Social economic balanced development monitoring system based on population flow big data

Abstract

The invention discloses a social economic development monitoring system based on population flow big data, and particularly relates to the technical field of big data, and the system comprises an information collection module, a feature analysis module, a display confirmation module, and a display optimization module. Forming a policy environment information set and an index data set; the feature analysis module extracts policy decision features from the index data set, and generates a dual-view comprehensive evaluation value through a pre-trained machine learning model; the display confirmation module divides the policy information set into a high-dimensional response policy and a low-dimensional response policy based on the evaluation value; the display optimization module dynamically adjusts the length of a display window for the high-dimensional response policy and highlights the dynamic change of the policy influence; according to the method, the policy environment information set is divided into the high-dimensional response policy and the low-dimensional response policy through the double-view comprehensive evaluation value, and the high-dimensional response policy dynamically displays the dynamic change of the policy to the social and economic balanced development.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to a monitoring system for the balanced development of social economy based on big data of population flow. Background Art

[0002] With the rapid development of social economy and the promotion of the goal of balanced development of social economy, the issue of the balanced development of social economy of the population flow group has become an important research direction in policy formulation and implementation. However, the impact of the policy environment on the balanced development of social economy of the population flow group has significant multi-dimensional characteristics and dynamics. The existing policy display methods usually adopt a fixed display window and process all policy environment information in a unified manner, failing to fully distinguish the impact degree of policy environment changes on the promotion of the goal of balanced development of social economy. This method is likely to lead to the following problems: Uneven resource allocation: There is no dynamic adjustment mechanism for important high-dimensional response policies, which is likely to cause information to be ignored. Low efficiency: The system resources are not optimized, resulting in insufficient flexibility in display and affecting the scientific nature of policy display.

[0003] Therefore, there is an urgent need for a method that can perform dynamic and static classification displays according to the impact degree of policy environment changes, so as to effectively improve the pertinence of information display, the efficiency of resource utilization, and the scientific nature of decision-making support. Summary of the Invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A monitoring system for the balanced development of social economy based on big data of population flow, including an information collection module, a feature analysis module, a display confirmation module, and a display optimization module;

[0006] The information collection module is used to monitor the release information of the balanced development policy of social economy and perform policy environment information collection operations to obtain a policy environment information set, and regularly obtain a plurality of preset balanced development index data of social economy according to a preset strategy to obtain a balanced development index data set of social economy;

[0007] The feature analysis module is used to extract policy decision features from the balanced development index data set of social economy and perform analysis operations each time the policy environment information set is updated, and then input the analysis result into a pre-trained machine learning model to output a dual-perspective comprehensive evaluation value of the updated policy environment information set;

[0008] The display confirmation module divides the currently updated policy environment information set into high-dimensional response policies or low-dimensional response policies based on the dual-perspective comprehensive evaluation value output by the machine learning model;

[0009] When the display optimization module divides the currently updated policy environment information set into high-dimensional response policies, it optimizes the length of the display window based on the comprehensive evaluation value from dual perspectives output by the machine learning model.

[0010] In a preferred embodiment, the display confirmation module confirms the high-dimensional response policy as the dynamic display target and the low-dimensional response policy as the static display target.

[0011] In a preferred embodiment, the policy decision feature consists of a policy effectiveness feature group and a decision response feature group. A policy effectiveness index is generated based on the policy effectiveness feature group, and a decision response index is generated based on the decision response feature group.

[0012] In a preferred embodiment, the acquisition logic of the policy effectiveness index is as follows:

[0013] The formula for calculating the policy effectiveness index is:

[0014] ZCI represents the policy effectiveness index, ΔC represents the deviation value between the policy target coverage and the actual coverage, E policy represents the policy execution strength coefficient, DT represents the dynamic weighted effectiveness value, Deviation represents the deviation correction coefficient, γ is a preset policy sensitivity coefficient, β is a preset non-linear adjustment coefficient, α is a preset correction coefficient, and γ, β, and α are all non-zero;

[0015] is the target coverage population, N benefit is the actual beneficiary population, C region is the expected coverage rate of the policy implementation area;

[0016] i represents the category of the social and economic balanced development index data in the social and economic balanced development index dataset, n represents the total category, Wi represents the dynamic weight factor corresponding to the social and economic balanced development index data category i, and Fi represents the influence function corresponding to the social and economic balanced development index data category i;

