Land saving evaluation and analysis method and system for construction project land

Abstract

The application provides a land saving evaluation analysis method and system for a construction project. The method belongs to the technical field of construction project planning and comprises the following steps: constructing a multi-dimensional land saving evaluation index system; collecting construction project related data from multiple channels and storing the obtained related data in a cloud platform; processing the obtained related data through the cloud platform; constructing a land saving evaluation model by using a multi-objective optimization algorithm based on the evaluation index; simulating and calculating the land use of the construction project by using the constructed land saving evaluation model, obtaining specific values of various land saving indexes, and obtaining quantitative land saving evaluation results of the construction project in various systems through comparative analysis. The method collects construction project related data from multiple channels and stores the data in the cloud platform, thereby improving the data acquisition efficiency and storage security and providing sufficient data support for subsequent analysis and processing.

Description

TECHNICAL FIELD

[0001] The application provides a land saving evaluation analysis method and system for a construction project, and belongs to the technical field of construction project planning. BACKGROUND

[0002] With the acceleration of urbanization and the continuous expansion of infrastructure construction, the demand for construction project land is showing a growing trend year by year. However, as a non-renewable resource, the scarcity of land resources is becoming increasingly prominent, and therefore, how to meet the demand for construction projects while achieving the conservation of land resources has become a problem that needs to be solved.

[0003] Traditional construction project land evaluation methods often only focus on a single indicator, such as land area, land utilization rate, etc., and lack a comprehensive and comprehensive evaluation of land resources. At the same time, due to the limitations of data collection and processing methods, the evaluation results often have subjectivity and inaccuracy, making it difficult to provide effective reference for decision-makers.

[0004] In recent years, with the rapid development of cloud computing, big data and other technologies, new technical means have been provided for construction project land evaluation. Cloud platform can realize centralized storage, sharing and processing of data, improving data processing efficiency and accuracy. At the same time, the introduction of advanced technologies such as multi-objective optimization algorithm enables construction project land evaluation to start from multiple dimensions and multiple targets, achieving comprehensive and objective evaluation. SUMMARY

[0005] The application provides a land saving evaluation analysis method and system for a construction project, and belongs to the technical field of construction project planning.

[0006] The application provides a land saving evaluation analysis method and system for a construction project, and belongs to the technical field of construction project planning.

[0007] S1, a multi-dimensional land saving evaluation index system is constructed; construction project related data is collected from multiple channels, and the obtained related data is stored in a cloud platform;

[0008] S2, the obtained related data is processed through the cloud platform; based on the above evaluation index, a land saving evaluation model is constructed by using a multi-objective optimization algorithm;

[0009] S3, the land saving evaluation model is constructed, and the construction project land situation is simulated and calculated to obtain specific values of each land saving index, and through comparative analysis, quantitative land saving evaluation results of the construction project in each system are obtained;

[0010] S4, based on the land saving evaluation results, land saving evaluation suggestions are generated, and the land saving evaluation suggestions are fed back to relevant personnel in a visual manner.

[0011] The application provides a land saving evaluation and analysis system for a construction project, and the system comprises the following steps:

[0012] A data acquisition module: a multi-dimensional land saving evaluation index system is constructed; relevant data of the construction project is collected from multiple channels, and the acquired relevant data is stored in a cloud platform;

[0013] A data processing module: the relevant data acquired is processed through the cloud platform; based on the above evaluation indexes, a land saving evaluation model is constructed by using a multi-objective optimization algorithm;

[0014] A simulation operation module: the land saving evaluation model is used to simulate and operate the land use situation of the construction project, the specific values of various land saving indexes are obtained, and through comparative analysis, the quantitative land saving evaluation results of the construction project in various systems are obtained; the evaluation results should include:

[0015] An advice generation module: based on the land saving evaluation results, land saving evaluation suggestions are generated, and the land saving evaluation suggestions are fed back to relevant personnel in a visual manner.

[0016] The application has the following beneficial effects: by constructing a multi-dimensional evaluation index system, the land use situation of the construction project can be comprehensively and objectively evaluated, not only the space utilization efficiency is considered, but also factors such as environment and society are considered; relevant data of the construction project is collected from multiple channels, and the data is stored in the cloud platform, so that the data acquisition efficiency and storage security are improved, sufficient data support is provided for subsequent analysis and processing; a land saving evaluation model is constructed by using a multi-objective optimization algorithm, so that the optimal solution can be found under the condition of considering multiple evaluation indexes, and the accuracy and practicability of the evaluation results are improved; the data is processed through a distributed computing framework, so that the speed and efficiency of data processing can be effectively improved, and the scalability and stability of the system are ensured; the change conditions of system resources and data volume are monitored in real time, data division and adjustment are carried out according to the monitoring results, large-scale data can be processed in time and effectively, and the operation efficiency and data processing quality of the system are ensured; the land saving evaluation results are intuitively displayed through the data visualization function, and land saving evaluation suggestions are generated in combination with the project situation, so that clear and intuitive information can be provided for relevant personnel, and they can make more scientific and reasonable decisions. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The method steps described in the application are shown in the figure;

[0018] Figure 2 The system module diagram described in the application is shown in the figure. DETAILED DESCRIPTION

[0019] In order to enable the above-mentioned objects, features and advantages of the present application to be more clearly understood, the present application will be described in detail below with reference to the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0020] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application. The described embodiments are merely some of the embodiments of the present application, and are not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0022] One embodiment of the present application, as shown in Figure 1 A land saving evaluation and analysis method for a construction project, the method comprising:

[0023] S1, constructing a multi-dimensional land saving evaluation index system; collecting construction project related data from multiple channels, and storing the obtained related data in a cloud platform;

[0024] S2, processing the obtained related data through the cloud platform; based on the above evaluation index, a land saving evaluation model is constructed using a multi-objective optimization algorithm;

[0025] S3, simulating and calculating the land use of the construction project through the constructed land saving evaluation model, obtaining the specific values of each land saving index, and obtaining the quantitative land saving evaluation results of the construction project in each system through comparative analysis;

[0026] S4, based on the land saving evaluation results, generating land saving evaluation suggestions, and feeding back the land saving evaluation suggestions to relevant personnel through a visual method.

[0027] The working principle of the above technical solution is: a land saving evaluation index system covering multiple key dimensions is constructed, aiming to comprehensively and systematically measure the land saving performance of the construction project. The dimensions include:

[0028] Land use intensity: measures the construction scale and function carried on the unit area of land, such as building area, facility capacity, production capacity, etc. For highway projects, indicators reflecting road construction density such as roadbed width, road grade, number of lanes, number of interchanges, etc. can be considered;

[0029] Land Use Efficiency: Calculate the ratio of actual land area to approved land area to assess the degree of land conservation under the premise of meeting functional requirements. For airport projects, the land use efficiency of each functional area such as the flight area, terminal area, hangar area, and supporting facility area can be analyzed.

[0030] Building Density: Reflects the proportion of building coverage, used to measure the compactness of internal space layout. In airport planning, the floor area of main buildings such as terminal buildings, hangars, and office buildings and their proportion of total land can be analyzed.

[0031] Floor Area Ratio: Applicable to projects with a large number of buildings, such as residential, commercial, or comprehensive development projects, used to measure the ratio of total building area to land area, reflecting the intensity of space development upwards.

[0032] Green Space Ratio: Evaluate the proportion of green space area in the total land of the project, reflecting the configuration of green space and the awareness of ecological environment protection. For airports, greenery not only beautifies the environment, but also reduces noise and improves microclimate.

[0033] Compactness of Space Layout: Through quantitative analysis of the spatial distribution of buildings, roads, and facilities, it is determined whether the layout is compact and reasonable, avoiding land waste. In highway design, the compactness of road layout can be evaluated by analyzing parameters such as curve radius, straight line length, and intersection spacing.

[0034] Topographic Adaptability: Consider the full use of specific topographic conditions, such as the rational use of natural terrain such as mountains and valleys for design, reducing earthwork, and reducing the impact on the ecological environment.

[0035] Functional Integration: Evaluate whether multiple functions are integrated on the same plot, such as highway service facilities and land comprehensive development, airport and industrial park or logistics park integration, to enhance the comprehensive utilization value of land.

[0036] Technical Innovation and Process Optimization: Investigate whether new technologies and processes that contribute to land conservation are applied, such as underground space development, lightweight structures, and modular construction, to reduce the demand for land resources.

[0037] Under each dimension, specific evaluation indicators are set, such as roadbed width and lane number for highway projects, flight area and terminal area land for airport projects, as well as corresponding evaluation standards and weights to ensure the scientificity, comprehensiveness, and operability of the evaluation system; detailed data related to construction projects are obtained from various channels such as planning drawings, construction records, geographic information system data, environmental monitoring and evaluation reports. Specific include:

[0038] Planning drawings and design schemes: Obtain detailed information such as project layout, building size, road network, green layout, etc.

[0039] Construction records and completion materials: Understand the land use during the actual construction process and verify the consistency between design and implementation.

[0040] Geographic Information System (GIS) data: Use vector data, satellite images, topographic maps, etc. to accurately depict the project area's topography, land properties, and surrounding environment.

[0041] Environmental monitoring and assessment reports: Understand the impact of the project on the ecological environment and evaluate the effectiveness of environmental protection measures.

[0042] After these data are sorted and verified, they are uploaded to the cloud platform for storage. The cloud platform processes the stored construction project data, builds a land saving evaluation model based on the multi-dimensional land saving evaluation index system constructed in the early stage, and uses multi-objective optimization algorithms (such as AHP, fuzzy comprehensive evaluation method, data envelopment analysis, etc.). The processed construction project data is input into the constructed land saving evaluation model for simulation operation. The model operation results output the specific values of each land saving index, such as the specific value of land use intensity and the quantitative score of land use efficiency. By comparing and analyzing these values with the evaluation standards, the quantitative evaluation results of the construction project in each land saving system can be obtained, such as the overall land saving level score, single index score, and advantage and short board analysis. Based on the land saving evaluation results, the system generates land saving evaluation suggestions for the project, including land use strategy adjustment, technology and process improvement, policy and system docking, dynamic monitoring and continuous improvement, etc. In order to facilitate relevant personnel to understand and adopt these suggestions, the system uses visualization to present the land saving evaluation results and suggestions in the form of charts, maps, dashboards, etc. to intuitively display the project's land saving status, problem points and optimization path, making it easy for decision makers and relevant personnel to quickly grasp key information and make scientific decisions.

