Land space planning index dynamic evaluation model

Abstract

The invention discloses a territorial space planning index dynamic evaluation model, and particularly relates to the field of territorial planning, and the model comprises a multi-source heterogeneous data fusion module, an index system construction module, a dynamic adjustment model construction module, a scheme evaluation and optimization module, and a model application and dynamic updating module. According to the method, various spatial data are integrated through a multi-source heterogeneous data fusion technology, and the data quality is ensured by adopting a three-stage cleaning assembly line and an intelligent correction algorithm; the method comprises the following steps: constructing an index system based on six core contents of territorial space planning, and determining an index weight by applying a Delphi method and an analytic hierarchy process to realize adaptive adjustment of an index threshold; the model adopts time sequence analysis, regression analysis and a machine learning algorithm to predict a development trend, a dynamic feedback mechanism is established in combination with a system dynamics method, and an evaluation scheme is quantified through an analytic hierarchy process; the model performance is evaluated by adopting indexes such as accuracy rate and precision rate, and parameters are continuously optimized based on an evaluation result; finally, the model is integrated to a service system to realize real-time monitoring, and dynamic updating is realized through three mechanisms of data driving, performance triggering and regular maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of land planning, and more specifically, to a dynamic evaluation model for land space planning indicators. Background Art

[0002] Land space planning not only concerns the allocation of land resources, but also affects multiple aspects such as ecological environment protection, social public service supply, and infrastructure construction.

[0003] However, in actual use, there are still some drawbacks. For example, most of the monitoring and evaluation work on land space planning still stays in the theoretical exploration stage, and most of the work has not yet formed a unified consensus. There are scattered monitoring and evaluation indicators, and there is no unified model to comprehensively evaluate the monitoring results. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a dynamic evaluation model for land space planning indicators to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions: Multi-source heterogeneous data fusion module: used to integrate multi-source heterogeneous data into structured data through data acquisition, cleaning, transformation, and fusion; Index system construction module: used to screen and construct an initial index system based on the six core contents of the strategic positioning, spatial pattern, public services, infrastructure, ecological restoration, and resource elements of land space planning; Dynamic adjustment model construction module: used to predict the changing trends of population, economy, and land use by using time series analysis, regression analysis, and machine learning algorithms, and construct a comprehensive evaluation model in combination with the analytic hierarchy process to generate an index adjustment plan; Scheme evaluation and optimization module: used to quantitatively evaluate the adjustment plan through accuracy, precision, recall rate, and F1 value, and optimize the model parameters according to the evaluation results; Model application and dynamic update module: used to integrate the model into the land space planning business system, monitor the index changes in real time, and update the model regularly according to new data and performance thresholds.

[0006] Preferably, in the multi-source heterogeneous data fusion module, data is obtained from various data sources such as databases, file systems, Internet of Things devices, and social media platforms, and the scattered data is collected into the data center through ETL tools, data acquisition interfaces, and web crawler technologies; In data cleaning, a three-level cleaning pipeline is constructed. The first level performs basic cleaning, using an improved SimHash algorithm to handle duplicate data and providing multiple imputation schemes for missing values. The second level implements business rule cleaning, with more than 200 specific verification rules in the field of territorial space planning built in, such as land use nature compliance inspection and planning index logic verification. The third level is the intelligent correction layer, which applies deep learning technologies, such as a text error correction model based on the Transformer architecture and a GAN repair network for spatial data, to significantly improve data quality.

[0007] Preferably, in the index system construction module, based on the core content of territorial space planning compilation, decomposition and analysis are carried out from six major aspects: strategic positioning, spatial pattern, public services, infrastructure, disaster prevention and mitigation, ecological restoration and land improvement, and resource elements, and then index screening and selection are carried out. Referring to the territorial space planning physical examination and evaluation and the territorial space planning target body index, an initial index system is constructed. In the strategic positioning index, according to the regional development goals, indicators such as population size, total economic volume, and industrial structure ratio are selected. In the spatial pattern index, according to the urban-rural land use structure, ecological protection red line, and permanent basic farmland protection rate dimensions, the rationality of land use layout is evaluated through spatial analysis techniques, and dynamic monitoring indicators such as development intensity and connectivity index are set. In the public service index, according to the coverage rate and accessibility of education, medical care, and cultural facilities, indicators such as per capita service resource ratio and 15-minute living circle coverage rate are constructed, and resource allocation is optimized by combining population distribution and demand prediction.