[0017] Pi represents the initial weight corresponding to the social and economic balanced development index data category i, and Ri represents the correlation coefficient between the social and economic balanced development index data category i and the policy;

[0018] ΔXi represents the change value of the social and economic balanced development index corresponding to the data category i before and after the policy, and Xi,pre represents the benchmark value of the social and economic balanced development index corresponding to the data category i before the policy implementation;

[0019] E resourceLet \(X\) be the amount of resources invested in the policy, and \(XL\) be the execution efficiency;

[0020] The deviation correction coefficient Deviation is used to measure the resource allocation in the process of policy implementation. The policy coverage area is divided into \(m\) sub-regions, and the implementation results of each sub-region are obtained respectively. The standard deviation of the implementation results of all sub-regions is calculated, and the value of this standard deviation is the same as the deviation correction coefficient Deviation.

[0021] In a preferred implementation manner, the acquisition logic of the decision response index is as follows:

[0022] Obtain the change rate \(\Delta Xi\) of each data type \(i\) before and after the policy implementation, and then calculate the trend deviation value of the change rate of each index:

[0023] \(\overline{\Delta X}\) represents the average value of the change values \(\Delta Xi\) of the social and economic balanced development indicators corresponding to all data categories \(i\) before and after the policy, \(sgn(\Delta Xi)\) is the sign function indicating positive or negative changes, and \(Ti\) represents the trend deviation value corresponding to the index data category \(i\);

[0024] Obtain the dynamic weight factor \(Wi\) corresponding to the social and economic balanced development indicator data category \(i\), and calculate the short-term response value:

[0025] Calculate the current trend response value: \(D\) trend \(=\delta\cdot D\) short \(+(1 - \delta)\cdot D\) trend，prev ; \(D\) trend，prev is the previous trend response value, \(D\) trend represents the current trend response value, and \(\delta\) is the preset smoothing coefficient;

[0026] The calculation formula of the decision response index is: FYI represents the decision response index.

[0027] In a preferred implementation manner, inputting the analysis result into a pre-trained machine learning model, the dual-perspective comprehensive evaluation value of the updated policy environment information set refers to:

[0028] The machine learning model is a polynomial regression model. Input the decision response index and the policy effectiveness index into the polynomial regression model, and the polynomial regression model outputs the dual-perspective comprehensive evaluation value of the updated policy environment information set.

[0029] In a preferred implementation manner, based on the dual-perspective comprehensive evaluation value output by the machine learning model, dividing the currently updated policy environment information set into high-dimensional response policies or low-dimensional response policies refers to:

[0030] Compare the comprehensive evaluation value of the dual perspective with the preset division threshold. If the comprehensive evaluation value of the dual perspective is greater than or equal to the preset division threshold, divide the currently updated policy environment information set into high-dimensional response policies. If the comprehensive evaluation value of the dual perspective is less than the preset division threshold, divide the currently updated policy environment information set into low-dimensional response policies.

[0031] In a preferred embodiment, the logic for determining the length of the optimized display window is as follows:

[0032] ε represents a preset non-zero conversion coefficient, HF represents a preset division threshold, SCP represents the comprehensive evaluation value of the dual perspective, SCA represents the length of the basic window, and SCY represents the length of the optimized display window.

[0033] The technical effects and advantages of the present invention:

[0034] Through the comprehensive evaluation value of the dual perspective, the policy environment information set is divided into high-dimensional response policies and low-dimensional response policies. The high-dimensional response policies dynamically display the dynamic changes of policies on the balanced development of social economy in real time, highlighting key policy information. The low-dimensional response policies statically display stable trends, avoiding over-processing of policy information with relatively small changes. It solves the problem of the mixture of dynamic and static information in the existing methods and improves the pertinence and efficiency of information display.

[0035] Based on the comprehensive evaluation value output by the polynomial regression model, the display window length of the high-dimensional response policies is dynamically adjusted. While ensuring the display effect, it reduces the excessive consumption of system resources, enhances the adaptability and flexibility of the system. The dual perspective evaluation combines short-term dynamic response (decision response index) and long-term trend stability (policy efficacy index) to provide a comprehensive evaluation of the policy impact, focusing on high-dimensional response policies, intuitively showing the actual impact of policies on the goal of balanced social and economic development, providing an efficient and scientific decision-making basis for policy makers and managers, and enhancing the timeliness and pertinence of policy optimization and adjustment.