[0043] The effect of the above technical scheme is: a multi-dimensional land saving evaluation index system is constructed, ensuring that the evaluation covers multiple key dimensions such as land use intensity, land use efficiency, building density, volume rate, green space rate, and spatial layout, comprehensively reflecting the land saving characteristics of the construction project land, avoiding the one-sidedness that may be caused by single index evaluation, and improving the systematization and accuracy of the evaluation; related data of the construction project is collected through multiple channels and stored in the cloud platform for centralized management and processing, ensuring that the evaluation is based on detailed and accurate data. The data processing capability of the cloud platform helps to improve the data quality and consistency, provides high-quality input for building the land saving evaluation model, and thus realizes accurate simulation operation and quantitative evaluation of the construction project land; a multi-objective optimization algorithm is used to build the land saving evaluation model, which can take into account multiple objectives such as environmental benefits and land saving level, and provide a scientific basis for land saving decision of the construction project land. Through model simulation operation, the specific numerical value of each land saving index and the quantitative land saving evaluation result are obtained, which is conducive to objectively and fairly evaluating the project land saving effect and providing quantitative guidance for optimizing land resource allocation and improving land use efficiency; the land saving evaluation suggestions generated based on the land saving evaluation result not only diagnose the existing project land condition, but also put forward specific improvement suggestions such as technology and process improvement, which provides a clear land saving optimization path for project design, construction, management and other links, and helps the project team to take targeted measures to improve the land saving level; the land saving evaluation suggestions are fed back in a visual way, so that the complex land saving evaluation result and suggestions are presented in an intuitive and easy-to-understand form, enhancing the efficiency and effect of information transmission. This form facilitates project team members, management, regulatory agencies and related interest parties to quickly understand and accept the evaluation result, promotes information sharing and decision consensus, and is conducive to promoting the implementation and execution of land saving measures; the application of the cloud platform significantly improves the efficiency of data processing and the operation capability of the evaluation model, simplifies the data management process, and reduces the labor and time cost of data processing. At the same time, the elastic expansion capability and distributed computing capability of the cloud platform enable efficient completion of land saving evaluation of large-scale and complex projects, improving the efficiency and response speed of the overall evaluation work.

[0044] In an embodiment of the present application, the S1 comprises:

[0045] S11, determining the key dimensions of land saving evaluation, and setting evaluation indexes for each dimension;

[0046] S12, setting evaluation standards and weights for each evaluation index; collecting related data of the construction project through multiple channels;

[0047] S13, fragmenting and compressing the related data collected through multiple channels into multiple data blocks respectively, and transmitting the compressed data blocks to the cloud platform through a multi-thread transmission mode.

[0048] The working principle of the above technical solution is: systematically identify and determine the key dimensions that affect the land saving effect of the construction project, such as land use intensity, land use efficiency, building density, plot ratio, green space ratio, spatial layout compactness, topography adaptability, functional complexity, technological innovation and process optimization, etc., to ensure that the evaluation system fully covers the core factors affecting the land saving performance of the project; for each key dimension, set specific evaluation indicators to ensure that the indicators correspond closely to the dimensions and can accurately measure the land saving performance under that dimension. For example, for the land use intensity dimension, highway projects can set roadbed width, road grade, lane number, etc., and airport projects can set flight area, terminal area, hangar area, etc.; for the land use efficiency dimension, calculate the ratio of actual land area to approved land area; for the building density dimension, define the building coverage rate; for the plot ratio dimension, set the ratio of total building area to land area; for the green space ratio dimension, specify the proportion of green space area to total land; for the spatial layout compactness dimension, design evaluation standards for parameters such as curve radius, straight line length, intersection spacing, etc.; set evaluation standards (such as threshold, grading standards, etc.) for each evaluation indicator to clearly define the standard requirements or good-bad grade division of the indicator. At the same time, give each indicator an appropriate weight to reflect its relative importance in the overall land saving evaluation, ensuring that the evaluation results accurately reflect the overall contribution of each dimension to the land saving effect of the project; collect construction project related data through multiple channels, such as consulting planning drawings, obtaining construction records, accessing geographic information system data, and referring to environmental monitoring and evaluation reports, to ensure the diversity and comprehensiveness of data sources, providing sufficient information support for building a comprehensive and accurate land saving evaluation; process the collected large amount of construction project related data according to certain rules to form multiple logically independent and easily managed data segments; compress the data after fragmentation to reduce data volume, improve data transmission efficiency, and reduce storage space requirements; use multi-threading technology to transfer the compressed data blocks (i.e. related data segments after fragmentation) to the cloud platform in parallel, fully utilize network bandwidth, speed up data upload process, and shorten data processing cycle.

[0049] The effect of the above technical scheme is: by constructing a land saving evaluation index system including land use intensity, land use efficiency, building density, volume rate, green space rate, spatial layout compactness, topography adaptability, functional complexity, technical innovation and process optimization, it is ensured that the evaluation system comprehensively covers the core factors affecting the land saving effect of the construction project, avoids the one-sidedness that may be caused by single dimension evaluation, and improves the comprehensiveness and systematicness of the evaluation; specific evaluation indexes are set for each key dimension, such as roadbed width, road grade and lane number of a highway project, flight area, terminal area and hangar area of an airport project, and evaluation standards of parameters such as the ratio of actual land area to approved land area, definition of building coverage, setting of the ratio of total building area to land area, regulation of the proportion of green space area in total land area, design of bend radius, straight line length and intersection spacing, so that the evaluation is more targeted and can accurately reflect the land saving performance of the construction project in each dimension; evaluation standards (such as threshold, grading standard, etc.) and weights are set for each evaluation index, which provides a unified and clear reference benchmark for land saving evaluation, and enhances the standardization and comparability of the evaluation. The setting of the weight helps to reasonably balance the relative importance of each index in the overall land saving evaluation, and ensures that the evaluation result is fair and objective; the relevant data of the construction project is collected through multiple channels, such as planning drawings, construction records, geographic information system data, environmental protection monitoring and evaluation reports, etc., so that the evaluation is based on comprehensive, detailed and multi-angle information, and the reliability and persuasiveness of the evaluation are enhanced; the large amount of data obtained through multiple channels is fragmented and compressed, and is uploaded to the cloud platform through multi-thread transmission technology, which effectively improves the data processing efficiency, reduces the data transmission time and storage space requirement, and provides an efficient data processing and storage solution for land saving evaluation of large-scale and complex projects; the relevant data of the construction project stored in the cloud platform facilitates centralized management, rapid retrieval, remote access and multi-party sharing of data, greatly improves the convenience and collaboration efficiency of data utilization, and is conducive to cross-department and cross-region collaborative evaluation and decision-making; the technical scheme provides a scientific, comprehensive and accurate quantitative tool for land saving evaluation of construction projects, which helps project managers, designers, regulatory departments, etc. to make scientific decisions based on the evaluation results, develop reasonable land saving strategies, and promote efficient use and optimal allocation of land resources. At the same time, the evaluation results are continuously tracked, and continuous improvement is made according to the evaluation standards and suggestions, so as to continuously improve the land saving level of the project.

[0050] In an embodiment of the present application, the S2 comprises:

[0051] S21, the cloud platform receives the compressed data block, decompresses the data block, and the cloud platform pre-processes the data block; the preprocessing includes deleting duplicate data, missing value and abnormal value filling, data normalization and standardization;

[0052] S22, store the pre-processed data blocks into different subspaces respectively, and allocate computing resources to each subspace, and process the data of each subspace through a distributed computing framework;

[0053] S23, during the processing, the resource utilization of each subspace is monitored in real time through a load balancing algorithm, an adjustment threshold is set and an adjustment strategy is formulated, and the adjustment is triggered when the data volume of a certain subspace exceeds or is lower than a certain threshold;

[0054] S24, if the data volume of a certain subspace exceeds the threshold, the subspace is split into multiple subspaces, or part of the data is migrated to other subspaces;

[0055] S25, if the data volume of a certain subspace is too small, the subspace is merged into other subspaces, or the data of other subspaces is migrated to the subspace;

[0056] S26, implement real-time data division adjustment, and continuously monitor the changes of system resources and data volume; according to the monitoring results, continuously adjust the data division strategy;

[0057] S27, after the processing is completed, the processing results of each subspace are summarized, based on the obtained processing results, a land saving evaluation model considering environmental benefits and land saving level is constructed by using multi-objective optimization algorithms such as analytic hierarchy process, fuzzy comprehensive evaluation method and data envelopment analysis.

[0058] The S27 comprises:

[0059] According to the constructed multi-dimensional land saving evaluation index system, the characteristics related to the evaluation index are selected and extracted; according to the multiple objectives of land saving evaluation of the construction project, a suitable multi-objective optimization algorithm is selected;

[0060] An optimization algorithm model is constructed, the selected evaluation index is taken as a target function, and an optimal solution is found by using the optimization algorithm;

[0061] The constructed multi-objective optimization model is trained and optimized through the summarized data; the trained model is verified and evaluated to test its performance and accuracy in land saving evaluation of the construction project;

[0062] The trained optimization model is integrated into a cloud platform and deployed; the deployed model can receive the construction project related data input by the user, perform evaluation simulation operation and generate land saving evaluation results.

