A method and system for major policy evaluation prediction based on ordered logistic regression analysis

Abstract

This invention discloses a method and system for predicting major policy evaluations based on ordered logistic regression analysis. The method includes: selecting representative social groups using stratified judgment sampling; acquiring data on their current participation, psychological cognition, and needs preferences in major policy evaluations using standardized survey tools; analyzing factors influencing participation behavior based on the survey data; designing support strategies based on the analysis results to form a comprehensive support strategy system; verifying the effectiveness of the strategies and optimizing the parameters accordingly. Its significant effect is that it can effectively address the deep-seated obstacles to social participation in policy evaluations and predictions, achieving scientific guidance for social participation behavior and improving the quality of policy evaluation and prediction.

Description

Technical Field

[0001] This invention relates to the field of public policy evaluation technology, specifically to a method and system for evaluating and predicting major policies based on ordered logistic regression analysis. Background Technology

[0002] Major policy evaluation and forecasting are crucial for improving the scientific nature of policies and protecting the rights and interests of society members. However, the current situation regarding the participation of society members in major policy evaluation and forecasting presents several problems: the willingness of society members to participate varies, with some groups lacking the motivation to participate actively due to limited understanding and high participation costs; existing policy evaluation and forecasting systems often adopt a singular design, failing to fully consider the different needs of different categories of society members, resulting in a mismatch between the supply of systems and actual needs; policy publicity methods are rigid and information disclosure is insufficient, leading to a lack of awareness among society members of the importance of policy evaluation and forecasting, and making them prone to short-sightedness, status quo bias, and other behavioral deviations, which in turn affect the quality of participation and the comprehensiveness of policy evaluation and forecasting.

[0003] In existing technologies, policy evaluation and prediction of participation promotion largely rely on mandatory requirements or simple propaganda and guidance, lacking flexible intervention methods based on the behavioral patterns of social members, and thus failing to effectively correct cognitive biases or lower the participation threshold. Therefore, there is an urgent need for a major policy evaluation and prediction method that can accurately match the needs of social members, gently guide participation behavior, and enhance participation enthusiasm and effectiveness. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the purpose of this invention is to provide a method and system for evaluating and predicting major policies based on ordered logistic regression analysis. This method and system can solve the problems of low participation willingness among social members, mismatch between institutional supply and demand, and biased participation behavior in existing technologies, thereby achieving scientific guidance of social members' participation behavior and improving the quality of policy evaluation and prediction.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a method for evaluating and predicting major policies based on ordered logistic regression analysis, the key of which includes the following steps: Step 1: Select representative social groups using stratified judgment sampling and use standardized survey tools to obtain data on their current participation, psychological cognition, and demand preferences in the evaluation and prediction of major policies. Step 2: Analyze the factors influencing participation behavior based on survey data: Step 2.1: Clean and code the questionnaire data obtained from the survey, and remove invalid samples; conduct qualitative analysis on the interview data and case data to extract key information; Step 2.2: Use statistical software to conduct descriptive statistics on the psychological characteristics, cognitive status and participation behavior of social members participating in the evaluation and prediction of different major policies, and analyze the cognitive biases and behavioral biases of social members in the participation process; Step 2.3: Construct a quantitative analysis model based on behavioral decision theory, with social members’ willingness to participate, frequency of participation, and quality of participation as dependent variables, and basic characteristics, occupational characteristics, cognitive status, and policy and institutional factors as independent variables, to explore the core factors affecting participation behavior, conduct confirmatory factor analysis, and identify the key factors affecting participation behavior. Step 3: Based on the analysis results of factors influencing participation behavior, design a boosting strategy to form a comprehensive boosting strategy system; Step 4: Using a quasi-experimental method, the homogeneous social group is divided into an experimental group and a control group. The aforementioned boosting strategy system is implemented on the experimental group. The participation rate and participation quality data of the two groups are compared and analyzed to verify the effectiveness of the strategy and optimize the parameters accordingly.