[0036] Allocate more resources to high-dimensional response policies for real-time monitoring and display, use static display for low-dimensional response policies, reduce the occupation of computing and storage resources, and achieve refined allocation of resources through non-linear adjustment of the display window length, improve the utilization efficiency of system resources, and reduce the operating costs of data processing and display. The division of dynamic and static display enables users to quickly focus on important policy information and avoid being interfered by redundant information; dynamic display ensures the real-time update of key policy impacts, and static display provides a stable reference for long-term trends, improving the user experience and reducing the time cost for users to obtain and analyze information. Description of the Drawings

[0037] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0038] Figure 1 This is the schematic diagram of the social and economic balanced development monitoring system based on population flow big data in the present invention. Specific embodiments

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying 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 of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.

[0040] Refer to Figure 1 The following embodiments are obtained:

[0041] Embodiment 1

[0042] The object of the present invention is to generate dynamic charts when the policy environment highly affects the social and economic balanced development situation, and use static charts at other times, which has the following meanings:

[0043] Focus on critical moments and highlight dynamic changes: Policy adjustments are usually important variables in the process of social and economic balanced development and may have significant impacts. For example, new floating population subsidy policies, employment support policies, or education resource allocation reforms may quickly change the economic and social status of the floating population group. Dynamic charts can capture and present these dynamic changes in real time, enabling decision-makers and the public to intuitively understand the specific impacts of policies on the floating population group. By highlighting key change points, information redundancy is avoided, and the efficiency and effectiveness of information transmission are improved.

[0044] Dynamically monitor highly sensitive periods and provide timely decision support: In situations where the policy environment has a high impact, such as when a policy is just implemented or there is a strong social response, dynamic charts can update data and analysis results in real time, helping monitoring agencies quickly judge the policy effects. For example, the trends of indicators such as the income level, employment changes, and social participation of the floating population can be tracked in real time to discover potential problems and quickly adjust strategies. Decision-making lags are reduced, and the pertinence and implementation efficiency of policies are enhanced.

[0045] Save resources and improve system efficiency: Dynamic charts require more computing resources and data update frequencies, while static charts are suitable for use in situations where changes are slow or trends are stable. By combining dynamic and static charts, while meeting the analysis needs, the system operation cost and computing pressure can be reduced. It can not only ensure dynamic monitoring during critical periods but also avoid resource waste during stable stages, improving the overall operation efficiency of the system.

[0046] Provide a more intuitive information display: Dynamic charts can show the changing trajectories of various indicators of the floating population group through animation effects, making it easier for observers to understand the dynamic evolution of the data. For example, the gradual increase in income level, the fluctuations in the employment rate, etc. are more clearly presented dynamically. In stages with insignificant changes, static charts are more suitable for overview analysis. Enhance the readability and dissemination effect of the data, and provide targeted display forms for users with different needs.

[0047] Reduce the risk of information overload: In the case of no significant changes, continuous use of dynamic charts may lead to information fatigue and decreased attention. Presenting stable data through static charts can enable the audience to focus on key information without being distracted by meaningless dynamic changes. Enhance the focus of information, enabling decision-makers and the audience to efficiently obtain valuable content.

[0048] Therefore, the present invention proposes a monitoring system for the balanced development of social economy based on big data of population flow, including an information collection module, a feature analysis module, a display confirmation module, and a display optimization module; the information collection module, the feature analysis module, the display confirmation module, and the display optimization module are communicatively connected.

[0049] The information collection module is used to monitor the release information of the balanced development policy of social economy and perform the information collection operation of the policy environment information to obtain the policy environment information set, and regularly obtain a plurality of preset social economy balanced development indicator data according to a preset strategy to obtain the social economy balanced development indicator data set; the information collection module is the basic part of the entire system, mainly used to capture the dynamic changes of the policy environment and the relevant data of the balanced development of social economy in real time, and establish the comprehensiveness and timeliness of the data. Monitor policy release information: Obtain the latest policy content and implementation environment information to form a policy environment information set. Collect the affluent indicators of the floating population: Regularly collect multi-dimensional indicator data (such as income, employment rate, education resource coverage rate, etc.) reflecting the balanced development of social economy according to a preset strategy to generate an indicator data set. Ensure the comprehensiveness and accuracy of the data: By integrating data from different sources, build a comprehensive input basis to support subsequent analysis and model training. Provide the basic data required for the system decision-making analysis to ensure that the system can respond to policies and social dynamics in a timely manner.

