Scene demonstration evaluation method and system for public management virtual experiment case

Abstract

The invention relates to the technical field of public management, in particular to a scene demonstration evaluation method and system for public management virtual experiment cases, and the method comprises the following steps: S1, data collection: obtaining scene demonstration data; s2, data preprocessing: generating a structured scene data set comprising space-time labels; s3, dynamic feature modeling: generating a three-dimensional feature vector; s4, feature matching: generating a feature matching matrix including case similarity, a deviation index and an optimization weight; s5, real-time evaluation generation: generating real-time evaluation parameters according to the feature matching matrix; and S6, evaluation visualization: mapping the real-time evaluation parameters into a dynamic evaluation map, and synchronously driving topological structure optimization of the virtual experiment scene. According to the invention, the scientificity, real-time performance and operability of evaluation are improved, the transparency of decision making is enhanced, resource waste or insufficiency is avoided, and the intelligent management level of the public management field is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of public management, and in particular to a scenario demonstration evaluation method and system for public management virtual experiment cases. Background Art

[0002] With the rapid development of information technology and digital management, virtual experiment technology has been gradually introduced into the field of public management to simulate complex social governance, policy implementation, emergency management and other scenarios, so as to improve the scientificity and feasibility of decision-making. Virtual experiment cases can provide multi-dimensional management data, covering information such as policy texts, behavior trajectories, environmental parameters, etc., enabling managers to conduct policy deduction, plan testing and resource optimization in a low-risk environment. However, how to efficiently integrate multi-source heterogeneous data, evaluate the decision-making process in real time, and optimize the execution path of the experimental scenario is still an urgent problem to be solved in the process of intelligent development of public management.

[0003] Existing public management virtual experiment evaluation methods have many deficiencies. On the one hand, data collection and processing technologies are relatively limited, and it is difficult to make full use of heterogeneous data sources, resulting in poor integrity and consistency of experimental data. On the other hand, current evaluation methods mostly rely on static matching analysis and lack the ability to model dynamic characteristics, and cannot accurately quantify decision-making paths, behavior norms and environmental adaptability. In addition, existing optimization strategies mostly adopt manual intervention methods and lack intelligent evaluation and feedback mechanisms, resulting in a lag in the adjustment of experimental scenarios and being difficult to meet complex public management needs.

[0004] In view of the deficiencies of the prior art, the present invention proposes a scenario demonstration evaluation method and system for public management virtual experiment cases, which can significantly improve the analysis efficiency and accuracy of public management virtual experiment cases, provide data support for scientific management and optimization, and enhance the transparency and operability of public management decisions. Summary of the Invention

[0005] The present invention provides a scenario demonstration evaluation method and system for public management virtual experiment cases.

[0006] A scenario demonstration evaluation method for public management virtual experiment cases includes the following steps: S1, data collection: obtaining scenario demonstration data through multi-source heterogeneous interfaces, including decision text data streams, virtual character behavior trajectory data, and environmental parameter time series data; S2, data preprocessing: performing feature alignment on the obtained scenario demonstration data to generate a structured scenario data set including spatio-temporal tags; S3, dynamic feature modeling: constructing a dynamic feature model based on the structured scenario data set to generate a three-dimensional feature vector including decision correlation, behavior compliance, and environmental adaptability; S4, Feature Matching: Match the three-dimensional feature vector with a preset experimental case library to generate a feature matching matrix including case similarity, deviation index, and optimization weight; S5, Real-time Evaluation Generation: Generate real-time evaluation parameters based on the feature matching matrix, including case completion score, decision path deviation warning, and resource allocation optimization suggestions; S6, Evaluation Visualization: Map the real-time evaluation parameters to a dynamic evaluation atlas through a visualization engine, and synchronously drive the optimization of the topological structure of the virtual experiment scenario.

[0007] Optionally, the data collection in S1 includes: S11, Decision Text Data Stream Collection: Obtain decision text data related to scenario demonstration through an interface, including decision files, legal texts, and management plans, to form a dynamic data stream; S12, Virtual Character Behavior Trajectory Data Collection: Obtain its behavior trajectory data by recording the activities of virtual characters in the scenario, and record the action paths and decision-making behaviors of virtual characters; S13, Environmental Parameter Time Series Data Collection: Obtain environmental change data in the virtual scenario through sensors, including environmental parameters (temperature, humidity, air quality) in the form of time series.

[0008] Optionally, the data preprocessing in S2 includes: S21, Data Cleaning: Use the time series interpolation method to remove duplicates, fill in missing values, and detect anomalies in the decision text data stream, virtual character behavior trajectory data, and environmental parameter time series data; S22, Feature Alignment: Align the scenario demonstration data using the timestamp synchronization method; S23, Structured Data Set Generation: Based on the aligned scenario demonstration data, construct a structured scenario data set with spatio-temporal labels .

