantitative input for multi-objective optimization.

[0034] Technical Solution and Component Functions: The technical solution of this embodiment includes four core components: Cultural Value Analysis: The cultural element identification unit collects data on tangible / intangible cultural heritage sites, inputs it into a cultural influence dissemination model (using the exponential decay function f(d)=α·exp(-βd) to calculate spatial decay, combining the road network accessibility matrix to correct radiation intensity, and introducing the social media popularity index γ to dynamically adjust weights), and generates cultural value intensity distribution data through a spatial interpolation unit; Ecological Value Analysis: The ecological background extraction unit obtains hydrological, vegetation, and species distribution data, inputs it into an ecological service flow model (constructing a directed graph network, with nodes identifying ecologically critical areas, edge weights determined by surface resistance factors such as land use barriers and traffic barriers, and using the minimum path algorithm to simulate the flow efficiency of three types of ecological processes), and outputs ecological flow map data; Economic Value Analysis: The economic observation collection unit integrates multi-source indicators such as nighttime light and commercial density, inputs it into a value density estimation model (applying geographically weighted regression GWR to analyze spatial heterogeneity, combined with hotspot detection Getis-Ord). Gi* identifies industrial clusters, and Kriging interpolation is used to generate economic value density distribution data. Finally, the data fusion unit normalizes the three types of data, integrates them into spatial value distribution data through a weighted superposition algorithm (the weights can be dynamically adjusted based on the analytic hierarchy process), and outputs a standardized value matrix with 100ha grids as units.

[0035] Beneficial effects: This implementation method realizes the spatial quantification of the "living" attributes of cultural heritage, overcoming the limitations of traditional point-based cultural relic assessment; the ecosystem service flow model replaces static indicators with process simulation, accurately identifying key nodes and vulnerable areas of corridor ecological functions; the economic value density model integrates multi-source real-time data, significantly improving the spatiotemporal resolution of regional economic vitality assessment; the unified spatial framework of three-dimensional value data provides a directly calculable basic layer for subsequent multi-objective optimization, effectively supporting the scientific nature and precision of land use decisions.

[0036] In some embodiments, based on the cultural information, the spatial distribution characteristics of various cultural heritage elements are identified, and tangible cultural heritage sites, intangible cultural heritage activity sites, historical and cultural routes, and traditional production and living areas are uniformly regarded as sources of cultural influence. Based on field strength theory, a cultural value dissemination model is constructed according to the sources of cultural influence. The cultural value dissemination model comprehensively considers the effects of distance attenuation, differences in accessibility, and social activity, and introduces a nonlinear attenuation function to describe the dissemination characteristics of cultural value. In areas with dense cultural heritage, the superposition effect and mutual reinforcement mechanism of influence are considered to quantify the spatial diffusion law of cultural influence. Multi-source cultural data are integrated, including the trajectory of cultural activities recorded in historical documents, the popularity of cultural practices reflected on social media, and the intensity of cultural space use obtained from on-site surveys. Based on the spatial diffusion law, the discrete cultural activity trajectories, the popularity of cultural practices, and the intensity of cultural space use are transformed into continuously distributed cultural value intensity surface data through spatial interpolation and field strength superposition methods to obtain the cultural value intensity distribution data.

[0037] Technical Background and Working Principle: Traditionally, the assessment of cultural value in Linear Heritage (LCH) areas relies on discrete records of artifact sites, lacking quantitative analysis of the spatial continuity and dynamic dissemination characteristics of intangible heritage, historical routes, and living cultural practices. This leads to the simplification or neglect of cultural value in land use decisions, making it difficult to optimize in synergy with ecological and economic values. This embodiment, based on field strength theory, treats cultural value as a "field" that radiates and attenuates in space. By simulating the dissemination patterns of cultural influence, it constructs continuously distributed data on the intensity of cultural value. The working principle is that sources of cultural influence (such as heritage sites and activity venues), like source points in a physical field, experience diminishing influence with increasing distance and are modulated by factors such as accessibility and social activity. The nonlinear decay function captures the rapid decline and local saturation characteristics of cultural value. In densely populated heritage areas, the superposition effect of multiple sources of influence more accurately reflects the accumulation of cultural value. By integrating multi-source data such as historical documents, social media, and field surveys, this method transforms cultural value from discrete observation to a continuous surface, providing precise spatial input of cultural value for multi-objective land use optimization.

[0038] Technical Solution and Component Functions: The technical solution of this embodiment includes the following steps: First, by using a cultural heritage database and a Geographic Information System (GIS), tangible cultural heritage sites, intangible cultural heritage activity venues, historical and cultural routes, and traditional production and living areas are identified and uniformly used as sources of cultural influence, and their spatial coordinates, type, and activity attributes are extracted; Second, a cultural value dissemination model based on field strength theory is constructed. This model uses a nonlinear decay function (such as an exponential or sigmoid function) to calculate the radiation intensity of each source of influence on a spatial grid, and introduces transportation network data (such as road density and public transportation coverage) to calculate accessibility weights, as well as social activity data (such as social media popularity and population flow) to adjust the radiation intensity. An initial cultural value field is formed. Then, in areas with dense cultural heritage, a field strength superposition algorithm (such as weighted accumulation) is used to handle the mutual reinforcement effect of multi-source influences, avoiding underestimation of value. Next, multi-source cultural data is integrated—historical document data is spatialized by extracting cultural activity trajectories through text mining; social media data obtains the cultural practice popularity index through API interfaces and maps it to geographic coordinates; and field survey data records the intensity of cultural space use through mobile collection terminals and is interpolated. Discrete observations are transformed into a continuous cultural value intensity surface through spatial interpolation methods (such as Kriging interpolation or inverse distance weighting). Finally, cultural value intensity distribution data is output and stored in raster form, with each grid cell value representing the cultural value intensity at that location. Component functions include: a cultural influence source identification component responsible for data collection and spatialization; a field strength model construction component implementing attenuation functions and accessibility calculations; a data integration component handling the formatting and fusion of multi-source cultural data; and a spatial interpolation and superposition component generating continuous surface data.

