Social development planning system and method

Abstract

The invention discloses a social development planning system and method, and particularly relates to digital and intelligent national economy and social development planning, which comprises a planning acquisition system S1, a planning analysis system S2, a planning compilation system S3, a planning joint review system S4, a planning implementation system S5 and a planning adjustment feedback system S6. The planning acquisition system S1 is used for collecting macroeconomic data, industrial data, financial data and spatial planning data, ensuring data quality and accuracy, formulating a unified data standard, and providing support for subsequent analysis. The social development planning system and method designed by the invention are of great significance to national economic and social development, and can improve policy scientificity and effectiveness, enhance cross-department and cross-domain collaboration, improve public participation and cognition and promote economic development and social progress.

Description

Technical Field

[0001] The invention relates to a social development planning system and method. Background Art

[0002] The national economic and social development plan is a plan and arrangement made by a country or region for the main activities of the national economy, science and technology, education, etc. within a certain period of time. The national economic and social development plan involves multiple departments, industries and fields such as economy, industry, finance, currency, income distribution, social security, urban and rural development, and national land space planning. As an important basis for the formulation of national land space planning, the national economic and social development plan provides strategic guidance for national land space planning. The process generally includes economic planning, industrial planning, financial planning, infrastructure investment planning, spatial planning, project cost planning and other links, and each link is interconnected and has a strict sequence. The current "multi-plan integration" involves more land use planning in national land space planning, such as urban and rural planning, environmental planning, forest land and cultivated land, and transportation planning. Since the work of each department is independent of each other and the information data is independent of each other, the following problems often exist: 1. Mismatch and overlap of planning content: Different plans may involve similar control content in the same time and space, but due to the different focuses of various plans, there is a lack of a national economic and social development plan that takes into account various factors in a comprehensive manner.

[0003] 2. Planning standards are different and complex: There is a lack of unified standard basis among various planning systems, and the data foundation is not unified, resulting in inconsistent time and space bases for various types of planning.

[0004] 3. It is difficult for planning departments to coordinate: The current "multiple plans in one" is more about land use planning in national land space planning, such as urban and rural planning, environmental planning, forest land and cultivated land, and transportation planning. The national economic and social development plan, as an important basis for the formulation of national land space planning, provides strategic guidance for national land space planning. Since it involves multiple departments, coordination is difficult, resulting in limited effectiveness in the connection between the national economic and social development plan and the national land space planning.

[0005] 4. Planning results cannot be shared: The same plan has gone through the approval of many departments from project establishment, compilation, approval, construction application, construction, acceptance and other links. The process information of each planning approval or the progress information of the current approval cannot be shared, which brings many problems to planning and construction management.

[0006] 5. The application of planning effects is limited: either the "multi-plan integration" or "one map" results are not compiled, or the compiled "one map" results are not shared among departments, or there is a lack of planning implementation and post-planning evaluation, resulting in a serious lack of synergy from macro-planning to micro-planning, making it difficult for planning to achieve maximum benefits. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a social development planning system and method. The system and method are an innovative model that uses big data and artificial intelligence technology to carry out multi-dimensional planning in a data-driven and intelligent way. It uses widely collected data in society, including socio-economic data, industrial data, fiscal data, infrastructure investment data, spatial planning data, project cost data, etc., to help decision makers at all levels in a country or region better understand, analyze, predict, and respond to the status, problems, and trends of social development through integration, cleaning, and analysis, and formulate more scientific and effective planning strategies.