[0009] Optionally, the dynamic feature modeling in S3 includes: S31, Decision Relevance Calculation: The decision relevance Measures the similarity between the structured scenario data and historical decision cases, and is calculated using a semantic matching model; S32, Behavior Compliance Calculation: The behavior compliance Measures whether the behavior trajectory of the virtual character conforms to the preset rules, and is calculated using the trajectory deviation analysis method; S33, Environment Adaptability Calculation: The environment adaptability Measures whether the environmental parameters of the current scenario meet the preset requirements of the experimental case, and is calculated using the weighted deviation measure; S34, Feature Vector Generation: Based on decision-making correlation, behavior compliance, and environmental adaptability, construct a three-dimensional feature vector 。

[0010] Optionally, the feature matching in S4 includes: S41, Normalization Processing: Use the min-max normalization method to normalize the three-dimensional feature vector ; S42, Case Similarity Calculation: Calculate the similarity between the three-dimensional feature vector of the current scenario after normalization and each case in the experimental case library, and use the weighted cosine similarity to calculate the similarity score ; S43, Deviation Index Calculation: Calculate the deviation index between the three-dimensional feature vector of the current scenario and the cases in the experimental case library , to quantify the differences in scenario features; S44, Optimized Weight Calculation: Based on the case similarity and deviation index, calculate the optimized weight for each experimental case ; S45, Feature Matching Matrix Generation: Integrate the case similarity, deviation index, and optimized weight to generate a feature matching matrix 。

[0011] Optionally, the real-time evaluation generation in S5 includes: S51, Case Completion Score Calculation: The case completion score is used to measure the matching degree of the current scenario to the target experimental case, and calculate the case completion score based on the feature matching matrix ; S52, Decision Path Deviation Warning Calculation: The decision path deviation warning is used to identify whether there is a deviation between the execution path of the current scenario and the reference experimental case, and make a warning judgment by calculating the decision path deviation index ; S53, Resource Allocation Optimization Suggestion Calculation: The resource allocation optimization suggestion is based on the feature matching result, calculate the resource deviation between the current resource demand and the optimal experimental case, and calculate the optimized resource allocation parameters ; S54, Evaluation Parameter Integration and Output: Integrate the calculated case completion score, decision path deviation index, and resource allocation parameters into a real-time evaluation parameter set 。

[0012] Optionally, the evaluation visualization in S6 includes: S61, Dynamic Evaluation Atlas Generation: Based on the real-time evaluation parameters, construct a multi-dimensional visualization evaluation atlas; S62, Topological Optimization of Virtual Experiment Scenarios: Based on the dynamic evaluation atlas, automatically adjust the topological structure of the virtual experiment scenario to optimize the decision-making path, resource allocation, and scenario layout.

[0013] Optionally, the generation of the dynamic evaluation atlas in S61 includes: S611, Evaluation Parameter Normalization: Normalize the evaluation parameters using the min-max normalization method; S612, Multi-dimensional Visualization Mapping: Based on the normalized evaluation parameters, use hierarchical data mapping to construct a dynamic evaluation atlas, including node representation and edge connection weight calculation, specifically including: Node Representation: Set three core evaluation dimensions (decision-making, behavior, environment), and map them to the node set in the visualization atlas ; Edge Connection Weight Calculation: Calculate the influence relationship between different evaluation dimensions, and use weighted similarity measurement to calculate the weight of the edge; Visualization Atlas Generation: Construct the connection relationship between nodes, and use visualization methods such as color gradient, heat map, and time series curve.

[0014] Optionally, the topological optimization of the virtual experiment scenario in S62 includes: S621, Scenario Topological Modeling: Construct the topological structure of the virtual experiment scenario, represented as a directed weighted graph , where are the key task nodes in the scenario, including decision-making points, resource allocation points, and behavior execution, is the connection between task nodes, representing the task execution path, and each edge has a weight , representing the time, cost, or resource consumption of task transfer; S622, Decision Path Optimization: Based on the decision path deviation index in the dynamic evaluation atlas, use the shortest path optimization algorithm to adjust the experimental task path to minimize the overall execution cost; S623, Resource Allocation Optimization: Based on the optimized resource configuration parameters , use the dynamic resource adjustment model to calculate the resource allocation plan and dynamically adjust the resource allocation in the scenario; S624, Scenario Layout Adaptive Optimization: Based on the optimized task path and resource allocation, use hierarchical clustering analysis to reorganize the task nodes and dynamically adjust the layout of the virtual experiment scenario.