[0050] The feature analysis module is used to extract and analyze policy decision features from the dataset of socio-economic balanced development indicators each time the policy environment information set is updated. Then, the analysis results are input into a pre-trained machine learning model to output the comprehensive evaluation value from a dual perspective of the updated policy environment information set. The feature analysis module is the in-depth processing part of the data collected by the information collection module. Its purpose is to extract key features from the complex policy environment and socio-economic balanced development indicators to support subsequent decision-making. The extracted features are input into a pre-trained machine learning model to generate the comprehensive evaluation value from a dual perspective (policy effectiveness perspective and decision response perspective) based on the policy environment update.

[0051] Based on the comprehensive evaluation value from a dual perspective output by the machine learning model, the display and confirmation module classifies the currently updated policy environment information set into high-dimensional response policies or low-dimensional response policies. The display and confirmation module is the core of data visualization, used to classify and display the response degree of the policy environment update, helping users quickly and intuitively understand the classification results of policy impacts. Classify policy environment information: According to the comprehensive evaluation value from a dual perspective, the policy environment is divided into high-dimensional response policies and low-dimensional response policies. High-dimensional response policies: The changes in the policy environment have a greater impact on the socio-economic balanced development indicators and need to be focused on and dynamically displayed. Low-dimensional response policies: The impact of policy environment changes is relatively small and can be processed through static display. Intuitively present policy impacts: Provide users with clear classification results for subsequent decision-making and optimization.

[0052] When the currently updated policy environment information set is classified as a high-dimensional response policy, the display optimization module optimizes the length of the display window based on the comprehensive evaluation value from a dual perspective output by the machine learning model. The display optimization module is the core part for responding to dynamic data changes. For high-dimensional response policies, by adjusting the length of the display window, it realizes more accurate visualization of dynamic information. Optimize the length of the display window: When the policy environment information is classified as a high-dimensional response policy, dynamically adjust the length of the display window according to the comprehensive evaluation value from a dual perspective to ensure the visualization effect of high-dynamic information, extend the window length to show the overall trend, and dynamically adjust the window length to adapt to policy characteristics and user needs, avoiding over-display or information omission.

[0053] The display and confirmation module designates high-dimensional response policies as dynamic display targets and low-dimensional response policies as static display targets. Dynamic display of high-dimensional response policies: High-dimensional response policies refer to policies that have a significant impact on the socio-economic balanced development indicators. Such policies usually exhibit rapid and significant dynamic changes. Through dynamic display, users can capture the changing trends of policies and their impacts on socio-economic balanced development in real time, providing a timely basis for policy adjustment. For example, the rapid promotion effect of a new floating population subsidy policy on income level, employment rate, and social participation rate.

[0054] Low - dimensional Response Policy Static Display: The low - dimensional response policy refers to policies that have a relatively small impact on the indicators of the balanced development of social economy or show a stable change trend. Static display avoids the interference caused by frequent updates, enabling users to intuitively and concisely understand the fundamental impact of policies on the overall environment. For example, long - term implemented basic education policies may show a gradually accumulating trend in their impact rather than significant short - term fluctuations.

[0055] The policy decision characteristics are composed of a policy efficacy characteristic group and a decision - response characteristic group. Based on the policy efficacy characteristic group, a policy efficacy index is generated, and based on the decision - response characteristic group, a decision - response index is generated. The policy efficacy index measures the implementation effect and resource utilization efficiency of the policy, reflecting the direct promotion role of the policy in the goal of promoting the balanced development of social economy. The larger the policy efficacy index, the stronger the matching between policy resource input and goal achievement, the more efficient the policy implementation, and the more significant the effect. The decision - response index measures the dynamic response of the floating population group or society to policy changes, reflecting the immediacy and adaptability of policy impacts. The larger the decision - response index, the stronger the social or economic reaction triggered by the policy, and the better the sensitivity and adaptability of the policy.

[0056] The acquisition logic of the policy efficacy index is as follows: The formula for calculating the policy efficacy index is:

[0057] ZCI represents the policy efficacy index, ΔC represents the deviation value between the policy target coverage and the actual coverage, E policy represents the policy implementation intensity coefficient, DT represents the dynamic weighted efficacy value, Deviation represents the deviation correction coefficient, γ is a preset policy sensitivity coefficient, β is a preset non - linear adjustment coefficient, α is a preset correction coefficient, and γ, β, and α are all non - zero; log 10 (1 + ΔC) performs logarithmic scaling on the policy coverage difference to avoid the influence of too large or too small deviations on the results.