[0008] Preferably, in the dynamic adjustment model construction module, according to the initial index system of territorial space planning, population prediction models, land use change models, and economic growth and spatial layout relationship models are used to make corresponding predictions for the indicators. A comprehensive evaluation model is constructed based on historical data and predicted data, and the analytic hierarchy process is used to analyze the adaptability of the model. The model is trained according to historical data, and the comprehensive evaluation model is dynamically adjusted accordingly with reference to the model evaluation index. The specific method for model framework construction is as follows: Time series analysis, regression analysis, and machine learning algorithms are used to construct prediction models to predict population growth, economic development, and land use change, providing a basis for index dynamic adjustment. The Logistic growth model is used to predict the future population quantity, and the calculation method of the Logistic growth model is specifically as follows: , where represents the total population after t years, K represents the environmental carrying capacity, that is, the maximum population capacity, represents the initial population, r represents the growth rate, t represents time, and e represents the base of the natural logarithm; The specific calculation method for predicting land use changes is as follows: , where represents the land use status in year t, and ΔLU represents the land use change amount.

[0009] Preferably, in the scheme evaluation and optimization module, the dynamic adjustment model is evaluated from aspects such as accuracy and precision, the optimal parameter model is selected, and the evaluation scheme is optimized. Then, the specific calculation method for accuracy in the quantitative evaluation of the scheme is as follows: , where represents accuracy, TP represents the number of samples that are actually positive and predicted to be positive, TN represents the number of samples that are actually negative and predicted to be negative, FP represents the number of samples that are actually negative but predicted to be positive, and FN represents the number of samples that are actually positive but predicted to be negative; The specific calculation method for precision is as follows: , where B represents precision, TP represents the number of samples that are actually positive and predicted to be positive, and FP represents the number of samples that are actually negative but predicted to be positive; The specific calculation method for recall is as follows: , where C represents recall, TP represents the number of samples that are actually positive and predicted to be positive, and FN represents the number of samples that are actually positive but predicted to be negative; The specific calculation method for the F1 value is as follows: , where D represents the value, B represents precision, and C represents recall; According to the F1 value evaluation result, adjust the model parameters and optimization algorithm, optimize the adjustment scheme, and determine the final recommended scheme.

[0010] Preferably, in the model application and dynamic update module, according to the compilation, implementation, and management processes of the territorial space planning, the model is integrated into the existing business system to uniformly evaluate the index monitoring results in real time; updates are triggered according to data changes, performance indicators, or time periods. When a certain amount of new data accumulates, the model is retrained; when the model accuracy drops below the set threshold, an update is started; according to a fixed time interval, the model is updated once every quarter; At the real-time monitoring level, a multi-level index evaluation system is constructed: at the basic layer, a streaming computing engine processes real-time data streams to achieve second-level index calculation; at the intermediate layer, a rule engine (Drools) is used to execute business rule verification to automatically identify index anomalies; at the application layer, a multi-dimensional evaluation model is integrated to generate comprehensive evaluation results from three dimensions: compliance, implementation progress, and implementation effect.

[0011] Technical effects and advantages of the present invention: Through data acquisition, cleaning, transformation and fusion, the present invention integrates multi-source heterogeneous data into structured data. An initial index system is constructed based on six core contents such as the strategic positioning of territorial space planning, and a hierarchical and extensible framework is formed through weight allocation and adaptive adjustment; time series analysis and other methods are used to predict the trends of population, economy and land use changes, and a comprehensive evaluation model is constructed by combining the analytic hierarchy process to generate an index adjustment plan, which is optimized through training to improve accuracy; the adjustment plan is quantitatively evaluated from aspects such as accuracy rate, and the model parameters are optimized. The model is integrated into the business system to monitor index changes in real time, and is updated regularly according to new data and performance thresholds, and a multi-level index evaluation system is constructed to ensure the dynamic update and accurate application of the model through different triggering mechanisms; through the index dynamic adjustment model, the present invention can improve the scientificity of planning, ensure the implementation of planning, promote sustainable development, improve decision-making efficiency and quality, and better serve territorial space planning. Description of the drawings

[0012] Figure 1 It is a schematic diagram of the module connection of the present invention.