[0015] A scenario demonstration evaluation system for virtual experiment cases in public management, used to implement the above-mentioned scenario demonstration evaluation method for virtual experiment cases in public management, includes the following modules: Data acquisition module: Obtain scenario demonstration data through multi-source heterogeneous interfaces, including decision text data streams, virtual character behavior trajectory data, and environmental parameter time-series data; Data preprocessing module: Align the features of the obtained scenario demonstration data to generate a structured scenario dataset including spatio-temporal tags; Dynamic feature modeling module: Build a dynamic feature model based on the structured scenario dataset to generate a three-dimensional feature vector including decision correlation, behavior compliance, and environmental adaptability; Feature matching module: Match the three-dimensional feature vector with a preset experimental case library to generate a feature matching matrix including case similarity, deviation index, and optimization weight; Real-time evaluation generation module: Generate real-time evaluation parameters based on the feature matching matrix, including case completion score, decision path deviation warning, and resource allocation optimization suggestions; Evaluation visualization module: Map the real-time evaluation parameters to a dynamic evaluation atlas through a visualization engine and synchronously drive the optimization of the topological structure of the virtual experiment scenario.

[0016] Advantages of the present invention: In the present invention, through data acquisition, data preprocessing, and dynamic feature modeling, efficient integration, standardized processing, and intelligent modeling of multi-source heterogeneous data are realized. It can accurately extract decision text data streams, virtual character behavior trajectory data, and environmental parameter time-series data, and through technologies such as feature alignment, time synchronization, and semantic matching, ensure the integrity, consistency, and spatio-temporal matching of the data. By constructing a three-dimensional feature vector including decision correlation, behavior compliance, and environmental adaptability, the accuracy and interpretability of the evaluation are improved, making the analysis of public management virtual experiment cases more intelligent and refined.

[0017] In the present invention, through the feature matching and real-time evaluation generation mechanisms, case similarity, deviation index, and optimization weight can be efficiently calculated, dynamically measuring the matching degree between the current scenario and the experimental case library. By calculating weighted cosine similarity, weighted deviation measure, and optimization weight, a feature matching matrix is established to achieve accurate matching analysis, and based on this, a case completion score, decision path deviation warning, and resource allocation optimization suggestions are generated. It can monitor the execution situation of the scenario in real time, identify deviations in a timely manner, and provide optimization and adjustment suggestions, thereby enhancing the scientificity, real-time performance, and operability of the evaluation, enhancing the transparency of decision-making, avoiding resource waste or insufficiency, and improving the intelligent management level in the field of public management.

[0018] In the present invention, through an evaluation visualization technique, a dynamic evaluation map is constructed, and based on a topology optimization mechanism, the structure of a virtual experimental scenario is adaptively adjusted. It can utilize hierarchical data mapping, color gradients, and time series analysis to enable managers to intuitively understand the matching degree of experimental cases, decision execution deviations, and resource adjustment requirements. At the same time, through optimal path optimization, intelligent resource allocation, and hierarchical clustering analysis, the layout of task nodes is effectively optimized, the resource utilization rate is improved, unnecessary path intersections are reduced, and the rationality and efficiency of the experimental execution process are ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 Schematic diagram of the evaluation method flow for the embodiment of the present invention; Figure 2 Schematic diagram of the system function modules for the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The present invention will be described in detail below in conjunction with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0022] It should be pointed out that in the specification, when referring to "an embodiment", "embodiment", "exemplary embodiment", "some embodiments", etc., it indicates that the described embodiment may include specific features, structures, or characteristics, but not necessarily every embodiment includes such specific features, structures, or characteristics. Additionally, when combining embodiments to describe specific features, structures, or characteristics, implementing such features, structures, or characteristics in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0023] Generally, the terms can be understood at least in part from their use in the context. For example, at least in part depending on the context, the term "one or more" used herein can be used to describe any feature, structure, or characteristic in a singular sense, or can be used to describe a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather, at least in part depending on the context, allowing for the existence of other factors that may not be explicitly described.

[0024] As Figure 1 shown, a scenario demonstration evaluation method for virtual experiment cases in public management includes the following steps: S1, Data collection: Obtain scenario demonstration data through multi-source heterogeneous interfaces, including decision text data streams, virtual character behavior trajectory data, and environmental parameter time series data; S2, Data preprocessing: Align the features of the obtained scenario demonstration data to generate a structured scenario dataset including spatio-temporal tags; S3, Dynamic feature modeling: Build a dynamic feature model based on the structured scenario dataset to generate a three-dimensional feature vector including decision correlation, behavior compliance, and environmental adaptability; S4, Feature matching: Match the three-dimensional feature vector with a preset experimental case library to generate a feature matching matrix including case similarity, deviation index, and optimization weight; S5, Real-time evaluation generation: Generate real-time evaluation parameters according to the feature matching matrix, including case completion score, decision path deviation warning, and resource allocation optimization suggestions; S6, Evaluation visualization: Map the real-time evaluation parameters to a dynamic evaluation atlas through a visualization engine, and synchronously drive the optimization of the topological structure of the virtual experiment scenario; Through the above content, accurate evaluation parameters can be generated in real time, and the structure of the virtual experiment scenario can be optimized through visualization technology, which can effectively improve the scientificity and efficiency of public management decisions. Through an intelligent evaluation and optimization mechanism, it helps managers monitor the decision path in real time, adjust resource allocation, and warn of potential problems, thereby improving the transparency and operability of the decision-making process.