[0039] Beneficial effects: This embodiment achieves continuous and dynamic quantification of cultural value in space through field strength theory and multi-source data fusion, overcoming the limitations of traditional point-based assessment; the nonlinear attenuation and superposition mechanism more accurately reflects the value accumulation of densely populated cultural heritage areas, improving the precision and authenticity of cultural value assessment; the integration of historical, real-time, and on-site data ensures the spatiotemporal integrity of cultural value analysis, providing reliable cultural dimension input for land use decisions; in addition, this method supports the spatial synergistic optimization of cultural value with ecological and economic value, which helps to achieve a balance between cultural inheritance and sustainable development in canal heritage areas.

[0040] In some embodiments, based on the environmental information, the ecological status within the target cultural heritage area is analyzed, and the ecological baseline conditions of the target cultural heritage area are extracted, including hydrological information, vegetation information, and biological information. The hydrological information, vegetation information, and biological information are used as node information to construct an ecoservice flow simulation model based on a directed graph. Resistance factors affecting key ecological processes are introduced into the ecoservice flow simulation model to simulate the flow changes of three key ecological processes—species migration, water conservation, and nutrient cycling—within corridors. The resistance factors include land use barriers, transportation infrastructure barriers, and topographical limitations. Based on the flow change information, the flow change information is visualized using a map processing method to construct the ecological flow map data reflecting the ecological value of different regions.

[0041] Technical Background and Working Principle: Traditional ecological assessment methods often focus on the static distribution of ecological elements, such as vegetation cover or species richness, while neglecting the dynamic flow characteristics of ecological processes in space. In linear cultural heritage areas such as canal corridors, the core of ecological function is manifested in the spatial flow of key ecological processes such as species migration, water conservation, and nutrient cycling. These processes are affected by multiple resistance factors, such as land use barriers, transportation infrastructure obstructions, and topographical limitations, forming a complex ecological flow network. This embodiment, based on landscape ecology and graph theory principles, treats ecological flow as a directed network system, where ecological nodes (such as wetlands and forest patches) serve as network vertices, ecological flow processes as directed edges, and resistance factors are quantified as edge weights. The working principle is as follows: by constructing a directed graph model, the spatial flow paths and intensity of three key ecological processes (species migration, water conservation, and nutrient cycling) under the influence of resistance factors are simulated; network analysis algorithms are used to identify key nodes (ecological hubs) and obstruction points (ecological pinch points) in ecological flow, thereby assessing the importance of different regions in maintaining the overall ecological function of the corridor, and finally generating flow map data that characterizes the strength of ecological function connectivity.

[0042] Technical Solution and Component Functions: The technical solution of this embodiment includes the following steps: First, the ecological baseline conditions of the target area are obtained through remote sensing image interpretation, field surveys, and monitoring data, including hydrological information (such as river networks and water level changes), vegetation information (such as vegetation type and cover), and biological information (such as species distribution and habitat range); Second, an ecological service flow simulation model based on a directed graph is constructed—areas with significant ecological functions are set as nodes, and the ecological flow process between nodes is set as directed edges, and resistance factors (land use barriers are assigned values ​​through land cover type, transportation facility barriers are calculated through road density, and topographic and geomorphological restrictions are used for flow) are considered. The system calculates the weights of each edge using a slope factor derived from a digital elevation model (DEM) to form a complete ecological flow network. Then, simulations are performed for three ecological processes: species migration, water conservation, and nutrient cycling. Species migration is analyzed using path analysis based on random walks or circuit theory; water conservation uses hydrological models to calculate runoff paths and catchment areas; and nutrient cycling simulates the spatial transport of nutrients through a nutrient flow network. Based on the simulation results, ecological hubs and pinch points are identified through network centrality analysis (such as betweenness centrality), and the flow intensity of each node is calculated. Finally, spatial interpolation transforms the node flow intensity into a continuous raster surface, generating ecological flow map data. The components include: an ecological baseline extraction component responsible for collecting and preprocessing multi-source environmental data; a directed graph construction component that generates node-edge network topology and calculates weights; an ecological process simulation component that performs spatial analysis of the three types of ecological flows; and a map generation component that calculates network indicators and outputs spatial interpolation.

[0043] Beneficial effects: This embodiment realizes the dynamic simulation of spatial flow of ecological processes through a directed graph model, overcoming the limitations of traditional static assessment; it introduces multiple resistance factors to quantify the impact of human activities and natural conditions on ecological flow, improving the real-world relevance of the assessment; identifying ecological hubs and pinch points helps to accurately locate key protection areas and priority restoration areas, optimizing the ecological spatial pattern; the generated flow map provides an intuitive ecological sensitivity basis for land use decisions, supporting the overall maintenance and enhancement of the ecological functions of the canal corridor.

[0044] In some embodiments, based on the environmental and economic information, the economic vitality of the target cultural heritage area under the dual verification of environment and economy is analyzed, and multi-source economic vitality observation data is constructed, including nighttime light intensity, commercial facility density, traffic flow statistics, land transaction prices, and industrial input-output data. Based on the multi-source economic vitality observation data, a value density estimation model based on geographically weighted regression and spatial econometrics is constructed, incorporating the effects of spatial heterogeneity and spatial dependence. The spatial agglomeration patterns of economic activities are analyzed in depth, and the distribution characteristics of industrial cluster areas, commercial centers, and innovation activity areas are identified. Spatial interpolation methods are used to transform point-like and area-like economic observation data into continuously distributed economic value density surfaces. The economic value density data is spatially registered with land use grid units to construct the economic value density distribution data.