[0013] Figure 2 It is a schematic diagram of the model construction and training of the present invention.

[0014] Figure 3 It is a schematic diagram of the key technology research on the dynamic monitoring and evaluation of territorial space planning of the present invention. Detailed implementation manners

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0016] Please refer to Figure 1 As shown, the present invention provides a dynamic evaluation model for territorial space planning indicators, including a multi-source heterogeneous data fusion module, an index system construction module, a dynamic adjustment model construction module, a plan evaluation and optimization module, and a model application and dynamic update module.

[0017] The multi-source heterogeneous data fusion module: is used to integrate multi-source heterogeneous data into structured data through data acquisition, cleaning, transformation and fusion; In the multi-source heterogeneous data fusion module, data is obtained from multiple data sources such as databases, file systems, Internet of Things devices, and social media platforms, and the scattered data is collected into the data center through ETL tools, data acquisition interfaces, and web crawler technologies; In data cleaning, a three-level cleaning pipeline is constructed. The first level performs basic cleaning, using an improved SimHash algorithm to process duplicate data and providing multiple imputation schemes for missing values. The second level implements business rule cleaning, with more than 200 specific verification rules in the field of territorial space planning built in, such as checking the compliance of land use nature and logical verification of planning indicators. The third level is the intelligent correction layer, which applies deep learning technologies, such as a text error correction model based on the Transformer architecture and a GAN repair network for spatial data, to significantly improve data quality. Unify the data formats and encodings of different data sources, and according to the requirements of the adjustment model, perform structured processing on the data, converting unstructured or semi-structured data into structured data. Based on the unified data model architecture, integrate the cleaned and transformed data, and use a data fusion algorithm to merge the data about the same entity from different data sources, eliminating data redundancy and conflicts.

[0018] Index system construction module: Used to screen and construct an initial index system based on the six core contents of the strategic positioning, spatial pattern, public services, infrastructure, ecological restoration, and resource elements of territorial space planning. In the index system construction module, based on the core content of territorial space planning compilation, decompose and analyze from six aspects including strategic positioning, spatial pattern, public services, infrastructure and disaster prevention and mitigation, ecological restoration and land improvement, and resource elements, and then screen and select indicators. Refer to the territorial space planning physical examination and evaluation and the territorial space planning target system to construct the initial index system. Among the strategic positioning indicators, select the population size, total economic volume, and industrial structure ratio indicators according to the regional development goals. Among the spatial pattern indicators, according to the urban-rural land use structure, ecological protection red line, and permanent basic farmland protection rate dimensions, evaluate the rationality of land use layout through spatial analysis techniques, and set dynamic monitoring indicators for development intensity and connectivity index. Among the public service indicators, according to the coverage rate and accessibility of education, medical care, and cultural facilities, construct indicators for the per capita service resource ratio and the 15-minute living circle coverage rate, and optimize resource allocation in combination with population distribution and demand prediction. Among the infrastructure indicators, including the traffic road network density, energy supply security rate, and municipal facility coverage rate, introduce the concept of resilient cities and add disaster prevention and mitigation capacity indicators. Among the ecological restoration and resource element indicators, based on the ecological security pattern, set binding indicators for forest coverage rate, soil erosion control rate, and carbon emission intensity, and synchronously connect resource utilization efficiency indicators, and dynamically correct the thresholds through remote sensing monitoring and on-site verification. Using the Delphi method and the analytic hierarchy process, the importance weights of the indicators are assigned. Combining the results of the physical examination and evaluation of the territorial space planning, redundant indicators are eliminated and required indicators are supplemented to form a hierarchical and expandable indicator system framework. Then, through training with machine learning models and historical data, the adaptive adjustment of the indicator thresholds is carried out to ensure the dynamic matching with the regional development stage and policy orientation.