[0025] The data collection in S1 includes: S11, Decision text data stream collection: Obtain decision text data related to scenario demonstration through an interface, including decision documents, legal texts, and management plans, to form a dynamic data stream; S12, Virtual character behavior trajectory data collection: Obtain its behavior trajectory data through the activity records of virtual characters in the scenario, and record the action paths and decision-making behaviors of virtual characters; S13, Environmental parameter time series data collection: Obtain environmental change data in the virtual scenario through sensors, including environmental parameters (temperature, humidity, air quality) in the form of time series; Through the above, the decision-making text data stream, virtual character behavior trajectory data, and environmental parameter time-series data are efficiently integrated, ensuring the comprehensiveness, real-time nature, and dynamic adaptability of the data. The collection of the decision-making text data stream can provide accurate management and legal basis, enhancing the scientific nature of decision-making. The collection of virtual character behavior trajectory data enables in-depth analysis of behavior patterns, improving the authenticity and interactivity of scenario demonstrations. The collection of environmental parameter time-series data ensures the dynamic adaptation of the experimental scenario, making the evaluation results more environmentally relevant and spatiotemporally consistent.

[0026] The data preprocessing in S2 includes: S21, data cleaning: The time-series interpolation method is used to remove duplicates, fill in missing values, and detect anomalies in the decision-making text data stream, virtual character behavior trajectory data, and environmental parameter time-series data to improve data quality, expressed as: ; Among them, is the missing time the data value at, , are the closest valid data points before and after the missing value; S22, feature alignment: The timestamp synchronization method is used to align the scenario demonstration data to ensure the consistency of different data sources within the same time window, expressed as: ; Among them, is the aligned timestamp, is the original data timestamp, is the reference timestamp (benchmark time series); S23, structured dataset generation: Based on the aligned scenario demonstration data, a structured scenario dataset with spatio-temporal labels is constructed , expressed as: ; Among them, is the structured dataset, is the time label of the data point, is the spatial position label of the data point, is the feature vector of the data point; Through the above, the integrity, consistency, and spatio-temporal matching of multi-source heterogeneous data are ensured. The data quality is improved through time-series interpolation and anomaly detection. The timestamp synchronization algorithm eliminates the time deviation of different data sources, enabling the data to be accurately aligned within the same time window. The construction of the structured dataset provides a standardized and efficient input for subsequent analysis, not only improving the reliability and availability of the data, but also enhancing the simulation accuracy and evaluation accuracy of the virtual experimental scenario.

[0027] The dynamic feature modeling in S3 includes: S31, Decision correlation degree calculation: The decision correlation degree measures the similarity between structured scenario data and historical decision cases, and is calculated using a semantic matching model, expressed as: ; Among them, is the decision correlation degree, is the feature vector of the current scenario data, is the corresponding historical decision feature vector in the case library, is the feature similarity calculation (cosine similarity), is the feature weight, reflecting the contribution of this feature to the decision correlation degree, is the number of features in the current scenario data; S32, Behavior compliance calculation: The behavior compliance measures whether the behavior trajectory of the virtual character conforms to the preset rules, and is calculated using a trajectory deviation analysis method, expressed as: ; Among them, is the behavior parameter of the current character (such as action path, operation method, etc.), is the standard parameter of the preset behavior rule, is the total number of behavior data points, is the behavior compliance score. When is close to 1, it indicates that the behavior highly conforms to the expected rules, and the closer it is to 0, the greater the deviation; S33, Environment adaptability calculation: The environment adaptability measures whether the environmental parameters of the current scenario meet the preset requirements of the experimental cases, and is calculated using a weighted deviation measure, expressed as: ; Among them, is the environment adaptability score, is the current environmental parameter (temperature, humidity, air quality), is the standard environmental parameter in the experimental case, is the weight coefficient, indicating the contribution of each environmental parameter to the adaptability, is the number of types of environmental parameters; S34, Feature vector generation: Based on the decision correlation degree, behavior compliance, and environment adaptability, construct a three-dimensional feature vector ; Through the above, the accurate evaluation of virtual experiment cases is achieved. By semantic matching, trajectory deviation analysis, and weighted deviation measurement, the integrity of data features and the scientific nature of calculations are ensured, which can effectively measure the matching degree between scenario demonstration data and historical cases. It not only guarantees the interpretability of the evaluation but also improves the automation degree of the evaluation, thereby enhancing the intelligent analysis ability of virtual experiment cases in public management and improving the accuracy and reliability of decision-making support.