[0045] Technical Background and Working Principle: Traditional economic value assessment methods rely heavily on statistical data from administrative units, making it difficult to reflect the spatial heterogeneity and local clustering characteristics of economic activities. In linear cultural heritage areas, economic activities exhibit a complex spatial pattern of gradient distribution along canal corridors and high clustering at specific nodes. This embodiment, based on spatial econometrics and the first law of geography, posits that economic value is spatially dependent and heterogeneous, with economic activities in neighboring areas influencing each other, and the weights of influencing factors varying across different locations. The working principle involves: integrating multi-source economic activity observation data (such as nighttime light and commercial facility density) to construct a geographically weighted regression (GWR) model. This model allows regression coefficients to vary with spatial location, thereby capturing the spatial non-stationarity of economic value; simultaneously, a spatial econometric model is introduced to handle spatial dependence, avoiding estimation bias caused by ignoring spatial autocorrelation; combined with spatial interpolation techniques, point and areal observation data are transformed into continuous value density surfaces, ultimately generating economic value density distribution data precisely registered with land use grids, providing refined economic dimension input for multi-objective land use optimization.

[0046] Technical Solution and Component Functions: The technical solution of this embodiment includes the following steps: First, economic vitality observation data is acquired through multi-source data collection, including satellite remote sensing nighttime light data (reflecting the intensity of economic activity), commercial facility POI density data (characterizing commercial activity), traffic flow monitoring data (indicating logistics and pedestrian flow), land transaction price data (reflecting land market value), and industrial input-output data (measuring economic efficiency); Second, a value density estimation model based on Geographically Weighted Regression (GWR) and spatial econometrics is constructed—the GWR model uses moving window weighted least squares estimation to calculate the local regression coefficients of each spatial unit, capturing the spatial heterogeneous effects of economic influencing factors (such as transportation accessibility and industrial agglomeration), while spatial econometric models (such as spatial lag models or spatial error models) handle the interaction and dependence between adjacent units by introducing a spatial weight matrix; Then, spatial autocorrelation analysis (such as global / local Moran's I) and hotspot detection (Getis-Ord) are used. The system identifies the spatial distribution characteristics of industrial clusters, commercial centers, and innovation hubs. Then, it uses spatial interpolation methods (such as Kriging interpolation or inverse distance weighting) to transform discrete economic observation data into a continuously distributed economic value density surface. Finally, it aligns the economic value density surface with land use grid cells through spatial registration, generating economic value density distribution data. The component functions include: an economic observation data acquisition component responsible for acquiring and standardizing preprocessing multi-source data; a model building module for estimating GWR parameters and calibrating spatial econometric models; a cluster analysis component for performing spatial statistics and hotspot detection; a spatial interpolation component for surface generation; and a registration component to ensure spatial consistency between economic data and land use grids.

[0047] Beneficial effects: This embodiment improves the real-time performance and precision of spatial economic value assessment by integrating multi-source high-frequency economic data; the geographically weighted regression model effectively captures the local impact of economic drivers and overcomes the homogenization assumption of the global model; the introduction of spatial econometric methods addresses the spatial spillover effects of economic activities and improves the statistical reliability of value estimation; clear cluster and hotspot identification provides a direct basis for the positioning of economic growth poles and the optimization of industrial layout in land use planning; the final output gridded economic value density data can be seamlessly integrated with cultural and ecological value data, supporting multi-dimensional collaborative land use optimization decisions.

[0048] In some embodiments, based on the policy rule engine and the spatialized value distribution data, the spatial regions corresponding to the prohibited, restricted, and encouraged rules are analyzed. The spatial constraint rules of the policy rule engine are used as hard constraints in the multi-objective optimization process. The core optimization objectives are to maximize the intensity of cultural value, the flow of ecological functions of corridors, and the density of economic value. At the same time, secondary optimization objectives are introduced for the structural rationality and spatial coordination of land use. A multi-objective optimization model is constructed. Based on the multi-objective optimization model, a targeted multi-objective evolutionary strategy is used for optimization. Through adaptive parameter adjustment and non-dominated ranking mechanisms, the land use optimization decision set is constructed. During the multi-objective optimization process, the compliance with policy constraints is monitored in real time, and the policy compliance degree and constraint violation location of each potential scheme are accurately recorded.

[0049] Technical Background and Working Principle: Land use decisions in Linear Cultural Heritage (LCH) areas involve a complex interplay of cultural, ecological, and economic values. Traditional methods struggle to achieve simultaneous optimization of multiple objectives under policy constraints. Policy rules typically exist in natural language, lacking direct spatial expression, leading to inefficient compliance checks and potential conflicting schemes during optimization. This implementation transforms the spatial constraints of the policy rule engine into hard constraints for the optimization process, ensuring all potential schemes comply with policy requirements. Simultaneously, it constructs a multi-objective optimization model with maximizing cultural value intensity, corridor ecological function flow, and economic value density as core optimization objectives, and introducing structural rationality and spatial coordination of land use as secondary objectives. In terms of working principle, a targeted multi-objective evolutionary strategy (such as NSGA-II) is employed for solving the problem. Through adaptive parameter adjustment and non-dominated ranking mechanisms, the Pareto front is searched in the solution space to generate a diverse set of land use optimization decisions. During optimization, policy constraint compliance is monitored in real-time, accurately recording the policy compliance degree and constraint violation location of each scheme, achieving pre-emptive conflict diagnosis and dynamic compliance management, thereby enhancing comprehensive value while ensuring policy compliance.

[0050] Technical Solution and Component Functions: The technical solution of this implementation includes: based on a policy rule engine, mapping spatial constraint rules (such as prohibited and restricted rules) into hard constraints of the optimization model to ensure that the solution does not violate policy requirements at the grid unit level; constructing a multi-objective optimization model, where the core objective function is the weighted maximization of cultural value intensity, corridor ecological function circulation, and economic value density, and the secondary objective functions are the structural rationality of land use (such as the balance of land type proportions) and spatial coordination (such as landscape connectivity); and employing a multi-objective evolutionary strategy for optimization, including constructing a chromosome coding scheme (each gene... The algorithm employs a multi-objective fitness function (quantifying cultural, ecological, and economic value through weighted summation) to determine the land use type corresponding to the grid unit. It sets the genetic algorithm's parameters (e.g., crossover probability 0.7, mutation probability 0.3) and executes an iterative optimization process (including population initialization, simulated binary crossover, polynomial mutation, non-dominated sorting, and crowding calculation). During optimization, a real-time conflict diagnosis unit monitors policy constraint compliance, compares the spatial mapping of land use configurations with policy rules, and records the policy compliance degree (e.g., compliance ratio) and constraint violation location (e.g., coordinates of violating units) for each scheme. Functionally, the constraint rule mapping unit transforms policy spatial constraints into binary feasibility markers; the multi-objective optimization model integrates core and secondary objective functions; the evolutionary strategy module is responsible for population evolution and solution set generation; and the conflict diagnosis unit assesses policy compliance and locates violations.