[0006] Furthermore, step 1, which involves obtaining data on participation status, psychological cognition, and demand preferences in major policy evaluation and prediction, specifically includes: Step 1.1: Using stratified judgment sampling, representative members of society in typical cities were selected, and managers responsible for major policy evaluation and forecasting were also selected as interviewees. Step 1.2: Design research tools, including standardized open-ended questionnaires and semi-structured interview outlines. The questionnaires cover the basic characteristics, occupational features, cognitive status, participation experience, and needs and preferences of social members; the interview outlines include key issues in policy evaluation and prediction system formulation and implementation. Step 1.3: Obtain sample data through questionnaires, collect feedback from special social members and managers through semi-structured interviews and case studies, and collect implementation case data of major policy evaluation and prediction in different regions to form data on the participation status, psychological cognition and demand preferences of representative social groups in major policy evaluation and prediction.

[0007] Furthermore, the social groups selected by the stratified judgment sampling method include: political social members, economic social members, social status social members, professional workers and practitioners, ordinary members in communities and groups, and individuals and family units.

[0008] Furthermore, the econometric analysis model employs ordered logistic regression analysis, and the key factors include one or more of the following: income stability, ease of participation process, information transparency, industry relevance, information acquisition cost, and timeliness of result feedback.

[0009] Furthermore, the policy support strategy design described in step 3 includes optimization of top-level systems, optimization of framework effects, optimization of information disclosure, and optimization of technical support.

[0010] Furthermore, the optimization of the top-level system includes: setting differentiated evaluation and prediction indicators, methods, participation procedures, and result application mechanisms for different policy types and social groups; The optimization of the framework effect includes: simplifying and reconstructing the presentation of policy assessment and forecasting information by using visual charts, concise manuals, or short videos; The optimization of information disclosure includes: regularly disclosing to participants the adoption status of their opinions, related cases of policy adjustments and participation feedback, and data on the actual impact of policy implementation; The technical support optimizations include: building a convenient participation interface with personalized reminders, voice input, progress query, batch participation, and one-click assistance functions based on the Internet or mobile application platform.

[0011] Furthermore, step 4, which involves verifying the effectiveness of the strategy and optimizing the parameters accordingly, specifically includes: Step 4.1: Quasi-experimental design. Two homogeneous social groups are selected as the experimental group and the control group. The experimental group adopts the comprehensive boosting strategy system designed in Step 3, while the control group adopts the traditional participatory guidance method. Step 4.2: Implement intervention under natural conditions. In the same policy evaluation and prediction scenario, guide the participation of the two groups respectively, and continuously collect data on the participation intention, participation rate, and participation completion quality of the two groups. Step 4.3: Compare the differences between the experimental group and the control group to verify the effectiveness of the boosting strategy; and adjust the specific parameters of the boosting strategy based on the verification results to optimize the system design and technical support scheme.

[0012] Secondly, the present invention provides a major policy evaluation and prediction system based on ordered logistic regression analysis, capable of implementing the steps of the method described in the first aspect, including: The data acquisition module is used to select representative social groups using stratified judgment sampling and to obtain data on their participation status, psychological cognition, and demand preferences in the evaluation and prediction of major policies using standardized survey tools. The data analysis and modeling module is used to store and process the data, build econometric analysis models, and output a report analyzing key factors affecting participation behavior. The boosting strategy generation module is used to design boosting strategies based on the key influencing factor analysis report, and generate a comprehensive boosting strategy system for specific policies and social groups. The effect verification and optimization module is used to divide a homogeneous social group into an experimental group and a control group using a quasi-experimental method. The boosting strategy system is implemented on the experimental group, and the participation rate and participation quality data of the two groups are compared and analyzed to verify the effectiveness of the strategy and optimize the parameters accordingly.