[0058] N target is the target coverage population, N benefit is the actual beneficiary population, C region is the expected coverage rate of the policy implementation area, and ΔC represents the deviation between the actual coverage and the target coverage, which affects the benchmark value of the overall index;

[0059] i represents the category of social - economic balanced development index data in the social - economic balanced development index dataset, n represents the total number of categories, Wi represents the dynamic weight factor corresponding to the social - economic balanced development index data category i, reflecting the importance of each index, and Fi represents the influence function corresponding to the social - economic balanced development index data category i;

[0060] Pi represents the initial weight corresponding to the social and economic balanced development indicator data category i, and Ri represents the correlation coefficient between the social and economic balanced development indicator data category i and the policy;

[0061] The policy impact of each indicator is modeled through a non-linear function: ΔXi represents the change value of the social and economic balanced development indicator corresponding to the data category i before and after the policy, and Xi,pre represents the benchmark value of the social and economic balanced development indicator corresponding to the data category i before the implementation of the policy;

[0062] E resource is the amount of resources invested in the policy, and XL is the execution efficiency;

[0063] First, calculate the ratio one of the effective resource utilization amount to the amount of resources invested in the policy, then calculate the ratio two of the actual number of beneficiaries to the target coverage number, and the product of ratio one and ratio two gives the execution efficiency;

[0064] The deviation correction coefficient Deviation is used to measure the resource allocation situation in the process of policy implementation. α·Deviation is the deviation correction term for policy execution. Considering the errors in actual policy implementation such as uneven resource allocation, the policy coverage area is divided into m sub-regions, and the policy implementation results of each sub-region are obtained respectively. By calculating, the standard deviation of the policy implementation results of all sub-regions is obtained, and the value of this standard deviation is the same as the deviation correction coefficient Deviation.

[0065] The acquisition logic of the decision response index is as follows:

[0066] Obtain the change rate ΔXi of each data type i before and after the policy implementation, and then calculate the trend deviation value of the change rate of each indicator:

[0067] represents the average value of the change values ΔXi of the social and economic balanced development indicators corresponding to all data categories i before and after the policy. sgn(ΔXi) is the sign function, indicating positive or negative changes. Ti represents the trend deviation value corresponding to the indicator data category i. Before and after the policy implementation, there may be differences in the data change rates of each indicator. The formula measures the impact range of the policy on the indicator by calculating the deviation degree of the change rate from the average value. The sign function ensures that the information of the positive and negative change directions is not lost, that is, whether it advances (positively) or deviates (negatively) towards the social and economic balanced development goal. reflects the deviation degree (percentage) of each indicator relative to the average change, and is used to measure the response intensity of the indicator.

[0068] Obtain the dynamic weight factor Wi corresponding to the social and economic balanced development indicator data category i, and calculate the short-term response value: By performing a weighted sum of the trend deviation values (Ti) of all indicators, the short-term response value of the policy is obtained. The importance of each indicator may vary, and the weight factor Wi reflects its relative contribution in the policy response. For example, the employment rate may be more important than the utilization rate of educational resources.

[0069] Calculate the current trend response value: D trend = δ·D short +(1 - δ)·D trend，prev ; D trend，prev is the previous trend response value, D trend represents the current trend response value, δ is a preset smoothing coefficient. The closer the value is to 1, the more it emphasizes short-term fluctuations; the closer the value is to 0, the more it emphasizes long-term fluctuations. By combining short-term dynamic response and historical trend response, the integration of short-term fluctuations and long-term trends is achieved through the smoothing coefficient.

[0070] The calculation formula for the decision response index is: FYI represents the decision response index. It is calculated through the Euclidean distance between the short-term response value and the trend response value, ensuring that the decision response index can reflect both short-term dynamics and long-term trends. The sum of squares emphasizes the complementary role of short-term dynamics and long-term trends, avoiding a single aspect dominating the decision evaluation.

[0071] Input the analysis results into a pre-trained machine learning model. The dual-perspective comprehensive evaluation value of the updated policy environment information set output refers to:

[0072] The machine learning model is a polynomial regression model. Input the decision response index and the policy effectiveness index into the polynomial regression model, and the polynomial regression model outputs the dual-perspective comprehensive evaluation value of the updated policy environment information set. The polynomial regression model takes the decision response index and the policy effectiveness index as inputs and outputs a comprehensive dual-perspective evaluation value. The significance of this process lies in:

[0073] Integrate multi-dimensional information and improve evaluation accuracy: Dual-perspective integration: The decision response index and the policy effectiveness index respectively reflect short-term dynamic impacts and policy implementation effectiveness. The polynomial regression model can capture the complex relationship between the two through non-linear mapping and integrate them into a comprehensive evaluation value.