[0008] 1. A multi-dimensional digital intelligent planning system, comprising a planning collection system S1, a planning analysis system S2, a planning compilation system S3, a planning joint review system S4, a planning implementation system S5, and a planning adjustment feedback system S6, characterized in that: S1: Input relevant legal economic data files into the information collection port. The AI ​​Diagrams technology for converting text to diagrams and the OCR technology for converting diagrams to text embedded in the information collection port automatically identify the legal economic data files and convert them into digital information. The acquired legal economic data are integrated into information data units with the help of ETL technology, and then Huffman coding technology is used to formulate them into ArcGIS data formats that can be shared and recognized in different fields, which are then transmitted and used in S2. S2: Use machine learning algorithms to classify, cluster, regress, and predict the data obtained from S1, discover patterns and trends in the data, and pass them on to S3; S3: The S3 system includes an economic planning system S301, an industrial planning system S302, a financial planning system S303, an infrastructure planning system S304, a spatial planning system S305 and a project cost planning system S306. ArcGIS is mainly used to prepare a full-field planning plan, and the plan is submitted to S4 for approval. The specific steps include: S301: By receiving the data from S2, S301 generates the legal economic planning indicators containing GDP values ​​and planning periods using the built-in Python technology, and transmits them to S302; S302: S302 generates statutory industrial planning indicators based on S301 using the embedded Python technology and passes them to S303; S303: S303 generates statutory fiscal planning indicators using embedded Python technology based on S302 and passes them to S304; S304: S304 generates statutory infrastructure planning indicators based on S303 using embedded Python technology and passes them to S305; S305: S305 uses embedded ArcGIS technology and machine learning methods to generate statutory spatial planning indicators based on S304 and pass them to S306; S306: S306 generates statutory project cost planning indicators based on S305 using embedded BIM technology and machine learning methods, and transmits them to S307; S307: S307 uses the embedded Stata regression model to establish a statutory "multi-regulation integration" indicator system based on S306 and transmits it to S4; S4: The planning scheme of S4 for S3 is jointly reviewed by the approval agency, industry associations, experts and scholars, enterprises, communities, and the public, and the Python stratified random sampling technology is used to extract review experts from the pre-registered review entities. The channel allocation technology is used to notify and invite the experts who participate in the joint review to participate in the review on S4, forming the final "multi-plan integration" planning scheme, which is approved by the approval agency and forms the final planning scheme to provide support for S5; S5: The required resources for the planning scheme are realized through the ERP system embedded in S5, and the implementation status is fed back in real time with the help of the OA system embedded in S5, and the implementation progress of the planning is adjusted in time. Based on the machine learning method, the OCR technology used for objective evaluation of the planning scheme and the NLP technology used for subjective evaluation of the planning scheme are combined to obtain the final implementation effect evaluation index, and the implementation status and evaluation results are delivered to S6; S6: It mainly uses optimization algorithm technology to adjust and feedback the planning scheme. It is used for the planning differences between S4 and S5, namely "patch", to give adjustment schemes according to preset rules. If the adjustment scheme is adopted, it will be fed back to S4 or S5 to form a planning scheme. If the adjustment scheme is not adopted, it will be fed back to S1 to enter the next round of planning scheme. This cycle can be continuously updated to form a new planning scheme.

[0009] 2. A multi-dimensional digital intelligence planning method, the method comprising a planning collection method M1, a planning analysis method M2, a planning compilation method M3, a planning joint review method M4, a planning implementation method M5, and a planning adjustment feedback method M6, characterized in that: M1: S1 is used to collect regional planning data sources and data types, especially macroeconomic data, and formulate them into ArcGIS data formats that can be shared and recognized in different fields in coordination with the system, providing support for the implementation of M2 methods in S2; M2: Use machine learning algorithm technology to classify, cluster, regress, and predict the data obtained from the implementation of the M1 method in S1, discover the patterns and trends in the data, and provide support for the implementation of the M3 method in S3; M3: Mainly use ArcGIS to prepare the planning scheme for the entire field, and submit the scheme to S4 for approval. The specific steps include; S301: The data obtained by implementing the M2 method in S2 is set in S301 to include GDP values ​​and statutory economic planning indicators for the planning period, and is transmitted to S302; S302: S302 decomposes the statutory industrial planning indicators based on the Python technology embedded in S301 and transmits them to S303; S303: S303 decomposes the statutory fiscal planning indicators based on the Python technology embedded in S302 and passes them to S304; S304: S304 decomposes the statutory infrastructure planning indicators based on the Python technology embedded in S303 and transmits them to S305; S305: S305 generates statutory spatial planning indicators based on the statutory infrastructure planning indicators generated in S304 using ArcGIS technology and machine learning methods, and transmits them to S306; S306: S306 generates statutory project cost planning indicators based on the statutory spatial planning indicators generated in S305 using BIM technology and machine learning methods, and transmits them to S307; S307: The statutory economic planning indicators, statutory industrial planning indicators, statutory fiscal planning indicators, statutory infrastructure planning indicators, statutory spatial planning indicators, and statutory project cost planning indicators mentioned in S307 are used to establish a statutory "multi-plan integration" indicator system using the Stata regression model and transferred to S4; M4: S4 implements the M3 method in S3 to obtain the planning scheme. The approval agency, industry associations, experts and scholars, enterprises, communities, and the public jointly form a multi-audit subject joint review mechanism. The Python stratified random sampling technology is used to extract audit experts from the pre-stored audit subjects. The channel allocation technology is used to notify and invite the participating joint review experts to participate in the review on S4, forming the final "multi-plan integration" planning scheme. After approval by the approval agency, the final planning scheme is formed to provide support for the implementation of the M2 method in S5; M5: The required resources for the planning scheme are realized through the ERP system embedded in S5, and the implementation status is fed back in real time with the help of the OA system embedded in S5, and the implementation progress of the plan is adjusted in time. Based on the machine learning method, the OCR technology used for objective evaluation of the planning scheme and the NLP technology used for subjective evaluation of the planning scheme are combined to obtain the final implementation effect evaluation index, providing support for the implementation of the M6 ​​method in S6; M6: It mainly uses optimization algorithm technology to adjust and feedback planning schemes. It is used for planning differences between S4 and S5, namely "patch" to give adjustment schemes according to preset rules. If the adjustment scheme is adopted, it will be fed back to S4 or S5 to form a planning scheme. If the adjustment scheme is not adopted, it will be fed back to S1 and the M1 processing method will be used to enter the next round of planning schemes. This cycle can be continuously updated to form a new planning scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 The figure is a structural diagram of a social development planning system and method.