[0013] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor; The memory is used to store programs; The processor is configured to execute the program and implement the steps of the method as described in the first aspect.

[0014] Fourthly, the present invention provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0015] The significant effects of this invention are: 1. Accurately match supply and demand: Through stratified research and differentiated institutional design, the needs of different categories of social members are fully considered, which solves the problem of homogeneity in the existing institutional supply and improves the pertinence of policy evaluation and prediction.

[0016] 2. Effectively guide participation behavior: Based on the nudge theory, the flexible intervention strategy corrected cognitive biases and lowered the participation threshold while respecting the voluntary choice of social members, thus significantly improving the participation willingness and participation rate of social members.

[0017] 3. Improve the quality of participation and the scientific nature of policies: Through information optimization and technical support, behavioral biases in the participation process of social members are reduced, ensuring the authenticity and comprehensiveness of participation feedback, providing high-quality data support for the evaluation and prediction of major policies, and improving the scientific nature of policy formulation and adjustment.

[0018] 4. It is replicable and adaptable: the methodology is standardized and parameters can be flexibly adjusted according to different regions and types of major policies. It is applicable to various public policy evaluation and prediction scenarios and has broad application prospects. Attached Figure Description

[0019] Figure 1 This is a flowchart of the method described in this invention; Figure 2 This is a schematic diagram of the module structure of the system described in this invention; Figure 3 This is a schematic diagram of the structure of the electronic device described in this invention. Detailed Implementation

[0020] The specific embodiments and working principles of the present invention will be further described in detail below with reference to the accompanying drawings. Example 1

[0021] like Figure 1 As shown, a method for evaluating and predicting major policies based on ordered logistic regression analysis is presented, with the following specific steps: Step 1: Select representative social groups using stratified judgment sampling and use standardized survey tools to obtain data on their current participation, psychological cognition, and demand preferences in the evaluation and prediction of major policies. In this embodiment of the invention, the acquisition of data on participation status, psychological cognition, and demand preferences in major policy evaluation and prediction specifically includes: Step 1.1: Using stratified judgment sampling, representative members of society in typical cities were selected, and managers responsible for major policy evaluation and forecasting were also selected as interviewees. The social groups selected by the stratified judgment sampling method include: political social members, economic social members, social status social members, professional workers and practitioners, ordinary members in communities and groups, and individuals and family units.

[0022] Step 1.2: Design research tools, including standardized open-ended questionnaires and semi-structured interview outlines. The questionnaires cover the basic characteristics, occupational features, cognitive status, participation experience, and needs and preferences of social members; the interview outlines include key issues in policy evaluation and prediction system formulation and implementation. In practice, the basic characteristics of the social members include age, gender, marital status, and household registration; the occupational characteristics include industry, income level, income stability, working hours, and work environment; and the cognitive status includes biases such as short-sightedness, loss aversion, overconfidence, and status quo bias when participating in decision-making.

[0023] Step 1.3: Obtain sample data through questionnaires, collect feedback from special social members and managers through semi-structured interviews and case studies, and collect implementation case data of major policy evaluation and prediction in different regions to form data on the participation status, psychological cognition and demand preferences of representative social groups in major policy evaluation and prediction.

[0024] Step 2: Introduce behavioral decision theory, construct an econometric model based on survey data, analyze the factors influencing participation behavior, and accurately identify the key drivers and obstacles affecting participation: Step 2.1: Clean and code the questionnaire data obtained from the survey, and remove invalid samples; conduct qualitative analysis on the interview data and case data to extract key information; Step 2.2: Use statistical software to conduct descriptive statistics on the psychological characteristics, cognitive status and participation behavior of social members participating in the evaluation and prediction of different major policies, and analyze the cognitive biases and behavioral biases of social members in the participation process; Step 2.3: Construct a quantitative analysis model based on behavioral decision theory, with social members’ willingness to participate, frequency of participation, and quality of participation as dependent variables, and basic characteristics, occupational characteristics, cognitive status, and policy and institutional factors as independent variables, to explore the core factors affecting participation behavior, conduct confirmatory factor analysis, and identify the key factors affecting participation behavior. Generally, the policy and institutional factors mentioned in the implementation include assessment and forecasting indicators, methods, procedures, information disclosure, and application of results.