[0028] The feature matching in S4 includes: S41, normalization processing: The three-dimensional feature vector is normalized using the min-max normalization method to ensure that each feature dimension has the same influence in the matching calculation, expressed as: ; where, is the normalized three-dimensional feature vector, is the original three-dimensional feature vector, and are the maximum and minimum values of the feature vector in all cases respectively; S42, case similarity calculation: Calculate the similarity between the three-dimensional feature vector of the current scenario after normalization and each case in the experimental case library, and use the weighted cosine similarity to calculate the similarity score , expressed as: ; where, is the similarity between the current scenario and the th case in the experimental case library, is the th dimensional component of the normalized three-dimensional feature vector of the current scenario, is the th dimensional component of the feature vector of the th case in the normalized experimental case library, is the weight of the feature dimension ; S43, deviation index calculation: Calculate the deviation index between the three-dimensional feature vector of the current scenario and the cases in the experimental case library to quantify the difference in scenario features, expressed as: ; where, is the deviation index between the current scenario and the th case in the experimental case library, The smaller the S44, Optimize weight calculation: Calculate the optimized weight of each experimental case based on case similarity and deviation index, expressed as: , which is expressed as: ; where, is the optimized weight of experimental case , is a very small number to prevent the denominator from being zero ( ); S45, Generate feature matching matrix: Integrate case similarity, deviation index, and optimized weight to generate a feature matching matrix, expressed as: , which is expressed as: ; Through the above content, the accurate matching between the current scenario and the experimental case library is achieved. It can comprehensively consider decision relevance, behavior compliance, and environmental adaptability, ensuring the comprehensiveness and scientificity of feature matching. By constructing the matching matrix, not only the accuracy of case matching is improved, but also the differences in scenario features can be quantified, providing a basis for optimization and adjustment, thereby enhancing the adaptability and intelligent optimization ability of virtual experimental cases, providing a strong data foundation for the intelligent analysis and decision support of public management virtual experiments, and improving the reliability and efficiency of evaluation.

[0029] The real-time evaluation generation in S5 includes: S51, Calculate case completion score: The case completion score is used to measure the matching degree of the current scenario to the target experimental case, and calculate the case completion score based on the feature matching matrix, expressed as: , which is expressed as: ; where, is the case completion score, and its value range is . The closer the value is to 1, the closer the current scenario is to the target case, and the higher the completion degree. is the total number of cases in the experimental case library, is the similarity between the current scenario and case ; S52, Calculate decision path deviation warning: The decision path deviation warning is used to identify whether there is a deviation between the execution path of the current scenario and the reference experimental case, and make a warning judgment by calculating the decision path deviation index , expressed as: ; where, is the decision path deviation index. When exceeds the set threshold (0.2), a warning is triggered, indicating that there may be a large deviation in the decision path and adjustment is required. is the number of decision-making steps, is the decision path eigenvalue in the previous scenario (such as the behavior decision sequence, policy execution order, etc.), is the standard path eigenvalue of the target experimental case; S53, Calculation of resource allocation optimization suggestions: The resource allocation optimization suggestions are based on the feature matching results, calculate the resource deviation between the current resource requirements and the optimal experimental case, and calculate the optimized resource allocation parameters , expressed as: ; Among them, is the optimized resource allocation parameter, is the standard resource allocation in the target experimental case, is the actual resource allocation in the current scenario, is the adjustment coefficient , used to control the adjustment intensity. When exceeds the set threshold (15), automatically recommend adjustment plans, including increasing human resources, optimizing task allocation or adjusting environmental parameters; S54, Evaluation parameter integration and output: Integrate the calculated case completion score, decision path deviation index and resource allocation parameters into a real-time evaluation parameter set ; Through the above content, calculating the case completion score, decision path deviation warning and resource allocation optimization suggestions realizes the accurate evaluation and dynamic optimization of virtual experimental cases, can comprehensively measure the matching degree between the current scenario and the target experimental case, timely identify the deviation of the decision path and provide optimization and adjustment suggestions to ensure the standardization and rationality of the execution process. At the same time, the resource allocation adjustment mechanism based on the intelligent optimization algorithm helps to improve the resource utilization efficiency and avoid resource waste or shortage.

[0030] The evaluation visualization in S6 includes: S61, Generation of dynamic evaluation atlas: Construct a multi-dimensional visual evaluation atlas according to the real-time evaluation parameters; S62, Topology optimization of virtual experimental scenarios: Automatically adjust the topology of virtual experimental scenarios based on the dynamic evaluation atlas to optimize the decision path, resource allocation and scenario layout; Through the above, the intuitive presentation and intelligent adjustment of real-time evaluation results are realized. The dynamic evaluation map can visualize key evaluation parameters in multiple dimensions, enabling managers to quickly understand the decision-making matching degree, path deviation, and resource allocation situation, improving the transparency and operability of the evaluation. At the same time, based on the topology optimization mechanism driven by evaluation data, it can adaptively adjust the structure of the virtual experiment scenario, optimize the task process and resource allocation, thereby enhancing the rationality and efficiency of experiment execution, strengthening the intelligent analysis ability of public management virtual experiment cases, making decision-making adjustments more accurate and efficient, and providing strong support for scientific management and optimization.