[0011] Figure 2 It is a structural diagram of the planning and compilation system S3 in the present invention. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the specification of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] Embodiment 1: Figure 1 As shown, the embodiment of the present application provides a multi-dimensional digital intelligent planning system, which includes a planning collection system S1, a planning analysis system S2, a planning compilation system S3, a planning joint review system S4, a planning implementation system S5, and a planning adjustment feedback system S6, characterized in that: S1: Input relevant legal economic data files into the information collection port of S1. The AI ​​Diagrams technology for converting text to diagrams and the OCR technology for converting diagrams to text embedded in the information collection port automatically identify the legal economic data files and convert them into digital information. The acquired legal economic data are integrated into information data units with the help of ETL technology, and then Huffman coding technology is used to formulate them into ArcGIS data formats that can be shared and recognized in different fields, which are then transmitted and used in S2. S2: Use machine learning algorithms to classify, cluster, regress, and predict the data obtained from S1, discover patterns and trends in the data, and pass them on to S3; S3: The S3 system includes economic planning system S301, industrial planning system S302, financial planning system S303, infrastructure planning system S304, spatial planning system S305 and project cost planning system S306. It mainly uses ArcGIS to prepare all-domain planning schemes and submits the prepared schemes to S4 for approval. The specific steps are as follows: Figure 2 : S301: By receiving the data from S2, S301 generates statutory economic planning indicators (including GDP value and planning period) using the built-in Python technology and transmits them to S302; S302: S302 generates statutory industrial planning indicators based on S301 using the embedded Python technology and passes them to S303; S303: S303 generates statutory fiscal planning indicators using embedded Python technology based on S302 and passes them to S304; S304: S304 generates statutory infrastructure planning indicators based on S303 using embedded Python technology and passes them to S305; S305: S305 uses embedded ArcGIS technology and machine learning methods to generate statutory spatial planning indicators based on S304 and pass them to S306; S306: S306 generates statutory project cost planning indicators based on S305 using embedded BIM technology and machine learning methods, and transmits them to S307; S307: S307 uses the embedded Stata regression model to establish a statutory "multi-regulation integration" indicator system based on S306 and transmits it to S4; S4: The planning scheme of S4 for S3 is jointly reviewed by the approval agency, industry associations, experts and scholars, enterprises, communities, and the public, and the Python stratified random sampling technology is used to extract review experts from the pre-registered review entities. The channel allocation technology is used to notify and invite the experts who participate in the joint review to participate in the review on S4, forming the final "multi-plan integration" planning scheme, which is approved by the approval agency and forms the final planning scheme to provide support for S5; S5: The required resources for the planning scheme are realized through the ERP system embedded in S5, and the implementation status is fed back in real time with the help of the OA system embedded in S5, and the implementation progress of the planning is adjusted in time. Based on the machine learning method, the OCR technology used for objective evaluation of the planning scheme and the NLP technology used for subjective evaluation of the planning scheme are combined to obtain the final implementation effect evaluation index, and the implementation status and evaluation results are delivered to S6; S6: It mainly uses optimization algorithm technology to adjust and feedback the planning scheme. It is used for the planning differences between S4 and S5, namely "patch", to give adjustment schemes according to preset rules. If the adjustment scheme is adopted, it will be fed back to S4 or S5 to form a planning scheme. If the adjustment scheme is not adopted, it will be fed back to S1 to enter the next round of planning scheme. This cycle can be continuously updated to form a new planning scheme.