[0025] In addition, the econometric analysis model adopts ordered logistic regression analysis, and the key factors include one or more of the following: income stability, ease of participation process, information transparency, industry relevance, information acquisition cost, and timeliness of result feedback.

[0026] Step 3: Based on the analysis results of factors influencing participation behavior, design a boosting strategy to form a comprehensive boosting strategy system; In this embodiment, the policy support strategy design includes top-level institutional optimization, framework effect optimization, information disclosure optimization, and technical support optimization, specifically: The aforementioned top-level institutional optimization includes: setting differentiated assessment and forecasting indicators, methods, participation procedures, and result application mechanisms for different policy types and social groups. Specifically, based on survey results and influencing factor analysis, a comprehensive review of the existing major policy assessment and forecasting system will be conducted to identify obstacles in the participation phase. Systematic optimization will be carried out in terms of assessment and forecasting principles, indicator systems, implementation methods, participation procedures, result application mechanisms, and transparency to construct a differentiated institutional supply system that matches the needs of different categories of social members. Through top-level institutional optimization, the institutional framework for policy assessment and forecasting can be reshaped to be more inclusive and differentiated, for example, by setting dedicated channels and indicators for different groups. The optimization of the framing effect includes simplifying and reconstructing the presentation of policy evaluation and forecasting information by using visual charts, concise manuals, or short videos. This optimization can enrich the methods and forms of communication for the policy evaluation and forecasting system, shorten the information transmission chain, and thus convey information in a more easily understood visual and story-based manner. It emphasizes strengthening members of society's awareness of the importance of participation and policy common sense, reducing cognitive costs, and highlighting the value and benefits of participation. The optimized information disclosure includes: regularly disclosing to participants the adoption status of their opinions, related cases of policy adjustments and participation feedback, and data on the actual impact of policy implementation. Optimized information disclosure can focus on the core concerns of society members, emphasizing the disclosure of key information such as the correlation between participation costs and benefit levels, and the application of policy evaluation and forecast results. This enhances society members' expectations of policy benefits, strengthens their motivation to actively participate, and increases the transparency of key information, especially the establishment of a feedback loop, allowing participants to see the value of their opinions and improving their sense of efficacy. The technical support optimizations include: building a convenient participation interface based on the internet or mobile application platform, featuring personalized reminders, voice input, progress tracking, batch participation, and one-click assistance; providing self-service participation; and setting personalized participation reminders. This leverages information technology to create a convenient and low-cost participation platform, reducing time and technical barriers, and adapting to the professional characteristics and usage habits of members of society.

[0027] Step 4: Using a quasi-experimental method, the homogeneous social group is divided into an experimental group and a control group. The aforementioned boosting strategy system is implemented on the experimental group. The participation rate and participation quality data of the two groups are compared and analyzed to verify the effectiveness of the strategy and optimize the parameters accordingly.

[0028] In this embodiment, the verification of the effectiveness of the strategy and the optimization of parameters accordingly specifically includes: Step 4.1: Quasi-experimental design. Two homogeneous social groups are selected as the experimental group and the control group. The experimental group adopts the comprehensive boosting strategy system designed in Step 3, while the control group adopts the traditional participatory guidance method. Step 4.2: Implement intervention under natural conditions. In the same policy evaluation and prediction scenario, guide the participation of the two groups respectively, and continuously collect data on the participation intention, participation rate, and participation completion quality of the two groups. Step 4.3: Compare the differences between the experimental group and the control group using methods such as cross-tabulation tables and analysis of variance to verify the effectiveness of the boosting strategy; and adjust the specific parameters of the boosting strategy based on the verification results to optimize the system design and technical support scheme. Example 2