[0063] The working principle of the above technical solution is that the cloud platform receives compressed data blocks sent through a multi-thread transmission mode, decompresses the data blocks to restore the original data structure; pre-processes the decompressed data, including deleting duplicate data, filling missing values and abnormal values, to ensure the integrity and consistency of the data; performs data normalization or standardization processing to convert data of different sources and dimensions to the same scale, facilitating subsequent analysis and modeling; distributes the pre-processed data blocks to different subspaces for storage and allocates appropriate computing resources to each subspace; performs parallel processing of the data in each subspace through a distributed computing framework, greatly improving data processing efficiency; monitors the resource utilization of each subspace in real time, and when the data volume reaches a preset threshold, dynamically adjusts the subspace division, maintains the balance of resource use in each subspace through data migration, subspace splitting or merging, and ensures stable and efficient operation of the system; according to the constructed multi-dimensional land saving evaluation index system, select data features closely related to evaluation indexes as model input; according to the environmental benefits and land saving level involved in land saving evaluation of construction projects, select appropriate multi-objective optimization algorithms such as analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis, etc.; select the selected evaluation indexes as the objective function, and use the selected optimization algorithm to construct a land saving evaluation model that can consider multiple objectives at the same time; use the aggregated pre-processed data to train the constructed multi-objective optimization model, adjust the model parameters through iterative optimization, and improve the model performance. After training, the model is verified and evaluated to ensure its accuracy and stability in land saving evaluation of construction project land; integrate the trained and verified optimization model into the cloud platform to complete the deployment. The deployed model can receive user input data related to construction projects, perform land saving evaluation simulation, and quickly generate land saving evaluation results.

[0064] The effect of the above technical scheme is that the cloud platform automatically receives, decompresses and preprocesses (deletes duplicate data, fills in missing values and abnormal values, normalizes and standardizes data) data blocks, greatly improves data processing efficiency, reduces manual intervention and ensures data quality; the preprocessed data blocks are stored in different subspaces, parallel processing is performed through a distributed computing framework, and computing resources are effectively utilized. Real-time monitoring of the utilization rate of the sub-space resources, dynamic balancing of data distribution through adjustment of threshold and strategy, and ensuring efficient and stable operation of the system; based on a multi-dimensional land saving evaluation index system, selecting features related to evaluation indexes, constructing a land saving evaluation model that can consider environmental benefits and land saving levels at the same time, ensuring comprehensive and objective evaluation; according to the characteristics of the evaluation target, selecting appropriate multi-objective optimization algorithms (such as analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis, etc.), which can effectively handle the trade-off and compromise between multiple objectives, and generate evaluation results that meet actual needs; using the aggregated preprocessed data to train and optimize the multi-objective optimization model, improving the accuracy of the model in land saving evaluation of construction projects; verifying and evaluating the trained model to ensure its good prediction performance and stability in practical application, providing reliable basis for decision-making; integrating the trained and verified optimization model into the cloud platform to realize automatic deployment. Users only need to input the relevant data of the construction project to quickly obtain the land saving evaluation results, greatly simplifying the evaluation process and improving work efficiency; the cloud platform monitors system resources and data volume changes in real time, dynamically adjusts data division strategies as needed, ensures that the model can cope with changing data environments, and realizes real-time evaluation and feedback of the land saving situation of construction projects.

[0065] In one embodiment of the present application, the S22 comprises:

[0066] According to the characteristics of the preprocessed data, an improved k-means++ algorithm is used to perform initial clustering on the data to form logical subspace division;

[0067] Based on historical data and real-time monitoring, a lightweight LSTM neural network model is constructed to predict the computing resource demand of each subspace in the next 5 minutes, providing a pre-judgment for resource allocation;

[0068] A resource scheduler based on deep reinforcement learning is used to dynamically allocate containerized computing resources with the goal of minimizing task completion time and maximizing resource utilization;

[0069] On the basis of Spark / Flink, operators supporting geospatial data processing are extended, and PyTorch / TensorFlow GPU acceleration capabilities are integrated;

[0070] According to the scale and complexity of the subspace data, the task parallelism is automatically adjusted, and the optimal parallelism configuration is searched through genetic algorithm; based on the checkpoint of task state snapshot, combined with heartbeat detection and standby node pool, the task is recovered within 30 seconds when the node fails;

[0071] Through the rack-aware strategy of HDFS and the Snitch positioning of Cassandra, the subspace where the data is located is preferentially scheduled to the computing nodes of the same rack; for frequently accessed evaluation index data, the multi-level cache of Alluxio in-memory file system is adopted;

[0072] For structured data, semi-structured data and unstructured data, adapters are designed respectively, and cross-modal correlation query is realized through unified metadata model; for data with space-time attributes, Space-TimeCube model is adopted for three-dimensional visualization analysis to identify the space-time pattern of land use change;

[0073] For real-time monitoring data, Flink stream processing is adopted, and Spark batch processing is adopted for historical data, and the results are unified through Lambda architecture; when data is blocked, Laplace noise is added to sensitive attributes;

[0074] For subspace data involving multi-party cooperation, Paillier homomorphic encryption scheme is adopted to support index calculation in encrypted state; column-level dynamic desensitization is realized based on ApacheRanger to ensure that different tenants can only access authorized evaluation index fields.

[0075] The working principle of the above technical solution is as follows: according to the characteristics of the preprocessed data (data type, spatial and temporal distribution, correlation, etc.), the improved k-means++ algorithm is used for initial clustering of the data. This algorithm optimizes the selection of the initial clustering center, reduces randomness, and makes the clustering result more consistent with the intrinsic characteristics of the data, forming a logical subspace division. This division helps subsequent distributed computing and resource allocation, ensuring that the data is logically organized reasonably; based on historical data and real-time monitoring, a lightweight LSTM neural network model is constructed. The LSTM model can capture the time series patterns in the data and predict the computing resource demand (CPU, memory, bandwidth) in each subspace within the next 5 minutes. This prediction provides a pre-judgment for resource allocation, enabling the resource scheduler to make adjustments in advance to cope with the upcoming computing load; a resource scheduler based on deep reinforcement learning (DRL) is adopted, which aims to minimize task completion time and maximize resource utilization. DRL learns the optimal resource allocation strategy through interaction with the environment (i.e., the distributed computing system); the resource scheduler dynamically allocates containerized computing resources (such as Docker containers) based on the prediction results of the LSTM model and the current system state. This dynamic allocation ensures efficient use of resources and avoids waste or shortage of resources; on the basis of Spark / Flink, operators supporting geospatial data processing (such as spatial join and buffer analysis) are extended, enabling the distributed computing framework to handle complex geospatial data; PyTorch / TensorFlow GPU acceleration capabilities are integrated to accelerate model training and data processing using the parallel computing capabilities of GPUs, improving overall computing efficiency; according to the size and complexity of the subspace data, the task parallelism (such as the number of partitions in Spark) is automatically adjusted. The genetic algorithm is used to search for the optimal parallelism configuration to ensure efficient execution of tasks in the distributed computing framework; based on task state snapshots, combined with heartbeat detection and a standby node pool, the system can quickly recover tasks in the event of node failure. When a node failure is detected, the system can recover from the last task state snapshot and reschedule the task to execute on a standby node, ensuring task continuity; by optimizing the recovery process and resource allocation strategy, the system ensures that tasks are recovered within 30 seconds in the event of node failure, reducing the impact of task interruption on overall computing efficiency; through the rack-aware strategy of HDFS and the Snitch positioning of Cassandra, the subspace where the data is located is preferentially scheduled to the computing nodes on the same rack. This scheduling strategy reduces cross-rack network transmission and improves data access speed; for frequently accessed land use evaluation indicator data (such as land use intensity and volume rate), a multi-level cache is used in the Alluxio in-memory file system.Cache mechanism can accelerate data access and reduce I / O latency. For the model training phase in multi-objective optimization, we use RDMA-based Shuffle service combined with columnar storage format (Parquet) to reduce Shuffle time. RDMA technology provides low-latency and high-bandwidth network communication, while columnar storage format improves data reading efficiency. We design adapters for structured data (such as land use indicators), semi-structured data (such as CAD drawings), and unstructured data (such as remote sensing images) to implement cross-modal correlation queries through a unified metadata model. This design enables seamless integration and interaction of different types of data in the system. For data with spatial and temporal attributes (such as project cycles and geographic locations), we use the Space-TimeCube model for three-dimensional visualization analysis. This model can intuitively display the spatiotemporal patterns of land use changes and provide strong support for land saving evaluation. For real-time monitoring data (such as sensor data), we use Flink stream processing, and for historical data, we use Spark batch processing. Through the Lambda architecture, we unify the result output to ensure that the system can handle real-time data and historical data simultaneously and meet the diverse needs of land saving evaluation. When data is chunked, we add Laplace noise to sensitive attributes (such as land use cost) to achieve differential privacy protection. This protection mechanism ensures that sensitive information is not leaked during data sharing and analysis. For subspace data involving multi-party collaboration, we use the Paillier homomorphic encryption scheme to support indicator calculation in an encrypted state. At the same time, we implement column-level dynamic desensitization based on Apache Ranger to ensure that different tenants can only access authorized evaluation indicator fields. These measures collectively form the system's privacy protection and security computing system.

[0076] The effect of the upper data technical solution is: through the improved k-means++ algorithm for initial clustering and the LSTM neural network model for future resource demand prediction, the computing resource demand (such as CPU, memory, bandwidth) of each subspace can be accurately predicted, which provides a basis for resource allocation. This improves the efficiency of resource use and avoids the problems of over-provisioning or under-provisioning; the resource scheduler based on deep reinforcement learning (DRL) can dynamically allocate resources in real time according to task demand and system state, optimize task completion time and resource utilization, and improve the overall performance of the system; by extending the operators supporting geographic spatial data processing on the basis of Spark / Flink, functions such as spatial connection and buffer analysis can be processed, and the processing capacity of the system for geographic spatial data is improved. In addition, the integration of PyTorch / TensorFlow GPU acceleration further improves the computing performance; through genetic algorithm to search the optimal parallel degree configuration, the task parallel degree (such as the number of Spark partitions) is automatically adjusted according to the data scale and complexity of the subspace, which effectively improves the computing efficiency and task execution speed; based on the checkpoint-based task state snapshot and heartbeat detection mechanism, the task can be recovered within 30 seconds when a node fails, ensuring the high availability and business continuity of the system; the rack-aware strategy of HDFS and the Snitch positioning of Cassandra are used to preferentially schedule data to computing nodes on the same rack, reduce data transmission delay, and improve the access efficiency of the system; through the multi-level cache of Alluxio in-memory file system, the access efficiency of frequently accessed geographic evaluation index data is improved. Combined with the Shuffle service of RDMA and the columnar storage format (Parquet), the Shuffle time can be significantly reduced, and the data processing efficiency is improved; by designing an adapter and using a unified metadata model, cross-modal associated queries of different types of data (such as land use indicators, CAD drawings, and remote sensing images) are realized, which promotes comprehensive analysis and mining of data; the Space-TimeCube model is used for three-dimensional visualization analysis of data with spatio-temporal attributes, which can help identify the spatio-temporal patterns of land use changes and assist decision analysis and planning; by adding Laplacian noise when data is blocked and using the Paillier homomorphic encryption scheme, the calculation safety of sensitive data in the encrypted state is ensured. At the same time, column-level dynamic desensitization is realized based on ApacheRanger to ensure that different tenants can only access authorized evaluation index fields, effectively protecting data privacy and security.