[0031] The generation of the dynamic evaluation map in S61 includes: S611, evaluation parameter normalization: The evaluation parameters are normalized using the min-max normalization method, expressed as: ; Among them, The normalized evaluation parameter value, is the original evaluation parameter (case completion score, decision path deviation index, resource allocation optimization suggestion), 、 are the maximum and minimum values of the parameter respectively; S612, multi-dimensional visualization mapping: According to the normalized evaluation parameters, hierarchical data mapping is used to construct a dynamic evaluation map, including node representation and edge connection weight calculation, specifically including: Node representation: Three core evaluation dimensions (decision-making, behavior, environment) are set and mapped to the node set in the visualization map , expressed as: ; Among them, is the decision-making matching node, is the behavior compliance node, is the environment adaptability node; Edge connection weight calculation: Calculate the influence relationship between different evaluation dimensions, and use weighted similarity measurement to calculate the weight of the edge, expressed as: ; Among them, is the connection weight between node and node , 、 are the normalized evaluation parameter values, is the smoothing coefficient; Visualization map generation: Construct the connection relationship between nodes, and use visualization methods such as color gradient, heat map, and time series curve, for example: Case Completion Score: The matching degree is represented by the shade of color (e.g., blue indicates high matching and red indicates low matching); Decision Path Deviation Index: It is shown by the degree of path distortion. The greater the deviation, the higher the degree of path curvature; Suggestions for Optimizing Resource Allocation: The resource adjustment requirements are shown through bar charts or radar charts, enabling managers to intuitively understand the optimization direction; Through the above content, the intuitive display and scientific analysis of evaluation data are realized. It can effectively integrate the case completion score, decision path deviation index, and suggestions for optimizing resource allocation, enabling managers to intuitively understand the matching degree of experimental cases, decision execution deviations, and resource adjustment requirements. By using visualization methods such as color gradients, heat maps, and time series curves, the readability of evaluation results and decision-making efficiency are improved. At the same time, based on the calculation of influence weights between nodes, the structure of the evaluation graph can be dynamically adjusted, enhancing the intelligent analysis and management capabilities of virtual experimental cases in public administration.

[0032] The virtual experiment scenario topology optimization in S62 includes: S621, Scenario Topology Modeling: Construct the topological structure of the virtual experiment scenario, represented as a directed weighted graph , where are the key task nodes in the scenario, including decision points, resource allocation points, and behavior executions, is the connection between task nodes, representing the task execution path. Each edge has a weight , indicating the time, cost, or resource consumption of task transfer; The edge weight calculation is performed using the weighted path scoring method, expressed as: ; where, is the task execution weight from node to node , is the task execution time, is the resource demand (such as manpower, equipment, etc.), is the task execution cost, , , are the weight coefficients; S622, Decision Path Optimization: Based on the decision path deviation index in the dynamic evaluation graph, use the shortest path optimization algorithm to adjust the experimental task path to minimize the overall execution cost. The optimization objective function is expressed as: ; where, is the optimal decision path after optimization, is the set of all possible paths, is the path weight; S623, Resource Allocation Optimization: Based on the optimized resource configuration parameters , a dynamic resource adjustment model is used to calculate the resource allocation plan, dynamically adjust the resource allocation in the scenario, and ensure the matching of resource supply and demand, which is expressed as: ; Among them, is the optimized resource allocation value, is the resource configuration quantity of the current scenario, is the resource demand in the best case, is the adjustment coefficient; S624, Scenario Layout Adaptive Optimization: Based on the optimized task path and resource allocation, hierarchical clustering analysis is used to reorganize the task nodes and dynamically adjust the layout of the virtual experiment scenario to make the tasks with strong relevance closer, which is expressed as: ; Among them, is the number of target task groups, is the th task cluster, is the feature vector of the task node, is the th task center of the group; Through the above content, the connection relationship between task nodes can be dynamically adjusted, the decision execution path can be optimized based on the shortest path algorithm, the execution time and resource consumption can be reduced, and at the same time, the supply-demand matching can be ensured through the intelligent resource allocation strategy, improving the resource utilization rate. In addition, hierarchical clustering analysis is used to optimize the task layout, making the experimental process more reasonable and compact, reducing unnecessary path intersections, and enhancing the smoothness and efficiency of experimental execution.