[0029] See appendix Figure 2 This invention provides a major policy evaluation and prediction system based on ordered logistic regression analysis, which can implement the steps of the method described in Embodiment 1, including: The data acquisition module is used to select representative social groups using stratified judgment sampling and to obtain data on their participation status, psychological cognition, and demand preferences in the evaluation and prediction of major policies using standardized survey tools. The data analysis and modeling module is used to store and process the data, build econometric analysis models, and output a report analyzing key factors affecting participation behavior. The boosting strategy generation module is used to design boosting strategies based on the key influencing factor analysis report, and generate a comprehensive boosting strategy system for specific policies and social groups. The effect verification and optimization module is used to divide a homogeneous social group into an experimental group and a control group using a quasi-experimental method. The boosting strategy system is implemented on the experimental group, and the participation rate and participation quality data of the two groups are compared and analyzed to verify the effectiveness of the strategy and optimize the parameters accordingly. Example 3

[0030] See appendix Figure 3 This invention provides an electronic device, including: a memory and a processor; The memory is used to store programs; The processor is used to execute the program and implement the steps of the method as described in Embodiment 1. Example 4

[0031] This invention provides a readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0032] Application Example 1: Promoting Participation in Urban Social Security Policy Evaluation 1. Research phase: Three cities of different sizes were selected, and a sample of 2,000 members of society (covering six major groups: political power holders, economic power holders, social status holders, professional workers and practitioners, ordinary members in communities and groups, individuals and family units) were selected to conduct a questionnaire survey. Semi-structured interviews were conducted with 50 policy evaluation management personnel to collect data on the current status of participation in social security policy evaluation and feedback on needs.

[0033] 2. Analysis of influencing factors: Through ordered logistic regression analysis, it was found that income stability, ease of participation process, and information transparency are the core factors affecting participation in social security policy evaluation. The elderly group pays more attention to ease of operation, while the younger professional group pays more attention to the timeliness of information.

[0034] 3. Boosting Strategy Design: Top-level system optimization: For social security policies, special assessment indicators for the elderly have been added, the offline participation process has been simplified, and while online participation channels are retained, community assistance services are provided.

[0035] Framing effect optimization: Create a social security policy assessment participation guide that combines text and graphics, and disseminate it through multiple channels such as community bulletin boards, government WeChat accounts, and short video platforms, focusing on interpreting the relevance of participation to the optimization of social security benefits.

[0036] Information disclosure optimization: Regularly publicize the application of policy evaluation results through government affairs platforms, clarify the impact of participation opinions on social security policy adjustments, and enhance the participation confidence of social members.

[0037] Technical support optimization: A dedicated entry point for social security policy assessment has been added to the government affairs APP, supporting voice input of opinions and appointment scheduling, and providing a one-click community assistance function for the elderly.

[0038] 4. Effectiveness Verification: Two homogeneous communities were selected as the experimental and control groups. The experimental group adopted the aforementioned boosting strategy, while the control group used traditional promotional methods. The results showed that the participation rate in the experimental group was 35% higher than that in the control group, and the quality of participation (percentage of valid opinions) was 28% higher. The participation rate among the elderly group showed the most significant increase (42%).

[0039] Application Example 2: Regional Industrial Development Policy Forecasting and Promotion 1. Research Phase: Focusing on a specific industrial cluster area, a sample of 1,500 members of society (primarily including industry practitioners, business managers, and ordinary community members) was selected to conduct a survey, collecting information on their participation needs and current understanding of industrial development policy predictions.

[0040] 2. Analysis of influencing factors: Confirmatory factor analysis shows that industry relevance, information acquisition cost, and timeliness of result feedback are the core influencing factors. Practitioners pay more attention to the impact of policies on industry development, while ordinary members pay more attention to information related to employment and income.