[0077] In an embodiment of the present application, the S26 comprises:

[0078] Through the high-performance monitoring component, the key resource indicators of each subspace are collected in real time, including CPU usage, memory occupancy, disk I / O rate and network bandwidth.

[0079] Synchronize monitoring of data volume changes in each sub-space, including data growth rate, data compression ratio, and data access frequency;

[0080] Using time series analysis techniques, model historical data, and predict future resource demand and data growth trends for a certain period;

[0081] Based on machine learning algorithms, combine historical data characteristics to automatically set optimal threshold intervals for resource utilization and data volume in each sub-space, rather than fixed values;

[0082] Introduce an adaptive adjustment mechanism. When the resource utilization or data volume of a sub-space approaches the preset threshold, automatically trigger the evaluation process. Based on current system load, data characteristics, and future prediction trends, dynamically adjust the threshold;

[0083] Adjust the strategy library according to the evaluation results to intelligently select the most suitable adjustment strategy;

[0084] Develop an intelligent data migration engine to support efficient data transmission across sub-spaces, using incremental synchronization and compression transmission to reduce resource consumption and time cost during migration;

[0085] Implement fine-grained load balancing strategies, combining the characteristics of computing tasks (such as CPU-intensive and IO-intensive) to achieve optimal resource allocation;

[0086] Introduce a hot data recognition mechanism to cache or prioritize frequently accessed data;

[0087] Automatically execute selected adjustment strategies, including sub-space splitting, merging, and data migration operations, and record operation logs;

[0088] Evaluate the effectiveness of the implemented strategies by comparing resource utilization, data processing speed, system stability, and other indicators before and after adjustment to verify the effectiveness of the adjustment strategies;

[0089] Establish a feedback loop, using evaluation results as the basis for future strategy adjustments, to continuously optimize data division and resource allocation strategies, forming a closed-loop optimization system.

[0090] Implement strict data encryption and access control during data migration and adjustment;

[0091] Design fault recovery and disaster recovery mechanisms, including data backup, rapid recovery plans, and emergency response processes to address potential system failure or data loss risks;

[0092] Periodic system health checks and stress tests are conducted to ensure that the system remains stable and quickly responds to adjustment needs under high load or abnormal conditions.

[0093] The working principle of the above technical solution is as follows: Through the deployment of high-performance monitoring components, real-time and accurate collection of key resource indicators such as CPU usage, memory occupancy, disk I / O rate, and network bandwidth of each subspace is achieved. The data volume changes of each subspace are monitored simultaneously, including data growth rate, data compression ratio, and data access frequency, to fully understand the data state. Time series analysis technology is used to model the collected historical data to predict future resource demand and data growth trends. These prediction results will provide important data support for subsequent data division and resource allocation adjustment strategies. Based on machine learning algorithms such as K-means clustering and decision trees, combined with historical data characteristics, the optimal threshold intervals for resource utilization and data volume of each subspace are automatically set. These threshold intervals are dynamically adjustable and can automatically adjust to adapt to different loads and data characteristics. When the resource utilization or data volume of a subspace approaches the preset threshold, an evaluation process is automatically triggered. The evaluation process considers the current system load, data characteristics, and future prediction trends to dynamically adjust the threshold and select appropriate adjustment strategies such as splitting, merging, and migration. An intelligent data migration engine is developed to support efficient data transmission across subspaces, using incremental synchronization and compressed transmission techniques to reduce resource consumption and time costs during migration. A fine-grained load balancing strategy is implemented, combining the characteristics of computing tasks such as CPU-intensive and IO-intensive to achieve optimal resource allocation. A hot data recognition mechanism is introduced to cache or prioritize frequently accessed data, improving overall processing efficiency and user experience. The selected adjustment strategies, including subspace splitting, merging, and data migration, are automatically executed, and operation logs are recorded for subsequent analysis. The effectiveness of the implemented strategy is evaluated by comparing resource utilization, data processing speed, system stability, and other indicators before and after adjustment to verify the effectiveness of the adjustment strategy. A feedback loop mechanism is established, using evaluation results as the basis for future strategy adjustments. The data division and resource allocation strategies are continuously optimized to form a closed-loop optimization system, ensuring the sustained and efficient operation of the system. During data migration and adjustment, strict data encryption and access control are implemented to ensure data security and privacy protection. Fault recovery and disaster recovery mechanisms are designed, including data backup, rapid recovery plans, and emergency response processes to address potential system failure or data loss risks. Regular system health checks are conducted to ensure the normal operation of system components. Stress tests are performed to simulate system performance under high load or abnormal conditions, ensuring that the system remains stable and quickly responds to adjustment needs.

[0094] The effects of the above technical solutions are: through real-time monitoring and dynamic adjustment of data division strategies, the system can more reasonably allocate and utilize resources (such as CPU, memory, disk I / O, network bandwidth, etc.), avoid resource idling or overuse, and thus improve overall resource utilization. The introduction of fine-grained load balancing strategies and hot data identification mechanisms can ensure that high-load or frequently accessed data is given priority, reducing waiting time and processing delay and improving data processing speed and efficiency. The design of fault recovery and disaster recovery mechanisms, including data backup, rapid recovery plans, and emergency response processes, can effectively deal with system failure or data loss risks and ensure stable operation of the system under high load or abnormal conditions. By optimizing data processing and resource allocation, the system can respond to user requests more quickly and provide a smoother and more efficient user experience. At the same time, data encryption and access control mechanisms also enhance the security and privacy protection of user data. Based on machine learning algorithms and adaptive adjustment mechanisms, the system can automatically set optimal threshold intervals, trigger evaluation processes, select adjustment strategies, and perform operations, achieving intelligent and automated management of data division and resource allocation, reducing the complexity and error rate of manual intervention. A feedback loop mechanism is established, with evaluation results serving as the basis for future strategy adjustments, continuously optimizing data division and resource allocation strategies, forming a closed-loop optimization system. This continuous optimization mechanism ensures that the system always remains in the best operating state, adapting to changing data and business demands. By optimizing resource utilization and data processing performance, the system can reduce operating costs (such as reducing resource waste and improving device utilization), while improving business processing capacity and user satisfaction, thereby bringing higher economic benefits to enterprises. The design of this technical solution considers the scalability and upgradability of the system, making it easy to handle future growth in data volume and business demand. By adding subspaces, upgrading hardware, or optimizing algorithms, the system can maintain high performance and stability.

[0095] In one embodiment of the present application, the S3 comprises:

[0096] S31, input the aggregated data into the constructed land-saving evaluation model, and simulate and calculate the land use situation of the construction project through the quantitative evaluation model;

[0097] S32, after the simulation and calculation is completed, output the specific values of each land-saving index; compare and analyze the calculated land-saving index values with the preset evaluation standard to evaluate the land-saving level of the construction project in each system;

[0098] S33, at the same time, compare the land-saving effects between different schemes to find the optimal land-saving scheme.

[0099] The working principle of the above technical solution is: the construction project land related data after preprocessing, summarizing and standardizing is taken as input and sent to the constructed land saving evaluation model. The model comprehensively considers various land saving indicators such as land use efficiency, spatial layout rationality, ecological environment impact, etc., and simulates and calculates the land use of the construction project under different schemes through the built-in algorithm. The simulation and calculation process may include calculating the specific values of various indicators, evaluating the influence degree of different schemes on various indicators, simulating the change trend of land use under different schemes, etc.; after the model calculation is completed, the specific values of various land saving indicators are output, such as the percentage of land use efficiency, the compactness index of spatial layout, the quantitative score of ecological environment impact, etc. These values reflect the actual performance of the construction project in various land saving dimensions and provide quantitative basis for subsequent comparative analysis and scheme optimization; compare the calculated land saving indicator values with the preset evaluation standards (such as industry specifications, local policy requirements, best practice standards, etc.) to evaluate the land saving level of the construction project in each system (such as land use efficiency system, spatial layout system, ecological environment impact system, etc.). The comparative analysis may include calculating the deviation, compliance rate, ranking, etc. to intuitively show the gap between the land saving performance of the construction project and the standard requirements, and to clearly identify the advantages and disadvantages in land saving work; compare the land saving effects of different schemes, find out the optimal land saving scheme in the overall land saving effect by comparing the differences of various land saving indicator values. The optimal scheme may be the comprehensive optimization of various indicators, or it may be the optimization of several key indicators according to the specific situation and priority of the project. Through scheme comparison, clear land saving optimization direction and implementation strategy are provided for project decision makers.

[0100] The effect of the above technical scheme is: through the construction of land saving evaluation model, the land use of the construction project is converted into quantifiable land saving indicators, and the quantitative evaluation of the land saving effect is realized. This quantitative method makes the land saving evaluation more objective, comparable and scientific, provides clear and specific land saving performance data for project decision makers, and helps them make more accurate and rational decisions. The model comprehensively considers land use efficiency, spatial layout rationality, ecological environment impact and other land saving indicators to ensure that the evaluation system comprehensively covers the key factors affecting the land saving effect and avoids the one-sidedness that may be caused by single-dimensional evaluation. This multi-dimensional comprehensive evaluation helps to more comprehensively and accurately reflect the land saving characteristics of the construction project land, and provides a basis for formulating comprehensive land saving optimization strategies. Through model simulation operation of the land use of the construction project under different schemes, the influence of different land saving strategies on various indicators can be predicted to help decision makers evaluate the effect of various land saving schemes in advance. By comparing the land saving effects of different schemes, the optimal scheme in terms of overall land saving benefit can be found to provide a clear direction for project optimization design and implementation. By comparing and analyzing the calculated land saving indicator values with the preset evaluation standards, the land saving level of the construction project in each system is standardized evaluated to ensure the fairness and consistency of the evaluation results. This standardized evaluation helps to promote the standardization of construction project land saving work and is conducive to forming a unified land saving evaluation standard and benchmark in the industry to promote the continuous improvement and healthy competition of land saving work. Since the evaluation results are presented in the form of specific numerical values and the model operation process is clear and visible, the land saving evaluation process is more transparent, easy to understand and accept. This is very beneficial to the communication and negotiation between the parties involved in the project (such as the construction unit, the design unit, the regulatory agency, etc.), helps to reach a consensus, and promotes the smooth implementation of land saving measures. By finding the optimal land saving scheme, the land use efficiency can be maximized, unnecessary land occupation can be reduced, land cost can be reduced, ecological environment can be protected, and efficient, economical and sustainable use of land resources can be achieved, thereby improving the overall environmental benefit of the construction project.