[0051] Beneficial effects: This implementation method significantly reduces the cost of compliance rectification in the later stages of the plan and improves decision-making efficiency by using policy rules as hard constraints; the multi-objective optimization model achieves a balanced improvement of cultural, ecological and economic values ​​while ensuring policy compliance, avoiding bias caused by a single objective; real-time conflict diagnosis provides immediate feedback to help decision-makers quickly identify and adjust non-compliant areas, enhancing the operability and transparency of the plan; the evolutionary strategy based on non-dominated ranking generates diverse Pareto optimal solution sets to meet the decision-making needs of different value focuses and support flexible land use planning.

[0052] In some embodiments, a chromosome coding scheme for land use spatial configuration is constructed, wherein each chromosome individual represents a complete land use scheme, chromosome gene loci correspond to planning grid units, and gene values ​​characterize the land use types allocated within that unit; a multi-objective fitness function is designed, and a weighted summation mechanism is used to evaluate the fitness of the cultural value intensity distribution data, corridor ecological function circulation data, and economic value density distribution data, quantifying these data into corresponding fitness values ​​to evaluate the merits of each chromosome individual; the operating parameters and operations of the genetic algorithm are set, and a random population is initialized using the genetic algorithm. The algorithm employs simulated binary crossover to exchange gene segments between parent chromosomes in the random population to generate new individuals. It then performs polynomial mutation to randomly alter some gene loci in the new individuals, introducing low-probability random perturbations to maintain population diversity. An iterative optimization process is executed, where in each generation, the population is non-dominatedly ranked according to the fitness function to obtain the non-dominated ranking results. The crowding degree of individuals within the same frontier layer is calculated, and a tournament selection method is used to select superior individuals for the next generation based on the non-dominated ranking results and the crowding degree. Convergence conditions are set, and a solution set is output. When the number of iterations reaches a preset maximum value, the algorithm terminates, and all non-dominated solutions in the final population are output as the land use optimization decision set.

[0053] Technical Background and Working Principle: Land use optimization in linear cultural heritage areas involves complex trade-offs between multidimensional value objectives. Traditional optimization methods struggle to effectively approach the Pareto front while maintaining solution diversity. Multi-objective evolutionary algorithms, by simulating natural evolution, can search for multiple non-dominated solutions in parallel within a high-dimensional solution space, making them particularly suitable for handling discrete combinatorial optimization problems such as land use configuration. This implementation is based on the NSGA-II algorithm framework. It discretizes land use spatial configuration into heritable gene sequences through chromosome encoding, simultaneously evaluates cultural, ecological, and economic value using a multi-objective fitness function, maintains population diversity through crossover and mutation in genetic operations, and finally selects a uniformly distributed Pareto optimal solution set using non-dominated sorting and crowding calculations. Its core working principle is to use an iterative evolutionary mechanism to gradually converge the population towards the Pareto front in the multidimensional objective space, while maintaining the diversity and uniformity of the solution set, providing decision-makers with multiple value trade-off options.

[0054] Technical Solution and Component Functions: The technical solution of this implementation first constructs a chromosome coding scheme for land use spatial configuration, dividing the planning area into uniform grids. Each chromosome represents a complete land use scheme, with chromosome gene loci corresponding to grid units. Gene values ​​are encoded using integers to represent the land use type allocated to that unit. A multi-objective fitness function is designed, quantifying cultural value intensity distribution data, ecological circulation data, and economic value density distribution data into a unified fitness value through a weighted summation mechanism. The weight coefficients can be dynamically adjusted according to decision preferences. Genetic algorithm operating parameters are set, including initializing a random population (size 1000). The algorithm employs simulated binary crossover (probability 0.7) to exchange gene segments between parent chromosomes, and polynomial mutation (probability 0.3) to randomly alter some gene loci, while introducing low-probability random perturbations to prevent premature convergence. An iterative optimization process is executed, with the population rapidly non-dominated in each generation based on the fitness function. The crowding distance between individuals within the same frontier layer is calculated, and a tournament selection mechanism based on ranking and crowding is used to select superior individuals for the next generation. The convergence condition is set as 1208 iterations or an improvement of less than 1% in the solution set over 50 consecutive generations. The final output comprises all non-dominated solutions forming a land use optimization decision set. Functionally, the chromosome coding unit is responsible for grid division and land use type mapping; the fitness calculation module integrates multi-dimensional value data and performs weighted evaluation; the genetic operation module implements population updates and diversity maintenance; and the convergence judgment unit monitors the algorithm's termination condition and outputs the final solution set.

[0055] Beneficial effects: This implementation achieves efficient encoding and searching of complex land use schemes through a discretized chromosome structure, significantly improving optimization efficiency; the weighting mechanism of the multi-objective fitness function flexibly accommodates different decision preferences, ensuring the comprehensiveness of value assessment; adaptive crossover and mutation parameters, combined with a non-dominated sorting mechanism, effectively balance the algorithm's exploration and development capabilities, avoiding getting trapped in local optima; crowding calculation ensures a uniform distribution of the final solution set on the Pareto front, providing decision-makers with a diverse selection space; explicit convergence conditions control computational costs while ensuring solution set quality, enhancing the method's practicality.