[0074] Accurately measure the policy effect: By learning the non-linear relationship between the input data and the output results, the model can more accurately evaluate the overall changes in the policy environment and its impact on the goal of balanced social and economic development.

[0075] Dynamic Adaptation to Complex Policy Environments: Adapting to Policy Environment Diversity: The impacts of different policies on the balanced development of social economy may exhibit complex non-linear patterns. The polynomial regression model can dynamically adapt to this diversity and capture more comprehensive information. As the information set of the policy environment changes dynamically, the input data will be continuously updated, and the dual-perspective evaluation values output by the model can reflect the latest policy impacts in real time.

[0076] Unified Measurement Standard: The dual-perspective evaluation value provides a unified indicator for measuring the comprehensive impact of the current policy environment on the balanced development of social economy, simplifying subsequent classification operations.

[0077] Based on the dual-perspective comprehensive evaluation value output by the machine learning model, classifying the currently updated policy environment information set into high-dimensional response policies or low-dimensional response policies means:

[0078] Compare the dual-perspective comprehensive evaluation value with a preset classification threshold. If the dual-perspective comprehensive evaluation value is greater than or equal to the preset classification threshold, then classify the currently updated policy environment information set as a high-dimensional response policy; if the dual-perspective comprehensive evaluation value is less than the preset classification threshold, then classify the currently updated policy environment information set as a low-dimensional response policy. The dual-perspective evaluation value combines the short-term dynamics and long-term trend information of the policy. By classifying through comparison with the threshold, it can more scientifically reflect the degree of policy impact. Dynamic Adjustment Strategy: The classification of high-dimensional response policies provides key focus areas for decision-makers, helping to formulate more precise policy optimization plans. Hierarchical Information Display: Correspond the high-dimensional response policies and low-dimensional response policies to dynamic display and static display respectively, avoiding information overload. Quick Identification of Key Policies: Through classification, users can quickly focus on the changes in important policy environments, improving work efficiency. Dynamic Monitoring of High-dimensional Response Policies: It can capture in real time the policies that have a greater impact on the goal of balanced social and economic development and timely feedback their implementation effects. Reduction of Resource Waste in Inefficient Monitoring: Simplify the processing of low-dimensional response policies, saving system operation costs and human resources.

[0079] The logic for optimizing the determination of the display window length is as follows:

[0080] ε represents a preset non-zero conversion coefficient, HF represents a preset classification threshold, SCP represents the dual-perspective comprehensive evaluation value, SCA represents the basic window length, which represents the default basic display window length, provides the minimum display range, determines the initial scale of the display window, is suitable for basic dynamic display, SCY represents the length of the optimized display window, which represents the length of the finally dynamically optimized display window and is directly used to display the information of high-dimensional response policies. The larger the window length, the longer the dynamic display time. Achieve the dynamic optimization of the display window, adapt to different changes in the policy environment, can not only meet the dynamic information needs but also save system resources.

[0081] The above formulas are all dimensionless and only take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0082] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0083] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0084] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0085] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A social and economic development monitoring system based on population mobility big data, characterized in that: It includes information collection module, feature analysis module, display confirmation module and display optimization module; The information collection module is used to monitor the information released by the social and economic balanced development policy and collect policy environment information to obtain a policy environment information set, and regularly obtain multiple preset social and economic balanced development indicator data according to preset strategies to obtain a social and economic balanced development indicator data set; The feature analysis module is used to extract policy decision features from the social and economic balanced development indicator data set and perform analysis operations each time the policy environment information set is updated, and then input the analysis results into the pre-trained machine learning model to output the dual-perspective comprehensive evaluation value of the updated policy environment information set; The display confirmation module divides the currently updated policy environment information set into high-dimensional response policies or low-dimensional response policies based on the dual-perspective comprehensive evaluation value output by the machine learning model; The display optimization module optimizes the length of the display window based on the dual-perspective comprehensive evaluation value output by the machine learning model when the currently updated policy environment information set is divided into high-dimensional response policies.