[0014] Embodiment 2: Figure 1 As shown, the embodiment of the present application provides a multi-dimensional digital intelligence planning method, which includes a planning collection method M1, a planning analysis method M2, a planning preparation method M3, a planning joint review method M4, a planning implementation method M5, and a planning adjustment feedback method M6, characterized in that: M1: S1 is used to collect regional planning data sources and data types, especially macroeconomic data, and formulate them into ArcGIS data formats that can be shared and recognized in different fields in coordination with the system, providing support for the implementation of M2 methods in S2; M2: Use machine learning algorithm technology to classify, cluster, regress, and predict the data obtained from the implementation of the M1 method in S1, discover the patterns and trends in the data, and provide support for the implementation of the M3 method in S3; M3: Mainly use ArcGIS to prepare the planning scheme for the entire field, and submit the scheme to S4 for approval. The specific steps include; S301: By receiving the data from S2, S301 generates the legal economic planning indicators containing GDP values ​​and planning periods using the built-in Python technology, and transmits them to S302; S302: S302 generates statutory industrial planning indicators based on S301 using the embedded Python technology and passes them to S303; S303: S303 generates statutory fiscal planning indicators using embedded Python technology based on S302 and passes them to S304; S304: S304 generates statutory infrastructure planning indicators based on S303 using embedded Python technology and passes them to S305; S305: S305 uses embedded ArcGIS technology and machine learning methods to generate statutory spatial planning indicators based on S304 and pass them to S306; S306: S306 generates statutory project cost planning indicators based on S305 using embedded BIM technology and machine learning methods, and transmits them to S307; S307: S307 uses the embedded Stata regression model to establish a statutory "multi-regulation integration" indicator system based on S306 and transmits it to S4; M4: S4 implements the M3 method in S3 to obtain the planning scheme. The approval agency, industry associations, experts and scholars, enterprises, communities, and the public jointly form a multi-audit subject joint review mechanism. The Python stratified random sampling technology is used to extract audit experts from the pre-stored audit subjects. The channel allocation technology is used to notify and invite the participating joint review experts to participate in the review on S4, forming the final "multi-plan integration" planning scheme. After approval by the approval agency, the final planning scheme is formed to provide support for the implementation of the M2 method in S5; M5: The required resources for the planning scheme are realized through the ERP system embedded in S5, and the implementation status is fed back in real time with the help of the OA system embedded in S5, and the implementation progress of the plan is adjusted in time. Based on the machine learning method, the OCR technology used for objective evaluation of the planning scheme and the NLP technology used for subjective evaluation of the planning scheme are combined to obtain the final implementation effect evaluation index, providing support for the implementation of the M6 ​​method in S6; M6: It mainly uses optimization algorithm technology to adjust and feedback planning schemes. It is used for planning differences between S4 and S5, namely "patch" to give adjustment schemes according to preset rules. If the adjustment scheme is adopted, it will be fed back to S4 or S5 to form a planning scheme. If the adjustment scheme is not adopted, it will be fed back to S1 and the M1 processing method will be used to enter the next round of planning schemes. This cycle can be continuously updated to form a new planning scheme.