[0101] In one embodiment of the present application, the S4 comprises:

[0102] S41, through the data visualization function of the cloud platform, the land saving evaluation results are visually displayed in the form of charts, maps, dashboards, etc. Based on the quantitative land saving evaluation results, land saving evaluation suggestions are generated in combination with the project conditions, including specific measures such as land use strategy adjustment, technology and process improvement, policy and system docking, dynamic monitoring and continuous improvement, etc.

[0103] S42, the visual land saving evaluation results and land saving evaluation suggestions are pushed to relevant personnel, including relevant decision makers, design personnel and regulatory agencies.

[0104] The working principle of the above technical solution is: using the data visualization function of the cloud platform, the land saving evaluation results are presented in intuitive forms such as charts, maps, dashboards, etc. These visualization elements convert complex land saving index values and evaluation results into easy-to-understand graphical interfaces, making it easy for relevant personnel to quickly grasp the overall situation of land saving, key data points, and the relationship between various indicators. Based on quantitative land saving evaluation results, combined with the specific background, goals, constraints and other factors of the project, the system generates targeted land saving evaluation suggestions. These suggestions may include adjustments to land use strategies (such as optimizing land layout, improving land use intensity, etc.), improvements in technology and processes (such as using new building structures, promoting green construction technology, etc.), and the establishment of dynamic monitoring and continuous improvement mechanisms. The specific measures aim to guide the project to implement effective land saving strategies during the design, construction, and operation stages; the visualization of land saving evaluation results and land saving evaluation suggestions are pushed to relevant decision-makers, designers, and regulatory agencies through cloud platforms or other communication means (such as email, SMS, mobile application notifications, etc.). In this way, relevant personnel can receive the latest results and improvement suggestions of land saving evaluation in the first time, which is conducive to their timely adjustment of project planning, design ideas or regulatory measures, ensuring that land saving work is effectively implemented; through visualization and suggestion pushing, an information exchange and feedback platform is built, and relevant personnel can view, discuss, ask questions or provide feedback on land saving evaluation results and suggestions, forming an interactive exchange. The cloud platform can collect these feedback information to provide basis for further optimizing land saving evaluation model and improving land saving suggestions, forming a closed-loop management of land saving evaluation work.

[0105] The effect of the above technical solution is that: through the data visualization function of the cloud platform, the land saving evaluation results are displayed in the form of intuitive and easy-to-understand charts, maps, dashboards and the like, so that the complex land saving data and evaluation results become clear and easy to understand. This visualization method enhances the transparency of information, helps relevant decision makers, designers and regulatory agencies quickly understand the land saving status, problems and improvement space of the project land, and provides strong data support for them to formulate and adjust land saving strategies; based on the quantitative land saving evaluation results, the system generates targeted land saving evaluation suggestions, including land use strategy adjustment, technology and process improvement, policy and system docking, dynamic monitoring and continuous improvement and the like. These suggestions provide a clear land saving optimization path for the project in land use, planning and design, construction management, post-operation and the like, and help to continuously promote the land saving level of the project land; the visualized land saving evaluation results and land saving evaluation suggestions are pushed to relevant personnel in real time, realizing the instant sharing and synchronous updating of information, and promoting the efficient communication and cooperation between decision makers, designers and regulatory agencies. By jointly focusing on and discussing the land saving evaluation results and suggestions, a consensus can be formed, the decision-making process can be accelerated, and the execution efficiency of land saving measures can be improved; for regulatory agencies, by receiving and analyzing the visualized land saving evaluation results and suggestions, the land saving situation of the project land can be grasped in time, potential problems can be found, behaviors not meeting the land saving requirements can be corrected in time, and excellent land saving practices can be encouraged and promoted, so as to improve the regulatory efficiency and ensure the reasonable and efficient use of land resources; through the visualized display and suggestion pushing, the knowledge, methods and successful cases of land saving evaluation are widely spread to relevant personnel, which helps to improve their land saving awareness, professional knowledge and practical ability, and promotes the popularization and application of land saving concepts and technologies in construction projects.

[0106] One embodiment of the present application, as shown in Figure 2 A land saving evaluation and analysis system for construction project land, the system comprising:

[0107] The data acquisition module: a multi-dimensional land saving evaluation index system is constructed; construction project related data is collected from multiple channels, and the acquired related data is stored in the cloud platform;

[0108] The data processing module: the acquired related data is processed through the cloud platform;

[0109] Based on the above evaluation index, a multi-objective optimization algorithm is used to construct a land saving evaluation model;

[0110] The simulation operation module: through the constructed land saving evaluation model, the land saving situation of the construction project is simulated and operated to obtain the specific values of various land saving indexes, and through comparative analysis, the quantitative land saving evaluation results of the construction project in each system are obtained; the evaluation results should include:

[0111] The suggestion generation module generates land saving evaluation suggestions based on the land saving evaluation results and feeds back the land saving evaluation suggestions to relevant personnel through a visual method.

[0112] The working principle of the above technical solution is to construct a land saving evaluation index system covering multiple key dimensions, aiming to comprehensively and systematically measure the land saving performance of the construction project. The dimensions include:

[0113] Land use intensity: measures the construction scale and function carried on the unit area of land, such as building area, facility capacity, and production capacity, etc. For highway projects, indicators reflecting road construction density such as roadbed width, road grade, number of lanes, and number of interchanges can be considered;

[0114] Land use efficiency: calculates the ratio of actual land area to approved land area to evaluate the land saving degree of the project under the premise of meeting functional requirements. For airport projects, the land use efficiency of each functional block such as the flight area, terminal area, hangar area, and supporting facility area can be analyzed.

[0115] Building density: reflects the proportion of building coverage, used to measure the compactness of the internal space layout of the project. In airport planning, the floor area of main buildings such as terminal buildings, hangars, and office buildings and their proportion of total land can be analyzed.

[0116] FAR (Floor Area Ratio): applicable to projects with a large number of buildings, such as residential, commercial, or comprehensive development projects, used to measure the ratio of total building area to land area, reflecting the intensity of space development upwards.

[0117] Green space ratio: evaluates the proportion of green space area in total land, reflecting the configuration of green space and the awareness of ecological environment protection. For airports, greenery not only beautifies the environment, but also reduces noise and improves microclimate.

[0118] Spatial layout compactness: through quantitative analysis of the spatial distribution of buildings, roads, and facilities, it is determined whether the layout is compact and reasonable, avoiding land waste. In highway design, the compactness of road layout can be evaluated by analyzing parameters such as curve radius, straight line length, and intersection spacing.

[0119] Topography adaptability: considers the full use of specific topographic conditions by the project, such as rational use of natural topography such as mountains and valleys for design, reduction of earthwork, and reduction of impact on the ecological environment.

[0120] Functional integration: evaluates whether multiple functions are integrated on the same plot, such as highway service facilities and land comprehensive development, airport and industrial park or logistics park integration, etc., to improve the comprehensive utilization value of land.

[0121] Technical innovation and process optimization: Investigate whether the project has applied new technologies and processes that help save land, such as underground space development, lightweight structures, modular construction, etc., to reduce the demand for land resources.

[0122] Under each dimension, specific evaluation indicators are set, such as roadbed width and lane number for highway projects, and flight area and terminal area land use for airport projects, as well as corresponding evaluation standards and weights, to ensure the scientificity, comprehensiveness, and operability of the evaluation system; detailed data related to the construction project are obtained from various channels such as planning drawings, construction records, geographic information system data, environmental monitoring and assessment reports, etc. Specifically, they include:

[0123] Planning drawings and design schemes: Obtain detailed information such as project layout, building size, road network, and green space layout.

[0124] Construction records and completion materials: Understand the land use during the actual construction process and verify the consistency between design and implementation.

[0125] Geographic information system (GIS) data: Use vector data, satellite images, and topographic maps to accurately depict the terrain, land properties, and surrounding environment of the project area.

[0126] Environmental monitoring and assessment reports: Understand the impact of the project on the ecological environment and evaluate the effectiveness of environmental protection measures.

[0127] After these data are sorted and verified, they are uploaded to the cloud platform for storage; the cloud platform processes the stored construction project data, builds a land-saving evaluation model based on the multi-dimensional land-saving evaluation index system constructed in the early stage, and uses multi-objective optimization algorithms (such as analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis, etc.); input the processed construction project data into the constructed land-saving evaluation model for simulation operation. The model operation results output the specific values of each land-saving indicator, such as the specific value of land use intensity and the quantitative score of land use efficiency. By comparing and analyzing these values with the evaluation standards, the quantitative evaluation results of the construction project in each land-saving system can be obtained, such as the overall land-saving level score, single indicator score, and advantage and shortcoming analysis; based on the land-saving evaluation results, the system generates land-saving evaluation suggestions for the project, including land use strategy adjustment, technology and process improvement, policy and system docking, dynamic monitoring and continuous improvement, etc. To facilitate relevant personnel to understand and adopt these suggestions, the system presents the land-saving evaluation results and suggestions in the form of charts, maps, dashboards, etc. using visualization methods, which intuitively displays the project's land-saving status, problem points, and optimization path, facilitating decision-makers and relevant personnel to quickly grasp key information and make scientific decisions.