2. According to claim 1, a social and economic development monitoring system based on population mobility big data is characterized in that: The display confirmation module confirms the high-dimensional response policy as a dynamic display target and the low-dimensional response policy as a static display target.

3. According to claim 2, a social and economic development monitoring system based on population mobility big data is characterized in that: The policy decision characteristics consist of a policy effectiveness feature group and a decision response feature group. A policy effectiveness index is generated based on the policy effectiveness feature group, and a decision response index is generated based on the decision response feature group.

4. According to claim 3, a social and economic development monitoring system based on population mobility big data is characterized in that: The logic for obtaining the policy effectiveness index is: The calculation formula of policy effectiveness index is: ZCI represents the policy effectiveness index, ΔC represents the deviation between the policy target coverage and the actual coverage, and E policy represents the policy implementation strength coefficient, DT represents the dynamic weighted effectiveness value, Deviation represents the deviation correction coefficient, γ represents the preset policy sensitivity coefficient, β represents the preset nonlinear adjustment coefficient, α represents the preset correction coefficient, and γ, β, and α are all non-zero; N target is the target coverage number, N benefit is the actual number of beneficiaries, C region Expected coverage of policy implementation areas; i represents the category of the social and economic balanced development indicator data in the social and economic balanced development indicator data set, n represents the total category, Wi represents the dynamic weight factor corresponding to the social and economic balanced development indicator data category i, and Fi represents the influence function corresponding to the social and economic balanced development indicator data category i; Pi represents the initial weight corresponding to the category i of the social and economic balanced development indicator data, and Ri represents the correlation coefficient between the category i of the social and economic balanced development indicator data and the policy; ΔXi represents the change in the socio-economic balanced development index corresponding to data category i before and after the policy, and Xi,pre represents the baseline value of the socio-economic balanced development index corresponding to data category i before the policy was implemented; E resource is the amount of resources invested in the policy, and XL is the implementation efficiency; The deviation correction coefficient Deviation is used to measure the resource allocation during policy implementation. The policy coverage area is divided into m sub-areas, and the policy implementation results of each sub-area are obtained respectively. The standard deviation of the policy implementation results of all sub-areas is calculated. The standard deviation value is the same as the deviation correction coefficient Deviation.

5. According to claim 4, a social and economic development monitoring system based on population mobility big data is characterized in that: The logic for obtaining the decision response index is: Obtain the change rate ΔXi of each data type i before and after the policy implementation, and then calculate the trend deviation value of the change rate of each indicator: It represents the average value of the change value ΔXi of the socio-economic balanced development index before and after the policy for all data categories i. sgn(ΔXi) is a sign function indicating a positive or negative change. Ti represents the trend deviation value corresponding to the indicator data category i. Obtain the dynamic weight factor Wi corresponding to the socio-economic balanced development indicator data category i, and calculate the short-term response value: Calculate the current trend response value: D trend =δ·D short +(1-δ)·D trend，prev ;D trend，prev is the previous trend response value, D trend Represents the current trend response value, and δ is the preset smoothing coefficient; The calculation formula of decision response index is: FYI stands for Decision Yield Index.

6. A social and economic development monitoring system based on population mobility big data according to claim 5, characterized in that: The analysis results are input into the pre-trained machine learning model, and the dual-perspective comprehensive evaluation value of the output updated policy environment information set refers to: The machine learning model is a polynomial regression model. The decision response index and policy effectiveness index are input into the polynomial regression model together. The polynomial regression model outputs a dual-perspective comprehensive evaluation value of the updated policy environment information set.

7. The social and economic development monitoring system based on population mobility big data according to claim 6 is characterized in that: Based on the dual-perspective comprehensive evaluation value output by the machine learning model, the currently updated policy environment information set is divided into high-dimensional response policies or low-dimensional response policies, which means: The dual-perspective comprehensive evaluation value is compared with the preset division threshold. If the dual-perspective comprehensive evaluation value is greater than or equal to the preset division threshold, the currently updated policy environment information set is divided into a high-dimensional response policy. If the dual-perspective comprehensive evaluation value is less than the preset division threshold, the currently updated policy environment information set is divided into a low-dimensional response policy.

8. The social and economic development monitoring system based on population mobility big data according to claim 7 is characterized in that: The logic for determining the length of the optimized display window is: ε represents a preset non-zero conversion coefficient, HF represents a preset division threshold, SCP represents a dual-view comprehensive evaluation value, SCA represents a basic window length, and SCY represents the length of the optimized display window.

Images