[0056] In some embodiments, a scheme selection mechanism is established based on multi-attribute utility theory. Standardized utility values ​​in economic, ecological, and cultural dimensions are calculated for each scheme in the land use optimization decision set. All schemes are ranked and initially selected using a weighted comprehensive score to obtain a preliminary scheme set. Based on the preliminary scheme set, spatial overlay and change detection analysis are performed on different preliminary schemes. Land use layout maps of different preliminary schemes are spatially overlaid with current land use maps. A raster algorithm is used to identify areas where land use types have changed, and their spatial distribution, area, and direction of change are statistically analyzed. This data is then integrated to obtain the land use scheme set corresponding to the preliminary scheme set. For each preliminary scheme, the land use scheme set is analyzed, and each preliminary scheme... The corresponding land use plan is compared with the current situation in terms of cultural, ecological, and economic value. The percentage increase in cultural, ecological, and economic value compared to the current situation is quantified. A secondary compliance verification is performed using the policy rule engine to ensure that the initial selected plan does not contain any land use configurations that violate mandatory policy constraints, thus obtaining a set of optimal plans. The set of optimal plans is analyzed, and the land spatial configuration parameters of each plan are decoded and visualized to generate a planning map of the land use spatial layout corresponding to each optimal plan, a land use structure configuration table of land use area and spatial location for each land type, and an analysis report including a comprehensive benefit comparison, policy compliance conclusions, and potential implementation risks. The land use optimization report is then constructed and output.

[0057] Technical Background and Working Principle: The land use decision set generated by multi-objective optimization processes often contains a large number of Pareto non-dominated solutions. Traditional methods rely on manual experience for screening, which suffers from strong subjectivity, low efficiency, and difficulty in comprehensively evaluating the overall benefits of each scheme. This implementation method establishes an objective screening mechanism based on multi-attribute utility theory. By weighted comprehensive scoring of standardized utility values ​​across three dimensions—economic, ecological, and cultural—it achieves quantitative ranking and initial selection of schemes. Combining spatial overlay and change detection technologies, it accurately identifies land use conversion areas relative to the current situation and quantifies spatial change characteristics. Furthermore, it utilizes a policy rule engine for secondary compliance verification to ensure that the final selected scheme strictly adheres to mandatory policy constraints. Its core working principle is to systematically identify the optimal scheme with the best overall benefits, reasonable spatial conversion, and policy compliance from a massive set of optimization solutions through a three-level screening process of "quantitative assessment - spatial analysis - compliance verification," providing decision-makers with a reliable planning basis.

[0058] Technical Solution and Component Functions: The technical solution of this implementation first establishes a scheme screening mechanism based on multi-attribute utility theory. The utility calculation unit reads the original data of each scheme in three dimensions: economic value density, ecological circulation, and cultural value intensity. After eliminating the influence of dimensions using the range standardization method, a weighted comprehensive utility value is calculated based on preset weight coefficients (e.g., 0.4 for economic, 0.3 for ecological, and 0.3 for cultural). Based on this, all schemes are ranked, and the top 20% are selected as preliminary schemes. Subsequently, the spatial overlay analysis unit performs pixel-level overlay operations on the land use layout raster of the preliminary schemes and the existing land use raster. The change detection algorithm identifies areas where land use types are changing, statistically analyzing the changed area, spatial distribution pattern, and main conversion directions (e.g., farmland to construction land, water area to ecological land). Next, a compliance verification unit maps the land use configuration of each scheme to the spatial constraint rules of the policy rule engine, using Boolean operations to detect violations of prohibited rules, ensuring the optimal scheme set is fully compliant. Finally, a report generation unit integrates all analysis results, generating a complete report for each optimal scheme, including a land use planning map, land use structure configuration table, comprehensive benefit comparison chart, policy compliance statement, and implementation risk assessment. Functionally, the multi-attribute utility calculation module implements dimensional standardization and weighted summarization; the spatial overlay unit performs raster operations and change statistics; the compliance verification module performs rule matching and conflict detection; and the report generation module integrates text, charts, and spatial visualization output.

[0059] Beneficial effects: This implementation method achieves objective quantitative ranking of schemes through multi-attribute utility theory, significantly reducing the interference of subjective factors and improving the scientific nature of the selection; spatial overlay and change detection provide intuitive land use conversion information, helping decision-makers accurately assess the spatial impact range of scheme implementation; secondary compliance verification eliminates the risk of policy violations and avoids cost losses caused by later rectification; structured report output integrates spatial layout, statistical data and risk assessment, providing comprehensive technical support for scheme approval and implementation; the three-level screening process ensures that the final scheme achieves the optimal balance in the three dimensions of benefits, space and policy.

[0060] Figure 3 A schematic diagram of the structure of a digitally-enabled canal heritage land use decision-making system, as provided in one embodiment of this application, is shown below. Figure 3 As shown in this embodiment, a digitally-enabled canal heritage land use decision-making system 300 includes: an information collection module 301, a policy analysis module 302, a value analysis module 303, a decision optimization module 304, and a report output module 305.

[0061] The information collection module 301 is used to acquire environmental, policy, cultural, and economic information of the target cultural heritage area and construct multi-source cultural heritage information. The policy analysis module 302 is used to perform policy semantic parsing and spatialization on the policy information to obtain policy semantic and spatial information, and construct a policy rule engine based on the policy semantic and spatial information. The value analysis module 303 is used to perform multi-dimensional dynamic value analysis on the multi-source cultural heritage information to obtain spatial value distribution data of the target cultural heritage area. The decision optimization module 304 is used to perform multi-objective collaborative optimization and conflict diagnosis based on the spatial value distribution data and the policy rule engine to generate a land use optimization decision set. The report output module 305 is used to filter and analyze the land use optimization decision set and output a land use optimization report.

[0062] Optionally, the policy analysis module 302 is specifically used for: performing natural language parsing on the policy information, extracting control intensity terms and spatial scope descriptions from the policy information, establishing a multi-level classification system including prohibition rules, restriction rules, and encouragement rules, and obtaining the policy semantic information; based on the spatial scope description, transforming the abstract policy information into specific machine-executable spatial constraint rules, the spatial constraint rules being used to define the spatial scope of action, constraint strength parameters, and priority relationships of various policies; and based on the policy semantic information, associating the spatial constraint rules with the geographical coordinates corresponding to each rule under the multi-level classification system in the policy semantic information through a spatial matching algorithm to obtain the policy spatial information.