[0019] Dynamic adjustment model construction module: It is used to predict the trends of population, economy, and land use changes by using time series analysis, regression analysis, and machine learning algorithms, construct a comprehensive evaluation model by combining the analytic hierarchy process, and generate an indicator adjustment plan. In the dynamic adjustment model construction module, according to the initial indicator system of the territorial space planning, the population prediction model, land use change model, and the relationship model between economic growth and spatial layout are used to make corresponding predictions on the indicators. A comprehensive evaluation model is constructed based on historical data and predicted data, and the adaptability of the analytic hierarchy process analysis model is constructed. The model is trained according to historical data, and with reference to the model evaluation index, the comprehensive evaluation model is dynamically adjusted accordingly. The specific method for building the model framework is as follows: Predictive models are constructed using time series analysis, regression analysis, and machine learning algorithms to predict population growth, economic development, and land use changes, providing a basis for the dynamic adjustment of indicators. The Logistic growth model is used to predict the future population size, and the calculation method of the Logistic growth model is specifically: , where represents the total population after t years, K represents the environmental carrying capacity, that is, the maximum population capacity, represents the initial population, r represents the growth rate, t represents time, and e represents the base of the natural logarithm; The specific calculation method for predicting land use changes is: , where represents the land use situation in year t, and ΔLU represents the land use change amount; Using the regression analysis method, a multiple linear regression model of economic growth and spatial layout is established, and the calculation method of the economic growth value is specifically: , where Y represents the economic growth value, , , ……, represent the weight factors, represents other factors affecting economic growth, represents the error term; Based on the prediction results and planning goals, under resource constraints and multi-objective balance, determine the dynamic adjustment plan for the indicators; use the system dynamics method to establish a dynamic feedback mechanism for regional development. The calculation method of the system equation is specifically as follows: , where Y represents the state variable of the system, X represents the external input variable, and t represents time; Establish an evaluation index system from multiple dimensions of economic feasibility, social fairness, and ecological sustainability. The construction of multi-dimensional indicators is based on the indicators used in the model, such as per capita GDP, ecological restoration index, etc. Use the analytic hierarchy process to quantitatively evaluate the adjustment plan, determine the corresponding dimension weights according to the local actual situation, and compare the corresponding index coefficients in the comprehensive evaluation model with the importance ranking of different dimensions determined by the analytic hierarchy process to judge the advantages and disadvantages of the comprehensive evaluation model; In the analytic hierarchy process, decompose the evaluation goal into the goal layer, criterion layer, and index layer, and establish a hierarchical structure model; then compare the relative importance of elements in the same layer pairwise to construct a judgment matrix; calculate the maximum eigenvalue and the corresponding eigenvector of the judgment matrix to obtain the relative weights of each index, and conduct a consistency test to ensure the rationality of the judgment matrix; Train and optimize the constructed model. Use historical data to train the indicator dynamic adjustment model, and improve the accuracy and reliability of the model by adjusting model parameters, such as the weights and thresholds of the neural network.

[0020] Model optimization: Use methods such as cross-validation and holdout method to verify the model. According to the verification results, optimize and improve the model, such as adjusting algorithm parameters, adding feature variables, etc., to improve the model performance.

[0021] Scheme evaluation and optimization module: Used to quantitatively evaluate the adjustment plan through accuracy, precision, recall, and F1 value, and optimize the model parameters according to the evaluation results; In the above-mentioned scheme evaluation and optimization module, evaluate the dynamic adjustment model from aspects such as accuracy and precision, select the optimal parameter model, and optimize the evaluation plan. The calculation method of accuracy in the scheme quantitative evaluation is specifically as follows: , where represents accuracy, TP represents the number of samples that are actually positive and predicted to be positive, TN represents the number of samples that are actually negative and predicted to be negative, FP represents the number of samples that are actually negative but predicted to be positive, and FN represents the number of samples that are actually positive but predicted to be negative; The calculation method of precision is specifically as follows: , where B represents precision, TP represents the number of samples that are actually positive and predicted to be positive, and FP represents the number of samples that are actually negative but predicted to be positive; The calculation method of recall rate is specifically as follows: , where C represents the recall rate, TP represents the number of samples that are actually positive and predicted to be positive, and FN represents the number of samples that are actually positive but predicted to be negative; The calculation method of F1 value is specifically as follows: , where D represents value, B represents the precision rate, and C represents the recall rate; According to the F1 value evaluation results, adjust the model parameters and optimization algorithms, optimize the adjustment plan, and determine the final recommendation plan.