[0128] The effect of the above technical scheme is: a multi-dimensional land saving evaluation index system is constructed, ensuring that the evaluation covers multiple key dimensions such as land use intensity, land use efficiency, building density, volume rate, green space rate, and spatial layout, comprehensively reflecting the land saving characteristics of the construction project land, avoiding the one-sidedness that may be caused by single index evaluation, and improving the systematization and accuracy of the evaluation; through multi-channel collection of construction project related data, the data is stored in the cloud platform for centralized management and processing, ensuring that the evaluation is based on detailed and accurate data basis. The data processing capability of the cloud platform helps to improve the data quality and consistency, provides high-quality input for the construction of the land saving evaluation model, so as to realize the precise simulation operation and quantitative evaluation of the construction project land; the multi-objective optimization algorithm is used to construct the land saving evaluation model, which can take into account multiple targets such as environmental benefits and land saving level, and provide a scientific basis for land saving decision of the construction project land. Through model simulation operation, the specific numerical value of each land saving index and the quantitative land saving evaluation result are obtained, which is beneficial to objectively and fairly evaluate the project land saving effect, and provides quantitative guidance for optimizing land resource allocation and improving land use efficiency; the land saving evaluation suggestions generated based on the land saving evaluation result not only contain the diagnosis of the existing project land condition, but also put forward specific improvement suggestions such as land use strategy adjustment, technology and process improvement, etc., which provides a clear land saving optimization path for project design, construction, management and other links, and helps the project team to take targeted measures to improve the land saving level; the land saving evaluation suggestions are fed back in a visual way, so that the complex land saving evaluation result and suggestions are presented in an intuitive and easy-to-understand form, enhancing the efficiency and effect of information transmission. This form is convenient for project team members, management, regulatory agencies and related interest parties to quickly understand and accept the evaluation result, promotes information sharing and decision consensus, and is conducive to promoting the implementation and execution of land saving measures; the application of the cloud platform significantly improves the data processing efficiency and the operation capability of the evaluation model, simplifies the data management process, and reduces the labor and time cost of data processing. At the same time, the elastic expansion capability and distributed computing capability of the cloud platform enable the land saving evaluation of large-scale and complex projects to be efficiently completed, improving the efficiency and response speed of the overall evaluation work.

[0129] In an embodiment of the present application, the data acquisition module comprises:

[0130] The dimension determination module determines the key dimensions of land saving evaluation, and sets evaluation indexes for each dimension;

[0131] The standard specification module sets evaluation standards and weights for each evaluation index; the construction project related data is acquired through multiple channels;

[0132] The data transmission module: the relevant data obtained through multiple channels are respectively fragmented and compressed into multiple data blocks, and the compressed data blocks are transmitted to the cloud platform through a multi-thread transmission mode. The data block is the fragmented relevant data fragment.

[0133] The working principle of the above technical solution is: systematically identify and determine the key dimensions that affect the land saving effect of the construction project, such as land use intensity, land use efficiency, building density, plot ratio, green space ratio, spatial layout compactness, topography adaptability, functional complexity, technical innovation and process optimization, etc., to ensure that the evaluation system fully covers the core factors affecting the land saving performance of the project; for each key dimension, specific evaluation indicators are set to ensure that the indicators correspond closely to the dimensions and can accurately measure the land saving performance under that dimension. For example, for the land use intensity dimension, highway projects can set roadbed width, road grade, lane number, etc., and airport projects can set flight area, terminal area, hangar area, etc.; for the land use efficiency dimension, calculate the ratio of actual land area to approved land area; for the building density dimension, define the building coverage rate; for the plot ratio dimension, set the ratio of total building area to land area; for the green space ratio dimension, specify the proportion of green space area to total land; for the spatial layout compactness dimension, design evaluation standards for parameters such as curve radius, straight line length, intersection spacing, etc.; set evaluation standards (such as threshold, grading standards, etc.) for each evaluation indicator to clearly define the standard requirements or good-bad grade division of the indicator. At the same time, give each indicator an appropriate weight to reflect its relative importance in the overall land saving evaluation, ensuring that the evaluation results accurately reflect the overall contribution of each dimension to the land saving effect of the project; collect construction project related data through multiple channels, such as consulting planning drawings, obtaining construction records, accessing geographic information system data, and referring to environmental monitoring and evaluation reports, to ensure the diversity and comprehensiveness of data sources, providing sufficient information support for building a comprehensive and accurate land saving evaluation; fragment the collected large amount of construction project related data according to certain rules to form multiple logically independent and easily managed data fragments; compress the fragmented data to reduce data volume, improve data transmission efficiency, and reduce storage space requirements; use multi-thread technology to transmit the compressed data blocks (i.e. fragmented relevant data fragments) to the cloud platform in parallel, fully utilize network bandwidth, speed up the data upload process, and shorten the data processing cycle.

[0134] The effect of the above technical scheme is: by constructing a land saving evaluation index system including land use intensity, land use efficiency, building density, volume rate, green space rate, spatial layout compactness, topography adaptability, functional complexity, technical innovation and process optimization, the core factors affecting the land saving effect of the construction project are ensured to be covered comprehensively, the one-dimensional evaluation may cause one-sidedness is avoided, and the comprehensiveness and systematicness of the evaluation are improved;For each key dimension, specific evaluation indexes are set, such as roadbed width, road grade and lane number of highway projects, flight area, terminal area and hangar area of airport projects, and evaluation standards for calculating the ratio of actual land area to approved land area, defining building coverage, setting the ratio of total building area to land area, regulating the proportion of green area to total land, designing the radius of curved road, the length of straight section and the distance between intersections, etc., so that the evaluation is more targeted and can accurately reflect the land saving performance of the construction project in each dimension;Evaluation standards (such as threshold, grading standard, etc.) and weights are set for each evaluation index, providing a unified and clear reference benchmark for land saving evaluation, and enhancing the standardization and comparability of the evaluation;The setting of weights helps to reasonably balance the relative importance of each index in the overall land saving evaluation, ensuring that the evaluation result is fair and objective;Through multi-channel collection of construction project related data such as planning drawings, construction records, geographic information system data, environmental protection monitoring and evaluation reports, etc., the evaluation is based on comprehensive, detailed and multi-angle information, and the reliability and persuasiveness of the evaluation are enhanced;The large amount of data obtained from multiple channels is fragmented, compressed and processed, and uploaded to the cloud platform through multi-thread transmission technology, effectively improving the data processing efficiency, reducing the data transmission time and storage space requirement, and providing an efficient data processing and storage solution for large-scale and complex land saving evaluation of projects;The construction project related data stored in the cloud platform is convenient for centralized management, rapid retrieval, remote access and multi-party sharing, greatly improving the convenience and collaboration efficiency of data utilization, and being conducive to cross-department and cross-region collaborative evaluation and decision-making;The technical scheme provides a scientific, comprehensive and accurate quantitative tool for land saving evaluation of construction projects, which helps project managers, designers, regulatory departments, etc. to make scientific decisions based on the evaluation results, develop reasonable land saving strategies, and promote efficient use and optimal allocation of land resources. At the same time, the evaluation results are continuously tracked, and continuous improvement is made according to the evaluation standards and suggestions, so as to continuously improve the land saving level of the project.

[0135] In an embodiment of the present application, the data processing module comprises:

[0136] The data decompression module: the cloud platform receives the compressed data blocks, decompresses the data blocks, and pre-processes the data blocks by the cloud platform;The preprocessing includes deleting duplicate data, filling missing values and abnormal values, data normalization and standardization;

[0137] Data storage module: store the pre-processed data blocks into different subspaces respectively, and allocate computing resources to each subspace, and process the data in each subspace through a distributed computing framework;

[0138] Threshold comparison module: during the processing, the resource utilization of each subspace is monitored in real time through a load balancing algorithm, an adjustment threshold is set and an adjustment strategy is formulated, and the adjustment is triggered when the data volume of a certain subspace exceeds or is lower than a certain threshold;

[0139] First adjustment module: if the data volume of a certain subspace exceeds the threshold, it is split into multiple subspaces, or part of the data is migrated to other subspaces;

[0140] Second adjustment module: if the data volume of a certain subspace is too small, it is merged into other subspaces, or the data of other subspaces is migrated to the subspace;

[0141] Strategy adjustment module: implement real-time data division adjustment and continuously monitor the changes of system resources and data volume; based on the monitoring results, continuously adjust the data division strategy;

[0142] Result aggregation module: after processing, the processing results of each subspace are aggregated, based on the obtained processing results, multi-objective optimization algorithms such as analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis are used to construct a land saving evaluation model that can consider both environmental benefits and land saving level.

[0143] Based on the obtained processing results, multi-objective optimization algorithms such as analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis are used to construct a land saving evaluation model that can consider both environmental benefits and land saving level, including:

[0144] According to the constructed multi-dimensional land saving evaluation index system, select and extract the features related to the evaluation index; according to the multiple goals of land saving evaluation of construction projects, select the appropriate multi-objective optimization algorithm;

[0145] Build an optimization algorithm model, select the evaluation index as the objective function, and use the optimization algorithm to find a set of optimal solutions.

[0146] Through the aggregated data, the constructed multi-objective optimization model is trained and optimized; the trained model is verified and evaluated to test its performance and accuracy in land saving evaluation of construction projects.

[0147] Integrate the trained optimization model into the cloud platform and deploy it; the deployed model can receive user input of construction project related data, perform evaluation simulation operation and generate land saving evaluation results.