[0033] As Figure 2 shown, a scenario demonstration evaluation system for a public management virtual experiment case, used to implement the above-mentioned scenario demonstration evaluation method for a public management virtual experiment case, includes the following modules: Data Acquisition Module: Obtain scenario demonstration data through multi-source heterogeneous interfaces, including decision text data streams, virtual character behavior trajectory data, and environmental parameter time series data; Data Preprocessing Module: Align the features of the obtained scenario demonstration data to generate a structured scenario data set including spatio-temporal tags; Dynamic Feature Modeling Module: Build a dynamic feature model based on the structured scenario data set to generate a three-dimensional feature vector including decision correlation, behavior compliance, and environmental adaptability; Feature matching module: It performs feature matching on the three-dimensional feature vector with a preset experimental case library to generate a feature matching matrix including case similarity, deviation index, and optimization weight; Real-time evaluation generation module: It generates real-time evaluation parameters based on the feature matching matrix, including case completion score, decision path deviation warning, and resource allocation optimization suggestions; Evaluation visualization module: It maps the real-time evaluation parameters into a dynamic evaluation atlas through a visualization engine and synchronously drives the optimization of the topological structure of the virtual experiment scenario.

[0034] This invention covers any substitutions, modifications, equivalent methods, and solutions made within the essence and scope of this invention. For the public to have a thorough understanding of this invention, specific details are elaborated in the following preferred embodiments of this invention. However, those skilled in the art can fully understand this invention even without the description of these details. Additionally, well-known methods, processes, flows, components, and circuits, etc. are not described in detail to avoid unnecessary confusion to the essence of this invention.

[0035] The above are only the preferred embodiments of this invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of this invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this invention.

Claims

1. A scenario demonstration evaluation method for virtual experiment cases in public management, characterized in that It includes the following steps: S1, Data collection: Obtain scenario demonstration data through multi-source heterogeneous interfaces, including decision text data streams, virtual character behavior trajectory data, and environmental parameter time series data; S2, Data preprocessing: Align the features of the obtained scenario demonstration data to generate a structured scenario dataset including spatio-temporal tags; S3, Dynamic feature modeling: Build a dynamic feature model based on the structured scenario dataset to generate a three-dimensional feature vector including decision correlation, behavior compliance, and environmental adaptability; S4, Feature matching: Match the three-dimensional feature vector with a preset experimental case library to generate a feature matching matrix including case similarity, deviation index, and optimization weight; S5, Real-time evaluation generation: Generate real-time evaluation parameters according to the feature matching matrix, including case completion score, decision path deviation warning, and resource allocation optimization suggestions; S6, Evaluation visualization: Map the real-time evaluation parameters to a dynamic evaluation atlas through a visualization engine, and synchronously drive the optimization of the topological structure of the virtual experiment scenario.

2. The scenario demonstration evaluation method for a virtual experiment case for public management according to claim 1, wherein The data collection in S1 includes: S11, Decision text data stream collection: Obtain decision text data related to scenario demonstrations through the interface, including decision files, legal texts, and management plans, to form a dynamic data stream; S12, Virtual character behavior trajectory data collection: Obtain its behavior trajectory data through the activity records of virtual characters in the scenario, and record the action paths and decision-making behaviors of virtual characters; S13, Environmental parameter time series data collection: Obtain environmental change data in the virtual scenario through sensors, including environmental parameters in the form of time series.

3. The scenario demonstration evaluation method for a virtual experiment case oriented to public management according to claim 1, characterized in that, The data preprocessing in S2 includes: S21, Data cleaning: Use the time series interpolation method to perform deduplication, missing value filling, and anomaly detection on the decision text data stream, virtual character behavior trajectory data, and environmental parameter time series data; S22, Feature alignment: Align the scenario demonstration data using the timestamp synchronization method; S23, Structured dataset generation: Based on the aligned scenario demonstration data, construct a structured scenario dataset with spatio-temporal labels .

4. A scenario demonstration evaluation method for a virtual experiment case oriented to public management, as described in claim 1, characterized in that The dynamic feature modeling in S3 includes: S31, Decision correlation calculation: Decision correlation Measure the similarity between structured scenario data and historical decision cases, and calculate using a semantic matching model; S32, Behavior compliance calculation: Behavior compliance Measure whether the behavior trajectory of the virtual character complies with the preset rules, and calculate using the trajectory deviation analysis method; S33, Environmental Adaptability Calculation: Environmental Adaptability Measure whether the environmental parameters of the current scenario meet the preset requirements of the experimental case, and calculate using the weighted deviation measure; S34, Feature vector generation: Based on decision-making correlation, behavior compliance, and environmental adaptability, construct a three-dimensional feature vector .

5. The scenario demonstration evaluation method for a virtual experiment case oriented to public management according to claim 4, wherein The feature matching in S4 includes: S41, Normalization processing: The three-dimensional feature vector is normalized by using the minimum-maximum normalization method for normalization; S42, Case Similarity Calculation: Calculate the similarity between the three-dimensional feature vector of the current scenario after normalization and each case in the experimental case library, and use weighted cosine similarity to calculate the similarity score ; S43, Deviation index calculation: Calculate the deviation index between the three-dimensional feature vector of the current scenario and the cases in the experimental case library , to quantify the differences in scenario features; S44, Optimize weight calculation: Calculate the optimized weight of each experimental case based on case similarity and deviation index ; S45, Feature matching matrix generation: Integrate the case similarity, deviation index, and optimization weight to generate a feature matching matrix .