Claims

1. A multi-dimensional digital intelligent planning system, comprising a planning collection system S1, a planning analysis system S2, a planning compilation system S3, a planning joint review system S4, a planning implementation system S5, and a planning adjustment feedback system S6, characterized in that: S1: The macroeconomic data, industrial data, fiscal data, infrastructure investment data, spatial planning data and project cost data obtained at the planning, consultation, design, approval, implementation, proposal and complaint information collection ports are integrated into information data units, formulated into data standards for the field, and transmitted and used in S2; S2: Process and analyze the data obtained from S1 using the cluster regression data analysis method. Through analysis, find the rules and trends in the data, and pass them on to S3; S3: Prepare a full-area planning plan based on the data analyzed in S2 and submit the plan to S4 for approval, including: S301: Includes goals, strategies, implementation steps and timetables, and requires cross-departmental and cross-field cooperation to formulate specific digital economic development plans based on data analysis results and national economic development strategies; S302: It also includes goals, strategies, implementation steps and timetables, and requires cross-departmental and cross-field cooperation to formulate specific digital and intelligent industry development plans based on data analysis results and industrial development strategies; S303: Includes strategies and implementation steps for fiscal expenditure, tax policy and debt management, and requires close cooperation with the finance department to formulate specific digital fiscal planning programs based on data analysis results and national fiscal policy goals; S304: including investment scale and funding sources, investment areas and project selection, investment benefit evaluation, investment risk control, and investment planning implementation and management, used to determine the scale and funding sources of infrastructure investment, determine the main areas and project selection of infrastructure investment according to national development strategies and urban needs, evaluate the economic, social and environmental benefits of infrastructure investment projects, analyze the risks and challenges that infrastructure investment may face, formulate corresponding risk control measures and response strategies, and formulate specific infrastructure investment planning programs; S305: Includes strategies and implementation steps for national land space planning, urban and rural planning, and infrastructure construction, and requires cooperation with relevant departments and experts to formulate specific spatial planning plans based on data analysis results and land space planning requirements; S306: including cost estimation methods, cost influencing factors analysis, cost budget preparation, cost management measures, and cost audit and supervision. According to the project type and the preset cost estimation method, a cost planning scheme (including budget estimate scheme and project audit and supervision scheme) is generated; S4: The planning scheme of S3 will be reviewed and handed over to S5 for organization and implementation. The joint review will be conducted by representatives of members from multiple fields, and opinions from the public, experts, scholars, industries, and enterprises will be widely absorbed. Through cross-field coordination and integration, the synergy and consistency of various plans will be ensured; S5: used to translate planning into concrete action plans, allocate resources and responsibilities; S6: For the planning differences among S3, S4 and S5 (including compilation control, adjustment, modification, increase and decrease), adjustment plans are given according to preset rules, and feedback is given to S1 on whether the adjustment plans are adopted and finally implemented; at the same time, the later implementation effects of various plans are evaluated, adjustment plans are given and fed back to S1.

2. A multi-dimensional digital intelligence planning method, the method comprising a planning collection method M1, a planning analysis method M2, a planning compilation method M3, a planning joint review method M4, a planning implementation method M5, and a planning adjustment feedback method M6, characterized in that: M1: Collect macroeconomic data, industrial data, fiscal data, and spatial planning data in S1 to ensure data quality and accuracy, develop unified data standards, and provide support for S2 analysis; M2: In S2, cluster regression data analysis methods are used to process and analyze the data collected in S1. Through analysis, the laws and trends in the data are discovered, providing a basis for planning in S3; M3: Establish economic planning system S301, industrial planning system S302, financial planning system S303, infrastructure planning system S304, spatial planning system S305 and project cost planning system S306 in S3, and coordinate the compilation of multiple plans based on the planning analysis system S2 to form a "multi-plan integration" planning scheme; M4: In S4, the "multi-plan integration" planning scheme completed in S3 is coordinated and integrated across fields to achieve joint review and approval of the planning, and the approval results are passed to S5; M5: Implement the planning scheme approved by S4 in S5 and pay continuous attention to various indicators and adjust strategies in a timely manner during the implementation process; M6: In S6, adjust the planning differences in S3, S4, and S5 and evaluate the implementation results to form necessary adjustments and feedback to optimize the implementation results; The method coordinates S1, S2, S3, S4, S5, and S6 to realize the planning scheme.

Images