[0063] Optionally, the value analysis module 303 is specifically used for: identifying the spatial distribution characteristics of cultural heritage elements based on the cultural information, and constructing a cultural influence dissemination model based on distance attenuation and spatial accessibility; calculating the spatial influence radiation range and intensity attenuation law of each cultural source through the cultural influence dissemination model, and constructing continuously distributed cultural value intensity distribution data; analyzing the ecological background characteristics and structural connectivity of the canal corridor based on the environmental information, and constructing a corridor service flow model based on ecological process simulation; identifying the key locations of ecological pinch points and ecological hubs through the corridor service flow model, assessing the importance of each region in maintaining the overall ecological function of the corridor, and constructing ecological circulation map data representing the strength of ecological function connectivity; integrating multi-source economic vitality indicator data based on the environmental and economic information, and constructing a value density estimation model based on spatial statistics and economic geography principles; analyzing the impact of industrial agglomeration effects and market size factors through the value density estimation model, and constructing economic value density distribution data; and constructing spatialized value distribution data based on the cultural value intensity distribution data, the ecological circulation map data, and the economic value density distribution data.

[0064] Optionally, in the value analysis module 303, the process of constructing the cultural value intensity distribution data is specifically used for: identifying the spatial distribution characteristics of various cultural heritage elements based on the cultural information, and unifying tangible cultural heritage sites, intangible cultural heritage activity sites, historical and cultural routes, and traditional production and living areas as sources of cultural influence; constructing a cultural value dissemination model based on field strength theory and the sources of cultural influence; comprehensively considering the influence of distance attenuation effect, differences in accessibility, and social activity factors through the cultural value dissemination model, and introducing a nonlinear attenuation function to describe the dissemination characteristics of cultural value, considering the superposition effect and mutual reinforcement mechanism of influence in areas with dense cultural heritage, and quantifying the spatial diffusion law of cultural influence; integrating multi-source cultural data, including the trajectory of cultural activities recorded in historical documents, the popularity of cultural practices reflected in social media, and the intensity of cultural space use obtained from on-site surveys; and, based on the spatial diffusion law, transforming the discrete cultural activity trajectories, the popularity of cultural practices, and the intensity of cultural space use into continuously distributed cultural value intensity surface data through spatial interpolation and field strength superposition methods, thereby obtaining the cultural value intensity distribution data.

[0065] Optionally, in the value analysis module 303, the process of constructing the ecological circulation map data is specifically used for: analyzing the ecological status within the target cultural heritage area based on the environmental information, extracting the ecological baseline conditions of the target cultural heritage area, including hydrological information, vegetation information, and biological information; using the hydrological information, vegetation information, and biological information as node information, constructing an ecological service flow simulation model based on a directed graph, and introducing resistance factors affecting key ecological processes into the ecological service flow simulation model to simulate the circulation and change information of the three key ecological processes—species migration, water conservation, and nutrient cycling—in the corridor; the resistance factors include land use barriers, transportation facility barriers, and topographic limitations; and performing visualization map processing on the circulation change information to construct the ecological circulation map data reflecting the ecological value of different regions.

[0066] Optionally, in the value analysis module 303, the process of constructing the economic value density distribution data is specifically used for: analyzing the economic vitality of the target cultural heritage area under the dual verification of environment and economy based on the environmental information and the economic information, and constructing multi-source economic vitality observation data, including nighttime light intensity, commercial facility density, traffic flow statistics, land transaction prices, and industrial input-output data; constructing a value density estimation model based on geographically weighted regression and spatial econometrics based on the multi-source economic vitality observation data, and introducing the influence of spatial heterogeneity and spatial dependence; deeply analyzing the spatial agglomeration pattern of economic activities, and identifying the distribution characteristics of industrial cluster areas, commercial center areas, and innovation activity areas; using spatial interpolation methods to transform point-like and area-like economic observation data into continuously distributed economic value density surfaces; and spatially registering the economic value density data with land use grid units to construct the economic value density distribution data.

[0067] Optionally, the decision optimization module 304 is specifically used for: based on the policy rule engine, analyzing the spatial regions corresponding to the prohibited, restricted, and encouraged rules according to the spatialized value distribution data; using the spatial constraint rules of the policy rule engine as hard constraints in the multi-objective optimization process; taking the maximization of cultural value intensity, corridor ecological function flow, and economic value density as the core optimization objectives; and introducing structural rationality and spatial coordination of land use as secondary optimization objectives to construct a multi-objective optimization model; based on the multi-objective optimization model, using a targeted multi-objective evolutionary strategy for optimization solution; and constructing the land use optimization decision set through adaptive parameter adjustment and non-dominated ranking mechanisms; and during the multi-objective optimization process, monitoring the compliance with policy constraints in real time and accurately recording the policy compliance degree and constraint violation location of each potential scheme.

[0068] Optionally, the decision optimization module 304 is specifically used for: constructing a chromosome coding scheme for land use spatial configuration, wherein each chromosome individual represents a complete land use scheme, chromosome gene loci correspond to planning grid units, and gene values ​​characterize the land use types allocated within the unit; designing a multi-objective fitness function, and using a weighted summation mechanism to evaluate the fitness of the cultural value intensity distribution data, corridor ecological function circulation data, and economic value density distribution data, quantifying the cultural value intensity distribution data, corridor ecological function circulation data, and economic value density distribution data into corresponding fitness values ​​to evaluate the merits of each chromosome individual; setting the running parameters and operations of the genetic algorithm, and using the genetic algorithm to initially... A random population is initialized; simulated binary crossover is used to exchange gene segments between parent chromosomes in the random population to generate new individuals; polynomial mutation is implemented to randomly change some gene loci of the new individuals, introducing a small probability of random perturbation to maintain population diversity; an iterative optimization process is executed, in each generation, the population is non-dominated and sorted according to the fitness function, the non-dominated sorting result is obtained, and the crowding degree of individuals in the same frontier layer is calculated. Based on the non-dominated sorting result and the crowding degree, a tournament selection method is used to select superior individuals to enter the next generation; a convergence condition is set and a solution set is output. When the number of iterations reaches a preset maximum value, the algorithm is terminated, and all non-dominated solutions in the final population are output as the land use optimization decision set.