[0148] The working principle of the above technical solution is that the cloud platform receives compressed data blocks sent through a multi-thread transmission mode, decompresses the data blocks to restore the original data structure; pre-processes the decompressed data, including deleting duplicate data, filling missing values and abnormal values, to ensure the integrity and consistency of the data; performs data normalization or standardization processing to convert data of different sources and dimensions to the same scale, facilitating subsequent analysis and modeling; distributes the pre-processed data blocks to different subspaces for storage and allocates appropriate computing resources to each subspace; performs parallel processing of the data in each subspace through a distributed computing framework, greatly improving data processing efficiency; monitors the resource utilization of each subspace in real time, and when the data volume reaches a preset threshold, dynamically adjusts the subspace division, maintains the balance of resource use in each subspace through data migration, subspace splitting or merging, and ensures stable and efficient operation of the system; according to the constructed multi-dimensional land saving evaluation index system, select data features closely related to evaluation indexes as model input; according to the environmental benefits and land saving level involved in land saving evaluation of construction projects, select appropriate multi-objective optimization algorithms such as analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis, etc.; select the selected evaluation indexes as the objective function, and use the selected optimization algorithm to construct a land saving evaluation model that can consider multiple objectives at the same time; use the aggregated pre-processed data to train the constructed multi-objective optimization model, adjust the model parameters through iterative optimization, and improve the model performance. After training, the model is verified and evaluated to ensure its accuracy and stability in land saving evaluation of construction project land; integrate the trained and verified optimization model into the cloud platform to complete the deployment. The deployed model can receive user input data related to construction projects, perform land saving evaluation simulation, and quickly generate land saving evaluation results.

[0149] The effect of the above technical scheme is: the cloud platform automatically receives, decompresses and preprocesses (deletes duplicate data, fills in missing values and abnormal values, normalizes and standardizes data) data blocks, greatly improves data processing efficiency, reduces manual intervention and ensures data quality; the preprocessed data blocks are stored in different subspaces, and parallel processing is performed through a distributed computing framework to effectively utilize computing resources. Real-time monitoring of the utilization rate of the sub-space resources, dynamic balancing of data distribution through adjustment of threshold and strategy, and ensuring efficient and stable operation of the system; based on a multi-dimensional land saving evaluation index system, selecting features related to evaluation indexes, constructing a land saving evaluation model that can consider environmental benefits and land saving level at the same time, and ensuring comprehensive and objective evaluation; according to the characteristics of the evaluation target, selecting appropriate multi-objective optimization algorithms (such as analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis, etc.), which can effectively handle the trade-off and compromise between multiple objectives, and generate evaluation results that meet actual needs; using the aggregated preprocessed data to train and optimize the multi-objective optimization model, improving the accuracy of the model in land saving evaluation of construction projects; verifying and evaluating the trained model to ensure its good prediction performance and stability in practical application, providing reliable basis for decision-making; integrating the trained and verified optimization model into the cloud platform to realize automatic deployment. Users only need to input the relevant data of the construction project to quickly obtain the land saving evaluation results, greatly simplifying the evaluation process and improving work efficiency; the cloud platform monitors system resources and data volume changes in real time, dynamically adjusts data division strategies as needed, ensures that the model can cope with changing data environment, and realizes real-time evaluation and feedback of land saving of construction projects.

[0150] In an embodiment of the present application, the simulation operation module comprises:

[0151] The data input module inputs the aggregated data into the constructed land saving evaluation model and performs simulation operation on the land saving of the construction project through quantitative evaluation model;

[0152] The system evaluation module outputs the specific values of each land saving index after simulation operation; compares and analyzes the calculated land saving index values with the preset evaluation standard, and evaluates the land saving level of the construction project in each system;

[0153] The scheme determination module compares the land saving effects of different schemes to find the optimal land saving scheme.

[0154] The working principle of the above technical solution is: the construction project land related data after preprocessing, summarizing and standardizing is taken as input and sent to the constructed land saving evaluation model. The model comprehensively considers various land saving indicators such as land use efficiency, spatial layout rationality, ecological environment impact, etc., and simulates and calculates the land use of the construction project under different schemes through the built-in algorithm. The simulation and calculation process may include calculating the specific values of various indicators, evaluating the influence degree of different schemes on various indicators, simulating the change trend of land use under different schemes, etc.; after the model calculation is completed, the specific values of various land saving indicators are output, such as the percentage of land use efficiency, the compactness index of spatial layout, the quantitative score of ecological environment impact, etc. These values reflect the actual performance of the construction project in various land saving dimensions and provide quantitative basis for subsequent comparative analysis and scheme optimization; compare the calculated land saving indicator values with the preset evaluation standards (such as industry specifications, local policy requirements, best practice standards, etc.) to evaluate the land saving level of the construction project in each system (such as land use efficiency system, spatial layout system, ecological environment impact system, etc.). The comparative analysis may include calculating the deviation, compliance rate, ranking, etc. to intuitively show the gap between the land saving performance of the construction project and the standard requirements, and to clearly identify the advantages and disadvantages in land saving work; compare the land saving effects of different schemes, find out the optimal land saving scheme in the overall land saving effect by comparing the differences of various land saving indicator values. The optimal scheme may be the comprehensive optimization of various indicators, or it may be the optimization of several key indicators according to the specific situation and priority of the project. Through scheme comparison, clear land saving optimization direction and implementation strategy are provided for project decision makers.

[0155] The effect of the above technical scheme is: through the construction of land saving evaluation model, the land use of the construction project is converted into quantifiable land saving indicators, and the quantitative evaluation of the land saving effect is realized. This quantitative method makes the land saving evaluation more objective, comparable and scientific, provides clear and specific land saving performance data for project decision makers, and helps them make more accurate and rational decisions; the model comprehensively considers land use efficiency, spatial layout rationality, ecological environment impact and other land saving indicators, ensures that the evaluation system comprehensively covers the key factors affecting the land saving effect, and avoids the one-sidedness that may be caused by single dimension evaluation. This multi-dimensional comprehensive evaluation helps to more comprehensively and accurately reflect the land saving characteristics of the construction project land, and provides basis for formulating comprehensive land saving optimization strategies; through the model simulation operation of the land use of the construction project under different schemes, the influence of different land saving strategies on various indicators can be predicted, helping decision makers to evaluate the effect of various land saving schemes in advance. By comparing the land saving effects of different schemes, the optimal scheme in terms of overall land saving benefit can be found, providing a clear direction for project optimization design and implementation; by comparing and analyzing the calculated land saving indicator values with the preset evaluation standards, the land saving level of the construction project in each system is standardized evaluated, ensuring the fairness and consistency of the evaluation results. This standardized evaluation helps to promote the standardization of construction project land saving work, is conducive to forming a unified land saving evaluation standard and benchmark in the industry, and promotes the continuous improvement and benign competition of land saving work; since the evaluation results are presented in the form of specific numerical values, and the model operation process is clear and visible, the land saving evaluation process is more transparent, easy to understand and accept. This is very beneficial to the communication and negotiation between the parties involved in the project (such as the construction unit, the design unit, etc.), helps to reach a consensus, and promotes the smooth implementation of land saving measures; by finding the optimal land saving scheme, the land use efficiency can be maximized, unnecessary land occupation can be reduced, land cost can be reduced, ecological environment can be protected, and efficient, economical and sustainable use of land resources can be realized, thereby improving the overall environmental benefit of the construction project.

[0156] In an embodiment of the present application, the suggestion generation module comprises:

[0157] The suggestion generation module: through the data visualization function of the cloud platform, the land saving evaluation results are intuitively displayed in the form of charts, maps, dashboards, etc.; based on the quantitative land saving evaluation results, the land saving evaluation suggestions are generated in combination with the project conditions; including specific measures such as land use strategy adjustment, technology and process improvement, policy and system docking, dynamic monitoring and continuous improvement, etc.

[0158] The suggestion pushing module: push the visual land saving evaluation results and land saving evaluation suggestions to relevant personnel, including relevant decision makers, designers and regulatory agencies.

[0159] The working principle of the above technical solution is: using the data visualization function of the cloud platform, the land saving evaluation results are presented in intuitive forms such as charts, maps, dashboards, etc. These visualization elements convert complex land saving index values and evaluation results into easy-to-understand graphical interfaces, making it easy for relevant personnel to quickly grasp the overall situation of land saving, key data points, and the relationship between various indicators. Based on quantitative land saving evaluation results, combined with the specific background, goals, constraints and other factors of the project, the system generates targeted land saving evaluation suggestions. These suggestions may include adjustments to land use strategies (such as optimizing land layout, improving land use intensity, etc.), improvements in technology and processes (such as using new building structures, promoting green construction technology, etc.), and the establishment of dynamic monitoring and continuous improvement mechanisms. The specific measures aim to guide the project to implement effective land saving strategies during the design, construction, and operation stages; the visualization of land saving evaluation results and land saving evaluation suggestions are pushed to relevant decision-makers, designers, and regulatory agencies through cloud platforms or other communication means (such as email, SMS, mobile application notifications, etc.). In this way, relevant personnel can receive the latest results and improvement suggestions of land saving evaluation in the first time, which is conducive to their timely adjustment of project planning, design ideas or regulatory measures, ensuring that land saving work is effectively implemented; through visualization and suggestion pushing, an information exchange and feedback platform is built, and relevant personnel can view, discuss, ask questions or provide feedback on land saving evaluation results and suggestions, forming an interactive exchange. The cloud platform can collect these feedback information to provide basis for further optimizing land saving evaluation model and improving land saving suggestions, forming a closed-loop management of land saving evaluation work.

[0160] The effect of the above technical scheme is that the land saving evaluation result is displayed in the form of intuitive and easy-to-understand charts, maps, dashboards and the like through the data visualization function of the cloud platform, so that the complex land saving data and evaluation result become clear and easy to understand. This visualization mode enhances the transparency of information, helps relevant decision makers, designers and regulatory agencies quickly understand the land saving status, problems and improvement space of the project land, and provides strong data support for them to formulate and adjust land saving strategies; based on the quantitative land saving evaluation result, the system generates targeted land saving evaluation suggestions, including land use strategy adjustment, technology and process improvement, policy and system docking, dynamic monitoring and continuous improvement and the like. These suggestions provide a clear land saving optimization path for the project in land use, planning and design, construction management, post-operation and the like, and help to continuously promote the land saving level of the project land; the visual land saving evaluation result and land saving evaluation suggestions are pushed to relevant personnel in real time, realizing the instant sharing and synchronous updating of information, and promoting the efficient communication and cooperation between decision makers, designers and regulatory agencies. Through the common attention and discussion of the land saving evaluation result and suggestions, the consensus is formed, the decision-making process is accelerated, and the execution efficiency of land saving measures is improved; for the regulatory agencies, by receiving and analyzing the visual land saving evaluation result and suggestions, the land saving situation of the project land can be mastered in time, potential problems can be found, behaviors not meeting the land saving requirements can be corrected in time, and excellent land saving practices can be encouraged and promoted, so as to improve the regulatory efficiency and ensure the reasonable and efficient use of land resources; through the visual display and suggestion pushing, the knowledge, method and successful cases of land saving evaluation are widely spread to relevant personnel, which helps to improve their land saving awareness, professional knowledge and practical ability, and promotes the popularization and application of land saving concept and technology in construction projects.