[0022] Model application and dynamic update module: used to integrate the model into the national land spatial planning business system, monitor the index changes in real time, and regularly update the model according to new data and performance thresholds; In the model application and dynamic update module, according to the compilation, implementation and management processes of national land spatial planning, the model is integrated into the existing business system to uniformly evaluate the index monitoring results in real time; updates are triggered according to data changes, performance indicators or time periods. When a certain amount of new data accumulates, the model is retrained; when the model accuracy drops below the set threshold, the update is started; according to a fixed time interval, the model is updated once every quarter; At the real-time monitoring level, a multi-level index evaluation system is constructed: the basic layer processes real-time data streams through a streaming computing engine to achieve second-level index calculation; the middle layer uses a rule engine (Drools) to execute business rule verification and automatically identify index anomalies; the application layer integrates multi-dimensional evaluation models to generate comprehensive evaluation results from three dimensions: compliance, implementation progress, and implementation effect; For the dynamic update mechanism, the data-driven update process monitors the change of data distribution through a sliding window algorithm and automatically triggers incremental training when a significant shift is detected; the performance-triggered update process continuously tracks the F1 score and AUC index of the model on the validation set, and uses an EWMA control chart for performance monitoring. When it is lower than the threshold for 3 consecutive cycles, full-scale training is started; the regular maintenance process performs a complete retraining of the model according to the quarterly cycle, including re-selection of features, hyperparameter optimization, and model structure tuning.

[0023] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A dynamic evaluation model for national land space planning indicators, characterized in that: include: Multi-source heterogeneous data fusion module: used to integrate multi-source heterogeneous data into structured data through data acquisition, cleaning, conversion and fusion; Index system construction module: used to screen and construct the initial index system based on the six core contents of national land space planning, namely, strategic positioning, spatial pattern, public services, infrastructure, ecological restoration and resource elements; Dynamic adjustment model building module: used to use time series analysis, regression analysis and machine learning algorithms to predict population, economic and land use change trends, build a comprehensive evaluation model in combination with the hierarchical analysis method, and generate indicator adjustment plans; Solution evaluation and optimization module: used to quantitatively evaluate the adjustment solution through accuracy, precision, recall and F1 value, and optimize the model parameters according to the evaluation results; Model application and dynamic update module: used to integrate the model into the national land space planning business system, monitor indicator changes in real time, and regularly update the model based on new data and performance thresholds.

2. According to claim 1, a dynamic evaluation model for national land space planning indicators is characterized by: In the multi-source heterogeneous data fusion module, data is obtained from multiple data sources such as databases, file systems, IoT devices, and social media platforms, and the scattered data is aggregated into the data center through ETL tools, data collection interfaces, and web crawler technology; In data cleaning, a three-level cleaning pipeline is constructed. The first level performs basic cleaning, uses the improved SimHash algorithm to process duplicate data, and provides multiple interpolation solutions for missing values. The second level implements business rule cleaning, with more than 200 built-in verification rules unique to the field of national land space planning, such as land use nature compliance inspection, planning indicator logic verification, etc. The third level is the intelligent correction layer, which uses deep learning technology, text error correction models based on the Transformer architecture, GAN repair networks for spatial data, etc., to significantly improve data quality.

3. According to claim 1, a dynamic evaluation model for national land space planning indicators is characterized by: In the indicator system construction module, based on the core content of the national land space planning, indicators are screened and selected after decomposition and analysis from six aspects, namely, strategic positioning, spatial pattern, public services, infrastructure and disaster prevention and mitigation, ecological restoration and land consolidation, and resource elements. The initial indicator system is constructed with reference to the national land space planning physical examination and evaluation and the national land space planning target indicators.

4. The dynamic evaluation model of national land space planning indicators according to claim 3 is characterized by: Among the strategic positioning indicators, the indicators of population size, economic output and industrial structure proportion are selected according to the regional development goals; among the spatial pattern indicators, the rationality of land use layout is evaluated through spatial analysis technology according to the dimensions of urban and rural land use structure, ecological protection red line and permanent basic farmland protection rate, and dynamic monitoring indicators of development intensity and connectivity index are set; among the public service indicators, the per capita service resource ratio and 15-minute living circle coverage rate indicators are constructed according to the coverage rate and accessibility of education, medical care and cultural facilities, and resource allocation is optimized in combination with population distribution and demand forecast.