[0069] Optionally, the report output module 305 is specifically used for: establishing a scheme screening mechanism based on multi-attribute utility theory; calculating the standardized utility values ​​of each scheme in the economic, ecological, and cultural dimensions for each scheme in the land use optimization decision set; ranking and initially selecting all schemes through weighted comprehensive scoring to obtain a preliminary scheme set; performing spatial overlay and change detection analysis on different preliminary schemes based on the preliminary scheme set; spatially overlaying the land use layout maps of different preliminary schemes with the current land use map; identifying the areas where land use types have changed through raster algorithms; and statistically analyzing their spatial distribution, area, and direction of change to obtain the land use scheme set corresponding to the preliminary scheme set; and analyzing the land use scheme set for each preliminary scheme. Each preliminary land use scheme is compared with the current situation in terms of cultural, ecological, and economic value. The percentage increase in cultural, ecological, and economic value compared to the current situation is quantified. A secondary compliance check is performed using the policy rule engine to ensure that the preliminary schemes do not contain any land use configurations that violate mandatory policy constraints, thus obtaining a set of optimal schemes. The optimal scheme set is analyzed, and the land spatial configuration parameters of each scheme are decoded and visualized to generate a planning map of the land use spatial layout corresponding to each optimal scheme, a land use structure configuration table of land use area and spatial location for each land type, and an analysis report including a comprehensive benefit comparison, policy compliance conclusions, and potential implementation risks. The land use optimization report is then constructed and output.

[0070] The system in this embodiment can be used to execute the methods of any of the above embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

Claims

1. A digitally-enabled, scenario-based land use decision-making method for canal heritage sites, characterized in that, include: Acquire environmental, policy, cultural, and economic information about the target cultural heritage area to construct multi-source cultural heritage information; The policy information is subjected to policy semantic parsing and spatialization to obtain policy semantic information and spatial information, and a policy rule engine is constructed based on the policy semantic information and spatial information; Multidimensional dynamic value analysis is performed on the multi-source cultural heritage information to obtain spatial value distribution data of the target cultural heritage area; Based on the spatialized value distribution data and the policy rule engine, multi-objective collaborative optimization and conflict diagnosis are performed to generate a land use optimization decision set; The land use optimization decision set is screened and analyzed to output a land use optimization report.

2. The method according to claim 1, characterized in that, The process of performing policy semantic parsing and spatialization on the policy information to obtain policy semantic information and spatial information, and constructing a policy rule engine based on the policy semantic information and spatial information, includes: The policy information is parsed using natural language processing to extract control intensity terms and spatial scope descriptions. A multi-level classification system including prohibition rules, restriction rules, and encouragement rules is established to obtain the policy semantic information. Based on the spatial scope description, the abstract policy information is transformed into specific machine-executable spatial constraint rules, which are used to define the spatial scope of action, constraint strength parameters, and priority relationships of various policies. Based on the policy semantic information, the spatial constraint rules are associated with the geographic coordinates corresponding to each rule under the multi-level classification system in the policy semantic information through a spatial matching algorithm to obtain the policy spatial information.

3. The method according to claim 2, characterized in that, The process of performing multidimensional dynamic value analysis on the multi-source cultural heritage information to obtain spatial value distribution data of the target cultural heritage area includes: Based on the cultural information, identify the spatial distribution characteristics of cultural heritage elements and construct a cultural influence dissemination model based on distance attenuation and spatial accessibility; The cultural influence dissemination model is used to calculate the spatial influence radiation range and intensity decay law of each cultural source, and to construct a continuously distributed cultural value intensity distribution data. Based on the environmental information, the ecological background characteristics and structural connectivity of the canal corridor are analyzed, and a corridor service flow model based on ecological process simulation is constructed. The corridor service flow model identifies key locations of ecological pinch points and ecological hubs, assesses the importance of each region in maintaining the overall ecological function of the corridor, and constructs ecological flow map data that characterizes the strength of ecological function connectivity. Based on the aforementioned environmental and economic information, multi-source economic vitality indicator data are integrated to construct a value density estimation model based on spatial statistics and economic geography principles. The impact of industrial agglomeration effect and market size factor is analyzed through the value density estimation model to construct economic value density distribution data. Based on the cultural value intensity distribution data, the ecological circulation map data, and the economic value density distribution data, the spatialized value distribution data is constructed.

4. The method according to claim 3, characterized in that, The process of constructing the cultural value intensity distribution data includes: Based on the cultural information, the spatial distribution characteristics of various cultural heritage elements are identified, and tangible cultural heritage sites, intangible cultural heritage activity sites, historical and cultural routes, and traditional production and living areas are uniformly regarded as sources of cultural influence. Based on field strength theory, a cultural value dissemination model is constructed according to the aforementioned sources of cultural influence. The cultural value dissemination model comprehensively considers the effects of distance attenuation, differences in accessibility, and social activity, and introduces a nonlinear attenuation function to describe the dissemination characteristics of cultural values. In areas with dense cultural heritage, the superposition effect and mutual reinforcement mechanism of influence are considered to quantify the spatial diffusion law of cultural influence. Integrate multi-source cultural data, including the trajectory of cultural activities recorded in historical documents, the popularity of cultural practices reflected on social media, and the intensity of cultural space use obtained from on-site surveys; Based on the aforementioned spatial diffusion pattern, the discrete cultural activity trajectories, cultural practice popularity, and cultural space usage intensity are transformed into continuously distributed cultural value intensity surface data through spatial interpolation and field strength superposition methods, thereby obtaining the cultural value intensity distribution data.

5. The method according to claim 4, characterized in that, The process of constructing the ecological circulation map data includes: Based on the environmental information, the ecological status of the target cultural heritage area is analyzed, and the ecological baseline conditions of the target cultural heritage area are extracted, including hydrological information, vegetation information, and biological information. Using the hydrological information, vegetation information, and biological information as node information, an ecoservice flow simulation model based on a directed graph is constructed. The resistance factors affecting key ecological processes are introduced into the ecoservice flow simulation model to simulate the flow and change information of the three key ecological processes—species migration, water conservation, and nutrient cycling—in the corridor. The resistance factors include land use barriers, transportation infrastructure barriers, and topographical limitations; Based on the circulation change information, the circulation change information is visualized and processed into a map to construct the ecological circulation map data that reflects the ecological value of different regions.