[0041] 3. Boosting Strategy Design: Top-level system optimization: For industrial development policy forecasting, a forecasting indicator system is set up for each industry, and a dedicated participation channel for practitioners and a channel for soliciting opinions from ordinary members are opened to achieve classified feedback.

[0042] Framing effect optimization: Adopt the "policy impacts individual benefits" related publicity approach, create visual charts linking industry policy forecasts with employment and income, and push them out through industry association channels.

[0043] Information disclosure optimization: Establish a policy forecast result feedback mechanism to regularly push data on the adoption of forecast opinions and the actual impact of policy implementation to participants.

[0044] Technical support optimization: Based on the industrial park service platform, a participation portal is built to support enterprises to participate in batches and individuals to submit prediction suggestions online, and a progress query function is set up after the opinions are submitted.

[0045] 4. Effect Verification: Two homogeneous industrial parks were selected as the experimental and control groups. The experimental group implemented a boosting strategy, while the control group used traditional notification methods. The results showed that the participation rate in the experimental group increased by 30%, the proportion of valid opinions from industry practitioners increased by 33%, and the comprehensiveness and accuracy of policy predictions were significantly improved.

[0046] In summary, this invention obtains data on the needs and current status of social members through the survey phase, providing a foundation for the analysis of influencing factors; based on the analysis results, it designs targeted support strategies, forming a closed-loop system of "survey-analysis-design-verification"; the quasi-experimental verification phase ensures the effectiveness of the support strategies, ultimately achieving the scientific guidance of social members' participation behavior and the optimization and improvement of the policy evaluation and prediction system.

[0047] The technical solution provided by this invention has been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. It should be noted that those skilled in the art can make several improvements and modifications to this invention without departing from the principles of this invention, and these improvements and modifications also fall within the protection scope of the claims of this invention.

Claims

1. A method for evaluating and predicting major policies based on ordered logistic regression analysis, characterized in that, Includes the following steps: Step 1: Select representative social groups using stratified judgment sampling and use standardized survey tools to obtain data on their current participation, psychological cognition, and demand preferences in the evaluation and prediction of major policies. Step 2: Analyze the factors influencing participation behavior based on survey data: Step 2.1: Clean and code the questionnaire data obtained from the survey, and remove invalid samples; conduct qualitative analysis on the interview data and case data to extract key information; Step 2.2: Use statistical software to conduct descriptive statistics on the psychological characteristics, cognitive status and participation behavior of social members participating in the evaluation and prediction of different major policies, and analyze the cognitive biases and behavioral biases of social members in the participation process; Step 2.3: Construct a quantitative analysis model based on behavioral decision theory, with social members’ willingness to participate, frequency of participation, and quality of participation as dependent variables, and basic characteristics, occupational characteristics, cognitive status, and policy and institutional factors as independent variables, to explore the core factors affecting participation behavior, conduct confirmatory factor analysis, and identify the key factors affecting participation behavior. Step 3: Based on the analysis results of factors influencing participation behavior, design a boosting strategy to form a comprehensive boosting strategy system; Step 4: Using a quasi-experimental method, the homogeneous social group is divided into an experimental group and a control group. The aforementioned boosting strategy system is implemented on the experimental group. The participation rate and participation quality data of the two groups are compared and analyzed to verify the effectiveness of the strategy and optimize the parameters accordingly.

2. The method for evaluating and predicting major policies based on ordered logistic regression analysis according to claim 1, characterized in that, Step 1, which involves obtaining data on participation status, psychological cognition, and demand preferences in major policy evaluation and forecasting, specifically includes: Step 1.1: Using stratified judgment sampling, representative members of society in typical cities were selected, and managers responsible for major policy evaluation and forecasting were also selected as interviewees. Step 1.2: Design research tools, including standardized open-ended questionnaires and semi-structured interview outlines. The questionnaires cover the basic characteristics, occupational features, cognitive status, participation experience, and needs and preferences of social members; the interview outlines include key issues in policy evaluation and prediction system formulation and implementation. Step 1.3: Obtain sample data through questionnaires, collect feedback from special social members and managers through semi-structured interviews and case studies, and collect implementation case data of major policy evaluation and prediction in different regions to form data on the participation status, psychological cognition and demand preferences of representative social groups in major policy evaluation and prediction.