5. The dynamic evaluation model of national land space planning indicators according to claim 1 is characterized by: In the dynamic adjustment model construction module, according to the initial indicator system of national land space planning, the population prediction model, the land use change model, and the economic growth and spatial layout relationship model are used to make corresponding predictions on the indicators, and a comprehensive evaluation model is constructed based on historical data and predicted data. The adaptability of the analytic hierarchy process analysis model is constructed, and the model is trained based on historical data. With reference to the model evaluation index, the comprehensive evaluation model is dynamically adjusted accordingly; Time series analysis, regression analysis, and machine learning algorithms are used to build a forecasting model to predict population growth, economic development, and land use changes, providing a basis for dynamic adjustment of indicators. The Logistic growth model is used to predict future population. The specific calculation method of the Logistic growth model is as follows: ,in, It is represented by the total population after t years, K is represented by the environmental carrying capacity, that is, the maximum population capacity, represents the initial population, r represents the growth rate, t represents the time, and e represents the base of the natural logarithm; The specific calculation method for land use change prediction is as follows: ,in, It represents the land use status in year t, and ΔLU represents the change in land use.

6. The dynamic evaluation model of national land space planning indicators according to claim 1 is characterized by: Using regression analysis method, a multivariate linear regression model of economic growth and spatial layout is established. The specific calculation method of economic growth value is as follows: , where Y represents the economic growth value, , ,……, Expressed as a weight factor, Represents other factors that affect economic growth, It is represented as the error term; Based on the prediction results and planning goals, under the resource constraints and multi-objective balance, the dynamic adjustment plan of the indicators is determined; using the system dynamics method, a dynamic feedback mechanism for regional development is established. The calculation method of the system equation is as follows: , where Y represents the state variable of the system, X represents the external input variable, and t represents time.

7. The dynamic evaluation model of national land space planning indicators according to claim 1 is characterized by: In the scheme evaluation and optimization module, the dynamic adjustment model is evaluated from the aspects of accuracy and precision, the optimal parameter model is selected, and the evaluation scheme is optimized. The calculation method of the accuracy in the quantitative evaluation of the scheme is specifically as follows: ,in, Expressed as accuracy, TP represents the number of samples that are actually positive and predicted to be positive, TN represents the number of samples that are actually negative and predicted to be negative, FP represents the number of samples that are actually negative but predicted to be positive, and FN represents the number of samples that are actually positive but predicted to be negative; The specific calculation method of accuracy is: , where B represents the precision rate, TP represents the number of samples that are actually positive and predicted to be positive, and FP represents the number of samples that are actually negative but predicted to be positive; The specific calculation method of recall rate is: , where C represents the recall rate, TP represents the number of samples that are actually positive and predicted to be positive, and FN represents the number of samples that are actually positive but predicted to be negative; The specific calculation method of F1 value is: , where D is represented by Value, B represents the precision and C represents the recall; According to the F1 value evaluation results, adjust the model parameters and optimization algorithm, optimize the adjustment plan, and determine the final recommendation plan.

8. The dynamic evaluation model of national land space planning indicators according to claim 1 is characterized by: In the model application and dynamic update module, the model is integrated into the existing business system according to the national land space planning preparation, implementation and management process, and the indicator monitoring results are uniformly evaluated in real time; updates are triggered according to data changes, performance indicators or time periods; when new data accumulates to a certain amount, the model is retrained; when the model accuracy drops below the set threshold, the update is initiated; and the model is updated once a quarter at a fixed time interval; At the real-time monitoring level, a multi-level indicator evaluation system has been built: the basic layer processes real-time data streams through a streaming computing engine to achieve second-level indicator calculations; the middle layer uses a rule engine (Drools) to perform business rule verification and automatically identify indicator anomalies; the application layer integrates a multi-dimensional evaluation model to generate comprehensive evaluation results from three dimensions: compliance, implementation progress, and implementation effect.

Images