6. The method according to claim 5, characterized in that, The process of constructing the economic value density distribution data includes: Based on the environmental and economic information, the economic vitality of the target cultural heritage area under the dual verification of environment and economy is analyzed, and multi-source economic vitality observation data is constructed, including nighttime light intensity, commercial facility density, traffic flow statistics, land transaction prices, and industrial input-output data. Based on the multi-source economic vitality observation data, a value density estimation model based on geographically weighted regression and spatial econometrics is constructed, incorporating the effects of spatial heterogeneity and spatial dependence. In-depth analysis of the spatial agglomeration patterns of economic activities, identifying the distribution characteristics of industrial clusters, commercial centers, and innovation hubs; Spatial interpolation methods are used to transform point-like and area-like economic observation data into continuously distributed economic value density surfaces; The economic value density data is spatially registered with land use grid cells to construct the economic value density distribution data.

7. The method according to claim 6, characterized in that, The process of generating a land use optimization decision set based on the spatialized value distribution data and the policy rule engine, involving multi-objective collaborative optimization and conflict diagnosis, includes: Based on the policy rule engine, and according to the spatialized value distribution data, the spatial regions corresponding to the prohibited rules, restricted rules, and encouraged rules are analyzed. The spatial constraint rules of the policy rule engine are used as hard constraints in the multi-objective optimization process. The core optimization objectives are to maximize the intensity of cultural value, the circulation of corridor ecological functions, and the density of economic value. At the same time, the structural rationality and spatial coordination of land use are introduced as secondary optimization objectives to construct a multi-objective optimization model. Based on the multi-objective optimization model, a targeted multi-objective evolutionary strategy is adopted for optimization solution. Through adaptive parameter adjustment and non-dominated ranking mechanism, the land use optimization decision set is constructed. During the multi-objective optimization process, the compliance with policy constraints is monitored in real time, and the policy compliance and constraint violation locations of each potential solution are accurately recorded.

8. The method according to claim 7, characterized in that, The targeted multi-objective evolutionary strategy includes: Construct a chromosome coding scheme for spatial configuration of land use, where each chromosome represents a complete land use scheme, chromosome gene loci correspond to planning grid units, and gene values ​​characterize the land use types allocated within the unit; A multi-objective fitness function is designed, and a weighted summation mechanism is used to evaluate the fitness of the cultural value intensity distribution data, corridor ecological function circulation data, and economic value density distribution data. The cultural value intensity distribution data, corridor ecological function circulation data, and economic value density distribution data are quantified into corresponding fitness values ​​to evaluate the merits of each chromosome individual. Set the running parameters and operations of the genetic algorithm, and initialize the random population through the genetic algorithm; New individuals are generated by exchanging gene segments between parent chromosomes in the random population using a simulated binary crossover operation. Polynomial mutation operations are performed to randomly change some gene loci of the new individuals, introducing a small probability of random perturbation to maintain population diversity. An iterative optimization process is performed. In each generation, the population is non-dominated and sorted according to the fitness function to obtain the non-dominated sorting results. The crowding degree of individuals in the same frontier layer is calculated. Based on the non-dominated sorting results and the crowding degree, a tournament selection method is used to select superior individuals to enter the next generation. Set convergence conditions and output the solution set. When the number of iterations reaches the preset maximum value, terminate the algorithm and output all non-dominated solutions in the final population as the land use optimization decision set.

9. The method according to claim 8, characterized in that, The process of screening and analyzing the land use optimization decision set and outputting a land use optimization report includes: A scheme selection mechanism is established based on the multi-attribute utility theory. The standardized utility values ​​of each scheme in the economic, ecological and cultural dimensions are calculated for each scheme in the land use optimization decision set. All schemes are ranked and initially selected through weighted comprehensive scoring to obtain a preliminary scheme set. Based on the preliminary selection scheme set, spatial overlay and change detection analysis are performed on different preliminary selection schemes. The land use layout maps of different preliminary selection schemes are spatially overlaid with the current land use maps. The change areas where land use types have changed are identified through the raster algorithm, and their spatial distribution, area and change direction are statistically analyzed. The land use scheme set corresponding to the preliminary selection scheme set is then integrated. For each preliminary selection scheme, the land use scheme set is analyzed. The land use scheme corresponding to each preliminary selection scheme is compared with the current situation in terms of cultural, ecological and economic value. The percentage increase in cultural value, ecological value and economic value compared with the current situation is quantified. The policy rule engine is used to perform a second compliance verification to ensure that the preliminary selection schemes do not contain any land use configurations that violate mandatory policy constraints, thus obtaining the optimal scheme set. The optimal solution set is analyzed, and the land space configuration parameters of each solution are decoded and visualized to generate a planning map of land use spatial layout, a land use structure configuration table of land use area and spatial location for each optimal solution, and an analysis report including comprehensive benefit comparison, policy compliance conclusions and potential implementation risks. The land use optimization report is then constructed and output.

10. A digitally-enabled, scenario-based land use decision-making system for canal heritage sites, characterized in that: The method applied to any one of claims 1-9 includes: The information collection module is used to acquire environmental, policy, cultural, and economic information about the target cultural heritage area, and to construct multi-source cultural heritage information. The policy analysis module is used to perform policy semantic parsing and spatialization based on the policy information, and to build a policy rule engine; The value analysis module is used to perform multi-dimensional dynamic value analysis based on the multi-source cultural heritage information to obtain spatial value distribution data of the target cultural heritage area; The decision optimization module is used to perform multi-objective collaborative optimization and conflict diagnosis based on the spatialized value distribution data and the policy rule engine, and generate a land use optimization decision set. The report output module is used to filter and analyze the land use optimization decision set and output a land use optimization report.

Images