3. The method for evaluating and predicting major policies based on ordered logistic regression analysis according to claim 2, characterized in that, The social groups selected by the stratified judgment sampling method include: political social members, economic social members, social status social members, professional workers and practitioners, ordinary members in communities and groups, and individuals and family units.

4. The method for evaluating and predicting major policies based on ordered logistic regression analysis according to claim 1, characterized in that, The econometric analysis model employs ordered logistic regression analysis, and the key factors include one or more of the following: income stability, ease of participation process, information transparency, industry relevance, information acquisition cost, and timeliness of result feedback.

5. The method for evaluating and predicting major policies based on ordered logistic regression analysis according to claim 1, characterized in that, Step 3 describes a policy support strategy design that includes top-level institutional optimization, framework effect optimization, information disclosure optimization, and technical support optimization.

6. The method for evaluating and predicting major policies based on ordered logistic regression analysis according to claim 5, characterized in that, The aforementioned top-level institutional optimization includes: setting differentiated evaluation and forecasting indicators, methods, participation procedures, and result application mechanisms for different policy types and social groups; The optimization of the framework effect includes: simplifying and reconstructing the presentation of policy assessment and forecasting information by using visual charts, concise manuals, or short videos; The optimization of information disclosure includes: regularly disclosing to participants the adoption status of their opinions, related cases of policy adjustments and participation feedback, and data on the actual impact of policy implementation; The technical support optimizations include: building a convenient participation interface with personalized reminders, voice input, progress query, batch participation, and one-click assistance functions based on the Internet or mobile application platform.

7. The method for evaluating and predicting major policies based on ordered logistic regression analysis according to claim 1, characterized in that, Step 4, which involves verifying the effectiveness of the strategy and optimizing the parameters accordingly, specifically includes: Step 4.1: Quasi-experimental design. Two homogeneous social groups are selected as the experimental group and the control group. The experimental group adopts the comprehensive boosting strategy system designed in Step 3, while the control group adopts the traditional participatory guidance method. Step 4.2: Implement intervention under natural conditions. In the same policy evaluation and prediction scenario, guide the participation of the two groups respectively, and continuously collect data on the participation intention, participation rate, and participation completion quality of the two groups. Step 4.3: Compare the differences between the experimental group and the control group to verify the effectiveness of the boosting strategy; and adjust the specific parameters of the boosting strategy based on the verification results to optimize the system design and technical support scheme.

8. A major policy evaluation and prediction system based on ordered logistic regression analysis, used to implement the steps of the method as described in any one of claims 1 to 7, characterized in that, include: The data acquisition module is used to select representative social groups using stratified judgment sampling and to obtain data on their participation status, psychological cognition, and demand preferences in the evaluation and prediction of major policies using standardized survey tools. The data analysis and modeling module is used to store and process the data, build econometric analysis models, and output a report analyzing key factors affecting participation behavior. The boosting strategy generation module is used to design boosting strategies based on the key influencing factor analysis report, and generate a comprehensive boosting strategy system for specific policies and social groups. The effect verification and optimization module is used to divide a homogeneous social group into an experimental group and a control group using a quasi-experimental method. The boosting strategy system is implemented on the experimental group, and the participation rate and participation quality data of the two groups are compared and analyzed to verify the effectiveness of the strategy and optimize the parameters accordingly.

9. An electronic device, characterized in that, include: Memory and processor; The memory is used to store programs; The processor is configured to execute the program to implement the steps of the method as described in any one of claims 1 to 7.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images