6. The scenario demonstration evaluation method for a virtual experiment case oriented to public management according to claim 5, wherein The real-time evaluation generation in S5 includes: S51, Calculation of case completion score: The case completion score is used to measure the matching degree of the current scenario to the target experimental case, and the case completion score is calculated based on the feature matching matrix ; S52, Decision Path Deviation Warning Calculation: The decision path deviation warning is used to identify whether the current scenario execution path deviates from the reference experimental case, and warning judgment is carried out by calculating the decision path deviation index ; S53, Calculation of resource allocation optimization suggestions: The resource allocation optimization suggestions are based on the feature matching results, calculate the resource deviation between the current resource requirements and the optimal experimental cases, and calculate the optimized resource allocation parameters ; S54, Evaluation Parameter Integration and Output: Integrate the calculated case completion score, decision path deviation index, and resource allocation parameters into a real-time evaluation parameter set .

7. A method for evaluating scenario demonstrations of virtual experiment cases for public management, according to claim 6, characterized in that The evaluation visualization in S6 includes: S61, Dynamic evaluation atlas generation: Build a multi-dimensional visualization evaluation atlas according to the real-time evaluation parameters; S62, Virtual experiment scenario topology optimization: Automatically adjust the topological structure of the virtual experiment scenario based on the dynamic evaluation atlas to optimize the decision path, resource allocation, and scenario layout.

8. The scenario demonstration evaluation method for a virtual experiment case oriented to public management according to claim 7, characterized in that The dynamic evaluation atlas generation in S61 includes: S611, Evaluation parameter normalization: Normalize the evaluation parameters using the min-max normalization method; S612, Multi-dimensional visualization mapping: According to the normalized evaluation parameters, use hierarchical data mapping to build a dynamic evaluation atlas, including node representation and edge connection weight calculation, specifically including: Node representation: Three types of core evaluation dimensions are set and mapped to the node set in the visualization atlas ; Edge connection weight calculation: Calculate the influence relationship between different evaluation dimensions, and calculate the weight of the edge using weighted similarity measurement; Visualization atlas generation: Build the connection relationship between nodes and use visualization methods such as color gradient, heat map, and time series curve.

9. The scenario demonstration evaluation method for public management virtual experiment cases according to claim 8, wherein, The virtual experiment scenario topology optimization in S62 includes: S621, Scenario Topology Modeling: Construct the topology of the virtual experiment scenario, represented as a directed weighted graph , where are the key task nodes in the scenario, including decision points, resource allocation points, and behavior executions are the connections between task nodes, representing the task execution path, and each edge has a weight , representing the time, cost, or resource consumption of task transfer; S622, Decision Path Optimization: Based on the Decision Path Deviation Index in the Dynamic Evaluation Atlas , the shortest path optimization algorithm is used to adjust the experimental task path to minimize the overall execution cost; S623, Resource Allocation Optimization: Based on the optimized resource configuration parameters , a dynamic resource adjustment model is used to calculate the resource allocation plan and dynamically adjust the resource allocation in the scenario; S624, Adaptive Optimization of Scenario Layout: Based on the optimized task path and resource allocation, hierarchical clustering analysis is used to reorganize task nodes and dynamically adjust the layout of the virtual experiment scenario.

10. A scenario demonstration evaluation system for public management virtual experiment cases, which is used to implement a scenario demonstration evaluation method for public management virtual experiment cases as described in any one of claims 1-9, and is characterized in that It includes the following modules: Data Acquisition Module: Obtain scenario demonstration data through multi-source heterogeneous interfaces, including decision text data streams, virtual character behavior trajectory data, and environmental parameter time-series data; Data Preprocessing Module: Align the features of the obtained scenario demonstration data to generate a structured scenario dataset including spatio-temporal tags; Dynamic Feature Modeling Module: Build a dynamic feature model based on the structured scenario dataset to generate a three-dimensional feature vector including decision correlation, behavior compliance, and environmental adaptability; Feature Matching Module: Match the three-dimensional feature vector with the preset experimental case library to generate a feature matching matrix including case similarity, deviation index, and optimization weight; Real-time Evaluation Generation Module: Generate real-time evaluation parameters according to the feature matching matrix, including case completion score, decision path deviation warning, and resource allocation optimization suggestions; Evaluation Visualization Module: Map the real-time evaluation parameters into a dynamic evaluation atlas through a visualization engine and synchronously drive the optimization of the topological structure of the virtual experiment scenario.

Images