[0161] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and equivalent technologies thereof, the present application also intends to include these modifications and variations.

Claims

1. A land saving evaluation analysis method for a construction project site, characterized by, The method comprises: S1, constructing a multi-dimensional land saving evaluation index system; collecting construction project related data from multiple channels, and storing the obtained related data in a cloud platform; S2, processing the obtained related data through the cloud platform; based on the above evaluation index, a land saving evaluation model is constructed by using a multi-objective optimization algorithm; S3, simulating and operating the land use of the construction project through the constructed land saving evaluation model, obtaining the specific values of various land saving indexes, and obtaining the quantitative land saving evaluation results of the construction project in each system through comparative analysis; S4, based on the land saving evaluation results, generating land saving evaluation suggestions, and feeding back the land saving evaluation suggestions to relevant personnel through a visual method; The S2 comprises: S21, the cloud platform receives the compressed data block, decompresses the data block, and the cloud platform preprocesses the data block; S22, the preprocessed data block is stored in different subspaces, and each subspace is allocated with computing resources, and the data of each subspace is processed through a distributed computing framework; S23, in the processing process, the resource utilization rate of each subspace is monitored in real time through a load balancing algorithm, an adjustment threshold is set and an adjustment strategy is developed, and the adjustment is triggered when the data volume of a certain subspace exceeds or is lower than a certain threshold; S24, if the data volume of a certain subspace exceeds the threshold, the subspace is split into multiple subspaces, or part of the data is migrated to other subspaces; S25, if the data volume of a certain subspace is too small, the subspace is merged into other subspaces, or the data of other subspaces is migrated to the subspace; S26, implement real-time data division adjustment, and continuously monitor the changes of system resources and data volume; according to the monitoring result, the data division strategy is adjusted constantly; S27, after the processing is completed, the processing results of each subspace are summarized, based on the obtained processing results, a land saving evaluation model is constructed by using a multi-objective optimization algorithm; The S22 comprises: According to the characteristics of the preprocessed data, an improved k-means++ algorithm is used to perform initial clustering on the data to form logical subspace division; Based on historical data and real-time monitoring, a lightweight LSTM neural network model is constructed to predict the computing resource demand of each subspace in the next 5 minutes; A resource scheduler based on deep reinforcement learning is used to dynamically allocate containerized computing resources, aiming to minimize task completion time and maximize resource utilization; On the basis of Spark / Flink, operators supporting geospatial data processing are extended, and PyTorch / TensorFlow GPU acceleration capabilities are integrated; According to the data size and complexity of the subspace, the task parallelism is automatically adjusted, the optimal parallelism configuration is searched through a genetic algorithm, and the task state snapshot based on checkpoint is combined with heartbeat detection and standby node pool to recover the task within 30 seconds when a node fails; Through the rack-aware strategy of HDFS and the Snitch positioning of Cassandra, the subspace where the data is located is preferentially scheduled to the computing nodes of the same rack; for frequently accessed land evaluation index data, the Alluxio in-memory file system is used for multi-level caching; Different data are designed with adapters, and cross-modal correlation queries are implemented through a unified metadata model; for data with spatial and temporal attributes, the Space-TimeCube model is used for three-dimensional visualization analysis to identify the spatiotemporal pattern of land use changes; For real-time monitoring data, Flink stream processing is used, and for historical data, Spark batch processing is used, and the results are output through the Lambda architecture; and when the data is blocked, Laplace noise is added to sensitive attributes; For subspace data involving multi-party collaboration, the Paillier homomorphic encryption scheme is used to support index calculation in an encrypted state; and ApacheRanger is used for column-level dynamic desensitization.

2. The land saving evaluation and analysis method for a construction project site according to claim 1, characterized by, The S1 comprises: S11, determining the key dimensions of land evaluation, and setting evaluation indexes for each dimension; S12, setting evaluation standards and weights for each evaluation index; obtaining construction project related data through multiple channels; S13, the related data obtained through multiple channels are respectively fragmented and compressed into multiple data blocks, and the compressed data blocks are transmitted to the cloud platform through a multi-thread transmission mode.

3. The land saving evaluation and analysis method for a construction project site according to claim 1, characterized by, The S3 comprises: S31, inputting the summarized data into the constructed land evaluation model, and performing simulation operation on the land use of the construction project through the quantitative evaluation model; S32, after the simulation operation is completed, the specific values of each land saving index are output; the land saving index values calculated are compared and analyzed with the preset evaluation standards to evaluate the land saving level of the construction project in each system; S33, at the same time, the land saving effects between different schemes are compared to find out the optimal land saving scheme.

4. The land saving evaluation and analysis method for a construction project site according to claim 1, characterized by, The S4 comprises: S41, intuitively displaying the land evaluation results through the data visualization function of the cloud platform; based on the quantitative land evaluation results, the land evaluation suggestions are generated in combination with the project conditions; S42, the visual land evaluation results and land evaluation suggestions are pushed to relevant personnel, including relevant decision makers and designers.

5. A land-saving evaluation and analysis system for construction projects, characterized in that, The system comprises: A data acquisition module: constructing a multi-dimensional land evaluation index system; collecting construction project related data from multiple channels and storing the obtained related data in a cloud platform; A data processing module: processing the obtained related data through the cloud platform; based on the above evaluation indexes, a land evaluation model is constructed using a multi-objective optimization algorithm; A simulation operation module: through the constructed land evaluation model, the land use of the construction project is simulated and operated to obtain the specific values of each land saving index, and through comparison and analysis, the quantitative land evaluation results of the construction project in each system are obtained; the evaluation results should include: An advice generation module: based on the land evaluation results, land evaluation suggestions are generated and fed back to relevant personnel through visualization; The data processing module comprises: Data decompression module: the cloud platform receives compressed data blocks, decompresses the data blocks, and pre-processes the data blocks; Data storage module: store the pre-processed data blocks in different subspaces and allocate computing resources to each subspace. Process the data in each subspace separately through a distributed computing framework; Threshold comparison module: during processing, monitor the resource utilization of each subspace in real time through a load balancing algorithm, set an adjustment threshold and develop an adjustment strategy. Trigger adjustment when the data volume of a subspace exceeds or falls below a certain threshold; First adjustment module: if the data volume of a subspace exceeds the threshold, split it into multiple subspaces or migrate part of the data to other subspaces; Second adjustment module: if the data volume of a subspace is too small, merge it into other subspaces or migrate data from other subspaces to it; Strategy adjustment module: implement real-time data division adjustment and continuously monitor system resources and data volume changes. Based on the monitoring results, continuously adjust the data division strategy; Result aggregation module: after processing, aggregate the processing results of each subspace. Based on the obtained processing results, use a multi-objective optimization algorithm to build a land evaluation model. The data storage steps of the data storage module include: According to the characteristics of the pre-processed data, use the improved k-means++ algorithm to perform initial clustering on the data to form logical subspace division; Based on historical data and real-time monitoring, build a lightweight LSTM neural network model to predict the computing resource demand of each subspace in the next 5 minutes; Use a resource scheduler based on deep reinforcement learning to dynamically allocate containerized computing resources, aiming to minimize task completion time and maximize resource utilization; Extend the operators supporting geospatial data processing on the basis of Spark / Flink, and integrate PyTorch / TensorFlow GPU acceleration capabilities; According to the data size and complexity of the subspace, automatically adjust the task parallelism, and search for the optimal parallelism configuration through genetic algorithm. Based on the task state snapshot of the checkpoint, combined with heartbeat detection and standby node pool, restore the task within 30 seconds when the node fails; Through the rack awareness strategy of HDFS and the Snitch positioning of Cassandra, preferentially schedule the data to the computing nodes on the same rack; for frequently accessed land evaluation index data, use the Alluxio in-memory file system for multi-level caching; Design adapters for different data to implement cross-modal correlation query through a unified metadata model; for data with spatio-temporal attributes, use the Space-TimeCube model for three-dimensional visualization analysis to identify the spatio-temporal patterns of land use changes; Use Flink stream processing for real-time monitoring data and Spark batch processing for historical data, and output the results uniformly through the Lambda architecture; and when data is blocked, add Laplace noise to sensitive attributes; Paillier homomorphic encryption scheme is used to support index calculation in an encrypted state for subspace data involving multi-party collaboration; and column-level dynamic desensitization is performed based on Apache Ranger.

6. The land saving evaluation and analysis system for a construction project site according to claim 5, wherein The data acquisition module comprises: A dimension determination module determines key dimensions of land saving evaluation, and sets evaluation indexes for each dimension; A standard specification module sets evaluation standards and weights for each evaluation index; and construction project related data is acquired through multiple channels; A data transmission module divides and compresses the related data acquired through multiple channels into multiple data blocks, and transmits the compressed data blocks to a cloud platform through a multi-thread transmission mode.

7. The land saving evaluation and analysis system for a construction project site according to claim 5, wherein The simulation operation module comprises: A data input module inputs the summarized data into a constructed land saving evaluation model, and performs simulation operation on the land use situation of the construction project through a quantitative evaluation model; A system evaluation module outputs specific values of land saving indexes after simulation operation; compares and analyzes the calculated land saving index values with preset evaluation standards, and evaluates the land saving level of the construction project in each system; A scheme determination module compares the land saving effects of different schemes to find the optimal land saving scheme.

8. The land saving evaluation and analysis system for a construction project site according to claim 5, wherein The suggestion generation module comprises: A suggestion generation module visually displays the land saving evaluation results through the data visualization function of the cloud platform; and generates land saving evaluation suggestions based on the quantitative land saving evaluation results and in combination with the project situation; A suggestion pushing module pushes the visual land saving evaluation results and the land saving evaluation suggestions to relevant personnel, including relevant decision makers and designers.

Images